papers

Publications (9)

cs.CV2024

Building Universal Foundation Models for Medical Image Analysis with Spatially Adaptive Networks

Lingxiao Luo, Xuanzhong Chen, Bingda Tang +5

Recent advancements in foundation models, typically trained with self-supervised learning on large-scale and diverse datasets, have shown great potential in medical image analysis.…

cs.CL2025

GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

5 Team, Aohan Zeng, Xin Lv +167

We present GLM-4.5, an open-source Mixture-of-Experts (MoE) large language model with 355B total parameters and 32B activated parameters, featuring a hybrid reasoning method that s…

cs.LG2026

Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning

Zhenyu Hou, Yujiang Li, Jie Tang +1

Reinforcement learning (RL) is becoming increasingly important for post-training large language models (LLMs). Previous RL pipelines for LLMs were mostly synchronous and batch-inte…

cs.LG2026

GLM-5: from Vibe Coding to Agentic Engineering

GLM-5-Team, :, Aohan Zeng +184

We present GLM-5, a next-generation foundation model designed to transition the paradigm of vibe coding to agentic engineering. Building upon the agentic, reasoning, and coding (AR…

cs.LG2026

CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents

Yujiang Li, Zhenyu Hou, Yi Jing +2

Long-horizon agentic LLMs are increasingly limited by finite context windows, as extended interaction trajectories can exceed the maximum context length before a task is completed.…

cs.CV2024

Recovering Complete Actions for Cross-dataset Skeleton Action Recognition

Hanchao Liu, Yujiang Li, Tai-Jiang Mu +1

Despite huge progress in skeleton-based action recognition, its generalizability to different domains remains a challenging issue. In this paper, to solve the skeleton action gener…

cs.CL2025

DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RL

Rui Lu, Zhenyu Hou, Zihan Wang +6

Augmenting large language models (LLMs) with browsing tools substantially improves their potential as deep search agents to solve complex, real-world tasks. Yet, open LLMs still pe…

cs.LG2025

TreeRL: LLM Reinforcement Learning with On-Policy Tree Search

Zhenyu Hou, Ziniu Hu, Yujiang Li +3

Reinforcement learning (RL) with tree search has demonstrated superior performance in traditional reasoning tasks. Compared to conventional independent chain sampling strategies wi…

cs.LG2025

T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling

Zhenyu Hou, Xin Lv, Rui Lu +6

Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks. However, existing approaches mainly rely on imitation learning and struggle to ac…