Search Results for author: Tianyi Zhang

Found 163 papers, 76 papers with code

Splitting vs. Merging: Mining Object Regions with Discrepancy and Intersection Loss for Weakly Supervised Semantic Segmentation

no code implementations ECCV 2020 Tianyi Zhang, Guosheng Lin, Weide Liu, Jianfei Cai, Alex Kot

Finally, by training the segmentation model with the masks generated by our Splitting vs Merging strategy, we achieve the state-of-the-art weakly-supervised segmentation results on the Pascal VOC 2012 benchmark.

Segmentation Weakly supervised segmentation +2

Incorporating Uncertainty-Guided and Top-k Codebook Matching for Real-World Blind Image Super-Resolution

no code implementations9 Jun 2025 Weilei Wen, Tianyi Zhang, Qianqian Zhao, Zhaohui Zheng, Chunle Guo, Xiuli Shao, Chongyi Li

Experimental results demonstrate significant improvements in texture realism and reconstruction fidelity compared to existing methods.

Image Super-Resolution

A Systematic Investigation on Deep Learning-Based Omnidirectional Image and Video Super-Resolution

1 code implementation7 Jun 2025 Qianqian Zhao, Chunle Guo, Tianyi Zhang, Junpei Zhang, Peiyang Jia, Tan Su, Wenjie Jiang, Chongyi Li

This paper presents a systematic review of recent progress in omnidirectional image and video super-resolution, focusing on deep learning-based methods.

Video Super-Resolution

Deployability-Centric Infrastructure-as-Code Generation: An LLM-based Iterative Framework

1 code implementation5 Jun 2025 Tianyi Zhang, Shidong Pan, Zejun Zhang, Zhenchang Xing, Xiaoyu Sun

Our evaluation reveals that state-of-the-art LLMs initially performed poorly, with Claude-3. 5 and Claude-3. 7 achieving only 30. 2% and 26. 8% deployment success on the first attempt respectively.

Code Generation

Visual Embodied Brain: Let Multimodal Large Language Models See, Think, and Control in Spaces

no code implementations30 May 2025 Gen Luo, Ganlin Yang, Ziyang Gong, Guanzhou Chen, Haonan Duan, Erfei Cui, Ronglei Tong, Zhi Hou, Tianyi Zhang, Zhe Chen, Shenglong Ye, Lewei Lu, Jingbo Wang, Wenhai Wang, Jifeng Dai, Yu Qiao, Rongrong Ji, Xizhou Zhu

In VeBrain-600k, we take hundreds of hours to collect, curate and annotate the data, and adopt multimodal chain-of-thought(CoT) to mix the different capabilities into a single conversation.

Spatial Reasoning

Bi-Manual Joint Camera Calibration and Scene Representation

no code implementations30 May 2025 Haozhan Tang, Tianyi Zhang, Matthew Johnson-Roberson, Weiming Zhi

Bi-JCR enables multiple robot manipulators, each with cameras mounted, to circumvent taking images of calibration markers.

Camera Calibration Robot Manipulation +1

Active Layer-Contrastive Decoding Reduces Hallucination in Large Language Model Generation

no code implementations29 May 2025 Hongxiang Zhang, Hao Chen, Tianyi Zhang, Muhao Chen

Recent decoding methods improve the factuality of large language models~(LLMs) by refining how the next token is selected during generation.

Decision Making Hallucination +4

From Single Images to Motion Policies via Video-Generation Environment Representations

no code implementations25 May 2025 Weiming Zhi, Ziyong Ma, Tianyi Zhang, Matthew Johnson-Roberson

Here, we tackle the problem of constructing a policy model for collision-free motion generation, consistent with the environment, from a single input RGB image.

Monocular Depth Estimation Motion Generation +1

Enhancing Code Generation via Bidirectional Comment-Level Mutual Grounding

1 code implementation12 May 2025 Yifeng Di, Tianyi Zhang

Large Language Models (LLMs) have demonstrated unprecedented capability in code generation.

Code Generation Comment Generation +2

Neighbor-Based Feature and Index Enhancement for Person Re-Identification

no code implementations16 Apr 2025 Chao Yuan, Tianyi Zhang, Guanglin Niu

Existing methods usually improve feature representation by improving model architecture, but most methods ignore the potential contextual information, which limits the effectiveness of feature representation and retrieval performance.

Person Re-Identification Retrieval

70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float

1 code implementation15 Apr 2025 Tianyi Zhang, Yang Sui, Shaochen Zhong, Vipin Chaudhary, Xia Hu, Anshumali Shrivastava

To facilitate efficient inference with dynamic-length encodings, we develop a custom GPU kernel for fast online decompression.

Zero-shot Autonomous Microscopy for Scalable and Intelligent Characterization of 2D Materials

no code implementations14 Apr 2025 Jingyun Yang, Ruoyan Avery Yin, Chi Jiang, Yuepeng Hu, Xiaokai Zhu, Xingjian Hu, Sutharsika Kumar, Xiao Wang, Xiaohua Zhai, Keran Rong, Yunyue Zhu, Tianyi Zhang, Zongyou Yin, Jing Kong, Neil Zhenqiang Gong, Zhichu Ren, Haozhe Wang

This work represents the implementation of foundation models to achieve autonomous analysis, establishing a scalable and data-efficient characterization paradigm that fundamentally transforms the approach to nanoscale materials research.

Image Segmentation Prompt Engineering +1

GraphSeg: Segmented 3D Representations via Graph Edge Addition and Contraction

1 code implementation4 Apr 2025 Haozhan Tang, Tianyi Zhang, Oliver Kroemer, Matthew Johnson-Roberson, Weiming Zhi

These advances do not translate directly to performance in the physical 3D world, where they often over-segment objects and fail to produce consistent mask correspondences across views.

Image Segmentation Segmentation +1

Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy

1 code implementation25 Mar 2025 Zhi Hou, Tianyi Zhang, Yuwen Xiong, Haonan Duan, Hengjun Pu, Ronglei Tong, Chengyang Zhao, Xizhou Zhu, Yu Qiao, Jifeng Dai, Yuntao Chen

While recent vision-language-action models trained on diverse robot datasets exhibit promising generalization capabilities with limited in-domain data, their reliance on compact action heads to predict discretized or continuous actions constrains adaptability to heterogeneous action spaces.

Ranked #3 on Robot Manipulation on SimplerEnv-Google Robot (using extra training data)

Denoising Robot Manipulation +1

Your voice is your voice: Supporting Self-expression through Speech Generation and LLMs in Augmented and Alternative Communication

no code implementations21 Mar 2025 Yiwen Xu, Monideep Chakraborti, Tianyi Zhang, Katelyn Eng, Aanchan Mohan, Mirjana Prpa

The findings highlight the priorities and needs of AAC users and the system's ability to enhance user expressivity by supporting more personalized and contextually relevant communication.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

SurgRAW: Multi-Agent Workflow with Chain-of-Thought Reasoning for Surgical Intelligence

no code implementations13 Mar 2025 Chang Han Low, Ziyue Wang, Tianyi Zhang, Zhitao Zeng, Zhu Zhuo, Evangelos B. Mazomenos, Yueming Jin

Integration of Vision-Language Models (VLMs) in surgical intelligence is hindered by hallucinations, domain knowledge gaps, and limited understanding of task interdependencies within surgical scenes, undermining clinical reliability.

