hee-suk-yoon / ConfPOView external linksLinks
[ICML'25] Official code for "ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization"
☆18Dec 22, 2025Updated last month
Alternatives and similar repositories for ConfPO
Users that are interested in ConfPO are comparing it to the libraries listed below
Sorting:
- DimCL: Dimensional Contrastive Learning☆30Dec 9, 2025Updated 2 months ago
- [ICLR'25] Official code for "Can Video LLMs Refuse to Answer? Alignment for Answerability in Video Large Language Models"☆34Dec 26, 2025Updated last month
- [ICCV'25] TARO: Timestep-Adaptive Representation Alignment with Onset-Aware Conditioning for Synchronized Video-to-Audio Synthesis☆33Sep 22, 2025Updated 4 months ago
- Implementation of Uncertainty-Aware Rank-One MIMO Q Network Framework for Accelerated Offline Reinforcement Learning☆31Dec 9, 2025Updated 2 months ago
- ☆39Dec 21, 2024Updated last year
- PyTorch implementation of **Towards Robust Policy: Enhancing Offline Reinforcement Learning with Adversarial Attacks and Defenses**☆31Dec 9, 2025Updated 2 months ago
- ☆39Dec 14, 2021Updated 4 years ago
- [INTERSPEECH'24] Official code for "LI-TTA: Language Informed Test-Time Adaptation for Automatic Speech Recognition"☆33Jul 10, 2025Updated 7 months ago
- 비디오 기반 인공지능 대화시스템☆14Dec 23, 2023Updated 2 years ago
- ☆33Nov 26, 2024Updated last year
- SCANet: Scene Complexity Aware Network for Weakly-Supervised Video Moment Retrieval (ICCV'2023), [STARLAB] This repositery is a system to…☆57Apr 14, 2025Updated 9 months ago
- Winning SubNetwork (WSN), Soft-SubNetwork (SoftNet)☆44Mar 12, 2024Updated last year
- CCFDM reinforcement learning☆40Dec 28, 2021Updated 4 years ago
- Enhancing Rating-Based Reinforcement Learning to Effectively Leverage Feedback from Large Vision-Language Models (ICML 2025)☆53Dec 26, 2025Updated last month
- DNI: Dilutional Noise Initialization for Diffusion Video Editing (ECCV 2024)☆46Jul 17, 2024Updated last year
- [ECCV'24] Official code for "BI-MDRG: Bridging Image History in Multimodal Dialogue Response Generation"☆42Nov 19, 2024Updated last year
- [CVPR 2025] ITA-MDT official implementation☆67Dec 21, 2025Updated last month
- Dual-scale Doppler Attention for Human Identification☆47Aug 13, 2025Updated 6 months ago
- HEAR: Hearing Enhanced Audio Response for Video-grounded Dialogue, EMNLP 2023 (long, findings) [STARLAB] Audio Enhancement for video-dial…☆57Dec 23, 2023Updated 2 years ago
- Weakly-Supervised Moment Retrieval Network for Video Corpus Moment Retrieval☆65Dec 13, 2021Updated 4 years ago
- [ICLR'25] MDSGen: Fast and Efficient Masked Diffusion Temporal-Aware Transformers for Open-Domain Sound Generation☆38Dec 25, 2025Updated last month
- Predictive Coding for Decision Transformer (IROS 2024)☆41Jun 19, 2025Updated 7 months ago
- Policy Learning from Large Vision-Language Model Feedback Without Reward Modeling (IROS 2025)☆36Dec 26, 2025Updated last month
- [ICML'25 Spotlight] FlowDrag: 3D-aware Drag-based Image Editing with Mesh-guided Deformation Vector Flow Fields☆45Dec 28, 2025Updated last month
- ICML 2024, Official Implementation of "Cross-view Masked Diffusion Transformers for Person Image Synthesis."☆53Nov 5, 2024Updated last year
- Causal Localization Network for Radar Human Localization with micro-Doppler signature☆60Sep 26, 2024Updated last year
- (ICCV2025) Occlusion-robust Stylization for Drawing-based 3D Animation☆50Dec 26, 2025Updated last month
- Test-time Procrustes Calibration for Diffusion-based Human Image Animation, NeurIPS 2024☆52Aug 23, 2025Updated 5 months ago
- FRAG: Frequency Adaptive Group for Diffusion Video Editing (ICML 2024)☆70Aug 23, 2025Updated 5 months ago
- Fast and Efficient MMD-based Fair PCA via Optimization over Stiefel Manifold (AAAI 2022)☆11Sep 27, 2022Updated 3 years ago
- ☆13Dec 13, 2023Updated 2 years ago
- This is official repository for Dual Temperature Helps Contrastive Learning without Many Negative Samples (CVPR2022)☆27Dec 1, 2022Updated 3 years ago
- Official code for "SimPSI: A Simple Strategy to Preserve Spectral Information in Time Series Data Augmentation", AAAI 2024.☆36Jan 22, 2025Updated last year
- ☆18Nov 19, 2024Updated last year
- AI Development in Evolving Policy [AI DEP]☆46Jul 7, 2025Updated 7 months ago
- Code for AAAI 2021 paper "SCNet: Traning Inference Sample Consistency for Instance Segmentation".☆22Jan 31, 2021Updated 5 years ago
- ☆28Mar 13, 2025Updated 11 months ago
- ☆28Mar 13, 2025Updated 11 months ago
- Control Dobot Arm Magician to wrap out any object that it see in its vision☆10Jul 31, 2019Updated 6 years ago