-
Nankai University
- Tianjin
-
02:23
(UTC +08:00) - https://montaellis.github.io
Starred repositories
VLA-RFT: Vision-Language-Action Models with Reinforcement Fine-Tuning
[ICML 2024] 3D-VLA: A 3D Vision-Language-Action Generative World Model
[NeurIPS 2025] DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge
A Curated List of Awesome Works in World Modeling, Aiming to Serve as a One-stop Resource for Researchers, Practitioners, and Enthusiasts Interested in World Modeling.
A paper list for spatial reasoning
Resources on Differential Geometry in Robotics
PhysWorld: From Real Videos to World Models of Deformable Objects via Physics-Aware Demonstration Synthesis
Codebase of GRPO: Implementations and Resources of GRPO and Its Variants
[NeurIPS 2025]SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction.
Trace Anything: Representing Any Video in 4D via Trajectory Fields
Torch-native, batchable, atomistic simulations.
Reinforcement learning in differentiable multiphysics simulation with NVIDIA Warp.
Collection of Cloth Simulation Papers.
[CVPR'25 Oral] Official implementation for "DiffusionRenderer: Neural Inverse and Forward Rendering with Video Diffusion Models"
This is a 3DGS(3D Gaussian Splatting) viewer built on Three.js, with features for marking, measurements, text watermarks, etc.
A universal summary of current robotics simulators
「妙幕」是一款跨平台客户端工具,可以批量为视频或者音频生成字幕文件,并支持对字幕进行翻译,支持百度、火山、openai、ollama、deepseek 等多家翻译
A collection of awesome LaTeX Thesis/Dissertation templates and beyond! //(LaTeX / Word / Typst / Markdown 格式的学位论文、演示文稿、报告、项目申请书、简历、书籍等模板收藏)
Hunyuan 3D Part Segmentation and Generation Pipeline
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper, Ada and Blackwell GPUs, to provide better performance with lower memory…
《代码随想录》LeetCode 刷题攻略:200道经典题目刷题顺序,共60w字的详细图解,视频难点剖析,50余张思维导图,支持C++,Java,Python,Go,JavaScript等多语言版本,从此算法学习不再迷茫!🔥🔥 来看看,你会发现相见恨晚!🚀
libpgo: Library for Physically based Simulation (P), Geometric Shape Modeling (G), and Optimization (O)
A Taichi-powered high-performance numerical simulator for multiscale and multifield geophysical problems
[SIGGRAPH Asia 2025 (ACM TOG)] AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views
MapAnything: Universal Feed-Forward Metric 3D Reconstruction