Action Recognition Instrument Recognition +2

Infinite Leagues Under the Sea: Photorealistic 3D Underwater Terrain Generation by Latent Fractal Diffusion Models

no code implementations9 Mar 2025 Tianyi Zhang, Weiming Zhi, Joshua Mangelson, Matthew Johnson-Roberson

Off-the-shelf generative models, trained on Internet-scale data but not on specialized underwater images, exhibit downgraded realism, as images of the seafloor are relatively uncommon.

3D geometry 3DGS

Towards Ambiguity-Free Spatial Foundation Model: Rethinking and Decoupling Depth Ambiguity

1 code implementation8 Mar 2025 Xiaohao Xu, Feng Xue, Xiang Li, Haowei Li, Shusheng Yang, Tianyi Zhang, Matthew Johnson-Roberson, Xiaonan Huang

Depth ambiguity is a fundamental challenge in spatial scene understanding, especially in transparent scenes where single-depth estimates fail to capture full 3D structure.

Depth Estimation Scene Understanding +2

PathRWKV: Enabling Whole Slide Prediction with Recurrent-Transformer

no code implementations5 Mar 2025 Sicheng Chen, Tianyi Zhang, Dankai Liao, Dandan Li, Low Chang Han, Yanqin Jiang, Yueming Jin, Shangqing Lyu

Lastly, we hinge multi-task learning to enable modeling on versatile tasks simultaneously, improving training efficiency, and asynchronous structure design to draw an effective conclusion on all tiles during inference, enhancing inference performance.

Multiple Instance Learning Multi-Task Learning +2

From Poses to Identity: Training-Free Person Re-Identification via Feature Centralization

1 code implementation CVPR 2025 Chao Yuan, Guiwei Zhang, Changxiao Ma, Tianyi Zhang, Guanglin Niu

Considering that features from the same identity follow a normal distribution around identity centers after training, we propose a Training-Free Feature Centralization ReID framework (Pose2ID) by aggregating the same identity features to reduce individual noise and enhance the stability of identity representation, which preserves the feature's original distribution for following strategies such as re-ranking.

Cross-Modal Person Re-Identification Re-Ranking

Sentence-level Reward Model can Generalize Better for Aligning LLM from Human Preference

no code implementations1 Mar 2025 Wenjie Qiu, Yi-Chen Li, Xuqin Zhang, Tianyi Zhang, Yihang Zhang, Zongzhang Zhang, Yang Yu

By segmenting the complete response into sentences and applying differential operations to reward output at the start and end positions of each sentence, we can effectively model the rewards of sentences.

Sentence

DOSE3 : Diffusion-based Out-of-distribution detection on SE(3) trajectories

no code implementations23 Feb 2025 Hongzhe Cheng, Tianyou Zheng, Tianyi Zhang, Matthew Johnson-Roberson, Weiming Zhi

Out-of-Distribution(OOD) detection, a fundamental machine learning task aimed at identifying abnormal samples, traditionally requires model retraining for different inlier distributions.

Out-of-Distribution Detection Out of Distribution (OOD) Detection

Text-to-SQL Domain Adaptation via Human-LLM Collaborative Data Annotation

no code implementations21 Feb 2025 Yuan Tian, Daniel Lee, Fei Wu, Tung Mai, Kun Qian, Siddhartha Sahai, Tianyi Zhang, Yunyao Li

Text-to-SQL models, which parse natural language (NL) questions to executable SQL queries, are increasingly adopted in real-world applications.

Domain Adaptation Text to SQL +1

Soybean pod and seed counting in both outdoor fields and indoor laboratories using unions of deep neural networks

no code implementations21 Feb 2025 Tianyou Jiang, Mingshun Shao, Tianyi Zhang, Xiaoyu Liu, Qun Yu

Automatic counting soybean pods and seeds in outdoor fields allows for rapid yield estimation before harvesting, while indoor laboratory counting offers greater accuracy.

Domain Adaptation

A Training-Free Length Extrapolation Approach for LLMs: Greedy Attention Logit Interpolation (GALI)

1 code implementation4 Feb 2025 Yan Li, Tianyi Zhang, Zechuan Li, Soyeon Caren Han

To address this, we propose Greedy Attention Logit Interpolation (GALI), a training-free length extrapolation method that maximizes the utilization of pretrained positional intervals while avoiding attention logit outliers through attention logit interpolation.

Long-Context Understanding

MASTER: A Multi-Agent System with LLM Specialized MCTS

no code implementations24 Jan 2025 Bingzheng Gan, Yufan Zhao, Tianyi Zhang, Jing Huang, Yusu Li, Shu Xian Teo, Changwang Zhang, Wei Shi

Firstly, MCTS is effective for tasks like the Game of Go, where simulation results can yield objective rewards (e. g., 1 for a win and 0 for a loss).

Game of Go Question Answering

Scalable Benchmarking and Robust Learning for Noise-Free Ego-Motion and 3D Reconstruction from Noisy Video

1 code implementation24 Jan 2025 Xiaohao Xu, Tianyi Zhang, Shibo Zhao, Xiang Li, Sibo Wang, Yongqi Chen, Ye Li, Bhiksha Raj, Matthew Johnson-Roberson, Sebastian Scherer, Xiaonan Huang

We aim to redefine robust ego-motion estimation and photorealistic 3D reconstruction by addressing a critical limitation: the reliance on noise-free data in existing models.

3D Reconstruction Benchmarking +2

Stronger Than You Think: Benchmarking Weak Supervision on Realistic Tasks

1 code implementation13 Jan 2025 Tianyi Zhang, Linrong Cai, Jeffrey Li, Nicholas Roberts, Neel Guha, Jinoh Lee, Frederic Sala

Weak supervision (WS) is a popular approach for label-efficient learning, leveraging diverse sources of noisy but inexpensive weak labels to automatically annotate training data.

Benchmarking

Transferable and Forecastable User Targeting Foundation Model

no code implementations17 Dec 2024 Bin Dou, Baokun Wang, Yun Zhu, Xiaotong LIN, Yike Xu, Xiaorui Huang, Yang Chen, Yun Liu, Shaoshuai Han, Yongchao Liu, Tianyi Zhang, Yu Cheng, Weiqiang Wang, Chuntao Hong

User targeting, the process of selecting targeted users from a pool of candidates for non-expert marketers, has garnered substantial attention with the advancements in digital marketing.

Marketing model +1

MambaXCTrack: Mamba-based Tracker with SSM Cross-correlation and Motion Prompt for Ultrasound Needle Tracking

no code implementations13 Nov 2024 Yuelin Zhang, Long Lei, Wanquan Yan, Tianyi Zhang, Raymond Shing-Yan Tang, Shing Shin Cheng

In this paper, a Mamba-based US needle tracker MambaXCTrack utilizing structured state space models cross-correlation (SSMX-Corr) and implicit motion prompt is proposed, which is the first application of Mamba in US needle tracking.

Inductive Bias Long-range modeling +2

GraphRPM: Risk Pattern Mining on Industrial Large Attributed Graphs

no code implementations11 Nov 2024 Sheng Tian, Xintan Zeng, Yifei Hu, Baokun Wang, Yongchao Liu, Yue Jin, Changhua Meng, Chuntao Hong, Tianyi Zhang, Weiqiang Wang

Graph-based patterns are extensively employed and favored by practitioners within industrial companies due to their capacity to represent the behavioral attributes and topological relationships among users, thereby offering enhanced interpretability in comparison to black-box models commonly utilized for classification and recognition tasks.

