-
University of Chinese Academy of Science / City University of Hong Kong
- Beijing / Hong Kong, China
-
09:08
(UTC -12:00) - https://likaiucas.github.io/
- https://orcid.org/0000-0001-7161-434X
- @kaili37
Highlights
- Pro
Lists (1)
Sort Name ascending (A-Z)
Stars
[NeurIPS 2025] Video World Models with Long-term Spatial Memory
This repository tracks the latest advancements in 3D Gaussian Splatting from Arxiv, with daily automated updates. Stay up-to-date with cutting-edge research in this exciting field!
[ECCV 2026] Argus: Metric Panoramic 3D Reconstruction for Indoor Scenes
[ICLR 2026] Sat3DGen: Comprehensive Street-Level 3D Scene Generation from Single Satellite Image
Official repository for the ECCV 2026 paper: Align and Segment (AnS)
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
A Minimal and Elegant Framework & Tutorial for Real-Time Interactive World Models
UniPoly: A Unified Instance-Level Framework for Polygon and Polyline Extraction from Remote Sensing Images
大厂打工人,日报 / 周报解决方案。依据当日 / 本周的AI使用情况,一键日报 / 周报生成。
[CVPR 2026] Implementation of paper "SceneMaker: Open-set 3D Scene Generation with Decoupled De-occlusion and Pose Estimation Model"
From a single casual image to a visually consistent and physically stable interactive 3D scene.
Gen3DSR: Generalizable 3D Scene Reconstruction via Divide and Conquer from a Single View, 3DV2025
[CVPR 2025] MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation
[CVPR 2026] 3D-Fixer: Coarse-to-Fine In-place Completion for 3D Scenes from a Single Image
NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.
You're reading this. The skill predicted it. A workflow that turns every post into a calibrated experiment—score, blind-predict, retro, evolve. The future doesn't reward effort, it rewards those wh…
Public companion kit for ForgeCAD: examples, agent skills, docs links, and issue tracking. The hosted CAD app and core source live elsewhere.
[NeurIPS 2025] PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers
[NeurIPS 2024] ODGS: 3D Scene Reconstruction from Omnidirectional Images with 3D Gaussian Splatting
Reference code for the Meta-Harness paper.
Local-first cross-platform desktop workspace for Claude Code / agents: multi-agent, Git worktrees, code diffs, skill marketplace, multi-model, Computer Use, task-aware desktop pets, with WeChat, Fe…
Claude Code Dedicated Development Harness - Achieving High-Quality Development Through an Autonomous Plan→Work→Review Cycle
Open3DIS: Open-vocabulary 3D Instance Segmentation with 2D Mask Guidance (CVPR 2024)
A MLLM-based agentic system converts a single room image into executable Blender code for 3D room reconstruction.