GitHunt

JIA Lab

JIA-Lab-research

JIA Lab

Languages

Python96%Jupyter Notebook4%

Top Repositories

Repositories

92
JI
JIA-Lab-research/outpainting_srn

Wide-Context Semantic Image Extrapolation, CVPR2019

Python13532Updated just now
cvpr2019ganimage-extrapolationimage-generationimage-inpaintingimage-outpaintingtensorflow
JI
JIA-Lab-research/Seg-Zero

Project Page For "Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement"

Python60828Updated 2 hours ago
multimodalmultimodel-large-language-modelreasoning-language-modelsreinforcement-learningsegmentation
JI
JIA-Lab-research/LISA

Project Page for "LISA: Reasoning Segmentation via Large Language Model"

Python2.6k199Updated 18 hours ago
large-language-modelllmmulti-modalsegmentation
JI
JIA-Lab-research/DreamOmni2

This project is the official implementation of 'DreamOmni2: Multimodal Instruction-based Editing and Generation''

Python2.3k191Updated 22 hours ago
image-editingimage-generationunified-generation-editing-model
JI
JIA-Lab-research/PointGroup

PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation

Python44581Updated 23 hours ago
JI
JIA-Lab-research/VisionZip

Official repository for VisionZip (CVPR 2025)

Python41118Updated 1 day ago
efficiencymulti-modalityvision-language-modelvlms
JI
JIA-Lab-research/SphereFormer

The official implementation for "Spherical Transformer for LiDAR-based 3D Recognition" (CVPR 2023).

Python36341Updated 1 day ago
3d-object-detection3d-semantic-segmentationcvpr2023lidar-point-cloudnuscenessemantickittitransformerwaymo
JI
JIA-Lab-research/RePlan

RePlan: Reasoning-Guided Region Planning for Complex Instruction-Based Image Editing

Python592Updated 1 day ago
benchmarkcontroleditinggrpoimage-editinginpaintingplanning
JI
JIA-Lab-research/VisionReasoner

VisionReasoner: Unified Reasoning-Integrated Visual Perception via Reinforcement Learning

Python32415Updated 1 day ago
counting-objectsmultimodalmultimodal-large-language-modelsobject-detectionreasoning-language-modelsreinforcement-learningsegmentationvisual-perception
JI
JIA-Lab-research/VisionThink

[NeurIPS 2025] Efficient Reasoning Vision Language Models

Python45130Updated 1 day ago
JI
JIA-Lab-research/Video-P2P

Video-P2P: Video Editing with Cross-attention Control

Python42627Updated 1 day ago
generative-modelimage-editingstable-diffusiontext-driven-editingvideo-editing
JI
JIA-Lab-research/MGM

Official repo for "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models"

Python3.3k276Updated 1 day ago
generationlarge-language-modelsvision-language-model
JI
JIA-Lab-research/LongLoRA

Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)

Python2.7k292Updated 1 day ago
fine-tuning-llmlarge-language-modelsllmlong-contextlora
JI
JIA-Lab-research/VoxelNeXt

Long Range 3D Perception - VoxelNeXt (CVPR 2023)

Python85579Updated 2 days ago
3d-multi-object-tracking3d-object-detectionargoverseautonomous-drivinglidarnusceneswaymo-open-dataset
JI
JIA-Lab-research/ARPO

Official Implementation of ARPO: End-to-End Policy Optimization for GUI Agents with Experience Replay

Python15110Updated 3 days ago
JI
JIA-Lab-research/MR-GSM8K

Challenge LLMs to Reason About Reasoning: A Benchmark to Unveil Cognitive Depth in LLMs

Python522Updated 3 days ago
JI
JIA-Lab-research/LargeKernel3D

LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs (CVPR 2023)

Python21411Updated 4 days ago
3dnuscenesobject-detectionscannetsemantic-segmentation
JI
JIA-Lab-research/ControlNeXt

Controllable video and image Generation, SVD, Animate Anyone, ControlNet, ControlNeXt, LoRA

Python1.6k79Updated 4 days ago
JI
JIA-Lab-research/UnityVideo

This project is the official implementation of "UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation"

2098Updated 4 days ago
JI
JIA-Lab-research/spconv-plus

No description provided.

Python1636Updated 5 days ago
JI
JIA-Lab-research/FocalsConv

Focal Sparse Convolutional Networks for 3D Object Detection (CVPR 2022, Oral)

Python38934Updated 5 days ago
3d-object-detectionautonomous-drivingkittinuscenessparse-convolution
JI
JIA-Lab-research/ReviewKD

Distilling Knowledge via Knowledge Review, CVPR 2021

Python27937Updated 5 days ago
JI
JIA-Lab-research/SA-AutoAug

Scale-aware Automatic Augmentation for Object Detection (CVPR 2021)

Python19823Updated 5 days ago
JI
JIA-Lab-research/GridMask

No description provided.

Python28354Updated 5 days ago
JI
JIA-Lab-research/TraveLLaMA

Offical Repo for TraveLLaMA: A Multimodal Travel Assistant with Large-Scale Dataset and Structured Reasoning (AAAI 2026 Oral)

40Updated 5 days ago
JI
JIA-Lab-research/DiffComplete

Official Codebase of "DiffComplete: Diffusion-based Generative 3D Shape Completion"

Python1258Updated 5 days ago
3d-completion3d-shape-generationdiffusion-models
JI
JIA-Lab-research/3D-Box-Segment-Anything

We extend Segment Anything to 3D perception by combining it with VoxelNeXt.

Jupyter Notebook56325Updated 6 days ago
3dautonomous-drivingsegment-anything
JI
JIA-Lab-research/LLaMA-VID

LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models (ECCV 2024)

Python86052Updated 6 days ago
JI
JIA-Lab-research/SearchGym

No description provided.

Python90Updated 6 days ago
JI
JIA-Lab-research/Jenga

[NeurIPS 2025] Training-Free Efficient Video Generation via Dynamic Token Carving

Python27514Updated 1 week ago

Gists

Recent Activity