AI-Powered Operator Network Operations Automation
Published:
Developed AI-based automation systems for operator network operations, improving efficiency and reducing manual intervention in network management.
Posts by Collection
portfolio
AI-Based Base Station Error Handling and Diagnosis
Published:
Developed intelligent systems for automated base station error detection, diagnosis, and resolution, reducing downtime and maintenance costs.
Road Detection and Autonomous Driving
Published:
Research and development on road detection and autonomous driving systems, focusing on computer vision and perception for autonomous vehicles.
Robot Reinforcement Learning
Published:
Research on reinforcement learning for robotic control and manipulation, developing intelligent agents for robotic tasks.
Text-to-Scene Generation
Published:
Generating 3D scenes from natural language descriptions, bridging the gap between language understanding and 3D scene representation.
MLLM-MCTS-CoT: Monte Carlo Tree Search for Multimodal Reasoning
Published:
Combining Monte Carlo Tree Search (MCTS) with Chain-of-Thought reasoning for enhanced reasoning in multimodal large language models.
Multimodal Large Language Model Chain-of-Thought
Published:
Research on Chain-of-Thought (CoT) reasoning for multimodal large language models, improving reasoning capabilities in vision-language tasks.
Automated Evaluation Framework Improvements (lmms-eval)
Published:
Improving automated evaluation frameworks based on lmms-eval for comprehensive assessment of multimodal and language models.
openRLHF and lightRLHF Framework Improvements
Published:
Algorithm improvements and enhancements for the openRLHF reinforcement learning framework, including lightRLHF - a lightweight version based on openRLHF improvements.
veRL Framework Improvements
Published:
Framework integration and improvements for veRL (Volcano Engine Reinforcement Learning), a flexible, efficient and production-ready RL training library for large language models.
Research MCP Servers
Published:
A collection of Model Context Protocol (MCP) servers for research workflows, including arXiv integration and other research tools.
Multi-Agent Research Assistant
Published:
An intelligent multi-agent system for research assistance, enabling collaborative problem-solving among multiple AI agents.
Multi-round Reinforcement Learning and Self-Evolving Agents
Published:
Exploring multi-round reinforcement learning and self-evolving agent architectures for developing adaptive and continuously improving AI systems.
Agent Harness: Long-Term Memory for Adaptive AI Agents
Published:
A memory-augmented agent harness framework that enables AI agents to continuously learn and adapt through long-term episodic and semantic memory mechanisms.
Self-Evolving Multi-Agent Systems with Hierarchical Memory
Published:
A self-evolving multi-agent framework that enables agents to autonomously improve strategies through multi-round interactions and hierarchical memory structures.
publications
Collaborative Multi-Agent Reinforcement Learning for Complex Task Solving
Published in Under Review, 2025
We propose a collaborative multi-agent reinforcement learning framework that enables agents to efficiently coordinate and solve complex tasks through emergent communication and adaptive role assignment.
Recommended citation:
Download Paper
Harnessing Long-Term Memory for Adaptive AI Agents
Published in Under Review, 2025
We present a memory-augmented agent architecture that harnesses long-term episodic and semantic memory to enable adaptive behavior and continual learning in dynamic environments.
Recommended citation:
Download Paper
Self-Evolving Multi-Agent Systems with Hierarchical Memory
Published in Under Review, 2025
We propose a self-evolving multi-agent framework with hierarchical memory structures that enables agents to continuously improve their strategies through multi-round interactions and experience replay.
Recommended citation:
Download Paper
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45° Law
Published in arXiv, 2025
We introduce SafeWork-R1, a cutting-edge multimodal reasoning model that demonstrates the coevolution of capabilities and safety. It is developed by our proposed SafeLadder framework, which incorporates large-scale, progressive, safety-oriented reinforcement learning post-training, supported by a suite of multi-principled verifiers.
Recommended citation: Shanghai AI Lab et al. (2025). "SafeWork-R1: Coevolving Safety and Intelligence under the AI-45° Law." arXiv preprint arXiv:2507.18576.
Download Paper
Native Reasoning Models: Training Language Models to Reason on Unverifiable Data
Published in ICLR 2026 Poster, 2026
We propose a novel approach for training language models to reason on unverifiable data, enabling native reasoning capabilities without requiring ground-truth supervision.
Recommended citation: Wang, Y., Liu, Z., Li, X., Lu, C., & Yang, C. (2026). "Native Reasoning Models: Training Language Models to Reason on Unverifiable Data." ICLR 2026 Poster.
Download Paper
TrinityGuard: A Unified Framework for Safeguarding Multi-Agent Systems
Published in arXiv, 2026
We present TrinityGuard, a unified safety framework for multi-agent systems that ensures robust and trustworthy coordination among AI agents through multi-layered safeguarding mechanisms.
Recommended citation:
Download Paper
Reflector: Internalizing Step-wise Reflection against Indirect Jailbreaks
Published in ICML 2026, 2026
We propose Reflector, a framework that internalizes step-wise reflection mechanisms to defend against indirect jailbreak attacks on large language models.
Recommended citation: Ma, J., Zhang, J., Li, X., Zou, B., Lu, C., & Yang, C. (2026). "REFLECTOR: Internalizing Step-wise Reflection against Indirect Jailbreak." ICML 2026.
Download Paper
talks
Talk 1 on Relevant Topic in Your Field
Published:
This is a description of your talk, which is a markdown file that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
teaching
Teaching experience 1
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Teaching experience 2
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.