Sierkinhane
Follow
Lists (3)
Stars
Official PyTorch re-implementation of MiniT2I.
Don't trust an Agent. Test it. Open-source lab for agent credit — exams → evidence → explainable, recomputable scores. Built for the day agents hire and pay each other. A2A-native.
SoL-Pi: Scaling Auto-Research Loops for Efficient Agent Harnesses
Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation (NeurIPS 2025)
Official Code for GPIC: A Giant Permissive Image Corpus for Visual Generation
🧠 Train a 64M-parameter LLM from scratch in just 2h!
Archived — ML Intern is no longer maintained. Continue with HuggingChat.
Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.
LLM大模型（重点）以及搜广推等 AI 算法中手写的面试题，（非 LeetCode），比如 Self-Attention, AUC等，一般比 LeetCode 更考察一个人的综合能力，又更贴近业务和基础知识一点
[CVPR 2026] Emergent Extreme-View Geometry in 3D Foundation Models
A benchmark for evaluating LLMs on open-ended CS problems. Exploring the Next Frontier of Computer Science.
EVOLVE-VLA: Test-Time Training from Environment Feedback for Vision-Language-Action Models
Video Generation, Physical Commonsense, Semantic Adherence, VideoCon-Physics
[ECCV 2024] Efficient Diffusion Transformer with Step-wise Dynamic Attention Mediators
[CVPR 2026] Official Implementation of Edit2Perceive
[CVPR 2026] An official implementation of Adv-GRPO. The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation.
[CVPR 2026] SpatialVID: A Large-Scale Video Dataset with Spatial Annotations
[ICLR 2026] A simple state update rule to enhance length generalization for CUT3R
A Curated List of Awesome Works in World Modeling, Aiming to Serve as a One-stop Resource for Researchers, Practitioners, and Enthusiasts Interested in World Modeling.
ULMEvalKit: One-Stop Eval ToolKit for Image Generation
Automatic Video Generation from Scientific Papers
《代码随想录》LeetCode 刷题攻略：200道经典题目刷题顺序，共60w字的详细图解，视频难点剖析，50余张思维导图，支持C++，Java，Python，Go，JavaScript等多语言版本，从此算法学习不再迷茫！🔥🔥 来看看，你会发现相见恨晚！🚀