Picture for Yu Bai

Yu Bai

Beijing Friendship Hospital

Movable Antenna-Equipped UAV for Data Collection in Backscatter Sensor Networks: A Deep Reinforcement Learning-based Approach

Add code
Nov 21, 2024
Viaarxiv icon

Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs

Add code
Oct 17, 2024
Figure 1 for Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs
Figure 2 for Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs
Figure 3 for Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs
Figure 4 for Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs
Viaarxiv icon

An Efficient Real-Time Object Detection Framework on Resource-Constricted Hardware Devices via Software and Hardware Co-design

Add code
Aug 20, 2024
Figure 1 for An Efficient Real-Time Object Detection Framework on Resource-Constricted Hardware Devices via Software and Hardware Co-design
Figure 2 for An Efficient Real-Time Object Detection Framework on Resource-Constricted Hardware Devices via Software and Hardware Co-design
Figure 3 for An Efficient Real-Time Object Detection Framework on Resource-Constricted Hardware Devices via Software and Hardware Co-design
Figure 4 for An Efficient Real-Time Object Detection Framework on Resource-Constricted Hardware Devices via Software and Hardware Co-design
Viaarxiv icon

MMRA: A Benchmark for Evaluating Multi-Granularity and Multi-Image Relational Association Capabilities in Large Visual Language Models

Add code
Aug 06, 2024
Figure 1 for MMRA: A Benchmark for Evaluating Multi-Granularity and Multi-Image Relational Association Capabilities in Large Visual Language Models
Figure 2 for MMRA: A Benchmark for Evaluating Multi-Granularity and Multi-Image Relational Association Capabilities in Large Visual Language Models
Figure 3 for MMRA: A Benchmark for Evaluating Multi-Granularity and Multi-Image Relational Association Capabilities in Large Visual Language Models
Figure 4 for MMRA: A Benchmark for Evaluating Multi-Granularity and Multi-Image Relational Association Capabilities in Large Visual Language Models
Viaarxiv icon

An Adaptive Tensor-Train Decomposition Approach for Efficient Deep Neural Network Compression

Add code
Aug 02, 2024
Figure 1 for An Adaptive Tensor-Train Decomposition Approach for Efficient Deep Neural Network Compression
Figure 2 for An Adaptive Tensor-Train Decomposition Approach for Efficient Deep Neural Network Compression
Figure 3 for An Adaptive Tensor-Train Decomposition Approach for Efficient Deep Neural Network Compression
Figure 4 for An Adaptive Tensor-Train Decomposition Approach for Efficient Deep Neural Network Compression
Viaarxiv icon

Design and Development of Laughter Recognition System Based on Multimodal Fusion and Deep Learning

Add code
Jul 31, 2024
Viaarxiv icon

Label-Guided Prompt for Multi-label Few-shot Aspect Category Detection

Add code
Jul 30, 2024
Figure 1 for Label-Guided Prompt for Multi-label Few-shot Aspect Category Detection
Figure 2 for Label-Guided Prompt for Multi-label Few-shot Aspect Category Detection
Figure 3 for Label-Guided Prompt for Multi-label Few-shot Aspect Category Detection
Figure 4 for Label-Guided Prompt for Multi-label Few-shot Aspect Category Detection
Viaarxiv icon

MMRA: A Benchmark for Multi-granularity Multi-image Relational Association

Add code
Jul 24, 2024
Figure 1 for MMRA: A Benchmark for Multi-granularity Multi-image Relational Association
Figure 2 for MMRA: A Benchmark for Multi-granularity Multi-image Relational Association
Figure 3 for MMRA: A Benchmark for Multi-granularity Multi-image Relational Association
Figure 4 for MMRA: A Benchmark for Multi-granularity Multi-image Relational Association
Viaarxiv icon

Pistis-RAG: A Scalable Cascading Framework Towards Trustworthy Retrieval-Augmented Generation

Add code
Jun 21, 2024
Figure 1 for Pistis-RAG: A Scalable Cascading Framework Towards Trustworthy Retrieval-Augmented Generation
Figure 2 for Pistis-RAG: A Scalable Cascading Framework Towards Trustworthy Retrieval-Augmented Generation
Figure 3 for Pistis-RAG: A Scalable Cascading Framework Towards Trustworthy Retrieval-Augmented Generation
Figure 4 for Pistis-RAG: A Scalable Cascading Framework Towards Trustworthy Retrieval-Augmented Generation
Viaarxiv icon

CItruS: Chunked Instruction-aware State Eviction for Long Sequence Modeling

Add code
Jun 17, 2024
Viaarxiv icon