8 papers
-Balancing for Mixture-of-Experts Training
Lizhang Chen, Jonathan Li, Qi Wang +5
Mixture-of-Experts (MoE) models rely on balanced expert utilization to fully realize their scalability. However, existing load-balancing methods are largely heuristic and operate o…
Filtered Reasoning Score: Evaluating Reasoning Quality on a Model's Most-Confident Traces
Manas Pathak, Xingyao Chen, Shuozhe Li +2
Should we trust Large Language Models (LLMs) with high accuracy? LLMs achieve high accuracy on reasoning benchmarks, but correctness alone does not reveal the quality of the reason…
Learning Robust Reasoning through Guided Adversarial Self-Play
Shuozhe Li, Vaishnav Tadiparthi, Kwonjoon Lee +6
Reinforcement learning from verifiable rewards (RLVR) produces strong reasoning models, yet they can fail catastrophically when the conditioning context is fallible (e.g., corrupte…
CARE-RFT: Confidence-Anchored Reinforcement Finetuning for Reliable Reasoning in Large Language Models
Shuozhe Li, Jincheng Cao, Bodun Hu +3
Reinforcement finetuning (RFT) has emerged as a powerful paradigm for unlocking reasoning capabilities in large language models. However, we identify a critical trade-off: while un…
A Learnable Wavelet Transformer for Long-Short Equity Trading and Risk-Adjusted Return Optimization
Shuozhe Li, Du Cheng, Leqi Liu
Learning profitable intraday trading policies from financial time series is challenging due to heavy noise, non-stationarity, and strong cross-sectional dependence among related as…
ExPO: Unlocking Hard Reasoning with Self-Explanation-Guided Reinforcement Learning
Ruiyang Zhou, Shuozhe Li, Amy Zhang +1
Self-improvement via RL often fails on complex reasoning tasks because GRPO-style post-training methods rely on the model's initial ability to generate positive samples. Without gu…
An Optimal Discriminator Weighted Imitation Perspective for Reinforcement Learning
Haoran Xu, Shuozhe Li, Harshit Sikchi +2
We introduce Iterative Dual Reinforcement Learning (IDRL), a new method that takes an optimal discriminator-weighted imitation view of solving RL. Our method is motivated by a simp…
Robot Air Hockey: A Manipulation Testbed for Robot Learning with Reinforcement Learning
Caleb Chuck, Carl Qi, Michael J. Munje +13
Reinforcement Learning is a promising tool for learning complex policies even in fast-moving and object-interactive domains where human teleoperation or hard-coded policies might f…