Kaitao Song

Linking Process to Outcome: Conditional Reward Modeling for LLM Reasoning

Trade in Minutes! Rationality-Driven Agentic System for Quantitative Financial Trading

Interpreting and Controlling LLM Reasoning through Integrated Policy Gradient

Context-Aware Alignment: Adapting Large Language Models to Individual Historical Data

FoPO: Foresight Policy Optimization Incentivizes Strategic Reasoning in LLMs

Chain-of-Model Learning for Language Model

Mind the Gap: Bridging Thought Leap for Improved Chain-of-Thought Tuning

Let LRMs Break Free from Overthinking via Self-Braking Tuning

Sparse Training: Do All Tokens Matter for Long Sequence Generalization?