Context-Aware Token Selection and Packing for Enhanced Vision Transformer

no code implementations31 Oct 2024 Tianyi Zhang, Baoxin Li, Jae-sun Seo, Yu Cao

In recent years, the long-range attention mechanism of vision transformers has driven significant performance breakthroughs across various computer vision tasks.

object-detection Object Detection

Diffusion Transformer Policy

1 code implementation21 Oct 2024 Zhi Hou, Tianyi Zhang, Yuwen Xiong, Hengjun Pu, Chengyang Zhao, Ronglei Tong, Yu Qiao, Jifeng Dai, Yuntao Chen

In contrast, we model the continuous action sequence with a large multi-modal diffusion transformer, dubbed as Diffusion Transformer Policy, in which we directly denoise action chunks by a large transformer model rather than a small action head for action embedding.

Denoising Vision-Language-Action

Nonlinear Bayesian Filtering with Natural Gradient Gaussian Approximation

no code implementations21 Oct 2024 Wenhan Cao, Tianyi Zhang, Zeju Sun, Chang Liu, Stephen S. -T. Yau, Shengbo Eben Li

Practical Bayes filters often assume the state distribution of each time step to be Gaussian for computational tractability, resulting in the so-called Gaussian filters.

LEMMA

MMDS: A Multimodal Medical Diagnosis System Integrating Image Analysis and Knowledge-based Departmental Consultation

no code implementations20 Oct 2024 Yi Ren, Hanzhi Zhang, Weibin Li, Jun Fu, Diandong Liu, Tianyi Zhang, Jie He, Licheng Jiao

In tests on 30 videos of facial paralysis patients, the system demonstrated a grading accuracy of 83. 3%. The second component is the generation of professional medical responses.

Facial Emotion Recognition Language Modeling +6

A new approach for fine-tuning sentence transformers for intent classification and out-of-scope detection tasks

1 code implementation17 Oct 2024 Tianyi Zhang, Atta Norouzian, Aanchan Mohan, Frederick Ducatelle

One of the most accurate approaches for out-of-scope (OOS) rejection is to combine it with the task of intent classification on in-scope queries, and to use methods based on the similarity of embeddings produced by transformer-based sentence encoders.

Classification intent-classification +4

Collu-Bench: A Benchmark for Predicting Language Model Hallucinations in Code

no code implementations13 Oct 2024 Nan Jiang, Qi Li, Lin Tan, Tianyi Zhang

Despite their success, large language models (LLMs) face the critical challenge of hallucinations, generating plausible but incorrect content.

Code Generation Hallucination +3

SpaLLM: Unified Compressive Adaptation of Large Language Models with Sketching

no code implementations8 Oct 2024 Tianyi Zhang, Junda Su, Oscar Wu, Zhaozhuo Xu, Anshumali Shrivastava

In response to these known limitations, we propose SpaLLM (Sketched Parameter Adaptation of LLMs), a novel compressive adaptation approach for LLMs.

Model Compression Natural Language Understanding

SplaTraj: Camera Trajectory Generation with Semantic Gaussian Splatting

no code implementations8 Oct 2024 Xinyi Liu, Tianyi Zhang, Matthew Johnson-Roberson, Weiming Zhi

These regions are then projected to the camera's view as it moves over time and a cost is constructed.

PhotoReg: Photometrically Registering 3D Gaussian Splatting Models

no code implementations7 Oct 2024 Ziwen Yuan, Tianyi Zhang, Matthew Johnson-Roberson, Weiming Zhi

Advances in photorealistic environment models have enabled robots to develop hyper-realistic reconstructions, which can be used to generate images that are intuitive for human inspection.

3DGS

CodeJudge: Evaluating Code Generation with Large Language Models

1 code implementation3 Oct 2024 Weixi Tong, Tianyi Zhang

This paper presents CodeJudge, a code evaluation framework that leverages LLMs to evaluate the semantic correctness of generated code without the need for test cases.

Code Generation

Robust Incremental Structure-from-Motion with Hybrid Features

no code implementations29 Sep 2024 Shaohui Liu, Yidan Gao, Tianyi Zhang, Rémi Pautrat, Johannes L. Schönberger, Viktor Larsson, Marc Pollefeys

In this work, we introduce an incremental SfM system that, in addition to points, leverages lines and their structured geometric relations.

Camera Calibration

Research on Predicting Public Opinion Event Heat Levels Based on Large Language Models

no code implementations27 Sep 2024 Yi Ren, Tianyi Zhang, Weibin Li, DuoMu Zhou, Chenhao Qin, FangCheng Dong

Next, we randomly selected 250 events from each heat level, totalling 1, 000 events, to build the evaluation dataset.

Prediction

Proof Automation with Large Language Models

no code implementations22 Sep 2024 Minghai Lu, Benjamin Delaware, Tianyi Zhang

Our results show that PALM significantly outperforms other state-of-the-art approaches, successfully proving 76. 6% to 180. 4% more theorems.

SQLucid: Grounding Natural Language Database Queries with Interactive Explanations

1 code implementation10 Sep 2024 Yuan Tian, Jonathan K. Kummerfeld, Toby Jia-Jun Li, Tianyi Zhang

Though recent advances in machine learning have led to significant improvements in natural language interfaces for databases, the accuracy and reliability of these systems remain limited, especially in high-stakes domains.

Predicting Affective States from Screen Text Sentiment

no code implementations23 Aug 2024 Songyan Teng, Tianyi Zhang, Simon D'Alfonso, Vassilis Kostakos

We employed linear regression, zero-shot, and multi-shot prompting using a large language model (LLM) to analyse relationships between screen text and affective states.

Language Modeling Language Modelling +2

Selective Prompt Anchoring for Code Generation

1 code implementation17 Aug 2024 Yuan Tian, Tianyi Zhang

To mitigate this issue, we propose Selective Prompt Anchoring (SPA) to guide code LLMs to pay more attention to user intent when generating code.

Code Generation

Phases Calibration of RIS Using Backpropagation Algorithm

1 code implementation16 Jul 2024 Wei zhang, Bin Zhou, Tianyi Zhang, Yi Jiang, Zhiyong Bu

Reconfigurable intelligent surface (RIS) technology has emerged in recent years as a promising solution to the ever-increasing demand for wireless communication capacity.

LeanQuant: Accurate Large Language Model Quantization with Loss-Error-Aware Grid

no code implementations14 Jul 2024 Tianyi Zhang, Anshumali Shrivastava

Large language models (LLMs) have numerous applications across various domains, but their high computational and memory demands pose significant deployment challenges.

Language Modeling Language Modelling +2

Leveraging LLMs to Predict Affective States via Smartphone Sensor Features

no code implementations11 Jul 2024 Tianyi Zhang, Songyan Teng, Hong Jia, Simon D'Alfonso

Our findings reveal that LLMs can make promising predictions of affect measures using solely smartphone sensing data.

