Search Results for author:
Found 103 papers, 39 papers with code
Understanding the Tradeoff between Cost and Quality of Expert Annotations for Keyphrase Extraction
We evaluate these annotation strategies with respect to their cost and on the task of learning keyphrase extraction models applied with an experimental dataset in the real-estate domain.
Seed1.5-VL Technical Report
We present Seed1. 5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning.
Low-bit Model Quantization for Deep Neural Networks: A Survey
Therefore, it has become increasingly popular and critical to investigate how to perform the conversion and how to compensate for the information loss.
A Thin Flexible Acoustic Transducer with piezoelectric-actuated microdomes for Underwater Communication
This paper presents a flexible thin-film underwater transducer based on a mesoporous PVDF membrane embedded with piezoelectrical-actuated microdomes.
NTIRE 2025 Challenge on Image Super-Resolution ($\times$4): Methods and Results
This paper presents the NTIRE 2025 image super-resolution ($\times$4) challenge, one of the associated competitions of the 10th NTIRE Workshop at CVPR 2025.
NTIRE 2025 Challenge on Real-World Face Restoration: Methods and Results
This paper provides a review of the NTIRE 2025 challenge on real-world face restoration, highlighting the proposed solutions and the resulting outcomes.
JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronization
This paper introduces JavisDiT, a novel Joint Audio-Video Diffusion Transformer designed for synchronized audio-video generation (JAVG).
UniMoMo: Unified Generative Modeling of 3D Molecules for De Novo Binder Design
The design of target-specific molecules such as small molecules, peptides, and antibodies is vital for biological research and drug discovery.
OmniScience: A Domain-Specialized LLM for Scientific Reasoning and Discovery
Large Language Models (LLMs) have demonstrated remarkable potential in advancing scientific knowledge and addressing complex challenges.
A Modular Dataset to Demonstrate LLM Abstraction Capability
Large language models (LLMs) exhibit impressive capabilities but struggle with reasoning errors due to hallucinations and flawed logic.
UniMamba: Unified Spatial-Channel Representation Learning with Group-Efficient Mamba for LiDAR-based 3D Object Detection
Inspired by the impressive performance of State Space Models (SSM) achieved in the field of 2D vision tasks, in this paper, we propose a novel Unified Mamba (UniMamba), which seamlessly integrates the merits of 3D convolution and SSM in a concise multi-head manner, aiming to perform "local and global" spatial context aggregation efficiently and simultaneously.
Fast Critical Clearing Time Calculation for Power Systems with Synchronous and Asynchronous Generation
The increasing penetration of renewables is replacing traditional synchronous generation in modern power systems with low-inertia asynchronous converter-interfaced generators (CIGs).
CondiQuant: Condition Number Based Low-Bit Quantization for Image Super-Resolution
Experimentally, we observe that the degradation of quantization is mainly attributed to the quantization of activation instead of model weights.
Robust 6DoF Pose Tracking Considering Contour and Interior Correspondence Uncertainty for AR Assembly Guidance
It utilizes a fan-shaped search strategy to refine correspondences and models local contour shape and noise uncertainty as mixed probability distribution, resulting in a highly robust contour energy function.
BiMaCoSR: Binary One-Step Diffusion Model Leveraging Flexible Matrix Compression for Real Super-Resolution
One is to compress the DM into 1-bit, aka binarization, alleviating the storage and computation pressure.
SCDiar: a streaming diarization system based on speaker change detection and speech recognition
In hours-long meeting scenarios, real-time speech stream often struggles with achieving accurate speaker diarization, commonly leading to speaker identification and speaker count errors.
Distributed Model Predictive Control Design for Multi-agent Systems via Bayesian Optimization
This paper introduces a new approach that leverages Multi-agent Bayesian Optimization (MABO) to design Distributed Model Predictive Control (DMPC) schemes for multi-agent systems.
Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation
This system includes two foundation components: a large-scale shape generation model -- Hunyuan3D-DiT, and a large-scale texture synthesis model -- Hunyuan3D-Paint.
UAV-DETR: Efficient End-to-End Object Detection for Unmanned Aerial Vehicle Imagery
End-to-end models that do not depend on such manually designed components are mainly designed for natural images, which are less effective for UAV imagery.
ACQ: A Unified Framework for Automated Programmatic Creativity in Online Advertising
ACQ comprises two components: a prediction module to estimate the cost of a photo under different numbers of ad creatives, and an allocation module to decide the quota for photos considering their estimated costs in the prediction module.
Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent
In this paper, we introduce Hunyuan-Large, which is currently the largest open-source Transformer-based mixture of experts model, with a total of 389 billion parameters and 52 billion activation parameters, capable of handling up to 256K tokens.
Learning Identifiable Factorized Causal Representations of Cellular Responses
The study of cells and their responses to genetic or chemical perturbations promises to accelerate the discovery of therapeutic targets.
Delving into the Reversal Curse: How Far Can Large Language Models Generalize?
(2) This generalization ability is highly correlated to the structure of the fact "A is B" in the training documents.
Att2CPC: Attention-Guided Lossy Attribute Compression of Point Clouds
In this paper, we focus on the task of learned lossy point cloud attribute compression (PCAC).
CKSP: Cross-species Knowledge Sharing and Preserving for Universal Animal Activity Recognition
The results show that our approach remarkably boosts the classification performance compared to the baseline method (one-for-one framework) solely trained on individual-species data, with increments of 6. 04%, 2. 06%, and 3. 66% in accuracy, and 10. 33%, 3. 67%, and 7. 90% in F1-score for the horse, sheep, and cattle datasets, respectively.
Dog-IQA: Standard-guided Zero-shot MLLM for Mix-grained Image Quality Assessment
Image quality assessment (IQA) serves as the golden standard for all models' performance in nearly all computer vision fields.
Diff-PCC: Diffusion-based Neural Compression for 3D Point Clouds
Stable diffusion networks have emerged as a groundbreaking development for their ability to produce realistic and detailed visual content.
XCB: an effective contextual biasing approach to bias cross-lingual phrases in speech recognition
Contextualized ASR models have been demonstrated to effectively improve the recognition accuracy of uncommon phrases when a predefined phrase list is available.
Parallel Speculative Decoding with Adaptive Draft Length
Speculative decoding (SD), where an extra draft model is employed to provide multiple \textit{draft} tokens first and then the original target model verifies these tokens in parallel, has shown great power for LLM inference acceleration.
Enhancing LLM's Cognition via Structurization
Besides, we show the feasibility of distilling advanced LLMs' language processing abilities to a smaller yet effective StruXGPT-7B to execute structurization, addressing the practicality of our approach.
ESOD: Efficient Small Object Detection on High-Resolution Images
The resulting Efficient Small Object Detection (ESOD) approach is a generic framework, which can be applied to both CNN- and ViT-based detectors to save the computation and GPU memory costs.
Rethinking Out-of-Distribution Detection on Imbalanced Data Distribution
Detecting and rejecting unknown out-of-distribution (OOD) samples is critical for deployed neural networks to void unreliable predictions.
Category-Extensible Out-of-Distribution Detection via Hierarchical Context Descriptions
The key to OOD detection has two aspects: generalized feature representation and precise category description.
Structure-aware Domain Knowledge Injection for Large Language Models
Remarkably, our method demonstrates the potential of comparable improvement against the state-of-the-art MMedLM2 on MMedBench, while significantly reducing the training costs to 5%.
Bucket Pre-training is All You Need
Large language models (LLMs) have demonstrated exceptional performance across various natural language processing tasks.
An efficient text augmentation approach for contextualized Mandarin speech recognition
Although contextualized automatic speech recognition (ASR) systems are commonly used to improve the recognition of uncommon words, their effectiveness is hindered by the inherent limitations of speech-text data availability.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
2DQuant: Low-bit Post-Training Quantization for Image Super-Resolution
Low-bit quantization has become widespread for compressing image super-resolution (SR) models for edge deployment, which allows advanced SR models to enjoy compact low-bit parameters and efficient integer/bitwise constructions for storage compression and inference acceleration, respectively.
Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
For fine-grained language understanding, we train a Multimodal Large Language Model to refine the captions of the images.
Differentiable Model Scaling using Differentiable Topk
Specifically, for image classification on ImageNet, our DMS improves the top-1 accuracy of EfficientNet-B0 and Deit-Tiny by 1. 4% and 0. 6%, respectively, and outperforms the state-of-the-art zero-shot NAS method, ZiCo, by 1. 3% while requiring only 0. 4 GPU days for searching.
Learning-to-solve unit commitment based on few-shot physics-guided spatial-temporal graph convolution network
This letter proposes a few-shot physics-guided spatial temporal graph convolutional network (FPG-STGCN) to fast solve unit commitment (UC).
