Shu Yang

When Thinking Backfires: Mechanistic Insights into Reason-induced Misalignment

Can AI Truly Represent Your Voice in Deliberations? A Comprehensive Study of Large-Scale Opinion Aggregation with LLMs

Dissecting Representation Misalignment in Contrastive Learning via Influence Function

Evaluating Data Influence in Meta Learning

MONICA: Real-Time Monitoring and Calibration of Chain-of-Thought Sycophancy in Large Reasoning Models

Neuron-Aware Data Selection in Instruction Tuning for Large Language Models

Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs

Investigating CoT Monitorability in Large Reasoning Models

Concept-Based Dictionary Learning for Inference-Time Safety in Vision–Language–Action Models

Backdooring CLIP through Concept Confusion

Compositional Architecture of Regret in Large Language Models

EAP-GP: Mitigating Saturation Effect in Gradient-based Automated Circuit Identification

Dissecting Misalignment of Multimodal Large Language Models via Influence Function

Representation Confusion: Towards Representation Backdoor on CLIP via Concept Activation

Understanding Reasoning in Chain-of-Thought from the Hopfieldian View

What Makes Your Model a Low-empathy or Warmth Person: Exploring the Origins of Personality in LLMs