collaborators

10 papers

cs.LG2026

MAG: MAnifold Guided Semi-Supervised Multi-modal In-Context Learning

Zirui Cheng, Xun Xu, Tiankai Chen +7

Few-shot in-context learning (ICL) with multi-modal large language models (MLLMs) enables task adaptation without parameter updates, but its performance is highly sensitive to the…

cs.AI2026

TARL: Transaction-Aware Reliable Ledgers for Executable Memory Management in Long-Term Agents

Han Xiao, Hongjun Xu, Xin Zhang +2

Persistent memory helps long-term agents retain knowledge, yet a single update error can repeatedly distort future retrieval and reasoning. Most existing systems reduce memory upda…

cs.AI2026

Don't Peek at the Answer: Outcome-Masked Group Relative Policy Optimization for Label-Free RLVR

Yongshi Ye, Liang Zhang, Yidong Chen +2

Reinforcement Learning with Verifiable Rewards (RLVR) improves LLM reasoning but typically relies on ground-truth (GT) answers, limiting scalability. Voting-based label-free RLVR r…

cs.CL2026

PAMT: Process-Aligned Reinforcement Learning for Multi-Domain Machine Translation

Yongshi Ye, Biao Fu, Chongxuan Huang +2

Multi-domain machine translation (MDMT) requires more than fluent generation: it demands domain-sensitive translation decisions such as domain disambiguation, terminology control,…

cs.CL2026

Translation with Thought: Difficulty-Adaptive Reasoning via Reinforcement Learning for Multi-Domain Machine Translation

Yongshi Ye, Biao Fu, Chongxuan Huang +2

Multi-domain machine translation (MDMT) poses a unique challenge due to varying levels of linguistic complexity across domains. Inspired by human translators' ability to adapt reas…

cs.CL2026

UMEM: Unified Memory Extraction and Management Framework for Generalizable Memory

Yongshi Ye, Hui Jiang, Feihu Jiang +7

Self-evolving memory serves as the trainable parameters for Large Language Models (LLMs)-based agents, where extraction (distilling insights from experience) and management (updati…