← authors · overview

• CEBin: A Cost-Effective Framework for Large-Scale Binary Code Similarity Detection
  2024 · 20 citations
• Longhalqa: Long-context Hallucination Evaluation For Multimodal Large Language Models
  2024 · 7 citations
• Aegis: Mitigating Targeted Bit-flip Attacks against Deep Neural Networks
  2023 · 7 citations
• Spatial Preference Rewarding For Mllms Spatial Understanding
  2025
• The Side Effects of Being Smart: Safety Risks in MLLMs' Multi-Image Reasoning
  2026
• LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety
  2026
• State-Dependent Safety Failures in Multi-Turn Language Model Interaction
  2026
• Revisiting the Reliability of Language Models in Instruction-Following
  2025
• When Search Goes Wrong: Red-Teaming Web-Augmented Large Language Models
  2025
• SafeSearch: Automated Red-Teaming of LLM-Based Search Agents
  2025
• Understanding the Dilemma of Unlearning for Large Language Models
  2025
• Towards Understanding the Cognitive Habits of Large Reasoning Models
  2025
• SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models
  2023
• Course-Correction: Safety Alignment Using Synthetic Preferences
  2024