JIA Lab

All

93 repositories

VisionDirector
Public
CVPR 2026
Python
•0•1•0•0•Updated Mar 18, 2026Mar 18, 2026
MGM-Omni
Public
MGM-Omni: Scaling Omni LLMs to Personalized Long-Horizon Speech
text-to-speech multimodal multi-modality
text-to-speech multimodal multi-modality multi-modal-large-language-model audio-language-model
Python
•
Apache License 2.0
•16•265•4•0•Updated Mar 16, 2026Mar 16, 2026
VisionReasoner
Public
VisionReasoner: Unified Reasoning-Integrated Visual Perception via Reinforcement Learning
reinforcement-learning segmentation object-detection
reinforcement-learning segmentation object-detection multimodal counting-objects visual-perception multimodal-large-language-models reasoning-language-models
Python
•
Apache License 2.0
•15•326•0•0•Updated Feb 9, 2026Feb 9, 2026
Scaf-GRPO
Public
Scaf-GRPO: Scaffolded Group Relative Policy Optimization for Enhancing LLM Reasoning
Python
•1•15•0•0•Updated Feb 8, 2026Feb 8, 2026
UnityVideo
Public
[CVPR 2026]UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation
MIT License
•8•213•3•0•Updated Jan 29, 2026Jan 29, 2026
SearchGym
Public
Python
•0•9•0•0•Updated Jan 23, 2026Jan 23, 2026
TraveLLaMA
Public
Offical Repo for TraveLLaMA: A Multimodal Travel Assistant with Large-Scale Dataset and Structured Reasoning (AAAI 2026 Oral)
0•4•1•0•Updated Jan 21, 2026Jan 21, 2026
Seg-Zero
Public
Project Page For "Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement"
reinforcement-learning segmentation multimodal
reinforcement-learning segmentation multimodal multimodel-large-language-model reasoning-language-models
Python
•
Apache License 2.0
•29•613•4•0•Updated Jan 17, 2026Jan 17, 2026
DreamOmni3
Public
This project is the official implementation of 'DreamOmni3: Scribble-based Editing and Generation''
0•39•2•0•Updated Dec 30, 2025Dec 30, 2025
RePlan
Public
RePlan: Reasoning-Guided Region Planning for Complex Instruction-Based Image Editing
benchmark control image-editing
benchmark control image-editing planning editing inpainting grpo
Python
•
Apache License 2.0
•3•59•2•0•Updated Dec 26, 2025Dec 26, 2025
SmartSwitch
Public
SmartSwitch: Advancing LLM Reasoning by Overcoming Underthinking via Promoting Deeper Thought Exploration
Python
•0•7•0•0•Updated Oct 23, 2025Oct 23, 2025
DreamOmni2
Public
This project is the official implementation of 'DreamOmni2: Multimodal Instruction-based Editing and Generation''
image-editing image-generation unified-generation-editing-model
image-editing image-generation unified-generation-editing-model
Python
•
Apache License 2.0
•191•2.3k•23•1•Updated Oct 20, 2025Oct 20, 2025
VisionThink
Public
[NeurIPS 2025] Efficient Reasoning Vision Language Models
Python
•
Apache License 2.0
•30•452•14•0•Updated Sep 18, 2025Sep 18, 2025
LSDBench
Public
A benchmark that focuses on the sampling dilemma in long-video tasks. Through well-designed tasks, it evaluates the sampling efficiency of long-video VLMs. (ICC…
benchmark video-understanding sampling-strategies
benchmark video-understanding sampling-strategies reasoning-agent vision-language-model long-video-understanding multimodal-large-language-models video-understanding-dataset
Python
•
Apache License 2.0
•0•27•0•0•Updated Aug 7, 2025Aug 7, 2025
Jenga
Public
[NeurIPS 2025] Training-Free Efficient Video Generation via Dynamic Token Carving
Python
•14•276•9•0•Updated Aug 4, 2025Aug 4, 2025
VisionZip
Public
Official repository for VisionZip (CVPR 2025)
