Picture for Yifei Liu

Yifei Liu

R3-Avatar: Record and Retrieve Temporal Codebook for Reconstructing Photorealistic Human Avatars

Add code
Mar 17, 2025
Viaarxiv icon

MouseGPT: A Large-scale Vision-Language Model for Mouse Behavior Analysis

Add code
Mar 13, 2025
Viaarxiv icon

Discovering Influential Neuron Path in Vision Transformers

Add code
Mar 12, 2025
Viaarxiv icon

SGA-INTERACT: A 3D Skeleton-based Benchmark for Group Activity Understanding in Modern Basketball Tactic

Add code
Mar 09, 2025
Viaarxiv icon

rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking

Add code
Jan 08, 2025
Figure 1 for rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking
Figure 2 for rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking
Figure 3 for rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking
Figure 4 for rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking
Viaarxiv icon

LLMs Help Alleviate the Cross-Subject Variability in Brain Signal and Language Alignment

Add code
Jan 05, 2025
Viaarxiv icon

MaskGaussian: Adaptive 3D Gaussian Representation from Probabilistic Masks

Add code
Dec 29, 2024
Viaarxiv icon

VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models

Add code
Sep 25, 2024
Figure 1 for VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models
Figure 2 for VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models
Figure 3 for VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models
Figure 4 for VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models
Viaarxiv icon

FIReStereo: Forest InfraRed Stereo Dataset for UAS Depth Perception in Visually Degraded Environments

Add code
Sep 12, 2024
Viaarxiv icon

Xinyu: An Efficient LLM-based System for Commentary Generation

Add code
Aug 21, 2024
Figure 1 for Xinyu: An Efficient LLM-based System for Commentary Generation
Figure 2 for Xinyu: An Efficient LLM-based System for Commentary Generation
Figure 3 for Xinyu: An Efficient LLM-based System for Commentary Generation
Figure 4 for Xinyu: An Efficient LLM-based System for Commentary Generation
Viaarxiv icon