Pangea: A Fully Open Multilingual Multimodal LLM for 39 Languages Paper • 2410.16153 • Published Oct 21 • 42
The Curse of Multi-Modalities: Evaluating Hallucinations of Large Multimodal Models across Language, Visual, and Audio Paper • 2410.12787 • Published Oct 16 • 30
LEOPARD : A Vision Language Model For Text-Rich Multi-Image Tasks Paper • 2410.01744 • Published Oct 2 • 25
UCFE: A User-Centric Financial Expertise Benchmark for Large Language Models Paper • 2410.14059 • Published Oct 17 • 53
Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models Paper • 2409.17146 • Published Sep 25 • 103
Both Text and Images Leaked! A Systematic Analysis of Multimodal LLM Data Contamination Paper • 2411.03823 • Published 15 days ago • 43
SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration Paper • 2410.02367 • Published Oct 3 • 47
VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks Paper • 2410.05160 • Published Oct 7 • 4
LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models Paper • 2410.09732 • Published Oct 13 • 54
PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction Paper • 2410.17247 • Published about 1 month ago • 43
SageAttention2 Technical Report: Accurate 4 Bit Attention for Plug-and-play Inference Acceleration Paper • 2411.10958 • Published 5 days ago • 33
Awaker2.5-VL: Stably Scaling MLLMs with Parameter-Efficient Mixture of Experts Paper • 2411.10669 • Published 6 days ago • 9
LLM2CLIP: Powerful Language Model Unlock Richer Visual Representation Paper • 2411.04997 • Published 14 days ago • 34
Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models Paper • 2411.04996 • Published 14 days ago • 48