Search Results for author:
Found 163 papers, 76 papers with code
Splitting vs. Merging: Mining Object Regions with Discrepancy and Intersection Loss for Weakly Supervised Semantic Segmentation
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.
Incorporating Uncertainty-Guided and Top-k Codebook Matching for Real-World Blind Image Super-Resolution
Experimental results demonstrate significant improvements in texture realism and reconstruction fidelity compared to existing methods.
A Systematic Investigation on Deep Learning-Based Omnidirectional Image and Video Super-Resolution
This paper presents a systematic review of recent progress in omnidirectional image and video super-resolution, focusing on deep learning-based methods.
Deployability-Centric Infrastructure-as-Code Generation: An LLM-based Iterative Framework
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.
Visual Embodied Brain: Let Multimodal Large Language Models See, Think, and Control in Spaces
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.
Bi-Manual Joint Camera Calibration and Scene Representation
Bi-JCR enables multiple robot manipulators, each with cameras mounted, to circumvent taking images of calibration markers.
Active Layer-Contrastive Decoding Reduces Hallucination in Large Language Model Generation
Recent decoding methods improve the factuality of large language models~(LLMs) by refining how the next token is selected during generation.
From Single Images to Motion Policies via Video-Generation Environment Representations
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.
Distributional Soft Actor-Critic with Harmonic Gradient for Safe and Efficient Autonomous Driving in Multi-lane Scenarios
Reinforcement learning (RL), known for its self-evolution capability, offers a promising approach to training high-level autonomous driving systems.
Enhancing Code Generation via Bidirectional Comment-Level Mutual Grounding
Large Language Models (LLMs) have demonstrated unprecedented capability in code generation.
Neighbor-Based Feature and Index Enhancement for Person Re-Identification
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.
70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float
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
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.
GraphSeg: Segmented 3D Representations via Graph Edge Addition and Contraction
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.
Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy
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)
Your voice is your voice: Supporting Self-expression through Speech Generation and LLMs in Augmented and Alternative Communication
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
Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models
Large Language Models (LLMs) have demonstrated remarkable capabilities in complex tasks.
SurgRAW: Multi-Agent Workflow with Chain-of-Thought Reasoning for Surgical Intelligence
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.
Infinite Leagues Under the Sea: Photorealistic 3D Underwater Terrain Generation by Latent Fractal Diffusion Models
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.
Towards Ambiguity-Free Spatial Foundation Model: Rethinking and Decoupling Depth Ambiguity
Depth ambiguity is a fundamental challenge in spatial scene understanding, especially in transparent scenes where single-depth estimates fail to capture full 3D structure.
PathRWKV: Enabling Whole Slide Prediction with Recurrent-Transformer
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.
From Poses to Identity: Training-Free Person Re-Identification via Feature Centralization
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.
Ranked #1 on
Cross-Modal Person Re-Identification
on SYSU-MM01
Sentence-level Reward Model can Generalize Better for Aligning LLM from Human Preference
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.
DOSE3 : Diffusion-based Out-of-distribution detection on SE(3) trajectories
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
Text-to-SQL models, which parse natural language (NL) questions to executable SQL queries, are increasingly adopted in real-world applications.
Soybean pod and seed counting in both outdoor fields and indoor laboratories using unions of deep neural networks
Automatic counting soybean pods and seeds in outdoor fields allows for rapid yield estimation before harvesting, while indoor laboratory counting offers greater accuracy.
Mean of Means: Human Localization with Calibration-free and Unconstrained Camera Settings (extended version)
Accurate human localization is crucial for various applications, especially in the Metaverse era.
A Training-Free Length Extrapolation Approach for LLMs: Greedy Attention Logit Interpolation (GALI)
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.
Ranked #1 on
Long-Context Understanding
on L-Eval
MASTER: A Multi-Agent System with LLM Specialized MCTS
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).
Scalable Benchmarking and Robust Learning for Noise-Free Ego-Motion and 3D Reconstruction from Noisy Video
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.
Stronger Than You Think: Benchmarking Weak Supervision on Realistic Tasks
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.
A Multi-Agent Framework for Extensible Structured Text Generation in PLCs
In order to verify and improve the quality of the generated code, we designed an adaptable code checker.
MambaXCTrack: Mamba-based Tracker with SSM Cross-correlation and Motion Prompt for Ultrasound Needle Tracking
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.
GraphRPM: Risk Pattern Mining on Industrial Large Attributed Graphs
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.
AWARE Narrator and the Utilization of Large Language Models to Extract Behavioral Insights from Smartphone Sensing Data
Smartphones, equipped with an array of sensors, have become valuable tools for personal sensing.
