TongyiLab

company

https://careers-tongyi.alibaba.com/?lang=zh

Activity Feed Request to join this org

AI & ML interests

We advance the development of AGI and foster open source collaboration towards a smarter future.

Recent Activity

yanxi-chen submitted a paper 1 day ago

Connect the Dots: Training LLMs for Long-Lifecycle Agents with Cross-Domain Generalization Via Reinforcement Learning

shiyingcheng submitted a paper 13 days ago

EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning

BBBBCHAN submitted a paper about 1 month ago

See What I Mean: Aligning Vision and Language Representations for Video Fine-grained Object Understanding

View all activity

Papers

Connect the Dots: Training LLMs for Long-Lifecycle Agents with Cross-Domain Generalization Via Reinforcement Learning

EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning

View all Papers

AlibabaTongyiLab 's papers 28

Submitted by

Yanxi Chen

Connect the Dots: Training LLMs for Long-Lifecycle Agents with Cross-Domain Generalization Via Reinforcement Learning

AlibabaTongyiLab

1

Submitted by

youyou

EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning

AlibabaTongyiLab

2

Submitted by

Ting-En Lin

ESPO: Early-Stopping Proximal Policy Optimization

AlibabaTongyiLab

Submitted by

Yujie Wei

MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation

AlibabaTongyiLab

Submitted by

Boyuan Sun

See What I Mean: Aligning Vision and Language Representations for Video Fine-grained Object Understanding

AlibabaTongyiLab

Submitted by

XuHao Hu

ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents

AlibabaTongyiLab

Submitted by

jiaqi wang

TCOD: Exploring Temporal Curriculum in On-Policy Distillation for Multi-turn Autonomous Agents

AlibabaTongyiLab

Submitted by

Yujie Wei

DreamVideo-Omni: Omni-Motion Controlled Multi-Subject Video Customization with Latent Identity Reinforcement Learning

AlibabaTongyiLab

2

Submitted by

Jiajie Jin

LaSER: Internalizing Explicit Reasoning into Latent Space for Dense Retrieval

AlibabaTongyiLab

Submitted by

xuhaiyang

Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents

AlibabaTongyiLab

3

Submitted by

Haoyou Deng

DenseGRPO: From Sparse to Dense Reward for Flow Matching Model Alignment

AlibabaTongyiLab

2

Submitted by

Wenyuan Zhang

ExpSeek: Self-Triggered Experience Seeking for Web Agents

AlibabaTongyiLab

Submitted by

Jialong Wu

Nested Browser-Use Learning for Agentic Information Seeking

AlibabaTongyiLab

3

Submitted by

taesiri

MAI-UI Technical Report: Real-World Centric Foundation GUI Agents

AlibabaTongyiLab

Submitted by

Zihan Wang

Knot Forcing: Taming Autoregressive Video Diffusion Models for Real-time Infinite Interactive Portrait Animation

AlibabaTongyiLab

Submitted by

taesiri

MobileWorld: Benchmarking Autonomous Mobile Agents in Agent-User Interactive, and MCP-Augmented Environments

AlibabaTongyiLab

Submitted by

taesiri

QwenLong-L1.5: Post-Training Recipe for Long-Context Reasoning and Memory Management

AlibabaTongyiLab

Submitted by

taesiri

EcomBench: Towards Holistic Evaluation of Foundation Agents in E-commerce

AlibabaTongyiLab

Submitted by

taesiri

Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance

AlibabaTongyiLab

Submitted by

taesiri

Tongyi DeepResearch Technical Report

AlibabaTongyiLab

4

Submitted by

Jialong Wu

ParallelMuse: Agentic Parallel Thinking for Deep Information Seeking

AlibabaTongyiLab

2

Submitted by

Jialong Wu

AgentFold: Long-Horizon Web Agents with Proactive Context Management

AlibabaTongyiLab

Submitted by

Jialong Wu

WebLeaper: Empowering Efficiency and Efficacy in WebAgent via Enabling Info-Rich Seeking

AlibabaTongyiLab

2

Submitted by

Jialong Wu

AgentFrontier: Expanding the Capability Frontier of LLM Agents with ZPD-Guided Data Synthesis

AlibabaTongyiLab

Submitted by

Jialong Wu

Repurposing Synthetic Data for Fine-grained Search Agent Supervision

AlibabaTongyiLab

Submitted by

taesiri

OSWorld-MCP: Benchmarking MCP Tool Invocation In Computer-Use Agents

AlibabaTongyiLab

Submitted by

Yuqi Liu

UI-Ins: Enhancing GUI Grounding with Multi-Perspective Instruction-as-Reasoning

AlibabaTongyiLab

Submitted by

Shenghao Fu

LOVE-R1: Advancing Long Video Understanding with an Adaptive Zoom-in Mechanism via Multi-Step Reasoning

AlibabaTongyiLab