-
Tsinghua University
-
07:29
(UTC +08:00) - https://blog.algorithmpark.xyz/
Highlights
- Pro
Stars
[ACMMM 2026] PhyEdit: Towards Real-World Object Manipulation via Physically-Grounded Image Editing
🚀面向求职与开发场景的实用 AI Skills 集合,支持简历优化、岗位投递、面试准备与开发提效。
DeepSeek Harness: Everything is a Plugin.
[Official Repo] JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion
Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video Models
Self Gradient Forcing (SGF) recovers the missing context-gradient path for self-generated causal memory through a bounded two-pass replay, enabling models trained with only a 5-second window to ext…
Code for paper "Video Models Can Reason with Verifiable Rewards"
Ralph-style SVG generation loop with Claude Code, Codex, and multi-agent visual review.
[CVPR 2026 Oral] Official implementation for ChordEdit: One-Step Low-Energy Transport for Image Editing
Source code for 👏🏻"CLAP: Contrastive Latent Action Pretraining for Learning Vision-Language-Action Models from Human Videos" [IEEE T-RO]
[CVPR 2026] TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs
Synchronize Codex session provider metadata across rollout files and SQLite state.
[CVPR 2025] T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation
[NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL
A CLI tool to switch and manage Codex accounts
[CVPR 2026] Official code of the paper "Meta-CoT: Enhancing Granularity and Generalization in Image Editing"
Export and Share your ChatGPT conversation history
A unified framework for easy fine-tuning in Flow-Matching 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…
🔬 Harness Vibe Research with Self-evolving AI Scientists
A curated list of papers on reinforcement learning for video generation
Overleaf git bridge, fork of https://gitlab.com/axkibe/olgitbridge with support for the Overleaf v4 frontend
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.