From Perfect to Noisy World Simulation: Customizable Embodied Multi-modal Perturbations for SLAM Robustness Benchmarking

1 code implementation24 Jun 2024 Xiaohao Xu, Tianyi Zhang, Sibo Wang, Xiang Li, Yongqi Chen, Ye Li, Bhiksha Raj, Matthew Johnson-Roberson, Xiaonan Huang

Embodied agents require robust navigation systems to operate in unstructured environments, making the robustness of Simultaneous Localization and Mapping (SLAM) models critical to embodied agent autonomy.

Benchmarking NeRF +1

IDentity with Locality: An ideal hash for gene sequence search

no code implementations21 Jun 2024 Aditya Desai, Gaurav Gupta, Tianyi Zhang, Anshumali Shrivastava

The standard recipe is to cast the gene search problem as a sequence of membership problems testing if each subsequent gene substring (called kmer) of Q is present in the set of kmers of the entire gene database D. We observe that RH functions, which are crucial to the memory and the computational advantage of BF, are also detrimental to the system performance of gene-search systems.

Information Retrieval

NeST: Neural Stress Tensor Tomography by leveraging 3D Photoelasticity

no code implementations14 Jun 2024 Akshat Dave, Tianyi Zhang, Aaron Young, Ramesh Raskar, Wolfgang Heidrich, Ashok Veeraraghavan

We develop an experimental multi-axis polariscope setup to capture 3D photoelasticity and experimentally demonstrate that NeST reconstructs the internal stress distribution for objects with varying shape and force conditions.

Object Transparent objects

Convolutional Unscented Kalman Filter for Multi-Object Tracking with Outliers

no code implementations3 Jun 2024 Shiqi Liu, Wenhan Cao, Chang Liu, Tianyi Zhang, Shengbo Eben Li

Incorporating this operation into the widely used unscented Kalman filter (UKF) in commonly adopted tracking algorithms, we derive a variant of the UKF that is robust to outliers, called the convolutional UKF (ConvUKF).

Autonomous Driving Multi-Object Tracking

Streaming quanta sensors for online, high-performance imaging and vision

no code implementations2 Jun 2024 Tianyi Zhang, Matthew Dutson, Vivek Boominathan, Mohit Gupta, Ashok Veeraraghavan

To the best of our knowledge, our approach is the first to achieve online, real-time image reconstruction on QIS.

Image Reconstruction

PDDLEGO: Iterative Planning in Textual Environments

1 code implementation30 May 2024 Li Zhang, Peter Jansen, Tianyi Zhang, Peter Clark, Chris Callison-Burch, Niket Tandon

A recent, promising line of work uses LLMs to generate a formal representation of the environment that can be solved by a symbolic planner.

KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization

no code implementations7 May 2024 Tianyi Zhang, Jonah Yi, Zhaozhuo Xu, Anshumali Shrivastava

We observe that distinct channels of a key/value activation embedding are highly inter-dependent, and the joint entropy of multiple channels grows at a slower rate than the sum of their marginal entropies.

Language Modeling Language Modelling +2

Unifying Scene Representation and Hand-Eye Calibration with 3D Foundation Models

no code implementations17 Apr 2024 Weiming Zhi, Haozhan Tang, Tianyi Zhang, Matthew Johnson-Roberson

We demonstrate that JCR can build effective scene representations using a low-cost RGB camera attached to a manipulator, without prior calibration.

Decision Making

Human Latency Conversational Turns for Spoken Avatar Systems

no code implementations11 Apr 2024 Derek Jacoby, Tianyi Zhang, Aanchan Mohan, Yvonne Coady

We also provide some examples of utterances and the impacts of this information loss on the quality of LLM response in the context of an avatar that is currently under development.

Language Modelling Large Language Model

DarkGS: Learning Neural Illumination and 3D Gaussians Relighting for Robotic Exploration in the Dark

1 code implementation16 Mar 2024 Tianyi Zhang, Kaining Huang, Weiming Zhi, Matthew Johnson-Roberson

Humans have the remarkable ability to construct consistent mental models of an environment, even under limited or varying levels of illumination.

PromptCharm: Text-to-Image Generation through Multi-modal Prompting and Refinement

1 code implementation6 Mar 2024 Zhijie Wang, Yuheng Huang, Da Song, Lei Ma, Tianyi Zhang

However, prompting remains challenging for novice users due to the complexity of the stable diffusion model and the non-trivial efforts required for iteratively editing and refining the text prompts.

Image Inpainting Prompt Engineering +2

NoMAD-Attention: Efficient LLM Inference on CPUs Through Multiply-add-free Attention

1 code implementation2 Mar 2024 Tianyi Zhang, Jonah Wonkyu Yi, Bowen Yao, Zhaozhuo Xu, Anshumali Shrivastava

Large language model inference on Central Processing Units (CPU) is challenging due to the vast quantities of expensive Multiply-Add (MAD) matrix operations in the attention computations.

16k Language Modeling +2

Uncertainty-Based Extensible Codebook for Discrete Federated Learning in Heterogeneous Data Silos

1 code implementation29 Feb 2024 Tianyi Zhang, Yu Cao, Dianbo Liu

Federated learning (FL), aimed at leveraging vast distributed datasets, confronts a crucial challenge: the heterogeneity of data across different silos.

Diversity Federated Learning

Customizable Perturbation Synthesis for Robust SLAM Benchmarking

1 code implementation12 Feb 2024 Xiaohao Xu, Tianyi Zhang, Sibo Wang, Xiang Li, Yongqi Chen, Ye Li, Bhiksha Raj, Matthew Johnson-Roberson, Xiaonan Huang

To this end, we propose a novel, customizable pipeline for noisy data synthesis, aimed at assessing the resilience of multi-modal SLAM models against various perturbations.

Benchmarking Simultaneous Localization and Mapping

Learning Scalable Structural Representations for Link Prediction with Bloom Signatures

no code implementations28 Dec 2023 Tianyi Zhang, Haoteng Yin, Rongzhe Wei, Pan Li, Anshumali Shrivastava

We further show that any type of neighborhood overlap-based heuristic can be estimated by a neural network that takes Bloom signatures as input.

Link Prediction Prediction

Multi-modality Affinity Inference for Weakly Supervised 3D Semantic Segmentation

1 code implementation27 Dec 2023 Xiawei Li, Qingyuan Xu, Jing Zhang, Tianyi Zhang, Qian Yu, Lu Sheng, Dong Xu

The point affinity proposed in this paper is characterized by features from multiple modalities (e. g., point cloud and RGB), and is further refined by normalizing the classifier weights to alleviate the detrimental effects of long-tailed distribution without the need of the prior of category distribution.

3D Semantic Segmentation Point Cloud Segmentation +1

DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision

1 code implementation CVPR 2024 Lu Ling, Yichen Sheng, Zhi Tu, Wentian Zhao, Cheng Xin, Kun Wan, Lantao Yu, Qianyu Guo, Zixun Yu, Yawen Lu, Xuanmao Li, Xingpeng Sun, Rohan Ashok, Aniruddha Mukherjee, Hao Kang, Xiangrui Kong, Gang Hua, Tianyi Zhang, Bedrich Benes, Aniket Bera

We have witnessed significant progress in deep learning-based 3D vision, ranging from neural radiance field (NeRF) based 3D representation learning to applications in novel view synthesis (NVS).

