works on

From the 1 of 7 linked papers with an AI index.

collaborators

7 papers

cs.CL2026

Filtered Reasoning Score: Evaluating Reasoning Quality on a Model's Most-Confident Traces

Manas Pathak, Xingyao Chen, Shuozhe Li +2

The paper introduces the Filtered Reasoning Score (FRS), a metric that evaluates the quality of reasoning traces from large language models by focusing on the most confident genera…

cs.LG2026

-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…

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

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…