Context-Aware Token Selection and Packing for Enhanced Vision Transformer
In recent years, the long-range attention mechanism of vision transformers has driven significant performance breakthroughs across various computer vision tasks.
Diffusion Transformer Policy
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.
Nonlinear Bayesian Filtering with Natural Gradient Gaussian Approximation
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.
MMDS: A Multimodal Medical Diagnosis System Integrating Image Analysis and Knowledge-based Departmental Consultation
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.
A new approach for fine-tuning sentence transformers for intent classification and out-of-scope detection tasks
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.
Collu-Bench: A Benchmark for Predicting Language Model Hallucinations in Code
Despite their success, large language models (LLMs) face the critical challenge of hallucinations, generating plausible but incorrect content.
SpaLLM: Unified Compressive Adaptation of Large Language Models with Sketching
In response to these known limitations, we propose SpaLLM (Sketched Parameter Adaptation of LLMs), a novel compressive adaptation approach for LLMs.
SplaTraj: Camera Trajectory Generation with Semantic Gaussian Splatting
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
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.
CodeJudge: Evaluating Code Generation with Large Language Models
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.
Robust Incremental Structure-from-Motion with Hybrid Features
In this work, we introduce an incremental SfM system that, in addition to points, leverages lines and their structured geometric relations.
Research on Predicting Public Opinion Event Heat Levels Based on Large Language Models
Next, we randomly selected 250 events from each heat level, totalling 1, 000 events, to build the evaluation dataset.
CLSP: High-Fidelity Contrastive Language-State Pre-training for Agent State Representation
Then, we deploy contrastive learning to train the CLSP encoder to effectively represent precise state information.
Proof Automation with Large Language Models
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
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
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.
Selective Prompt Anchoring for Code Generation
To mitigate this issue, we propose Selective Prompt Anchoring (SPA) to guide code LLMs to pay more attention to user intent when generating code.
Mean of Means: A 10-dollar Solution for Human Localization with Calibration-free and Unconstrained Camera Settings
Accurate human localization is crucial for various applications, especially in the Metaverse era.
Phases Calibration of RIS Using Backpropagation Algorithm
Reconfigurable intelligent surface (RIS) technology has emerged in recent years as a promising solution to the ever-increasing demand for wireless communication capacity.
RecGS: Removing Water Caustic with Recurrent Gaussian Splatting
Water caustics are commonly observed in seafloor imaging data from shallow-water areas.
LeanQuant: Accurate Large Language Model Quantization with Loss-Error-Aware Grid
Large language models (LLMs) have numerous applications across various domains, but their high computational and memory demands pose significant deployment challenges.
3D Foundation Models Enable Simultaneous Geometry and Pose Estimation of Grasped Objects
We empirically evaluate our approach on a robot manipulator holding a diverse set of real-world objects.
Leveraging LLMs to Predict Affective States via Smartphone Sensor Features
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
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.
IDentity with Locality: An ideal hash for gene sequence search
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.
NeST: Neural Stress Tensor Tomography by leveraging 3D Photoelasticity
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.
Convolutional Unscented Kalman Filter for Multi-Object Tracking with Outliers
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).
Streaming quanta sensors for online, high-performance imaging and vision
To the best of our knowledge, our approach is the first to achieve online, real-time image reconstruction on QIS.
PDDLEGO: Iterative Planning in Textual Environments
A recent, promising line of work uses LLMs to generate a formal representation of the environment that can be solved by a symbolic planner.
Learning Shared RGB-D Fields: Unified Self-supervised Pre-training for Label-efficient LiDAR-Camera 3D Perception
Constructing large-scale labeled datasets for multi-modal perception model training in autonomous driving presents significant challenges.
KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization
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.
Unifying Scene Representation and Hand-Eye Calibration with 3D Foundation Models
We demonstrate that JCR can build effective scene representations using a low-cost RGB camera attached to a manipulator, without prior calibration.
Human Latency Conversational Turns for Spoken Avatar Systems
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.
DarkGS: Learning Neural Illumination and 3D Gaussians Relighting for Robotic Exploration in the Dark
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
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.
NoMAD-Attention: Efficient LLM Inference on CPUs Through Multiply-add-free Attention
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.
PROC2PDDL: Open-Domain Planning Representations from Texts
Planning in a text-based environment continues to be a major challenge for AI systems.
Uncertainty-Based Extensible Codebook for Discrete Federated Learning in Heterogeneous Data Silos
Federated learning (FL), aimed at leveraging vast distributed datasets, confronts a crucial challenge: the heterogeneity of data across different silos.
Effective Two-Stage Knowledge Transfer for Multi-Entity Cross-Domain Recommendation
In the end, the extracted common knowledge is adopted for target entity model training.
