Shuai Wang

GuidedBench: Measuring and Mitigating the Evaluation Discrepancies of In-the-wild LLM Jailbreak Methods

EAMET: ROBUST MASSIVE MODEL EDITING VIA EMBEDDING ALIGNMENT OPTIMIZATION

BadMoE: Backdooring Mixture-of-Experts LLMs via Optimizing Routing Triggers and Infecting Dormant Experts

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

Are Large Language Models Good XAI Annotators?

SQ-format: A Unified Sparse-Quantized Hardware-friendly Data Format for Large Language Models

ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization

WebSailor: Navigating Super-human Reasoning for Web Agent

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

Chain-of-Jailbreak Attack for Image Generation Models via Editing Step by Step

Boosting Concept Bottleneck Models with Supervised, Hierarchical Concept Learning

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