| Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimation | Mar 20, 2025 | Depth EstimationImage Reconstruction | —Unverified | 0 |
| Enhancing Zero-Shot Image Recognition in Vision-Language Models through Human-like Concept Guidance | Mar 20, 2025 | Prompt EngineeringZero-shot Generalization | —Unverified | 0 |
| Good Actions Succeed, Bad Actions Generalize: A Case Study on Why RL Generalizes Better | Mar 19, 2025 | AttributeReinforcement Learning (RL) | —Unverified | 0 |
| GenM^3: Generative Pretrained Multi-path Motion Model for Text Conditional Human Motion Generation | Mar 19, 2025 | Large Language ModelMotion Generation | —Unverified | 0 |
| Learning with Expert Abstractions for Efficient Multi-Task Continuous Control | Mar 19, 2025 | continuous-controlContinuous Control | CodeCode Available | 0 |
| Foundation Feature-Driven Online End-Effector Pose Estimation: A Marker-Free and Learning-Free Approach | Mar 18, 2025 | 6D Pose EstimationPose Estimation | —Unverified | 0 |
| Compound Expression Recognition via Large Vision-Language Models | Mar 14, 2025 | Emotion RecognitionZero-shot Generalization | —Unverified | 0 |
| Prompt-OT: An Optimal Transport Regularization Paradigm for Knowledge Preservation in Vision-Language Model Adaptation | Mar 11, 2025 | Domain GeneralizationLanguage Modeling | CodeCode Available | 0 |
| A Recipe for Improving Remote Sensing VLM Zero Shot Generalization | Mar 10, 2025 | Cross-Modal RetrievalZero-Shot Cross-Modal Retrieval | —Unverified | 0 |
| PoseLess: Depth-Free Vision-to-Joint Control via Direct Image Mapping with VLM | Mar 10, 2025 | DecoderPose Estimation | —Unverified | 0 |