Customizable Perturbation Synthesis for Robust SLAM Benchmarking
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.
Learning Scalable Structural Representations for Link Prediction with Bloom Signatures
We further show that any type of neighborhood overlap-based heuristic can be estimated by a neural network that takes Bloom signatures as input.
Multi-modality Affinity Inference for Weakly Supervised 3D Semantic Segmentation
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.
DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision
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).
Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis
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
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
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.
Transformer-based Selective Super-Resolution for Efficient Image Refinement
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.
Text as Image: Learning Transferable Adapter for Multi-Label Classification
Pre-trained vision-language models have notably accelerated progress of open-world concept recognition.
Generating Progressive Images from Pathological Transitions via Diffusion Model
Deep learning is widely applied in computer-aided pathological diagnosis, which alleviates the pathologist workload and provide timely clinical analysis.
PuzzleTuning: Explicitly Bridge Pathological and Natural Image with Puzzles
Pathological image analysis is a crucial field in computer vision.
Patch-based Selection and Refinement for Early Object Detection
Early object detection (OD) is a crucial task for the safety of many dynamic systems.
Privacy-preserving design of graph neural networks with applications to vertical federated learning
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).
CPIA Dataset: A Comprehensive Pathological Image Analysis Dataset for Self-supervised Learning Pre-training
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-supervision meets kernel graph neural models: From architecture to augmentations
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).
Point-Based Radiance Fields for Controllable Human Motion Synthesis
This paper proposes a novel controllable human motion synthesis method for fine-level deformation based on static point-based radiance fields.
Learning Orbitally Stable Systems for Diagrammatically Teaching
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.
Reasoning about the Unseen for Efficient Outdoor Object Navigation
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.
FedGKD: Unleashing the Power of Collaboration in Federated Graph Neural Networks
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.
Instructing Robots by Sketching: Learning from Demonstration via Probabilistic Diagrammatic Teaching
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
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.
Software Entity Recognition with Noise-Robust Learning
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
Despite this popularity, no comprehensive study has been conducted to evaluate the characteristics of ChatGPT's answers to programming questions.
PharmacyGPT: The AI Pharmacist
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
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.
The Effect of Masking Strategies on Knowledge Retention by Language Models
To foster reproducibility, the code, as well as the data used in this paper, are openly available.
Do Large Language Models Pay Similar Attention Like Human Programmers When Generating Code?
Large Language Models (LLMs) have recently been widely used for code generation.
SAD: Semi-Supervised Anomaly Detection on Dynamic Graphs
Anomaly detection aims to distinguish abnormal instances that deviate significantly from the majority of benign ones.
AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback
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.
Interactive Text-to-SQL Generation via Editable Step-by-Step Explanations
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.
Evaluating Verifiability in Generative Search Engines
Generative search engines directly generate responses to user queries, along with in-line citations.
CDFI: Cross Domain Feature Interaction for Robust Bronchi Lumen Detection
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
The proposed technique integrates underwater light effects into a volume rendering framework with end-to-end differentiability.
DeepLens: Interactive Out-of-distribution Data Detection in NLP Models
In this work, we propose DeepLens, an interactive system that helps users detect and explore OOD issues in massive text corpora.
DeepSeer: Interactive RNN Explanation and Debugging via State Abstraction
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.
Human-in-the-Loop Schema Induction
Schema induction builds a graph representation explaining how events unfold in a scenario.
FairPy: A Toolkit for Evaluation of Prediction Biases and their Mitigation in Large Language Models
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
The application of graph representation learning techniques to the area of financial risk management (FRM) has attracted significant attention recently.
Efficient Graph Field Integrators Meet Point Clouds
We present two new classes of algorithms for efficient field integration on graphs encoding point clouds.
Benchmarking Large Language Models for News Summarization
Large language models (LLMs) have shown promise for automatic summarization but the reasons behind their successes are poorly understood.
CellMix: A General Instance Relationship based Method for Data Augmentation Towards Pathology Image Classification
In pathology image analysis, obtaining and maintaining high-quality annotated samples is an extremely labor-intensive task.
LADIS: Language Disentanglement for 3D Shape Editing
Additionally, to measure edit locality, we define a new metric that we call part-wise edit precision.
Coder Reviewer Reranking for Code Generation
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.
Ranked #34 on
Code Generation
on MBPP
DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation
We introduce DS-1000, a code generation benchmark with a thousand data science problems spanning seven Python libraries, such as NumPy and Pandas.
Holistic Evaluation of Language Models
We present Holistic Evaluation of Language Models (HELM) to improve the transparency of language models.
CREATIVESUMM: Shared Task on Automatic Summarization for Creative Writing
We detail the process of curating these datasets for the task, as well as the metrics used for the evaluation of the submissions.
