Lists (6)
⚡ Accelerator / ML(LM)Ops
👀 Computer Vision
DL repositories in Computer Vision🪄 Generative Model(s)
👨🏻🎓 ML/DL
Awesome ML/DL repos which are found while random-walking in github🔻 Model Compression
😶🌫️ with facial data
Stars
한국인을 위한 스킬 모음집 - SRT, KTX, KBO, 카카오톡, 한글과 컴퓨터, 미세먼지, 우편번호, 블루리본 등등...
The highest-scoring AI memory system ever benchmarked. And it's free.
[CVPR 2026] EditCtrl: Disentangled Local and Global Control for Real-Time Generative Video Editing
CLEAR: Context-Aware Learning with End-to-End Mask-Free Inference for Adaptive Video Subtitle Removal
AutoGaze automatically removes redundant patches in a video, reducing #tokens in ViT/MLLM by 4x-100x.
Self-referential self-improving agents that can optimize for any computable task
[CVPR 2026 Findings] MambaEye: A Size-Agnostic Visual Encoder with Causal Sequential Processing
Train the smallest LM you can that fits in 16MB. Best model wins!
[CVPR 2026 Highlight] GlyphPrinter: Region-Grouped Direct Preference Optimization for Glyph-Accurate Visual Text Rendering
[ICCV 2025] Official Pytorch Implementation of FLOAT: Generative Motion Latent Flow Matching for Audio-driven Talking Portrait.
Generate high resolution videos with a custom voice and appearance, based on LTX-2/LTX-2.3 + Identity In-Context LoRA
AI agents running research on single-GPU nanochat training automatically
A TUI-based utility for real-time monitoring of InfiniBand traffic and performance metrics on the local node
"CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/
Helios: Real Real-Time Long Video Generation Model
Open-source RL Framework with Online Teacher-Student Distillation
A curated collection of research papers, models, and resources tracing the evolution from specialized models to unified world models.
[ICLR 26 Oral] Stable Video Infinity: Infinite-Length Video Generation with Error Recycling
BitDance & UniWeTok: Open-source autoregressive model with binary visual tokens. A research project for building powerful multimodal autoregressive model.
MOVA: Towards Scalable and Synchronized Video–Audio Generation
Qwen3.5 is the large language model series developed by Qwen team, Alibaba Cloud.
[ICLR 2026] rCM: SOTA JVP-Based Diffusion Distillation & Few-Step Video Generation & Scaling Up sCM/MeanFlow