Lists (10)
Starred repositories
Rebuild the object in a reference image as a code-only, procedural, quality-gated, animation-ready Three.js model. Token-efficient image-to-3D.
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…
Official implementation of UniWorld-View
The roadmap of long-horizon agents
A curated list for Self-Improvement in Foundation Model Based Agentic Systems.
LLM-as-a-Verifier is a general-purpose framework that provides fine-grained feedback for any agent without requiring additional training. It achieves SOTA performance across coding, robotics, and m…
Unified World Model Inference & Evaluation Infrastructure
MM-ToolSandBox: A Unified Framework for Evaluating Visual Tool-Calling Agents
AgenticVBench: Can AI Agents Complete Real-World Post-Production Tasks?
The open-source CapCut alternative
Infinite Worlds with Versatile Interactions
Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence
This is a framework for evaluating reasoning in foundational Video Models.
EdgeBench: Unveiling scaling laws of learning from real-world environments
PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation (ECCV 2024)
[ICML 2026] Code2Worlds: Empowering Coding LLMs for 4D World Generation
Scalable Agentic RL for Any Agent and Sandbox.
A Physics-Grounded Benchmark for Multi-Agent Dynamics in World Models (ECCV'26)
Awesome Claude Design: 68 ready-to-use design system inspirations in DESIGN.md format. Drop one in, scaffold a full UI in one shot.
Bounded, typed, ablatable memory contract for long-horizon LLM agents — Slay the Spire 2 testbed
A Blender extension for automated, editable, and inter-shot consistent 3D storyboard production.
Use commands in English to control Blender with OpenAI's GPT-4
Claude Code plugin: automated code review loop with Codex
Curated Blender + Seedance workflows for AI filmmaking: previs, camera control, Blender MCP, reference video, and agent-guided use cases.