activity
20242026
collaborators

5 papers

cs.AI2026

LC-ERD: Mining Latent Logic for Self-Evolving Reasoning via Consistency-Regulated Reward Decomposition

Yanyu Chen, Jiyue Jiang, Dianzhi Yu +8

The evolution of Large Language Model (LLM) reasoning is bottlenecked by the scarcity of high-quality process data. While self-alignment via endogenous rewards offers a solution, m…

cs.CV2026

Exploiting Low-Dimensional Manifold of Features for Few-Shot Whole Slide Image Classification

Conghao Xiong, Zhengrui Guo, Zhe Xu +6

Few-shot Whole Slide Image (WSI) classification is severely hampered by overfitting. We argue that this is not merely a data-scarcity issue but a fundamentally geometric problem. G…

cs.CL2026

TRACE: Trajectory-Aware Comprehensive Evaluation for Deep Research Agents

Yanyu Chen, Jiyue Jiang, Jiahong Liu +3

The evaluation of Deep Research Agents is a critical challenge, as conventional outcome-based metrics fail to capture the nuances of their complex reasoning. Current evaluation fac…

cs.LG2025

Soft Separation and Distillation: Toward Global Uniformity in Federated Unsupervised Learning

Hung-Chieh Fang, Hsuan-Tien Lin, Irwin King +1

Federated Unsupervised Learning (FUL) aims to learn expressive representations in federated and self-supervised settings. The quality of representations learned in FUL is usually d…

cs.LG2025

CSPO: Cross-Market Synergistic Stock Price Movement Forecasting with Pseudo-volatility Optimization

Sida Lin, Yankai Chen, Yiyan Qi +5

The stock market, as a cornerstone of the financial markets, places forecasting stock price movements at the forefront of challenges in quantitative finance. Emerging learning-base…