Picture for Xingyu Chen

Xingyu Chen

DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning

Add code
Apr 15, 2025
Viaarxiv icon

MInCo: Mitigating Information Conflicts in Distracted Visual Model-based Reinforcement Learning

Add code
Apr 05, 2025
Viaarxiv icon

Easi3R: Estimating Disentangled Motion from DUSt3R Without Training

Add code
Mar 31, 2025
Viaarxiv icon

HOIGPT: Learning Long Sequence Hand-Object Interaction with Language Models

Add code
Mar 24, 2025
Viaarxiv icon

Dancing with Critiques: Enhancing LLM Reasoning with Stepwise Natural Language Self-Critique

Add code
Mar 21, 2025
Viaarxiv icon

RaSA: Rank-Sharing Low-Rank Adaptation

Add code
Mar 16, 2025
Viaarxiv icon

Alignment for Efficient Tool Calling of Large Language Models

Add code
Mar 09, 2025
Viaarxiv icon

The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models

Add code
Mar 04, 2025
Viaarxiv icon

A Flexible FBG-Based Contact Force Sensor for Robotic Gripping Systems

Add code
Feb 06, 2025
Viaarxiv icon

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Add code
Jan 30, 2025
Figure 1 for Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs
Figure 2 for Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs
Figure 3 for Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs
Figure 4 for Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs
Viaarxiv icon