74 citations · 209 across the 38 of their papers we have counts for
13 papers · 2 filters
PaliGemma 2: A Family of Versatile VLMs for Transfer
Andreas Steiner, André Susano Pinto, Michael Tschannen +15
PaliGemma 2 is an upgrade of the PaliGemma open Vision-Language Model (VLM) based on the Gemma 2 family of language models. We combine the SigLIP-So400m vision encoder that was als…
Bridging the Visual Gap: Fine-Tuning Multimodal Models with Knowledge-Adapted Captions
Moran Yanuka, Assaf Ben Kish, Yonatan Bitton +2
Recent research increasingly focuses on training vision-language models (VLMs) with long, detailed image captions. However, small-scale VLMs often struggle to balance the richness…
NL-Eye: Abductive NLI for Images
Mor Ventura, Michael Toker, Nitay Calderon +3
Will a Visual Language Model (VLM)-based bot warn us about slipping if it detects a wet floor? Recent VLMs have demonstrated impressive capabilities, yet their ability to infer out…
KITTEN: A Knowledge-Intensive Evaluation of Image Generation on Visual Entities
Hsin-Ping Huang, Xinyi Wang, Yonatan Bitton +8
Recent advances in text-to-image generation have improved the quality of synthesized images, but evaluations mainly focus on aesthetics or alignment with text prompts. Thus, it rem…
Video-STaR: Self-Training Enables Video Instruction Tuning with Any Supervision
Orr Zohar, Xiaohan Wang, Yonatan Bitton +2
The performance of Large Vision Language Models (LVLMs) is dependent on the size and quality of their training datasets. Existing video instruction tuning datasets lack diversity a…
Visual Riddles: a Commonsense and World Knowledge Challenge for Large Vision and Language Models
Nitzan Bitton-Guetta, Aviv Slobodkin, Aviya Maimon +6
Imagine observing someone scratching their arm; to understand why, additional context would be necessary. However, spotting a mosquito nearby would immediately offer a likely expla…
Contrastive Sequential-Diffusion Learning: Non-linear and Multi-Scene Instructional Video Synthesis
Vasco Ramos, Yonatan Bitton, Michal Yarom +2
Generated video scenes for action-centric sequence descriptions, such as recipe instructions and do-it-yourself projects, often include non-linear patterns, where the next video ma…
VideoPhy: Evaluating Physical Commonsense for Video Generation
Hritik Bansal, Zongyu Lin, Tianyi Xie +7
Recent advances in internet-scale video data pretraining have led to the development of text-to-video generative models that can create high-quality videos across a broad range of…
Generating Coherent Sequences of Visual Illustrations for Real-World Manual Tasks
João Bordalo, Vasco Ramos, Rodrigo Valério +5
Multistep instructions, such as recipes and how-to guides, greatly benefit from visual aids, such as a series of images that accompany the instruction steps. While Large Language M…
TALC: Time-Aligned Captions for Multi-Scene Text-to-Video Generation
Hritik Bansal, Yonatan Bitton, Michal Yarom +3
Most of these text-to-video (T2V) generative models often produce single-scene video clips that depict an entity performing a particular action (e.g., 'a red panda climbing a tree'…
ImageInWords: Unlocking Hyper-Detailed Image Descriptions
Roopal Garg, Andrea Burns, Burcu Karagol Ayan +7
Despite the longstanding adage "an image is worth a thousand words," generating accurate hyper-detailed image descriptions remains unsolved. Trained on short web-scraped image text…
DOCCI: Descriptions of Connected and Contrasting Images
Yasumasa Onoe, Sunayana Rane, Zachary Berger +9
Vision-language datasets are vital for both text-to-image (T2I) and image-to-text (I2T) research. However, current datasets lack descriptions with fine-grained detail that would al…
GenEARL: A Training-Free Generative Framework for Multimodal Event Argument Role Labeling
Hritik Bansal, Po-Nien Kung, P. Jeffrey Brantingham +2
Multimodal event argument role labeling (EARL), a task that assigns a role for each event participant (object) in an image is a complex challenge. It requires reasoning over the en…