activity
20242026
collaborators

9 papers

cs.CL2026

State2State: Environment-Derived Mid-Training for LLM Agents

Xuanyu Lei, Yiqi Zhu, Chenliang Li +6

Training LLM agents commonly relies on supervised fine-tuning from expert trajectories or online reinforcement learning over human-specified tasks with handcrafted verifiers. Thoug…

cs.CL2026

Writing-RL: Advancing Long-form Writing via Adaptive Curriculum Reinforcement Learning

Xuanyu Lei, Chenliang Li, Yuning Wu +7

Recent advances in Large Language Models(LLMs) have enabled strong performance in long-form writing, but current training paradigms remain limited: Supervised Fine-Tuning (SFT) rem…

cs.AI2026

SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks

Tianyi Wang, Yixia Li, Long Li +6

Proximal Policy Optimization (PPO) is central to aligning Large Language Models (LLMs) in reasoning tasks with verifiable rewards. However, standard token-level PPO struggles in th…

cs.CV2026

VideoChat-M1: Collaborative Policy Planning for Video Understanding via Multi-Agent Reinforcement Learning

Boyu Chen, Zikang Wang, Zhengrong Yue +9

By leveraging tool-augmented Multimodal Large Language Models (MLLMs), multi-agent frameworks are driving progress in video understanding. However, most of them adopt static and no…

cs.CV2025

Visual-Friendly Concept Protection via Selective Adversarial Perturbations

Xiaoyue Mi, Fan Tang, You Wu +3

Personalized concept generation by tuning diffusion models with a few images raises potential legal and ethical concerns regarding privacy and intellectual property rights. Researc…

cs.CL2025

Inference-Time Scaling for Generalist Reward Modeling

Zijun Liu, Peiyi Wang, Runxin Xu +5

Reinforcement learning (RL) has been widely adopted in post-training for large language models (LLMs) at scale. Recently, the incentivization of reasoning capabilities in LLMs from…