efficiency multi-modality vision-language-model
efficiency multi-modality vision-language-model vlms
Python
•
Apache License 2.0
•19•412•24•0•Updated Jul 21, 2025Jul 21, 2025
Parametric-Contrastive-Learning
Public
Parametric Contrastive Learning (ICCV2021) & GPaCo (TPAMI 2023)
pytorch supervised-learning imagenet
pytorch supervised-learning imagenet image-classification class-imbalance imbalanced-data imbalanced-learning tpami contrastive-learning supervised-contrastive-learning
Python
•
MIT License
•32•259•7•0•Updated Jul 21, 2025Jul 21, 2025
TGDPO
Public
[ICML 2025] TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization
alignment preference-learning large-language-models
alignment preference-learning large-language-models llm rlhf preference-alignment direct-preference-optimization preference-optimization
Python
•0•10•0•0•Updated Jul 15, 2025Jul 15, 2025
Video-P2P
Public
Video-P2P: Video Editing with Cross-attention Control
image-editing generative-model video-editing
image-editing generative-model video-editing text-driven-editing stable-diffusion
Python
•27•426•5•0•Updated Jun 30, 2025Jun 30, 2025
RL-GPT
Public
Python
•2•10•1•0•Updated Jun 30, 2025Jun 30, 2025
MagicMirror
Public
[ICCV 2025] MagicMirror: ID-Preserved Video Generation in Video Diffusion Transformers
4•128•7•0•Updated Jun 26, 2025Jun 26, 2025
Logits-Based-Finetuning
Public
Official Code of Logits-Based-Finetuning
Python
•9•91•0•0•Updated Jun 14, 2025Jun 14, 2025
LLMGA
Public
This project is the official implementation of 'LLMGA: Multimodal Large Language Model based Generation Assistant', ECCV2024 Oral
image-editing image-generation multi-modal
image-editing image-generation multi-modal aigc llm large-language-model mllm image-design-assistant
Python
•
Apache License 2.0
•25•398•3•0•Updated Jun 2, 2025Jun 2, 2025
ARPO
Public
Official Implementation of ARPO: End-to-End Policy Optimization for GUI Agents with Experience Replay
Python
•
Apache License 2.0
•10•153•9•0•Updated May 29, 2025May 29, 2025
MoTCoder
Public
This is the official code repository of MoTCoder: Elevating Large Language Models with Modular of Thought for Challenging Programming Tasks.
natural-language-processing programming code
natural-language-processing programming code apps code-generation large-language-models
Python
•3•85•7•0•Updated Mar 30, 2025Mar 30, 2025
Open-Code-Zero
Public
0•1•0•0•Updated Mar 10, 2025Mar 10, 2025
LISA
Public
Project Page for "LISA: Reasoning Segmentation via Large Language Model"
segmentation multi-modal llm
segmentation multi-modal llm large-language-model
Python
•
Apache License 2.0
•200•2.6k•114•0•Updated Feb 16, 2025Feb 16, 2025
Step-DPO
Public
Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"
math reasoning dpo
math reasoning dpo llm
Python
•16•392•18•0•Updated Jan 19, 2025Jan 19, 2025
Lyra
Public
[ICCV 2025] Official Implementation for "Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition"
efficiency vision-language-model speech-language-model
efficiency vision-language-model speech-language-model omni-language-model multimodal-large-language-model
Python
•
Apache License 2.0
•29•305•4•0•Updated Jan 9, 2025Jan 9, 2025
LBGAT
Public
Learnable Boundary Guided Adversarial Training (ICCV2021)
image-recognition robustness adversarial-attacks
image-recognition robustness adversarial-attacks adversarial-training adversarial-defense iccv2021
Python
•
MIT License
•2•38•4•0•Updated Dec 9, 2024Dec 9, 2024