Lists (3)
Stars
Train a Language Model with GRPO to create a schedule from a list of events and priorities
A unified framework for 3D content generation.
From anything to mesh like human artists. Official impl. of "MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization"
Source code for the SIGGRAPH 2024 conference paper "Neural Geometry Fields for Meshes"
School project WIP. Implementation of the paper 'Neural Mesh Simplification' by Potamias et al.
An example of multi-agent orchestration with llama-index
Un-official and WIP Implementation of the Neural Mesh Simplification paper
Official implementation of "MeshDiffusion: Score-based Generative 3D Mesh Modeling" (ICLR 2023 Spotlight)
用于大模型 RLHF 进行人工数据标注排序的工具。A tool for manual response data annotation sorting in RLHF stage.
JDDC 2019 并列亚军（第三名）“网数ICT小分队”的检索模型部分
[NeurIPS 2024] Atlas3D: Physically Constrained Self-Supporting Text-to-3D for Simulation and Fabrication
A collection of awesome video generation studies.
The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
A Matlab implementation of the paper "Accelerated Quadratic Proxy for Geometric Optimization"
Globally Convergent Type-I Anderson Acceleration for Non-Smooth Fixed-Point Iterations
Supplemental code for the paper "A Splitting Scheme for Flip-Free Distortion Energies" by O. Stein, J. Li, and J. Solomon
Anderson Acceleration for Nonconvex ADMM Based on Douglas-Rachford Splitting
Anderson acceleration for geometry optimization and physics simulation
An efficient GPU-compatible library built on PyTorch, offering a wide range of proximal operators and constraints for optimization and machine learning tasks.
A C/x86 assembly implementation of proximal operators with SSE3/AVX SIMD instructions
SPH Realization of Fluid Simulation. Featuring Large Scale Simulation, Rigid-Fluid Coupling and High Viscosity Fluid.
FEM implementation with Stable Neo-Hookean energy in libigl.
Decomposed Optimization Time Integration (DOT) is a domain-decomposed optimization method for fast, reliable simulation of deformation dynamics. DOT efficiently converges with frame-rate time-steps…
ADMM ⊇ Projective Dynamics: Fast Simulation of Hyperelastic Models with Dynamic Constraints
repo for NIMBLE: A Non-rigid Hand Model with Bones and Muscles