Deep Learning NeRF +2

Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis

no code implementations14 Dec 2023 Yafei Hu, Quanting Xie, Vidhi Jain, Jonathan Francis, Jay Patrikar, Nikhil Keetha, Seungchan Kim, Yaqi Xie, Tianyi Zhang, Hao-Shu Fang, Shibo Zhao, Shayegan Omidshafiei, Dong-Ki Kim, Ali-akbar Agha-mohammadi, Katia Sycara, Matthew Johnson-Roberson, Dhruv Batra, Xiaolong Wang, Sebastian Scherer, Chen Wang, Zsolt Kira, Fei Xia, Yonatan Bisk

Motivated by the impressive open-set performance and content generation capabilities of web-scale, large-capacity pre-trained models (i. e., foundation models) in research fields such as Natural Language Processing (NLP) and Computer Vision (CV), we devote this survey to exploring (i) how these existing foundation models from NLP and CV can be applied to the field of general-purpose robotics, and also exploring (ii) what a robotics-specific foundation model would look like.

Compositional Inversion for Stable Diffusion Models

1 code implementation13 Dec 2023 Xulu Zhang, Xiao-Yong Wei, Jinlin Wu, Tianyi Zhang, Zhaoxiang Zhang, Zhen Lei, Qing Li

It stems from the fact that during inversion, the irrelevant semantics in the user images are also encoded, forcing the inverted concepts to occupy locations far from the core distribution in the embedding space.

Building Open-Ended Embodied Agent via Language-Policy Bidirectional Adaptation

no code implementations12 Dec 2023 Shaopeng Zhai, Jie Wang, Tianyi Zhang, Fuxian Huang, Qi Zhang, Ming Zhou, Jing Hou, Yu Qiao, Yu Liu

Building embodied agents on integrating Large Language Models (LLMs) and Reinforcement Learning (RL) have revolutionized human-AI interaction: researchers can now leverage language instructions to plan decision-making for open-ended tasks.

Decision Making Language Modelling +1

Transformer-based Selective Super-Resolution for Efficient Image Refinement

1 code implementation10 Dec 2023 Tianyi Zhang, Kishore Kasichainula, Yaoxin Zhuo, Baoxin Li, Jae-sun Seo, Yu Cao

Conventional super-resolution methods suffer from two drawbacks: substantial computational cost in upscaling an entire large image, and the introduction of extraneous or potentially detrimental information for downstream computer vision tasks during the refinement of the background.

Super-Resolution

Generating Progressive Images from Pathological Transitions via Diffusion Model

2 code implementations21 Nov 2023 Zeyu Liu, Tianyi Zhang, Yufang He, Yunlu Feng, Yu Zhao, Guanglei Zhang

Deep learning is widely applied in computer-aided pathological diagnosis, which alleviates the pathologist workload and provide timely clinical analysis.

Data Augmentation Diversity +1

Privacy-preserving design of graph neural networks with applications to vertical federated learning

no code implementations31 Oct 2023 Ruofan Wu, Mingyang Zhang, Lingjuan Lyu, Xiaolong Xu, Xiuquan Hao, Xinyi Fu, Tengfei Liu, Tianyi Zhang, Weiqiang Wang

The paradigm of vertical federated learning (VFL), where institutions collaboratively train machine learning models via combining each other's local feature or label information, has achieved great success in applications to financial risk management (FRM).

Graph Representation Learning Management +2

CPIA Dataset: A Comprehensive Pathological Image Analysis Dataset for Self-supervised Learning Pre-training

1 code implementation27 Oct 2023 Nan Ying, Yanli Lei, Tianyi Zhang, Shangqing Lyu, Chunhui Li, Sicheng Chen, Zeyu Liu, Yu Zhao, Guanglei Zhang

This paper presents the comprehensive pathological image analysis (CPIA) dataset, a large-scale SSL pre-training dataset combining 103 open-source datasets with extensive standardization.

Self-Supervised Learning Transfer Learning +1

Self-supervision meets kernel graph neural models: From architecture to augmentations

no code implementations17 Oct 2023 Jiawang Dan, Ruofan Wu, Yunpeng Liu, Baokun Wang, Changhua Meng, Tengfei Liu, Tianyi Zhang, Ningtao Wang, Xing Fu, Qi Li, Weiqiang Wang

Recently, the idea of designing neural models on graphs using the theory of graph kernels has emerged as a more transparent as well as sometimes more expressive alternative to MPNNs known as kernel graph neural networks (KGNNs).

Data Augmentation Graph Classification +2

Point-Based Radiance Fields for Controllable Human Motion Synthesis

1 code implementation5 Oct 2023 HaiTao Yu, Deheng Zhang, Peiyuan Xie, Tianyi Zhang

This paper proposes a novel controllable human motion synthesis method for fine-level deformation based on static point-based radiance fields.

Motion Synthesis Novel View Synthesis

Learning Orbitally Stable Systems for Diagrammatically Teaching

no code implementations19 Sep 2023 Weiming Zhi, Tianyi Zhang, Matthew Johnson-Roberson

In this work, we tackle the problem of teaching a robot to approach a surface and then follow cyclic motion on it, where the cycle of the motion can be arbitrarily specified by a single user-provided sketch over an image from the robot's camera.

MORPH

Reasoning about the Unseen for Efficient Outdoor Object Navigation

1 code implementation18 Sep 2023 Quanting Xie, Tianyi Zhang, Kedi Xu, Matthew Johnson-Roberson, Yonatan Bisk

We introduce a new task OUTDOOR, a new mechanism for Large Language Models (LLMs) to accurately hallucinate possible futures, and a new computationally aware success metric for pushing research forward in this more complex domain.

Navigate Object

FedGKD: Unleashing the Power of Collaboration in Federated Graph Neural Networks

no code implementations18 Sep 2023 Qiying Pan, Ruofan Wu, Tengfei Liu, Tianyi Zhang, Yifei Zhu, Weiqiang Wang

Federated training of Graph Neural Networks (GNN) has become popular in recent years due to its ability to perform graph-related tasks under data isolation scenarios while preserving data privacy.

Dataset Distillation

Instructing Robots by Sketching: Learning from Demonstration via Probabilistic Diagrammatic Teaching

no code implementations7 Sep 2023 Weiming Zhi, Tianyi Zhang, Matthew Johnson-Roberson

Diagrammatic Teaching aims to teach robots novel skills by prompting the user to sketch out demonstration trajectories on 2D images of the scene, these are then synthesised as a generative model of motion trajectories in 3D task space.

A Survey of Diffusion Based Image Generation Models: Issues and Their Solutions

no code implementations25 Aug 2023 Tianyi Zhang, Zheng Wang, Jing Huang, Mohiuddin Muhammad Tasnim, Wei Shi

Fortunately, the availability of open-source stable diffusion models and their underlying mathematical principles has enabled the academic community to extensively analyze the performance of current image generation models and make improvements based on this stable diffusion framework.

Image Generation

Software Entity Recognition with Noise-Robust Learning

1 code implementation21 Aug 2023 Tai Nguyen, Yifeng Di, Joohan Lee, Muhao Chen, Tianyi Zhang

Recognizing software entities such as library names from free-form text is essential to enable many software engineering (SE) technologies, such as traceability link recovery, automated documentation, and API recommendation.

Is Stack Overflow Obsolete? An Empirical Study of the Characteristics of ChatGPT Answers to Stack Overflow Questions

no code implementations4 Aug 2023 Samia Kabir, David N. Udo-Imeh, Bonan Kou, Tianyi Zhang

Despite this popularity, no comprehensive study has been conducted to evaluate the characteristics of ChatGPT's answers to programming questions.

