Picture for Wei Xiong

Wei Xiong

A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce

Add code
Apr 15, 2025
Viaarxiv icon

ZipIR: Latent Pyramid Diffusion Transformer for High-Resolution Image Restoration

Add code
Apr 11, 2025
Viaarxiv icon

Self-rewarding correction for mathematical reasoning

Add code
Feb 26, 2025
Viaarxiv icon

Can LLMs Simulate Social Media Engagement? A Study on Action-Guided Response Generation

Add code
Feb 17, 2025
Viaarxiv icon

Logarithmic Regret for Online KL-Regularized Reinforcement Learning

Add code
Feb 11, 2025
Viaarxiv icon

Motion Forecasting for Autonomous Vehicles: A Survey

Add code
Feb 10, 2025
Viaarxiv icon

LLM Alignment as Retriever Optimization: An Information Retrieval Perspective

Add code
Feb 06, 2025
Figure 1 for LLM Alignment as Retriever Optimization: An Information Retrieval Perspective
Figure 2 for LLM Alignment as Retriever Optimization: An Information Retrieval Perspective
Figure 3 for LLM Alignment as Retriever Optimization: An Information Retrieval Perspective
Figure 4 for LLM Alignment as Retriever Optimization: An Information Retrieval Perspective
Viaarxiv icon

EvTTC: An Event Camera Dataset for Time-to-Collision Estimation

Add code
Dec 06, 2024
Viaarxiv icon

DIVE: Taming DINO for Subject-Driven Video Editing

Add code
Dec 04, 2024
Figure 1 for DIVE: Taming DINO for Subject-Driven Video Editing
Figure 2 for DIVE: Taming DINO for Subject-Driven Video Editing
Figure 3 for DIVE: Taming DINO for Subject-Driven Video Editing
Figure 4 for DIVE: Taming DINO for Subject-Driven Video Editing
Viaarxiv icon

MetaShadow: Object-Centered Shadow Detection, Removal, and Synthesis

Add code
Dec 03, 2024
Figure 1 for MetaShadow: Object-Centered Shadow Detection, Removal, and Synthesis
Figure 2 for MetaShadow: Object-Centered Shadow Detection, Removal, and Synthesis
Figure 3 for MetaShadow: Object-Centered Shadow Detection, Removal, and Synthesis
Figure 4 for MetaShadow: Object-Centered Shadow Detection, Removal, and Synthesis
Viaarxiv icon