Minhao Cheng

Adaptive Code Watermarking Through Reinforcement Learning

Route Before Retrieve: Activating Latent Routing Abilities of LLMs for RAG vs. Long Context Selection

WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning

Exploring Expert Failures Improves LLM Agent Tuning

On the Fragility of Graph Backdoor Defenses: A Robust Strategy via Layer-wise Feature Divergence

POME: Post Optimization Model Edit via Matrix Orthogonalization

ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization

VisualThinker: First ever R1-Zero's Aha Moment on just a 2B non-SFT Model

SeedFT: Structure-Preserving Fusion for Multi-Seed LLM Fine-Tuning

WebSailor: Navigating Super-human Reasoning for Web Agent

Improving Your Model Ranking on Chatbot Arena by Vote Rigging

Practical and Effective Code Watermarking for Large Language Models

Safety Reasoning with Guidelines

Scaling Laws of Synthetic Data for Language Model

The Crystal Ball Hypothesis in diffusion models: Anticipating object positions from initial noise

Is Your Multimodal Language Model Oversensitive to Safe Queries?

Sparse MeZO: Less Parameters for Better Performance in Zeroth-Order LLM Fine-Tuning

Sparse MeZO: Less Parameters for Better Performance in Zeroth-Order LLM Fine-Tuning

SeedLoRA: A Fusion Approach to Efficient LLM Fine-Tuning

SeedLoRA: A Fusion Approach to Efficient LLM Fine-Tuning

Enhancing Dataset Distillation with Concurrent Learning: Addressing Negative Correlations and Catastrophic Forgetting in Trajectory Matching

LaRA: Benchmarking Retrieval-Augmented Generation and Long-Context LLMs – No Silver Bullet for LC or RAG Routing

MuLan: Multimodal-LLM Agent for Progressive and Interactive Multi-Object Diffusion