From the 1 of 61 linked papers with an AI index.
1 citations · 2 across the 23 of their papers we have counts for
10 papers · 1 filter
LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Signals
Lihao Sun, Hang Dong, Bo Qiao +3
This work characterizes large language models' chain-of-thought generation as a structured trajectory through representation space. We show that mathematical reasoning traverses fu…
Text2Grad: Reinforcement Learning from Natural Language Feedback
Hanyang Wang, Lu Wang, Chaoyun Zhang +5
Traditional RLHF optimizes language models with coarse, scalar rewards that mask the fine-grained reasons behind success or failure, leading to slow and opaque learning. Recent wor…
G-KV: Decoding-Time KV Cache Eviction with Global Attention
Mengqi Liao, Lu Wang, Chaoyun Zhang +7
Recent reasoning large language models (LLMs) excel in complex tasks but encounter significant computational and memory challenges due to long sequence lengths. KV cache compressio…
WarriorMath: Enhancing the Mathematical Ability of Large Language Models with a Defect-aware Framework
Yue Chen, Minghua He, Fangkai Yang +9
Large Language Models (LLMs) excel in solving mathematical problems, yet their performance is often limited by the availability of high-quality, diverse training data. Existing met…
GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents
Qianhui Wu, Kanzhi Cheng, Rui Yang +15
One of the principal challenges in building VLM-powered GUI agents is visual grounding, i.e., localizing the appropriate screen region for action execution based on both the visual…
Self-Evolved Reward Learning for LLMs
Chenghua Huang, Zhizhen Fan, Lu Wang +7
Reinforcement Learning from Human Feedback (RLHF) is a crucial technique for aligning language models with human preferences, playing a pivotal role in the success of conversationa…