Yu Yin

Expo-GS: Exposure-Aware Signed Distance Function in Gaussian Splatting for High Dynamic Range

Causal3D: a comprehensive benchmark for causal learning from visual data

NEBULA: Do We Evaluate Vision-Language-Action Agents Correctly?

Balancing Fidelity and Diversity: Synthetic data could stand on the shoulder of the real in visual recognition

Counterfactual Visual Explanation via Causally-Guided Adversarial Steering

ERC-SVD: Error-Controlled SVD for Large Language Model Compression

Fix False Transparency by Noise Guided Splatting

Praxis-VLM: Vision-Grounded Decision Making via Text-Driven Reinforcement Learning

Segment then Splat: Unified 3D Open-Vocabulary Segmentation via Gaussian Splatting

Dynamic Self-Distillation via Previous Mini-batches for Fine-tuning Small Language Models