Stars
[ICCV2025] Where, What, Why: Towards Explainable Driver Attention Prediction
OpenOmni: Official implementation of Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Alignment and Real-Time Self-Aware Emotional Speech Synthesis
[ICML 2025] DreamDPO: Aligning Text-to-3D Generation with Human Preferences via Direct Preference Optimization
Official implementation of GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents
Awesome-Long2short-on-LRMs is a collection of state-of-the-art, novel, exciting long2short methods on large reasoning models. It contains papers, codes, datasets, evaluations, and analyses.
(ICLR2025 Spotlight) DEEM: Official implementation of Diffusion models serve as the eyes of large language models for image perception.
Towards Modality Generalization: A Benchmark and Prospective Analysis
TPAMI: Tackling noisy labels with network parameter additive decomposition (PyTorch implementation).
awesome papers in LLM interpretability
Uni-OVSeg is a weakly supervised open-vocabulary segmentation framework that leverages unpaired mask-text pairs.
A Python toolbox for conformal prediction research on deep learning models, using PyTorch.
[NeurIPS 2023] "Out-of-distribution Detection Learning with Unreliable Out-of-distribution Sources"
[CIKM-2024] Official code for work "ERASE: Error-Resilient Representation Learning on Graphs for Label Noise Tolerance"
[arXiv:2311.03191] "DeepInception: Hypnotize Large Language Model to Be Jailbreaker"
ICCV'2023: Holistic Label Correction for Noisy Multi-Label Classification
IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Models
ICCV'2023: Combating Noisy Labels with Sample Selection by Mining High-Discrepancy Examples
[Open-source Project] UniMoCap: community implementation to unify the text-motion datasets (HumanML3D, KIT-ML, and BABEL) and whole-body motion dataset (Motion-X).
Phase-aware Adversarial Defense for Improving Adversarial Robustness
Improving Adversarial Robustness via Mutual Information Estimation
Removing Adversarial Noise in Class Activation Feature Space
Towards Defending against Adversarial Examples via Attack-Invariant Features