Misinformation

PharmacyGPT: The AI Pharmacist

no code implementations19 Jul 2023 Zhengliang Liu, Zihao Wu, Mengxuan Hu, Bokai Zhao, Lin Zhao, Tianyi Zhang, Haixing Dai, Xianyan Chen, Ye Shen, Sheng Li, Quanzheng Li, Xiang Li, Brian Murray, Tianming Liu, Andrea Sikora

In this study, we introduce PharmacyGPT, a novel framework to assess the capabilities of large language models (LLMs) such as ChatGPT and GPT-4 in emulating the role of clinical pharmacists.

Rapid Image Labeling via Neuro-Symbolic Learning

1 code implementation18 Jun 2023 Yifeng Wang, Zhi Tu, Yiwen Xiang, Shiyuan Zhou, Xiyuan Chen, Bingxuan Li, Tianyi Zhang

To address this challenge, we propose a neuro-symbolic approach called Rapid, which infers image labeling rules from a small amount of labeled data provided by domain experts and automatically labels unannotated data using the rules.

AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback

2 code implementations NeurIPS 2023 Yann Dubois, Xuechen Li, Rohan Taori, Tianyi Zhang, Ishaan Gulrajani, Jimmy Ba, Carlos Guestrin, Percy Liang, Tatsunori B. Hashimoto

As a demonstration of the research possible in AlpacaFarm, we find that methods that use a reward model can substantially improve over supervised fine-tuning and that our reference PPO implementation leads to a +10% improvement in win-rate against Davinci003.

Instruction Following

Interactive Text-to-SQL Generation via Editable Step-by-Step Explanations

1 code implementation12 May 2023 Yuan Tian, Zheng Zhang, Zheng Ning, Toby Jia-Jun Li, Jonathan K. Kummerfeld, Tianyi Zhang

Many techniques have been proposed to automatically generate SQL from natural language, but they suffer from two issues: (1) they still make many mistakes, particularly for complex queries, and (2) they do not provide a flexible way for non-expert users to validate and refine incorrect queries.

Text to SQL Text-To-SQL

Evaluating Verifiability in Generative Search Engines

2 code implementations19 Apr 2023 Nelson F. Liu, Tianyi Zhang, Percy Liang

Generative search engines directly generate responses to user queries, along with in-line citations.

Sentence

CDFI: Cross Domain Feature Interaction for Robust Bronchi Lumen Detection

no code implementations18 Apr 2023 Jiasheng Xu, Tianyi Zhang, Yangqian Wu, Jie Yang, Guang-Zhong Yang, Yun Gu

Endobronchial intervention is increasingly used as a minimally invasive means for the treatment of pulmonary diseases.

Beyond NeRF Underwater: Learning Neural Reflectance Fields for True Color Correction of Marine Imagery

1 code implementation6 Apr 2023 Tianyi Zhang, Matthew Johnson-Roberson

The proposed technique integrates underwater light effects into a volume rendering framework with end-to-end differentiability.

NeRF

DeepLens: Interactive Out-of-distribution Data Detection in NLP Models

1 code implementation2 Mar 2023 Da Song, Zhijie Wang, Yuheng Huang, Lei Ma, Tianyi Zhang

In this work, we propose DeepLens, an interactive system that helps users detect and explore OOD issues in massive text corpora.

Text Clustering

DeepSeer: Interactive RNN Explanation and Debugging via State Abstraction

1 code implementation2 Mar 2023 Zhijie Wang, Yuheng Huang, Da Song, Lei Ma, Tianyi Zhang

The core of DeepSeer is a state abstraction method that bundles semantically similar hidden states in an RNN model and abstracts the model as a finite state machine.

Explainable Artificial Intelligence (XAI)

FairPy: A Toolkit for Evaluation of Prediction Biases and their Mitigation in Large Language Models

1 code implementation10 Feb 2023 Hrishikesh Viswanath, Tianyi Zhang

Recent studies have demonstrated that large pretrained language models (LLMs) such as BERT and GPT-2 exhibit biases in token prediction, often inherited from the data distributions present in their training corpora.

GRANDE: a neural model over directed multigraphs with application to anti-money laundering

no code implementations4 Feb 2023 Ruofan Wu, Boqun Ma, Hong Jin, Wenlong Zhao, Weiqiang Wang, Tianyi Zhang

The application of graph representation learning techniques to the area of financial risk management (FRM) has attracted significant attention recently.

Edge Classification Graph Representation Learning +1

Benchmarking Large Language Models for News Summarization

1 code implementation31 Jan 2023 Tianyi Zhang, Faisal Ladhak, Esin Durmus, Percy Liang, Kathleen McKeown, Tatsunori B. Hashimoto

Large language models (LLMs) have shown promise for automatic summarization but the reasons behind their successes are poorly understood.

Benchmarking News Summarization

LADIS: Language Disentanglement for 3D Shape Editing

1 code implementation9 Dec 2022 IAn Huang, Panos Achlioptas, Tianyi Zhang, Sergey Tulyakov, Minhyuk Sung, Leonidas Guibas

Additionally, to measure edit locality, we define a new metric that we call part-wise edit precision.

3D geometry Disentanglement

Coder Reviewer Reranking for Code Generation

1 code implementation29 Nov 2022 Tianyi Zhang, Tao Yu, Tatsunori B. Hashimoto, Mike Lewis, Wen-tau Yih, Daniel Fried, Sida I. Wang

Sampling diverse programs from a code language model and reranking with model likelihood is a popular method for code generation but it is prone to preferring degenerate solutions.

Code Generation Language Modeling +2

DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation

2 code implementations18 Nov 2022 Yuhang Lai, Chengxi Li, Yiming Wang, Tianyi Zhang, Ruiqi Zhong, Luke Zettlemoyer, Scott Wen-tau Yih, Daniel Fried, Sida Wang, Tao Yu

We introduce DS-1000, a code generation benchmark with a thousand data science problems spanning seven Python libraries, such as NumPy and Pandas.

Code Generation Memorization

Shuffle Instances-based Vision Transformer for Pancreatic Cancer ROSE Image Classification

1 code implementation14 Aug 2022 Tianyi Zhang, Youdan Feng, Yunlu Feng, Yu Zhao, Yanli Lei, Nan Ying, Zhiling Yan, Yufang He, Guanglei Zhang

The rapid on-site evaluation (ROSE) technique can signifi-cantly accelerate the diagnosis of pancreatic cancer by im-mediately analyzing the fast-stained cytopathological images.

image-classification Image Classification

Multi-class Classification from Multiple Unlabeled Datasets with Partial Risk Regularization

1 code implementation4 Jul 2022 Yuting Tang, Nan Lu, Tianyi Zhang, Masashi Sugiyama

Recent years have witnessed a great success of supervised deep learning, where predictive models were trained from a large amount of fully labeled data.

Multi-class Classification

Pancreatic Cancer ROSE Image Classification Based on Multiple Instance Learning with Shuffle Instances

no code implementations7 Jun 2022 Tianyi Zhang, Youdan Feng, Yunlu Feng, Guanglei Zhang

Computer-aided diagnosis (CAD) using the deep learning method has the potential to solve the problem of insufficient pathology staffing.