Mixture-of-Instructions: Comprehensive Alignment of a Large Language Model through the Mixture of Diverse System Prompting Instructions
With the proliferation of large language models (LLMs), the comprehensive alignment of such models across multiple tasks has emerged as a critical area of research.
Pointsoup: High-Performance and Extremely Low-Decoding-Latency Learned Geometry Codec for Large-Scale Point Cloud Scenes
Despite considerable progress being achieved in point cloud geometry compression, there still remains a challenge in effectively compressing large-scale scenes with sparse surfaces.
Training-free Boost for Open-Vocabulary Object Detection with Confidence Aggregation
Specifically, in the region-proposal stage, proposals that contain novel instances showcase lower objectness scores, since they are treated as background proposals during the training phase.
Binomial Self-compensation for Motion Error in Dynamic 3D Scanning
Phase shifting profilometry (PSP) is favored in high-precision 3D scanning due to its high accuracy, robustness, and pixel-wise property.
EasyQuant: An Efficient Data-free Quantization Algorithm for LLMs
To our best knowledge, we are the first work that achieves almost lossless quantization performance for LLMs under a data-independent setting and our algorithm runs over 10 times faster than the data-dependent methods.
HoloVIC: Large-scale Dataset and Benchmark for Multi-Sensor Holographic Intersection and Vehicle-Infrastructure Cooperative
Based on HoloVIC, we formulated four tasks to facilitate the development of related research.
INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection
Knowledge hallucination have raised widespread concerns for the security and reliability of deployed LLMs.
Optimal Parameter and Neuron Pruning for Out-of-Distribution Detection
Most existing OOD detection methods focused on exploring advanced training skills or training-free tricks to prevent the model from yielding overconfident confidence score for unknown samples.
Query-LIFE: Query-aware Language Image Fusion Embedding for E-Commerce Relevance
Query-LIFE utilizes a query-based multimodal fusion to effectively incorporate the image and title based on the product types.
Phase Guided Light Field for Spatial-Depth High Resolution 3D Imaging
On 3D imaging, light field cameras typically are of single shot, and however, they heavily suffer from low spatial resolution and depth accuracy.
A Spatial-Temporal Transformer based Framework For Human Pose Assessment And Correction in Education Scenarios
Human pose assessment and correction play a crucial role in applications across various fields, including computer vision, robotics, sports analysis, healthcare, and entertainment.
E-Sparse: Boosting the Large Language Model Inference through Entropy-based N:M Sparsity
Traditional pruning methods are known to be challenging to work in Large Language Models (LLMs) for Generative AI because of their unaffordable training process and large computational demands.
GraphText: Graph Reasoning in Text Space
Furthermore, GraphText paves the way for interactive graph reasoning, allowing both humans and LLMs to communicate with the model seamlessly using natural language.
On Regularized Sparse Logistic Regression
Sparse logistic regression is for classification and feature selection simultaneously.
Uncertainty-aware Unsupervised Multi-Object Tracking
The resulting accurate pseudo-tracklets boost learning the feature consistency.
Strictly Low Rank Constraint Optimization -- An Asymptotically $\mathcal{O}(\frac{1}{t^2})$ Method
We study a class of non-convex and non-smooth problems with \textit{rank} regularization to promote sparsity in optimal solution.
Physics-Guided Graph Neural Networks for Real-time AC/DC Power Flow Analysis
The increasing scale of alternating current and direct current (AC/DC) hybrid systems necessitates a faster power flow analysis tool than ever.
SDFReg: Learning Signed Distance Functions for Point Cloud Registration
We then propose to alternately optimize the implicit function and the registration between the implicit function and point cloud.
Pyramid Multi-branch Fusion DCNN with Multi-Head Self-Attention for Mandarin Speech Recognition
On the other hand, we need to reduce the dimension of each subspace to keep the size of the overall feature space unchanged when we increase the number of heads, which will significantly weaken the ability to represent the feature of each subspace.
X-SepFormer: End-to-end Speaker Extraction Network with Explicit Optimization on Speaker Confusion
To mitigate the imperative SC issue, we reformulate the training objective and propose two novel loss schemes that explore the metric of reconstruction improvement performance defined at small chunk-level and leverage the metric associated distribution information.
Adaptive Weighted Multiview Kernel Matrix Factorization with its application in Alzheimer's Disease Analysis -- A clustering Perspective
Recent technology and equipment advancements provide with us opportunities to better analyze Alzheimer's disease (AD), where we could collect and employ the data from different image and genetic modalities that may potentially enhance the predictive performance.
