Heuristic Learning Blog Post

A Python framework for AI-driven character animation using neural networks.

Code of Strips as Tokens: Artist Mesh Generation with Native UV Segmentation. ACM Transactions on Graphics (SIGGRAPH 2026)

从嘉靖帝学习的极简主义Agent团队管理，免去上朝和微操

Auto-loop execution workflow with quality gates for Claude Code. Automatically decomposes tasks, implements code, runs tests, and iterates through quality gates until completion.

[ICML'26] Official repository of Utonia: Toward One Encoder for All Point Clouds

[CVPR 2026] EmbodMocap: In-the-Wild 4D Human-Scene Reconstruction for Embodied Agents

[arXiv 2025] Seeing to Act, Prompting to Specify: A Bayesian Factorization of Vision Language Action Policy

Code for "StreamingTalker: Audio-driven 3D Facial Animation with Autoregressive Diffusion Model", AAAI2026 Oral

[CVPR 2026] InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fields

HY-Motion model for 3D human motion or 3D character animation generation.

Code for the paper "Learning Generalizable Hand-Object Tracking Controller from Synthetic Hand-Object Demonstrations"

Official code of paper: MeshMosaic: Scaling Artist Mesh Generation via Local-to-Global Assembly.

Native Multimodal Models are World Learners

Code for "CoDA: Coordinated Diffusion Noise Optimization for Whole-Body Manipulation of Articulated Objects", NeurIPS 2025

✨✨Latest Advances on Multimodal Large Language Models

[ICCV 2025] SpatialTrackerV2: 3D Point Tracking Made Easy

Official implementation of ICCV 2025 paper "EgoAgent: A Joint Predictive Agent Model in Egocentric Worlds".

Official Implementation of [AnimaX: Animating the Inanimate in 3D with Joint Video-Pose Diffusion Models]

Code of ComboStoc, the diffusion models and training/sampling code for our paper exploring the Combinatorial Stochasticity for Diffusion Generative Models.

[CVPR25 Oral (Top 3.3%)] Official code for paper "Reconstructing Humans with a Biomechanically Accurate Skeleton".

[ICCV 2025] MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space

[TASE 2025] Efficient Alignment of Unconditioned Action Prior for Language-conditioned Pick and Place in Clutter

Lets make video diffusion practical!

[CVPR 2025 Oral] TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization

The modified 272-dimensional motion representation processing script.

[ICLR 2025] Ready-to-React: Online Reaction Policy for Two-Character Interaction Generation