Lijie Hu

Controlling Repetition in Protein Language Models

Dual-Kernel Adapter: Expanding Spatial Horizons for Data-Constrained Medical Image Analysis

Predicting LLM Output Length via Entropy-Guided Representations

The Price of Amortized inference in Sparse Autoencoders

When Modalities Conflict: How Unimodal Reasoning Uncertainty Governs Preference Dynamics in MLLMs

Dissecting Representation Misalignment in Contrastive Learning via Influence Function

Evaluating Data Influence in Meta Learning

Mechanistic Analysis of Demonstration Conflicts in In-Context Learning

MSRS: Adaptive Multi-Subspace Representation Steering for Attribute Alignment in Large Language Models

Learning Label-Efficient Interpretable Medical Image Diagnosis via Semi-supervised Hypergraph Concept Bottleneck Model

D-LEAF: Localizing and Correcting Hallucinations in Multimodal LLMs via Layer-to-head Attention Diagnostics

RuleEdit: Benchmarking Rule-Level Knowledge Editing in Large Language Models

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

Attributing Data for Sharpness-Aware Minimization

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

Backdooring CLIP through Concept Confusion

BadConcepts: Backdooring VLMs with Visual Concepts

Compositional Architecture of Regret in Large Language Models

Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing

Editable Concept Bottleneck Models

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

Backdooring Vision-Language Models with Out-Of-Distribution Data

Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing

Editable Concept Bottleneck Models

Dissecting Misalignment of Multimodal Large Language Models via Influence Function

Low-cost Enhancer for Text Attributed Graph Learning via Graph Alignment

CAT: Concept-level backdoor ATtacks for Concept Bottleneck Models

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

Evaluating the Unseen: A Novel Framework for Assessing Unsupervised Concept Bottleneck Models