Diagnostic image-classification +2

Decentralized Training of Foundation Models in Heterogeneous Environments

1 code implementation2 Jun 2022 Binhang Yuan, Yongjun He, Jared Quincy Davis, Tianyi Zhang, Tri Dao, Beidi Chen, Percy Liang, Christopher Re, Ce Zhang

Our key technical contribution is a scheduling algorithm that allocates different computational "tasklets" in the training of foundation models to a group of decentralized GPU devices connected by a slow heterogeneous network.

Scheduling

TempLM: Distilling Language Models into Template-Based Generators

1 code implementation23 May 2022 Tianyi Zhang, Mina Lee, Lisa Li, Ende Shen, Tatsunori B. Hashimoto

While pretrained language models (PLMs) have greatly improved text generation, they have also been known to produce unfaithful or inappropriate content.

Text Generation

Model-Based Neural Network and Its Application to Line Spectral Estimation

no code implementations14 Feb 2022 Yi Jiang, Tianyi Zhang, Wei zhang

Owing to the same layered form as an ANN, a MNN can also be optimized using the back-propagation (BP) algorithm.

parameter estimation

Rethinking Importance Weighting for Transfer Learning

no code implementations19 Dec 2021 Nan Lu, Tianyi Zhang, Tongtong Fang, Takeshi Teshima, Masashi Sugiyama

A key assumption in supervised learning is that training and test data follow the same probability distribution.

Selection bias Transfer Learning

PMFL: Partial Meta-Federated Learning for heterogeneous tasks and its applications on real-world medical records

1 code implementation10 Dec 2021 Tianyi Zhang, Shirui Zhang, Ziwei Chen, Dianbo Liu

Federated machine learning is a versatile and flexible tool to utilize distributed data from different sources, especially when communication technology develops rapidly and an unprecedented amount of data could be collected on mobile devices nowadays.

Federated Learning Meta-Learning +1

On the Opportunities and Risks of Foundation Models

2 code implementations16 Aug 2021 Rishi Bommasani, Drew A. Hudson, Ehsan Adeli, Russ Altman, Simran Arora, Sydney von Arx, Michael S. Bernstein, Jeannette Bohg, Antoine Bosselut, Emma Brunskill, Erik Brynjolfsson, Shyamal Buch, Dallas Card, Rodrigo Castellon, Niladri Chatterji, Annie Chen, Kathleen Creel, Jared Quincy Davis, Dora Demszky, Chris Donahue, Moussa Doumbouya, Esin Durmus, Stefano Ermon, John Etchemendy, Kawin Ethayarajh, Li Fei-Fei, Chelsea Finn, Trevor Gale, Lauren Gillespie, Karan Goel, Noah Goodman, Shelby Grossman, Neel Guha, Tatsunori Hashimoto, Peter Henderson, John Hewitt, Daniel E. Ho, Jenny Hong, Kyle Hsu, Jing Huang, Thomas Icard, Saahil Jain, Dan Jurafsky, Pratyusha Kalluri, Siddharth Karamcheti, Geoff Keeling, Fereshte Khani, Omar Khattab, Pang Wei Koh, Mark Krass, Ranjay Krishna, Rohith Kuditipudi, Ananya Kumar, Faisal Ladhak, Mina Lee, Tony Lee, Jure Leskovec, Isabelle Levent, Xiang Lisa Li, Xuechen Li, Tengyu Ma, Ali Malik, Christopher D. Manning, Suvir Mirchandani, Eric Mitchell, Zanele Munyikwa, Suraj Nair, Avanika Narayan, Deepak Narayanan, Ben Newman, Allen Nie, Juan Carlos Niebles, Hamed Nilforoshan, Julian Nyarko, Giray Ogut, Laurel Orr, Isabel Papadimitriou, Joon Sung Park, Chris Piech, Eva Portelance, Christopher Potts, aditi raghunathan, Rob Reich, Hongyu Ren, Frieda Rong, Yusuf Roohani, Camilo Ruiz, Jack Ryan, Christopher Ré, Dorsa Sadigh, Shiori Sagawa, Keshav Santhanam, Andy Shih, Krishnan Srinivasan, Alex Tamkin, Rohan Taori, Armin W. Thomas, Florian Tramèr, Rose E. Wang, William Wang, Bohan Wu, Jiajun Wu, Yuhuai Wu, Sang Michael Xie, Michihiro Yasunaga, Jiaxuan You, Matei Zaharia, Michael Zhang, Tianyi Zhang, Xikun Zhang, Yuhui Zhang, Lucia Zheng, Kaitlyn Zhou, Percy Liang

AI is undergoing a paradigm shift with the rise of models (e. g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks.

Transfer Learning

From block-Toeplitz matrices to differential equations on graphs: towards a general theory for scalable masked Transformers

1 code implementation16 Jul 2021 Krzysztof Choromanski, Han Lin, Haoxian Chen, Tianyi Zhang, Arijit Sehanobish, Valerii Likhosherstov, Jack Parker-Holder, Tamas Sarlos, Adrian Weller, Thomas Weingarten

In this paper we provide, to the best of our knowledge, the first comprehensive approach for incorporating various masking mechanisms into Transformers architectures in a scalable way.

Graph Attention

PSRR-MaxpoolNMS: Pyramid Shifted MaxpoolNMS with Relationship Recovery

no code implementations CVPR 2021 Tianyi Zhang, Jie Lin, Peng Hu, Bin Zhao, Mohamed M. Sabry Aly

Unlike convolutions which are inherently parallel, the de-facto standard for NMS, namely GreedyNMS, cannot be easily parallelized and thus could be the performance bottleneck in convolutional object detection pipelines.

object-detection Object Detection

On the Inductive Bias of Masked Language Modeling: From Statistical to Syntactic Dependencies

1 code implementation NAACL 2021 Tianyi Zhang, Tatsunori Hashimoto

We study how masking and predicting tokens in an unsupervised fashion can give rise to linguistic structures and downstream performance gains.

Inductive Bias Language Modeling +2

Sinusoidal Parameter Estimation from Signed Measurements via Majorization-Minimization Based RELAX

no code implementations21 Mar 2021 Jiaying Ren, Tianyi Zhang, Jian Li, Petre Stoica

In a previous paper, a relaxation-based algorithm, referred to as 1bRELAX, has been proposed to iteratively maximize the likelihood function.

Computational Efficiency parameter estimation

Joint RFI Mitigation and Radar Echo Recovery for One-Bit UWB Radar

no code implementations19 Mar 2021 Tianyi Zhang, Jiaying Ren, Jian Li, Lam H. Nguyen, Petre Stoica

Radio frequency interference (RFI) mitigation and radar echo recovery are critically important for the proper functioning of ultra-wideband (UWB) radar systems using one-bit sampling techniques.

parameter estimation

Learning to Stop with Surprisingly Few Samples

no code implementations19 Feb 2021 Daniel Russo, Assaf Zeevi, Tianyi Zhang

We consider a discounted infinite horizon optimal stopping problem.

RFI Mitigation for One-bit UWB Radar Systems

no code implementations17 Feb 2021 Tianyi Zhang, Jiaying Ren, Jian Li, Lam H. Nguyen, Petre Stoica

A one-bit UWB system obtains its signed measurements via a low-cost and high rate sampling scheme, referred to as the Continuous Time Binary Value (CTBV) technology.

