1 citations · 1 across the 20 of their papers we have counts for
12 papers · 1 filter
EntroPIC: Towards Stable Long-Term Training of LLMs via Entropy Stabilization with Proportional-Integral Control
Kai Yang, Xin Xu, Yangkun Chen +5
Long-term training of large language models (LLMs) requires maintaining stable exploration to prevent the model from collapsing into sub-optimal behaviors. Entropy is crucial in th…
On Predictability of Reinforcement Learning Dynamics for Large Language Models
Yuchen Cai, Ding Cao, Xin Xu +7
Recent advances in reasoning capabilities of large language models (LLMs) are largely driven by reinforcement learning (RL), yet the underlying parameter dynamics during RL trainin…
Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners
Xin Xu, Cliveb AI, Clive Bai +5
Reinforcement Learning with Verifiable Reward (RLVR) effectively solves complex tasks but demands extremely long context lengths during training, leading to substantial computation…
ALT4Decompile: Inferring C-aligned Abstract Loop Tree for LLM-Based Binary Decompilation
Yongpan Wang, Puzhuo Liu, Xin Xu +4
Decompilation refers to the process of recovering high-level (C) language code from low-level (assembly) code. Recent Large Language Model (LLM)-based methods can generate re-execu…
GPAS: Accelerating Convergence of LLM Pretraining via Gradient-Preserving Activation Scaling
Tianhao Chen, Xin Xu, Zijing Liu +12
Modern Large Language Models, such as the LLaMA, Qwen and DeepSeek series, predominantly adopt the Pre-LayerNorm (Pre-LN) Transformer architecture. While being stable during pretra…
Safe: Enhancing Mathematical Reasoning in Large Language Models via Retrospective Step-aware Formal Verification
Chengwu Liu, Ye Yuan, Yichun Yin +7
Chain-of-Thought (CoT) prompting has become the de facto method to elicit reasoning capabilities from large language models (LLMs). However, to mitigate hallucinations in CoT that…
Double-Checker: Enhancing Reasoning of Slow-Thinking LLMs via Self-Critical Fine-Tuning
Xin Xu, Tianhao Chen, Fan Zhang +11
While slow-thinking large language models (LLMs) exhibit reflection-like reasoning, commonly referred to as the "aha moment:, their ability to generate informative critiques and re…
VerifyBench: Benchmarking Reference-based Reward Systems for Large Language Models
Yuchen Yan, Jin Jiang, Zhenbang Ren +9
Large reasoning models such as OpenAI o1 and DeepSeek-R1 have demonstrated remarkable performance in complex reasoning tasks. A critical component of their training is the incorpor…
UGMathBench: A Diverse and Dynamic Benchmark for Undergraduate-Level Mathematical Reasoning with Large Language Models
Xin Xu, Jiaxin Zhang, Tianhao Chen +3
Large Language Models (LLMs) have made significant strides in mathematical reasoning, underscoring the need for a comprehensive and fair evaluation of their capabilities. However,…
Teaching LLMs According to Their Aptitude: Adaptive Reasoning for Mathematical Problem Solving
Xin Xu, Yan Xu, Tianhao Chen +9
Existing approaches to mathematical reasoning with large language models (LLMs) rely on Chain-of-Thought (CoT) for generalizability or Tool-Integrated Reasoning (TIR) for precise c…
MathFimer: Enhancing Mathematical Reasoning by Expanding Reasoning Steps through Fill-in-the-Middle Task
Yuchen Yan, Yongliang Shen, Yang Liu +5
Mathematical reasoning represents a critical frontier in advancing large language models (LLMs). While step-by-step approaches have emerged as the dominant paradigm for mathematica…
UGPhysics: A Comprehensive Benchmark for Undergraduate Physics Reasoning with Large Language Models
Xin Xu, Qiyun Xu, Tong Xiao +6
Large language models (LLMs) have demonstrated remarkable capabilities in solving complex reasoning tasks, particularly in mathematics. However, the domain of physics reasoning pre…