Picture for Yuhong Li

Yuhong Li

FlowCut: Rethinking Redundancy via Information Flow for Efficient Vision-Language Models

Add code
May 26, 2025
Viaarxiv icon

RA-BLIP: Multimodal Adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-training

Add code
Oct 18, 2024
Figure 1 for RA-BLIP: Multimodal Adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-training
Figure 2 for RA-BLIP: Multimodal Adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-training
Figure 3 for RA-BLIP: Multimodal Adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-training
Figure 4 for RA-BLIP: Multimodal Adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-training
Viaarxiv icon

New Solutions on LLM Acceleration, Optimization, and Application

Add code
Jun 16, 2024
Figure 1 for New Solutions on LLM Acceleration, Optimization, and Application
Figure 2 for New Solutions on LLM Acceleration, Optimization, and Application
Figure 3 for New Solutions on LLM Acceleration, Optimization, and Application
Figure 4 for New Solutions on LLM Acceleration, Optimization, and Application
Viaarxiv icon

Heterophilous Distribution Propagation for Graph Neural Networks

Add code
May 31, 2024
Figure 1 for Heterophilous Distribution Propagation for Graph Neural Networks
Figure 2 for Heterophilous Distribution Propagation for Graph Neural Networks
Figure 3 for Heterophilous Distribution Propagation for Graph Neural Networks
Figure 4 for Heterophilous Distribution Propagation for Graph Neural Networks
Viaarxiv icon

SnapKV: LLM Knows What You are Looking for Before Generation

Add code
Apr 22, 2024
Figure 1 for SnapKV: LLM Knows What You are Looking for Before Generation
Figure 2 for SnapKV: LLM Knows What You are Looking for Before Generation
Figure 3 for SnapKV: LLM Knows What You are Looking for Before Generation
Figure 4 for SnapKV: LLM Knows What You are Looking for Before Generation
Viaarxiv icon

Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads

Add code
Jan 19, 2024
Figure 1 for Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
Figure 2 for Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
Figure 3 for Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
Figure 4 for Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
Viaarxiv icon

Synthesizing Coherent Story with Auto-Regressive Latent Diffusion Models

Add code
Nov 20, 2022
Figure 1 for Synthesizing Coherent Story with Auto-Regressive Latent Diffusion Models
Figure 2 for Synthesizing Coherent Story with Auto-Regressive Latent Diffusion Models
Figure 3 for Synthesizing Coherent Story with Auto-Regressive Latent Diffusion Models
Figure 4 for Synthesizing Coherent Story with Auto-Regressive Latent Diffusion Models
Viaarxiv icon

What Makes Convolutional Models Great on Long Sequence Modeling?

Add code
Oct 17, 2022
Figure 1 for What Makes Convolutional Models Great on Long Sequence Modeling?
Figure 2 for What Makes Convolutional Models Great on Long Sequence Modeling?
Figure 3 for What Makes Convolutional Models Great on Long Sequence Modeling?
Figure 4 for What Makes Convolutional Models Great on Long Sequence Modeling?
Viaarxiv icon

Extensible Proxy for Efficient NAS

Add code
Oct 17, 2022
Figure 1 for Extensible Proxy for Efficient NAS
Figure 2 for Extensible Proxy for Efficient NAS
Figure 3 for Extensible Proxy for Efficient NAS
Figure 4 for Extensible Proxy for Efficient NAS
Viaarxiv icon

Efficient Machine Learning, Compilers, and Optimizations for Embedded Systems

Add code
Jun 06, 2022
Figure 1 for Efficient Machine Learning, Compilers, and Optimizations for Embedded Systems
Figure 2 for Efficient Machine Learning, Compilers, and Optimizations for Embedded Systems
Figure 3 for Efficient Machine Learning, Compilers, and Optimizations for Embedded Systems
Figure 4 for Efficient Machine Learning, Compilers, and Optimizations for Embedded Systems
Viaarxiv icon