Junhao Dong

Tug-of-War No More: Harmonizing Accuracy and Robustness in Vision-Language Models via Stability-Aware Task Vector Merging

OrthAlign: Orthogonal Subspace Decomposition for Non-Interfering Multi-Objective Alignment

DeCo-DETR: Decoupled Cognition DETR for efficient Open-Vocabulary Object Detection

Can LLMs Refuse Questions They Do Not Know? Measuring Knowledge-Aware Refusal in Factual Tasks

C3-OWD: A Curriculum Cross-modal Contrastive Learning Framework for Open-World Detection

MUOT-CLIP: Enhancing Few-Shot Adaptation of CLIP via Inter- and Intra- Modality Unbalanced Optimal Transport

Synergizing Dynamic Score Aggregation with Contrastive Regularization for Open-Set Semi-Supervised Out-of-Distribution Detection

Orthogonal Updates Are Optimal for Continual Learning

Polymorphic: Plug-and-Play Visual Token Compression for Scalable VLMs

CodeBiasBench: Benchmarking social fairness of large language model generated code

Robust SuperAlignment: Weak-to-Strong Robustness Generalization for Vision-Language Models

CrossSpectra: Exploiting Cross-Layer Smoothness for Parameter-Efficient Fine-Tuning

Machine Unlearning via Task Simplex Arithmetic

Solving Discrete (Semi) Unbalanced Optimal Transport with Equivalent Transformation Mechanism and KKT-Multiplier Regularization

Improving Zero-Shot Adversarial Robustness in Vision-Language Models by Closed-form Alignment of Adversarial Path Simplices

Unified (Semi) Unbalanced and Classic Optimal Transport with Equivalent Transformation Mechanism and KKT-Multiplier Regularization