Picture for Yehui Tang

Yehui Tang

Star-Agents: Automatic Data Optimization with LLM Agents for Instruction Tuning

Add code
Nov 21, 2024
Viaarxiv icon

MemoryFormer: Minimize Transformer Computation by Removing Fully-Connected Layers

Add code
Nov 20, 2024
Viaarxiv icon

Free Video-LLM: Prompt-guided Visual Perception for Efficient Training-free Video LLMs

Add code
Oct 14, 2024
Viaarxiv icon

Token Compensator: Altering Inference Cost of Vision Transformer without Re-Tuning

Add code
Aug 13, 2024
Viaarxiv icon

Multi-Granularity Semantic Revision for Large Language Model Distillation

Add code
Jul 14, 2024
Viaarxiv icon

ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking

Add code
Jun 17, 2024
Viaarxiv icon

SLAB: Efficient Transformers with Simplified Linear Attention and Progressive Re-parameterized Batch Normalization

Add code
May 19, 2024
Viaarxiv icon

No Time to Waste: Squeeze Time into Channel for Mobile Video Understanding

Add code
May 14, 2024
Figure 1 for No Time to Waste: Squeeze Time into Channel for Mobile Video Understanding
Figure 2 for No Time to Waste: Squeeze Time into Channel for Mobile Video Understanding
Figure 3 for No Time to Waste: Squeeze Time into Channel for Mobile Video Understanding
Figure 4 for No Time to Waste: Squeeze Time into Channel for Mobile Video Understanding
Viaarxiv icon

EMS-SD: Efficient Multi-sample Speculative Decoding for Accelerating Large Language Models

Add code
May 13, 2024
Viaarxiv icon

Context-Guided Spatial Feature Reconstruction for Efficient Semantic Segmentation

Add code
May 10, 2024
Figure 1 for Context-Guided Spatial Feature Reconstruction for Efficient Semantic Segmentation
Figure 2 for Context-Guided Spatial Feature Reconstruction for Efficient Semantic Segmentation
Figure 3 for Context-Guided Spatial Feature Reconstruction for Efficient Semantic Segmentation
Figure 4 for Context-Guided Spatial Feature Reconstruction for Efficient Semantic Segmentation
Viaarxiv icon