Fanghua Ye

ATTS: Asynchronous Test-Time Scaling via Conformal Prediction

RLVER: Reinforcement Learning with Verifiable Emotion Rewards for Empathetic Agents

SSFO: Self-Supervised Faithfulness Optimization for Retrieval-Augmented Generation

The Social Welfare Function Leaderboard: When LLM Agents Allocate Social Welfare

BatonVoice: An Operationalist Framework for Enhancing Controllable Speech Synthesis with Linguistic Intelligence from LLMs

From LLMs to LRMs: Rethinking Pruning for Reasoning-Centric Models

The Hunger Game Debate: On the Emergence of Over-Competition in Multi-Agent Systems

Soft-consensual Federated Learning for Data Heterogeneity via Multiple Paths

The Lighthouse of Language: Enhancing LLM Agents via Critique-Guided Improvement

SkipGPT: Each Token is One of a Kind

UNComp: Uncertainty-Aware Long-context Compressor for Efficient Large Language Model Inference

ParallelComp: Parallel Long-Context Compressor for Length Extrapolation

UncertaintyRAG: Span Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generation

Assessing Vulnerabilities of Large Language Models to Social Bias Attacks