1.3k citations · 3.2k across the 23 of their papers we have counts for
26 papers
FoodSense: A Multisensory Food Dataset and Benchmark for Predicting Taste, Smell, Texture, and Sound from Images
Sabab Ishraq, Aarushi Aarushi, Juncai Jiang +1
Humans routinely infer taste, smell, texture, and even sound from food images a phenomenon well studied in cognitive science. However, prior vision language research on food has fo…
The Bias is in the Details: An Assessment of Cognitive Bias in LLMs
R. Alexander Knipper, Charles S. Knipper, Kaiqi Zhang +3
As Large Language Models (LLMs) are increasingly embedded in real-world decision-making processes, it becomes crucial to examine the extent to which they exhibit cognitive biases.…
Assay2Mol: large language model-based drug design using BioAssay context
Yifan Deng, Spencer S. Ericksen, Anthony Gitter
Scientific databases aggregate vast amounts of quantitative data alongside descriptive text. In biochemistry, molecule screening assays evaluate candidate molecules' functional res…
Gemma 3 Technical Report
Gemma Team, Aishwarya Kamath, Johan Ferret +209
We introduce Gemma 3, a multimodal addition to the Gemma family of lightweight open models, ranging in scale from 1 to 27 billion parameters. This version introduces vision underst…
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…
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
Gemini Team, Petko Georgiev, Ving Ian Lei +1132
In this report, we introduce the Gemini 1.5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over…
A Simple Recipe for Contrastively Pre-training Video-First Encoders Beyond 16 Frames
Pinelopi Papalampidi, Skanda Koppula, Shreya Pathak +7
Understanding long, real-world videos requires modeling of long-range visual dependencies. To this end, we explore video-first architectures, building on the common paradigm of tra…
Making the Most of What You Have: Adapting Pre-trained Visual Language Models in the Low-data Regime
Chuhan Zhang, Antoine Miech, Jiajun Shen +2
Large-scale visual language models are widely used as pre-trained models and then adapted for various downstream tasks. While humans are known to efficiently learn new tasks from a…
Perception Test: A Diagnostic Benchmark for Multimodal Video Models
Viorica Pătrăucean, Lucas Smaira, Ankush Gupta +21
We propose a novel multimodal video benchmark - the Perception Test - to evaluate the perception and reasoning skills of pre-trained multimodal models (e.g. Flamingo, SeViLA, or GP…
Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning
Antoine Yang, Arsha Nagrani, Paul Hongsuck Seo +5
In this work, we introduce Vid2Seq, a multi-modal single-stage dense event captioning model pretrained on narrated videos which are readily-available at scale. The Vid2Seq architec…
Zorro: the masked multimodal transformer
Adrià Recasens, Jason Lin, Joāo Carreira +8
Attention-based models are appealing for multimodal processing because inputs from multiple modalities can be concatenated and fed to a single backbone network - thus requiring ver…
Multi-Task Learning of Object State Changes from Uncurated Videos
Tomáš Souček, Jean-Baptiste Alayrac, Antoine Miech +2
We aim to learn to temporally localize object state changes and the corresponding state-modifying actions by observing people interacting with objects in long uncurated web videos.…
Zero-Shot Video Question Answering via Frozen Bidirectional Language Models
Antoine Yang, Antoine Miech, Josef Sivic +2
Video question answering (VideoQA) is a complex task that requires diverse multi-modal data for training. Manual annotation of question and answers for videos, however, is tedious…
Learning to Answer Visual Questions from Web Videos
Antoine Yang, Antoine Miech, Josef Sivic +2
Recent methods for visual question answering rely on large-scale annotated datasets. Manual annotation of questions and answers for videos, however, is tedious, expensive and preve…
Flamingo: a Visual Language Model for Few-Shot Learning
Jean-Baptiste Alayrac, Jeff Donahue, Pauline Luc +24
Building models that can be rapidly adapted to novel tasks using only a handful of annotated examples is an open challenge for multimodal machine learning research. We introduce Fl…
Look for the Change: Learning Object States and State-Modifying Actions from Untrimmed Web Videos
Tomáš Souček, Jean-Baptiste Alayrac, Antoine Miech +2
Human actions often induce changes of object states such as "cutting an apple", "cleaning shoes" or "pouring coffee". In this paper, we seek to temporally localize object states (e…
TubeDETR: Spatio-Temporal Video Grounding with Transformers
Antoine Yang, Antoine Miech, Josef Sivic +2
We consider the problem of localizing a spatio-temporal tube in a video corresponding to a given text query. This is a challenging task that requires the joint and efficient modeli…
Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers
Antoine Miech, Jean-Baptiste Alayrac, Ivan Laptev +2
Our objective is language-based search of large-scale image and video datasets. For this task, the approach that consists of independently mapping text and vision to a joint embedd…
Just Ask: Learning to Answer Questions from Millions of Narrated Videos
Antoine Yang, Antoine Miech, Josef Sivic +2
Recent methods for visual question answering rely on large-scale annotated datasets. Manual annotation of questions and answers for videos, however, is tedious, expensive and preve…
RareAct: A video dataset of unusual interactions
Antoine Miech, Jean-Baptiste Alayrac, Ivan Laptev +2
This paper introduces a manually annotated video dataset of unusual actions, namely RareAct, including actions such as "blend phone", "cut keyboard" and "microwave shoes". RareAct…
The End-of-End-to-End: A Video Understanding Pentathlon Challenge (2020)
Samuel Albanie, Yang Liu, Arsha Nagrani +18
We present a new video understanding pentathlon challenge, an open competition held in conjunction with the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2020.…
End-to-End Learning of Visual Representations from Uncurated Instructional Videos
Antoine Miech, Jean-Baptiste Alayrac, Lucas Smaira +3
Annotating videos is cumbersome, expensive and not scalable. Yet, many strong video models still rely on manually annotated data. With the recent introduction of the HowTo100M data…
HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips
Antoine Miech, Dimitri Zhukov, Jean-Baptiste Alayrac +3
Learning text-video embeddings usually requires a dataset of video clips with manually provided captions. However, such datasets are expensive and time consuming to create and ther…
Learning a Text-Video Embedding from Incomplete and Heterogeneous Data
Antoine Miech, Ivan Laptev, Josef Sivic
Joint understanding of video and language is an active research area with many applications. Prior work in this domain typically relies on learning text-video embeddings. One diffi…