Bin Chen

VulKey introduces a novel LLM-based framework that uses a hierarchical abstraction of expert security knowledge to guide automatic vulnerability repair, achieving state-of-the-art performance on real-world benchmarks.

Prompt2Fingerprint (P2F) introduces a novel, scalable framework that injects unique LLM fingerprints by mapping text descriptions directly to low-rank parameter updates, eliminating the need for resource-intensive model retraining.

The paper proposes Reasoning-Conditioned Direct Preference Optimization (RC-DPO) to effectively mitigate hallucinations in multimodal large reasoning models by explicitly conditioning the preference optimization on the Chain-of-Thought (CoT) process.

The paper introduces Pocket-Dentist, an efficiency-aware benchmark and model that demonstrates that compact, smaller Vision-Language Models (VLMs) can outperform larger models in accuracy while drastically reducing computational cost for on-device dental image understanding.

The paper proposes Credit-Attenuated Privileged Feedback (CAPF), a training-time mechanism that uses verifier-side information to guide LLM search agents, significantly improving their performance on complex QA tasks.

OctoT2I introduces a self-evolving, agentic routing framework that efficiently selects and combines multiple Text-to-Image models, achieving high performance while significantly boosting inference speed and energy efficiency.