[ICML 2026] RLSF-V: Mitigating Hallucinations in MLLMs via Fuzzy Semantic Self-Feedback

Official implementation of paper "Towards Robust Pseudo-Label Learning in Semantic Segmentation: An Encoding Perspective" (NeurIPS 2025)

Official implementation of paper "Towards Unsupervised Domain Bridging via Image Degradation in Semantic Segmentation" (NeurIPS 2025)

Official implementation of "Balanced Learning for Domain Adaptive Semantic Segmentation" (ICML 2025)

Awesome GUI Agent Paper List

Claude Code skills for academic papers: deep analysis, comics, summaries | 论文工艺：深度解读、漫画生成、速览总结

A curated list of awesome AI tools, libraries, papers, datasets, and frameworks that accelerate scientific discovery — from physics and chemistry to biology, materials, and beyond.

[preprint] ReservoirTTA: Prolonged Test-time Adaptation for Evolving and Recurring Domains

CEDAS: Clustering of Evolving Data-streams into Arbitrary Shapes

🌊 Online machine learning in Python

AI agents running research on single-GPU nanochat training automatically

[CVPR 2022] Pytorch implementation for “Debiased Learning from Naturally Imbalanced Pseudo-Labels”

Public repository for Agent Skills

Installable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill c…

An agentic skills framework & software development methodology that works.

This repository implements continuous test-time adaptation algorithms for object detection on the SHIFT dataset.

The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…

Collection of papers about video-audio understanding

Processed / Cleaned Data for Paper Copilot

Online Hollow Knight save file editor .

Code for SCOMatch: Alleviating Overtrusting in Open-set Semi-supervised Learning (ECCV2024)

[ICLR2025] HiLo: A Learning Framework for Generalized Category Discovery Robust to Domain Shifts

定时获取谷歌学术和arxiv论文的相关更新 (代码只有一个py文件，较简单有注释)

An awesome paper list of Semi-Supervised Learning under realistic settings.

code for Robust Semi-supervised Learning by Wisely Leveraging Open-set Data

这个仓库用于记录我每周分享的技术内容文档。 This repository is used to document my weekly technical sharing content.

[Code for paper] The Mirage of Performance Gains: Why Contrastive Decoding Fails to Mitigate Object Hallucinations in MLLMs?

Code for paper: Unraveling the Shift of Visual Information Flow in MLLMs: From Phased Interaction to Efficient Inference

Code for paper: Visual Signal Enhancement for Object Hallucination Mitigation in Multimodal Large language Models