Computational Efficiency Quantization

Can Steering Wheel Detect Your Driving Fatigue?

no code implementations18 Oct 2020 Jianchao Lu, Xi Zheng, Tianyi Zhang, Michael Sheng, Chen Wang, Jiong Jin, Shui Yu, Wanlei Zhou

In this paper, we propose a novel driver fatigue detection method by embedding surface electromyography (sEMG) sensors on a steering wheel.

ICS-Assist: Intelligent Customer Inquiry Resolution Recommendation in Online Customer Service for Large E-Commerce Businesses

no code implementations22 Aug 2020 Min Fu, Jiwei Guan, Xi Zheng, Jie zhou, Jianchao Lu, Tianyi Zhang, Shoujie Zhuo, Lijun Zhan, Jian Yang

Existing solution recommendation methods for online customer service are unable to determine the best solutions at runtime, leading to poor satisfaction of end customers.

Modeling the Field Value Variations and Field Interactions Simultaneously for Fraud Detection

no code implementations8 Aug 2020 Dongbo Xi, Bowen Song, Fuzhen Zhuang, Yongchun Zhu, Shuai Chen, Tianyi Zhang, Yuan Qi, Qing He

In this paper, we propose the Dual Importance-aware Factorization Machines (DIFM), which exploits the internal field information among users' behavior sequence from dual perspectives, i. e., field value variations and field interactions simultaneously for fraud detection.

Fraud Detection Management

A One-step Approach to Covariate Shift Adaptation

no code implementations8 Jul 2020 Tianyi Zhang, Ikko Yamane, Nan Lu, Masashi Sugiyama

A default assumption in many machine learning scenarios is that the training and test samples are drawn from the same probability distribution.

Revisiting Few-sample BERT Fine-tuning

1 code implementation ICLR 2021 Tianyi Zhang, Felix Wu, Arzoo Katiyar, Kilian Q. Weinberger, Yoav Artzi

We empirically test the impact of these factors, and identify alternative practices that resolve the commonly observed instability of the process.

Demystifying Orthogonal Monte Carlo and Beyond

no code implementations NeurIPS 2020 Han Lin, Haoxian Chen, Tianyi Zhang, Clement Laroche, Krzysztof Choromanski

Orthogonal Monte Carlo (OMC) is a very effective sampling algorithm imposing structural geometric conditions (orthogonality) on samples for variance reduction.

Stereo Endoscopic Image Super-Resolution Using Disparity-Constrained Parallel Attention

no code implementations19 Mar 2020 Tianyi Zhang, Yun Gu, Xiaolin Huang, Enmei Tu, Jie Yang

In particular, we incorporate a disparity-based constraint mechanism into the generation of SR images in a deep neural network framework with an additional atrous parallax-attention modules.

Image Super-Resolution

Supporting OpenMP 5.0 Tasks in hpxMP -- A study of an OpenMP implementation within Task Based Runtime Systems

1 code implementation19 Feb 2020 Tianyi Zhang, Shahrzad Shirzad, Bibek Wagle, Adrian S. Lemoine, Patrick Diehl, Hartmut Kaiser

This paper is a follow-up paper on the fundamental implementation of hpxMP, an implementation of the OpenMP standard which utilizes the C++ standard library for Parallelism and Concurrency (HPX) to schedule and manage tasks.

Distributed, Parallel, and Cluster Computing Programming Languages

An Analysis of Adversarial Attacks and Defenses on Autonomous Driving Models

1 code implementation6 Feb 2020 Yao Deng, Xi Zheng, Tianyi Zhang, Chen Chen, Guannan Lou, Miryung Kim

We derive several implications for system and middleware builders: (1) when adding a defense component against adversarial attacks, it is important to deploy multiple defense methods in tandem to achieve a good coverage of various attacks, (2) a blackbox attack is much less effective compared with a white-box attack, implying that it is important to keep model details (e. g., model architecture, hyperparameters) confidential via model obfuscation, and (3) driving models with a complex architecture are preferred if computing resources permit as they are more resilient to adversarial attacks than simple models.

Autonomous Driving

Identifying Mislabeled Data using the Area Under the Margin Ranking

3 code implementations NeurIPS 2020 Geoff Pleiss, Tianyi Zhang, Ethan R. Elenberg, Kilian Q. Weinberger

Not all data in a typical training set help with generalization; some samples can be overly ambiguous or outrightly mislabeled.

Mitigating Overfitting in Supervised Classification from Two Unlabeled Datasets: A Consistent Risk Correction Approach

no code implementations20 Oct 2019 Nan Lu, Tianyi Zhang, Gang Niu, Masashi Sugiyama

The recently proposed unlabeled-unlabeled (UU) classification method allows us to train a binary classifier only from two unlabeled datasets with different class priors.

Classification General Classification

QPyTorch: A Low-Precision Arithmetic Simulation Framework

2 code implementations9 Oct 2019 Tianyi Zhang, Zhiqiu Lin, Guandao Yang, Christopher De Sa

Low-precision training reduces computational cost and produces efficient models.

Quantization

Detecting Noisy Training Data with Loss Curves

no code implementations25 Sep 2019 Geoff Pleiss, Tianyi Zhang, Ethan R. Elenberg, Kilian Q. Weinberger

This paper introduces a new method to discover mislabeled training samples and to mitigate their impact on the training process of deep networks.

Fixed-price Diffusion Mechanism Design

no code implementations14 May 2019 Tianyi Zhang, Dengji Zhao, Wen Zhang, Xuming He

We consider a fixed-price mechanism design setting where a seller sells one item via a social network, but the seller can only directly communicate with her neighbours initially.

SWALP : Stochastic Weight Averaging in Low-Precision Training

3 code implementations26 Apr 2019 Guandao Yang, Tianyi Zhang, Polina Kirichenko, Junwen Bai, Andrew Gordon Wilson, Christopher De Sa

Low precision operations can provide scalability, memory savings, portability, and energy efficiency.

An Introduction to hpxMP: A Modern OpenMP Implementation Leveraging HPX, An Asynchronous Many-Task System

1 code implementation7 Mar 2019 Tianyi Zhang, Shahrzad Shirzad, Patrick Diehl, R. Tohid, Weile Wei, Hartmut Kaiser

Not only must users port their own codes, but often users rely on highly optimized libraries such as BLAS and LAPACK which use OpenMP for parallization.

Distributed, Parallel, and Cluster Computing

Simplifying Graph Convolutional Networks

7 code implementations19 Feb 2019 Felix Wu, Tianyi Zhang, Amauri Holanda de Souza Jr., Christopher Fifty, Tao Yu, Kilian Q. Weinberger

Graph Convolutional Networks (GCNs) and their variants have experienced significant attention and have become the de facto methods for learning graph representations.

Graph Regression Image Classification +5

Stochastic Gradient Hamiltonian Monte Carlo with Variance Reduction for Bayesian Inference

no code implementations29 Mar 2018 Zhize Li, Tianyi Zhang, Shuyu Cheng, Jun Zhu, Jian Li

In this paper, we apply the variance reduction tricks on Hamiltonian Monte Carlo and achieve better theoretical convergence results compared with the variance-reduced Langevin dynamics.

Bayesian Inference

Cannot find the paper you are looking for? You can Submit a new open access paper.