2 citations · 2 across the 7 of their papers we have counts for
7 papers
GMTS: Gradient Magnitude-based Token Selection Improves RLVR Training for LLM Reasoning
Outongyi Lv, Yuanwei Zhang, Xiaoqun Zhang
Reinforcement learning (RL), particularly RL with Verifiable Rewards (RLVR), has recently emerged as a central paradigm for enhancing large language models' (LLMs) reasoning abilit…
Which Tokens Matter? Adaptive Token Selection for RLVR with the Relative Surprisal Index
Outongyi Lv, Yanzhao Zheng, Yuanwei Zhang +5
Reinforcement learning (RL) has become a powerful tool for propelling Large Language Models (LLMs) beyond imitation-based training towards more robust reasoning capabilities. Among…
Improved Offline Reinforcement Learning via Quantum Metric Encoding
Outongyi Lv, Yewei Yuan, Nana Liu
Reinforcement learning (RL) with limited samples is common in real-world applications. However, offline RL performance under this constraint is often suboptimal. We consider an alt…
ProteinEngine: Empower LLM with Domain Knowledge for Protein Engineering
Yiqing Shen, Outongyi Lv, Houying Zhu +1
Large language models (LLMs) have garnered considerable attention for their proficiency in tackling intricate tasks, particularly leveraging their capacities for zero-shot and in-c…
A Unified View on Neural Message Passing with Opinion Dynamics for Social Networks
Outongyi Lv, Bingxin Zhou, Jing Wang +3
Social networks represent a common form of interconnected data frequently depicted as graphs within the domain of deep learning-based inference. These communities inherently form d…
LLQL: Logistic Likelihood Q-Learning for Reinforcement Learning
Outongyi Lv, Bingxin Zhou
Modern reinforcement learning (RL) can be categorized into online and offline variants. As a pivotal aspect of both online and offline RL, current research on the Bellman equation…
Accurate and Definite Mutational Effect Prediction with Lightweight Equivariant Graph Neural Networks
Bingxin Zhou, Outongyi Lv, Kai Yi +4
Directed evolution as a widely-used engineering strategy faces obstacles in finding desired mutants from the massive size of candidate modifications. While deep learning methods le…