MLV Lab (Machine Learning and Vision Lab at KAIST)

All

75 repositories

PRESTO
Public
[NeurIPS 25] Official Implementation (Pytorch) of "PRESTO: Preimage-Informed Instruction Optimization for Prompting Black-Box LLMs"
Python
•
MIT License
•0•1•0•0•Updated Feb 15, 2026Feb 15, 2026
TransMiter
Public
[AAAI2026 (Oral)] Official Implementation of "Transferable Model-agnostic Vision-Language Model Adaptation for Efficient Weak-to-Strong Generalization"
Python
•1•0•0•0•Updated Feb 7, 2026Feb 7, 2026
Blockwise-Flow-Matching
Public
[NeurIPS25] Official Implementation (Pytorch) of "Blockwise Flow Matching: Improving Flow Matching Models For Efficient High-Quality Generation"
efficiency diffusion
Python
•0•13•1•0•Updated Jan 15, 2026Jan 15, 2026
Prompt_Tuning_tutorial
Public
Jupyter Notebook
•0•0•0•0•Updated Nov 28, 2025Nov 28, 2025
TabFlash
Public
[AAAI 2026] Official Implementation (PyTorch) of "TabFlash: Efficient Table Understanding with Progressive Question Conditioning and Token Focusing"
Python
•0•10•0•0•Updated Nov 27, 2025Nov 27, 2025
VDRP
Public
[NeurIPS 2025] Official code for Visual Diversity and Region-aware Prompt Learning for Zero-shot HOI detection
Jupyter Notebook
•
MIT License
•0•8•0•0•Updated Nov 18, 2025Nov 18, 2025
DeepVideoR1
Public
[NeurIPS25] Official Implementation (Pytorch) of "DeepVideo-R1"
multimodal-deep-learning video-language multimodal-large-language-models video-large-language-models grpo neurips-2025
0•31•1•0•Updated Nov 15, 2025Nov 15, 2025
CAF
Public
Official Implementation (Pytorch) of "Constant Acceleration Flow", NeurIPS 2024
Python
•0•35•0•0•Updated Oct 31, 2025Oct 31, 2025
vid-TLDR
Public
Official implementation of CVPR 2024 paper "vid-TLDR: Training Free Token merging for Light-weight Video Transformer".
computer-vision video-transformer token-pruning efficient-vision-transformers cvpr2024 token-merging
Python
•
MIT License
•3•54•0•0•Updated Oct 21, 2025Oct 21, 2025
CaReDPO
Public
Captioning for Text-Video Retrieval via Dual-Group Direct Preference Optimization (EMNLP 2025 Findings)
MIT License
•0•6•0•0•Updated Sep 19, 2025Sep 19, 2025
BLiM
Public
Bidirectional Likelihood Estimation with Multi-Modal Large Language Models for Text-Video Retrieval (ICCV 2025 Highlight)
Python
•
MIT License
•0•20•1•0•Updated Aug 1, 2025Aug 1, 2025
Representation-Shift
Public
Official Implementation (Pytorch) of the "Representation Shift: Unifying Token Compression with FlashAttention", ICCV 2025
token-pruning efficient-vision-transformers iccv2025
MIT License
•2•30•2•0•Updated Jul 30, 2025Jul 30, 2025
MCTF
Public
Official implementation of CVPR 2024 paper "Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers".
computer-vision efficient-vision-transformers cvpr2024 token-fusion
Python
•
MIT License
•4•40•0•0•Updated Jul 30, 2025Jul 30, 2025
COSE474_2024
Public
Jupyter Notebook
•1•3•0•0•Updated Apr 30, 2025Apr 30, 2025
NFBO
Public
Python
•2•16•0•0•Updated Apr 22, 2025Apr 22, 2025
CoBO
Public
Official PyTorch Implementation for Advancing Bayesian Optimization via Learning Correlated Latent Space (CoBO)
bayesian-optimization neurips-2023 neurips2023
Python
•
MIT License
•3•18•1•0•Updated Apr 22, 2025Apr 22, 2025
EfficientViM
Public
[CVPR 25] Official Implementation (Pytorch) of "EfficientViM: Efficient Vision Mamba with Hidden State Mixer-based State Space Duality"
computer-vision efficient-deep-learning vision-mamba cvpr2025
Python
•
MIT License
•5•118•1•0•Updated Apr 22, 2025Apr 22, 2025
ST-VLM
Public
0•13•1•0•Updated Mar 28, 2025Mar 28, 2025
SPoTr
Public
Official pytorch implementation of "Self-positioning Point-based Transformer for Point Cloud Understanding" (CVPR 2023).
cvpr2023
Python
•
MIT License
•7•114•0•0•Updated Mar 27, 2025Mar 27, 2025
Flipped-VQA
Public
Large Language Models are Temporal and Causal Reasoners for Video Question Answering (EMNLP 2023)
multi-modal visual-question-answering video-question-answering large-language-models emnlp2023
Python
•
MIT License
•12•77•4•0•Updated Mar 26, 2025Mar 26, 2025
DFC609-2022S
Public
Basic Artificial Intelligence Theory
Jupyter Notebook
•53•10•0•0•Updated Mar 11, 2025Mar 11, 2025
ProMetaR
Public
Official implementation of CVPR 2024 paper "Prompt Learning via Meta-Regularization".
prompt-learning parameter-efficient-tuning cvpr2024
Python
•
MIT License
•2•32•0•0•Updated Mar 10, 2025Mar 10, 2025
DialogGSR
Public
Official Implementation (Pytorch) of the "Generative Subgraph Retrieval for Knowledge Graph-Grounded Dialog Generation", EMNLP 2024 (main)
Python
•0•12•0•0•Updated Mar 10, 2025Mar 10, 2025
LLaMo
Public
Official Implementation (Pytorch) of the "LLaMo: Large Language Model-based Molecular Graph Assistant", NeurIPS 2024
graph-language multimodal-large-language-models neurips-2024 neurips2024 large-molecule-language-models
Python
•4•33•0•0•Updated Feb 12, 2025Feb 12, 2025
VidChain
Public
Official Implementation (Pytorch) of the "VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning", AAAI 2025
dense-video-captioning long-video-understanding multimodal-large-language-models direct-preference-optimization aaai2025
Python
•1•23•1•0•Updated Jan 26, 2025Jan 26, 2025
SugaFormer
Public
Official Implementation (Pytorch) of "Super-class guided Transformer for Zero-Shot Attribute Classification", AAAI 2025
zero-shot-learning aaai2025
Python
•1•15•1•0•Updated Jan 15, 2025Jan 15, 2025
SCDM
Public
Official PyTorch implementation of "Stochastic Conditional Diffusion Models for Robust Semantic Image Synthesis" (ICML 2024).
generative-model diffusion-models conditional-generation icml-2024
Python
•
MIT License
•0•20•0•0•Updated Nov 20, 2024Nov 20, 2024
InvBO
Public
[NeurIPS 24] Official Implementation (Pytorch) of "Inversion-based Latent Bayesian Optimization"
bayesian-optimization neurips-2024 latent-bayesian-optimizaiton
Python
•
MIT License
•2•10•0•0•Updated Nov 15, 2024Nov 15, 2024
RALF
Public
Official implementation of CVPR 2024 paper "Retrieval-Augmented Open-Vocabulary Object Detection".
computer-vision object-detection cvpr2024 open-vocabulary-object-detection
MIT License
•6•44•2•0•Updated Sep 12, 2024Sep 12, 2024
DAVI-project
Public
JavaScript
•0•1•0•0•Updated Aug 19, 2024Aug 19, 2024