Shuffle Instances-based Vision Transformer for Pancreatic Cancer ROSE Image Classification
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.
Multi-class Classification from Multiple Unlabeled Datasets with Partial Risk Regularization
Recent years have witnessed a great success of supervised deep learning, where predictive models were trained from a large amount of fully labeled data.
Pancreatic Cancer ROSE Image Classification Based on Multiple Instance Learning with Shuffle Instances
Computer-aided diagnosis (CAD) using the deep learning method has the potential to solve the problem of insufficient pathology staffing.
Decentralized Training of Foundation Models in Heterogeneous Environments
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.
TempLM: Distilling Language Models into Template-Based Generators
While pretrained language models (PLMs) have greatly improved text generation, they have also been known to produce unfaithful or inappropriate content.
Model-Based Neural Network and Its Application to Line Spectral Estimation
Owing to the same layered form as an ANN, a MNN can also be optimized using the back-propagation (BP) algorithm.
MSHT: Multi-stage Hybrid Transformer for the ROSE Image Analysis of Pancreatic Cancer
Pancreatic cancer is one of the most malignant cancers in the world, which deteriorates rapidly with very high mortality.
Rethinking Importance Weighting for Transfer Learning
A key assumption in supervised learning is that training and test data follow the same probability distribution.
PMFL: Partial Meta-Federated Learning for heterogeneous tasks and its applications on real-world medical records
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.
Learning Cross-Scale Visual Representations for Real-Time Image Geo-Localization
Robot localization remains a challenging task in GPS denied environments.
On the Opportunities and Risks of Foundation Models
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.
From block-Toeplitz matrices to differential equations on graphs: towards a general theory for scalable masked Transformers
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.
PSRR-MaxpoolNMS: Pyramid Shifted MaxpoolNMS with Relationship Recovery
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.
On the Inductive Bias of Masked Language Modeling: From Statistical to Syntactic Dependencies
We study how masking and predicting tokens in an unsupervised fashion can give rise to linguistic structures and downstream performance gains.
Sinusoidal Parameter Estimation from Signed Measurements via Majorization-Minimization Based RELAX
In a previous paper, a relaxation-based algorithm, referred to as 1bRELAX, has been proposed to iteratively maximize the likelihood function.
Joint RFI Mitigation and Radar Echo Recovery for One-Bit UWB Radar
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.
Learning to Stop with Surprisingly Few Samples
We consider a discounted infinite horizon optimal stopping problem.
RFI Mitigation for One-bit UWB Radar Systems
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.
Second- and third-order optical susceptibilities in bidimensional semiconductors near excitons states
Semiconducting Transition Metal Dichalcogenides (TMDs) have significant nonlinear optical effects.
Mesoscale and Nanoscale Physics
Generative Adversarial Network based Heuristics for Sampling-based Path Planning
Sampling-based path planning is a popular methodology for robot path planning.
Can Steering Wheel Detect Your Driving Fatigue?
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
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
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.
A One-step Approach to Covariate Shift Adaptation
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
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
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
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.
Supporting OpenMP 5.0 Tasks in hpxMP -- A study of an OpenMP implementation within Task Based Runtime Systems
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
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.
Identifying Mislabeled Data using the Area Under the Margin Ranking
Not all data in a typical training set help with generalization; some samples can be overly ambiguous or outrightly mislabeled.
Scalable NAS with Factorizable Architectural Parameters
Neural Architecture Search (NAS) is an emerging topic in machine learning and computer vision.
Mitigating Overfitting in Supervised Classification from Two Unlabeled Datasets: A Consistent Risk Correction Approach
The recently proposed unlabeled-unlabeled (UU) classification method allows us to train a binary classifier only from two unlabeled datasets with different class priors.
QPyTorch: A Low-Precision Arithmetic Simulation Framework
Low-precision training reduces computational cost and produces efficient models.
Detecting Noisy Training Data with Loss Curves
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
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
Low precision operations can provide scalability, memory savings, portability, and energy efficiency.
BERTScore: Evaluating Text Generation with BERT
We propose BERTScore, an automatic evaluation metric for text generation.
An Introduction to hpxMP: A Modern OpenMP Implementation Leveraging HPX, An Asynchronous Many-Task System
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
Graph Convolutional Networks (GCNs) and their variants have experienced significant attention and have become the de facto methods for learning graph representations.
Ranked #3 on
Text Classification
on Ohsumed
Stochastic Gradient Hamiltonian Monte Carlo with Variance Reduction for Bayesian Inference
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.
Decoupled Spatial Neural Attention for Weakly Supervised Semantic Segmentation
In our work, we focus on the weakly supervised semantic segmentation with image label annotations.
