MLV Lab

[MLV Lab @MLVLab]

We are presenting our work,
“MoE-GRPO: Optimizing Mixture-of-Experts via Reinforcement Learning in Vision-Language Models” at CVPR 2026 in Denver!

Time: Jun 6, 2026 • 11:45 AM – 1:45 PM
Location: Poster Session 3, Hall F

Paper: https://t.co/xDIXIk1qzq

[MLV Lab @MLVLab]

We are presenting our work,
“RegFormer: Transferable Relational Grounding for Efficient Weakly-Supervised Human-Object Interaction Detection” at CVPR 2026 in Denver!

Time: Jun 5, 2026 • 4:00 PM – 6:00 PM
Location: Poster Session 2, Hall A-F

Paper: https://t.co/I0a3VJt13F

[MLV Lab @MLVLab]

We are presenting our work,
“DocPrune: Efficient Document Question Answering via Background, Question, and Comprehension-aware Token Pruning” at CVPR 2026 in Denver!

Time: Jun 5, 2026 • 10:45 AM – 12:45 PM
Location: Poster Session 1, Hall A-F

Paper: https://t.co/DsD6X6tS36

[MLV Lab @MLVLab]

We are presenting our work,
“SPRINT: Sparse-Dense Residual Fusion for Efficient Diffusion Transformers” at ICLR 2026 in Brazil!

Time: Sat, Apr 25, 2026 • 3:15 PM – 5:45 PM
Location: Pavilion 4 P4-3017

Paper: https://t.co/rvKkwodSal

#ICLR2026 #Efficient #DiT #DiffusionModels

[MLV Lab @MLVLab]

We are presenting our work,

“Error as Signal: Stiffness-Aware Diffusion Sampling via Embedded Runge-Kutta Guidance” in Brazil, ICLR’26!

Time: 4/23(Thu), 10:30 AM – 1:00 PM
Location: Pavilion 4 P4-#3006

Paper: https://t.co/LdWL3wODG6
Video: https://t.co/TQHJtSHRyP

#ICLR2026

[MLV Lab @MLVLab]

Huge congrats to all co-authors! Three papers from MLV got accepted to CVPR 2026! Please visit our homepage to take a closer look. https://t.co/bsXtChQk2I

[MLV Lab @MLVLab]

🚀 Excited to share that we’ll be presenting our work, “DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO” at NeurIPS 2025 in San Diego!

🕙 When: 12/5 (Fri), 4:30 PM – 7:30 PM
📍 Where: Exhibit Hall C,D,E
🪧 Poster ID: 4418

See you soon!

[MLV Lab @MLVLab]

🚀 Excited to share that we’ll be presenting our work, “Visual Diversity and Region-aware Prompt Learning for Zero-shot HOI Detection” at NeurIPS 2025 in San Diego!

🕙 When: 12/5 (Fri), 11:00 AM – 2:00 PM
📍 Where: Exhibit Hall C,D,E
🪧 Poster ID: 4911

See you soon!

[MLV Lab @MLVLab]

😆 We presented our work "PRESTO: Preimage-Informed Instruction Optimization for Prompting Black-Box LLMs" at NeurIPS 2025 in San Diego!

🗓️ Date: 12/3 (Wed), 4:30 PM – 7:30 PM

Paper: https://t.co/lQhK9zbreH

We appreciate everyone who visited and discussed our work!
#NeurIPS25

[MLV Lab @MLVLab]

😆We presented our work "Blockwise Flow Matching: Improving Flow Matching Models For Efficient High-Quality Generation" at NeurIPS 2025 in San Diego

🗓️ Date: 12/3 (Wed), 11:00 AM – 2:00 PM

Paper: https://t.co/StZ3tqTzKT
We appreciate everyone who visited and discussed our work!

[MLV Lab @MLVLab]

😆 We are presenting our work,
“Captioning for Text-Video Retrieval via Dual-Group Direct Preference Optimization” in Suzhou, EMNLP’25!
@so0zip

Paper: https://t.co/WDEob1sjHl
Homepage: https://t.co/3SSQ3HIMrn

See you soon!!
#EMNLP2025 #Retrieval #VideoLLM #DPO

[MLV Lab @MLVLab]

😆 We are presenting our work,
“Representation Shift: Unifying Token Compression with FlashAttention” in Hawaii, ICCV’25!
Time: 10/23(Thu), 14:15
Location: Exhibit Hall I
PosterID: 1883
Paper: https://t.co/avx1I5UnQT
#ICCV2025 #Efficiency #Representation

[MLV Lab @MLVLab]

😆 We are presenting our work,
“Bidirectional Likelihood Estimation with Multi-Modal Large Language Models for Text-Video Retrieval” in Hawaii, ICCV’25!
Time:10/23(Thu), 10:45
Location: Exhibit Hall I
PosterID: 232
Paper: https://t.co/83Gc9OTJTB
#ICCV2025 #Retrieval #MLLM

[MLV Lab @MLVLab]

🎉 Four papers from MLV Lab have been accepted to NeurIPS 2025! 🎉
Huge congratulations to all the authors and collaborators on these amazing achievements
@dogyunPark @parkjiny777 @Jwon_chu
#NeurIPS2025 #MLVLab
See you at San Diego & Mexico City! 🇺🇸🇲🇽

[MLV Lab @MLVLab]

Congrats again! 🎉
One of our ICCV 2025 papers was selected as a Highlight!
Big shoutout to the team

“Bidirectional Likelihood Estimation with Multi-Modal LLMs for Text-Video Retrieval”
@godohwan
@so0zip
@metaai

#ICCV2025 #HighlightPaper #MLV #Multimodal #TextVideoRetrieval

[MLV Lab @MLVLab]

Huge congrats to all co-authors!
Two papers from MLV got accepted to ICCV 25!
Please visit our homepage to take a closer look. https://t.co/QJwDIiCV0O

@godohwan @so0zip @JoonMyungChoi @sanghyeok__Lee
#ICCV2025

[MLV Lab @MLVLab]

We are proud to share that Seunghun Lee successfully delivered an oral presentation of "Latent Bayesian Optimization via Autoregressive Normalizing Flows" at ICLR 2025!
Congrats on this great achievement!
Paper: https://t.co/rk1L0h64b5
Github: https://t.co/wMZlkWxaEf
#ICLR2025

[MLV Lab @MLVLab]

Huge congrats!
Our paper got accepted to CVPR’25.

EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space Duality
Sanghyeok Lee, Joonmyung Choi, Hyunwoo J. Kim*

Paper: https://t.co/cZ62LbnZDK
Github: https://t.co/b29TZ1Z7zp

#CVPR25 #Mamba

[MLV Lab @MLVLab]

We are presenting our work, “VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning” in Philadelphia, AAAI’24!

Time:2/27 (Thu.) 12:30 - 14:30
Location: Hall E, West Building

PosterID: 8542
Paper: https://t.co/JNkYJZYPGq
#AAAI2025

[MLV Lab @MLVLab]

We are presenting our work, “Super-class guided Transformer for Zero-Shot Attribute Classification” in Philadelphia, AAAI’24!

Time: 3/1 (Sat.) 12:30 - 14:30
Location: Hall E of the West Building
PosterID: 7611

Paper: https://t.co/JNkYJZYPGq
#AAAI2025