A Provable Splitting Approach for Symmetric Nonnegative Matrix Factorization
The symmetric Nonnegative Matrix Factorization (NMF), a special but important class of the general NMF, has found numerous applications in data analysis such as various clustering tasks.
Improving Target Speaker Extraction with Sparse LDA-transformed Speaker Embeddings
As a practical alternative of speech separation, target speaker extraction (TSE) aims to extract the speech from the desired speaker using additional speaker cue extracted from the speaker.
Randomized Greedy Algorithms and Composable Coreset for k-Center Clustering with Outliers
Though a number of methods have been developed in the past decades, it is still quite challenging to design quality guaranteed algorithm with low complexity for this problem.
Deep Biological Pathway Informed Pathology-Genomic Multimodal Survival Prediction
The integration of multi-modal data, such as pathological images and genomic data, is essential for understanding cancer heterogeneity and complexity for personalized treatments, as well as for enhancing survival predictions.
Multi-Task Learning with Prior Information
Multi-task learning aims to boost the generalization performance of multiple related tasks simultaneously by leveraging information contained in those tasks.
KAST: Knowledge Aware Adaptive Session Multi-Topic Network for Click-Through Rate Prediction
Capturing the evolving trends of user interest is important for both recommendation systems and advertising systems, and user behavior sequences have been successfully used in Click-Through-Rate(CTR) prediction problems.
A GPU-accelerated Algorithm for Distinct Discriminant Canonical Correlation Network
In this paper, a GPU-based accelerated algorithm is proposed to further optimize the DDCCANet algorithm.
Speech Enhancement with Perceptually-motivated Optimization and Dual Transformations
To validate the effectiveness of our proposed model, extensive experiments are conducted on the DNS2020 dataset.
Joint Speech Activity and Overlap Detection with Multi-Exit Architecture
Overlapped speech detection (OSD) is critical for speech applications in scenario of multi-party conversion.
Rethinking Symmetric Matrix Factorization: A More General and Better Clustering Perspective
Nonnegative matrix factorization (NMF) is widely used for clustering with strong interpretability.
Maximum Correntropy Value Decomposition for Multi-agent Deep Reinforcemen Learning
In this paper, we first demonstrate the flaw of Weighted QMIX using an ordinary One-Step Matrix Game (OMG), that no matter how the weight is chosen, Weighted QMIX struggles to deal with non-monotonic value decomposition problems with a large variance of reward distributions.
Weakly-supervised High-fidelity Ultrasound Video Synthesis with Feature Decoupling
First, leveraging the advantages of self- and fully-supervised learning, our proposed system is trained in weakly-supervised manner for keypoint detection.
Occlusion-Resistant Instance Segmentation of Piglets in Farrowing Pens Using Center Clustering Network
Specifically, CClusnet-Inseg uses each pixel to predict object centers and trace these centers to form masks based on clustering results, which consists of a network for segmentation and center offset vector map, Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm, Centers-to-Mask (C2M), and Remain-Centers-to-Mask (RC2M) algorithms.
Enriched Robust Multi-View Kernel Subspace Clustering
To address the above issues, in this paper we propose a novel Enriched Robust Multi-View Kernel Subspace Clustering framework where the consensus affinity matrix is learned from both multi-view data and spectral clustering.
MKQ-BERT: Quantized BERT with 4-bits Weights and Activations
In this work, we propose MKQ-BERT, which further improves the compression level and uses 4-bits for quantization.
Exploring the impact of spatiotemporal granularity on the demand prediction of dynamic ride-hailing
A convolutional, long short-term memory model combined with a hexagonal convolution operation (H-ConvLSTM) is proposed to explore the complex spatial and temporal relations.
Joint CNN and Transformer Network via weakly supervised Learning for efficient crowd counting
However, the transformer directly partitions the crowd images into a series of tokens, which may not be a good choice due to each pedestrian being an independent individual, and the parameter number of the network is very large.
Dynamic Group Transformer: A General Vision Transformer Backbone with Dynamic Group Attention
To reduce the quadratic computation complexity caused by each query attending to all keys/values, various methods have constrained the range of attention within local regions, where each query only attends to keys/values within a hand-crafted window.
Spherical Matrix Factorization
However, most of the studies aim to minimize the loss by measuring the Euclidean distance, though in some fields, angle distance is known to be more important and critical for analysis.
Robust Principal Component Analysis: A Construction Error Minimization Perspective
In this paper we propose a novel optimization framework to systematically solve robust PCA problem with rigorous theoretical guarantee, based on which we investigate very computationally economic updating algorithms.
