JIA-Lab-research

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

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

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

This project is the official implementation of 'DreamOmni2: Multimodal Instruction-based Editing and Generation (CVPR2026 Highlight)''

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

This is the official implementation for the paper "SNR-aware low-light image enhancement" in CVPR2022

Long Range 3D Perception - VoxelNeXt (CVPR 2023)

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

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

Underexposed Photo Enhancement Using Deep Illumination Estimation

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

[NeurIPS 2025] Efficient Reasoning Vision Language Models

Official repository for VisionZip (CVPR 2025)

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

Stratified Transformer for 3D Point Cloud Segmentation (CVPR 2022)

Video-P2P: Video Editing with Cross-attention Control

Fully Convolutional Networks for Panoptic Segmentation (CVPR2021 Oral)

Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"

This project is the official implementation of 'LLMGA: Multimodal Large Language Model based Generation Assistant', ECCV2024 Oral

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

3DSSD: Point-based 3D Single Stage Object Detector (CVPR 2020)

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

PFENet: Prior Guided Feature Enrichment Network for Few-shot Segmentation (TPAMI).

[ICLR 2026] VisionReasoner: Unified Reasoning-Integrated Visual Perception via Reinforcement Learning

[CVPR 2020] DSGN: Deep Stereo Geometry Network for 3D Object Detection

[CVPR 2026]UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation

[ICCV 2025] Official Implementation for "Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition"

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

Distilling Knowledge via Knowledge Review, CVPR 2021

Parametric Contrastive Learning (ICCV2021) & GPaCo (TPAMI 2023)

Unifying Voxel-based Representation with Transformer for 3D Object Detection (NeurIPS 2022)

Seeing Dynamic Scene in the Dark: High-Quality Video Dataset with Mechatronic Alignment (ICCV2021)

Include MuCAN, LAPAR, etc.

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

Facelet-Bank for Fast Portrait Manipulation (pytorch)

MGM-Omni: Scaling Omni LLMs to Personalized Long-Horizon Speech

Dynamic Divide-and-Conquer Adversarial Training for Robust Semantic Segmentation （ICCV2021）

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

A fast and memory-efficient libarary for sparse transformer with varying token numbers (e.g., 3D point cloud).

MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolution (CVPR2021)

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

The official code for our ECCV22 oral paper: tracking objects as pixel-wise distributions.

[CVPR 2024] Prompt Highlighter: Interactive Control for Multi-Modal LLMs

Semi-supervised Semantic Segmentation with Directional Context-aware Consistency (CVPR 2021)

The official code for "Efficient Neural Radiance Fields" in CVPR2022.

[NeurIPS 2023 Spotlight] Real-World Image Variation by Aligning Diffusion Inversion Chain

Improving Calibration for Long-Tailed Recognition (CVPR2021)

Official PyTorch implementation of MOOD series: (1) MOODv1: Rethinking Out-of-distributionDetection: Masked Image Modeling Is All You Need. (2) MOODv2: Masked Image Modeling for...

Wide-Context Semantic Image Extrapolation, CVPR2019

Video Frame Interpolation with Transformer (CVPR2022)

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

Multi-Scale Aligned Distillation for Low-Resolution Detection (CVPR2021)

[ICCV 2025] MagicMirror: ID-Preserved Video Generation in Video Diffusion Transformers

[CVPR 2023] Ref-NPR: Reference-Based Non-PhotoRealistic Radiance Fields

DeepVision3D is an open source toolbox for point-cloud understanding.

Voxel Field Fusion for 3D Object Detection (CVPR2022)

This project is the official implementation of "UnityShots: Memory-Driven Multi-Shot Audio-Video Generation with Boundary-Aware Gating"

Self-Supervised 3D Mesh Reconstruction from Single Images (CVPR2021)

Official Code of Logits-Based-Finetuning

Imbalanced learning tool for imbalanced recognition and segmentation

This is the official code repository of MoTCoder: Elevating Large Language Models with Modular of Thought for Challenging Programming Tasks.

The implementation of 'Image synthesis via semantic composition', ICCV2021.

Official Implementation for "Mask-Attention-Free Transformer for 3D Instance Segmentation"

This is the code for CVPR 2021 oral paper: Jigsaw Clustering for Unsupervised Visual Representation Learning

(ECCV2026) RePlan: Reasoning-Guided Region Planning for Complex Instruction-Based Image Editing

Attentive Normalization for Conditional Image Generation

The official implementation of Generalized Few-shot Semantic Segmentation (CVPR 2022)

This is the official repo of "QuickLLaMA: Query-aware Inference Acceleration for Large Language Models"

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

This is the repo for our paper "Mr-Ben: A Comprehensive Meta-Reasoning Benchmark for Large Language Models"