Bo Chen

The paper proposes a novel bi-level exact unlearning attack targeting Large Reasoning Models (LRMs) that forces incorrect final answers while generating misleading reasoning traces, highlighting new security vulnerabilities in unlearning pipelines.

The paper proposes Adaptive Stealing (AS), a novel and more robust watermark stealing algorithm that dynamically selects optimal attack perspectives to significantly increase the efficiency of compromising LLM watermarks.

The paper introduces eXTC, a novel framework that combines structured prompt optimization, knowledge distillation, and reinforcement learning to create a highly performant and fully interpretable text classifier.

The paper proposes Deep Research as Rubric (DR-rubric), a novel evidence-driven framework that treats rubric construction itself as a research problem to generate fine-grained, scalable reward signals for open-ended reasoning tasks.

The paper proposes Shallow-RHS, an asymmetric graph-completion model, to solve the cold-start problem for both new content and new devices in large-scale recommendation systems.