SA-MATD3:Self-attention-based multi-agent continuous control method in cooperative environments
Cooperative problems under continuous control have always been the focus of multi-agent reinforcement learning.
Exact Sparse Orthogonal Dictionary Learning
Over the past decade, learning a dictionary from input images for sparse modeling has been one of the topics which receive most research attention in image processing and compressed sensing.
RRCN: A Reinforced Random Convolutional Network based Reciprocal Recommendation Approach for Online Dating
In particular, we technically propose a novel random CNN component that can randomly convolute non-adjacent features to capture their interaction information and learn feature embeddings of key attributes to make the final recommendation.
RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering
In open-domain question answering, dense passage retrieval has become a new paradigm to retrieve relevant passages for finding answers.
Ranked #4 on
Passage Retrieval
on Natural Questions
Multi-band MelGAN: Faster Waveform Generation for High-Quality Text-to-Speech
In this paper, we propose multi-band MelGAN, a much faster waveform generation model targeting to high-quality text-to-speech.
Sound Audio and Speech Processing
Incentivized Exploration for Multi-Armed Bandits under Reward Drift
We study incentivized exploration for the multi-armed bandit (MAB) problem where the players receive compensation for exploring arms other than the greedy choice and may provide biased feedback on reward.
Gated Multiple Feedback Network for Image Super-Resolution
The rapid development of deep learning (DL) has driven single image super-resolution (SR) into a new era.
Ranked #24 on
Image Super-Resolution
on BSD100 - 4x upscaling
Enhancing Pre-Trained Language Representations with Rich Knowledge for Machine Reading Comprehension
In this work, we investigate the potential of leveraging external knowledge bases (KBs) to further improve BERT for MRC.
Spherical Principal Component Analysis
However, most of the studies on PCA aim to minimize the loss after projection, which usually measures the Euclidean distance, though in some fields, angle distance is known to be more important and critical for analysis.
Shubnikov-de Haas and de Haas-van Alphen oscillations in topological semimetal CaAl4
An electron-type quasi-2D Fermi surface is found by the angle-dependent Shubnikov-de Haas oscillations, de Haas-van Alphen oscillations and the first-principles calculations.
Materials Science Mesoscale and Nanoscale Physics
Dropping Symmetry for Fast Symmetric Nonnegative Matrix Factorization
Symmetric nonnegative matrix factorization (NMF), a special but important class of the general NMF, is demonstrated to be useful for data analysis and in particular for various clustering tasks.
Deep Item-based Collaborative Filtering for Top-N Recommendation
In this work, we propose a more expressive ICF solution by accounting for the nonlinear and higher-order relationship among items.
Adaptations of ROUGE and BLEU to Better Evaluate Machine Reading Comprehension Task
Current evaluation metrics to question answering based machine reading comprehension (MRC) systems generally focus on the lexical overlap between the candidate and reference answers, such as ROUGE and BLEU.
Learning Multi-Instance Enriched Image Representations via Non-Greedy Ratio Maximization of the l1-Norm Distances
To tackle these two challenges, in this paper we propose a novel image representation learning method that can integrate the local patches (the instances) of an input image (the bag) and its holistic representation into one single-vector representation.
Multi-Passage Machine Reading Comprehension with Cross-Passage Answer Verification
Machine reading comprehension (MRC) on real web data usually requires the machine to answer a question by analyzing multiple passages retrieved by search engine.
Ranked #3 on
Question Answering
on MS MARCO
Spatial Image Steganography Based on Generative Adversarial Network
The architecture contain three component modules: a generator, an embedding simulator and a discriminator.
Multimedia
DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applications
Experiments show that human performance is well above current state-of-the-art baseline systems, leaving plenty of room for the community to make improvements.
Structured Light Phase Measuring Profilometry Pattern Design for Binary Spatial Light Modulators
In the case of phase measuring profilometry (PMP), the projected patterns are composed of a rolling sinusoidal wave, but as a set of time-multiplexed patterns, PMP requires the target surface to remain motionless or for scanning to be performed at such high rates that any movement is small.
Learning Piece-wise Linear Models from Large Scale Data for Ad Click Prediction
CTR prediction in real-world business is a difficult machine learning problem with large scale nonlinear sparse data.
Learning Linear Dynamical Systems with High-Order Tensor Data for Skeleton based Action Recognition
Therefore, an action can be represented as a subspace corresponding to a point on a Grassmann manifold.
