Yaojie Lu

Scalable Oversight for Superhuman AI via Recursive Self-Critiquing

LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?

Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language Models

DeepRAG: Thinking to Retrieve Step by Step for Large Language Models

SAISA: Towards Multimodal Large Language Models with Both Training and Inference Efficiency

Beyond Turn Limits: Training Deep Search Agents with Dynamic Context Window

RefCritic: Training Long Chain-of-Thought Critic Models with Refinement Feedback

When Models Outthink Their Safety: Mitigating Self-Jailbreak in Large Reasoning Models with Chain-of-Guardrails

MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learning

Rethinking Reward Model Evaluation: Are We Barking up the Wrong Tree?

StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization

Critic-CoT: Boosting the reasoning abilities of large language model via Chain-of-Thought Critic

The Devil Is in the Details: Tackling Unimodal Spurious Correlations for Generalizable Multimodal Reward Models

The Rise and Down of Babel Tower: Investigating the Evolution Process of Multilingual Code Large Language Model

On-Policy Fine-grained Knowledge Feedback for Hallucination Mitigation

GameInstruct: Teaching Machines to Reason via Chameleon Game

ShortGPT: Layers in Large Language Models are More Redundant Than You Expect

Beyond Correctness: Benchmarking Multi-dimensional Code Generation for Large Language Models

Aligning Large Language Models via Self-Steering Optimization

A Unified View of Delta Parameter Editing in Post-Trained Large-Scale Models