Stars
An in-the-wild benchmark for AI agents in the OpenClaw Environment.
paper collection: alignment of diffusion models
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works…
Elevate your AI research writing, no more tedious polishing ✨
Official Implementation of "Visual-ERM: Reward Modeling for Visual Equivalence"
Official implementation of "EndoCoT". Scaling endogenous Chain-of-Thought (CoT) reasoning in diffusion models for complex structured generation.
A curated list of research papers, resources, and advancements on Diffusion Cache and related efficient diffusion model acceleration techniques.
[ICLR 2026 Oral] DiffusionNFT: Online Diffusion Reinforcement with Forward Process
⏰ Agenticly track worldwide conference deadlines (Website, Python Cli, Wechat Applet)
Official implementation of HPSv3: Towards Wide-Spectrum Human Preference Score (ICCV2025)
[CVPR 2026] V-RGBX: Video Editing with Accurate Controls over Intrinsic Properties
[ICLR 26] TempFlow-GRPO (Temporal Flow GRPO), a principled GRPO framework that captures and exploits the temporal structure inherent in flow-based generation.
[CVPR 2026] An official implementation of Adv-GRPO. The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation.
[CVPR 2026] Official Code for "ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning"
[NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL
[ICLR 2026] ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation
RLG: Inference-Time Alignment Control for Diffusion Models with Reinforcement Learning Guidance
This is a repository to collect training-free algorithms for visual generation and manipulation
Official repo for "IDArb: Intrinsic Decomposition for arbitrary number of input views and illuminations"
[CVPR 2026] Official release of "Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning"
[ICLR 2026] An official implementation of "STAR-Bench: Probing Deep Spatio-Temporal Reasoning as Audio 4D Intelligence"
[CVPR 2026] Official implementation of "DiT360: High-Fidelity Panoramic Image Generation via Hybrid Training".
[CVPR 2025 Oral] Alias-free Latent Diffusion Models (official implementation)
[NeurIPS 2025 Spotlight] A Generalist Diffusion Model for Vision Perception
S2R-HDR: A Large-Scale Rendered Dataset for HDR Fusion
[ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention