Publications

CLIPoint3D: Language-Grounded Few-Shot Unsupervised 3D Point Cloud Domain Adaptation

Chorus: Multi-Teacher Pretraining for Holistic 3D Gaussian Scene Encoding

Continual Vision-Language Action Learning in Robotic Manipulation

Deconstructing the Failure of Ideal Noise Correction: A Three-Pillar Diagnosis

From Weights to Concepts: Data-Free Interpretability of CLIP via Singular Vector Decomposition

Generalizable Knowledge Distillation from Vision Foundation Models for Semantic Segmentation

How to Take a Memorable Picture? Empowering Users with Actionable Feedback

Hyperbolic Busemann Neural Networks

Open-Vocabulary Domain Generalization in Urban-Scene Segmentation

PoInit-of-View: Poisoning Initialization of Views Transfers Across Multiple 3D Reconstruction Systems

Specificity-aware reinforcement learning for fine-grained open-world classification

TerraScope: Pixel-Grounded Visual Reasoning for Earth Observation

The Devil Is in Gradient Entanglement: Energy-Aware Gradient Coordinator for Robust Generalized Category Discovery

Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models

Large Multimodal Models as General In-Context Classifiers

Organizing Unstructured Image Collections using Natural Language

SEM: Sparse Embedding Modulation for Post-Hoc Debiasing of Vision-Language Models

NullFace: Training-Free Localized Face Anonymization

Towards Unconstrained Human-Object Interaction

Training-Free Semantic Multi-Object Tracking with Vision-Language Models

Efficient Degradation-agnostic Image Restoration via Channel-Wise Functional Decomposition and Manifold Regularization

Fast and Stable Riemannian Metrics on SPD Manifolds via Cholesky Product Geometry

Intrinsic Lorentz Neural Network

Inverse Virtual Try-On: Generating Multi-Category Product-Style Images from Clothed Individuals

Motion-Aligned Word Embeddings for Text-to-Motion Generation

Proper Velocity Neural Networks

Rethinking Expressivity and Degradation-Awareness in Attention for All-in-One Blind Image Restoration

Riemannian High-Order Pooling for Brain Foundation Models

Dense Motion Captioning