Publications

VCR: Visual Caption Restoration
Tianyu Zhang
Suyuchen Wang
Li Li
Ge Zhang
Perouz Taslakian
Sai Rajeswar
Jie Fu
Bang Liu
Yoshua Bengio
We introduce Visual Caption Restoration (VCR), a novel vision-language task that challenges models to accurately restore partially obscured … (voir plus)texts using pixel-level hints within images. This task stems from the observation that text embedded in images is intrinsically different from common visual elements and natural language due to the need to align the modalities of vision, text, and text embedded in images. While numerous works have integrated text embedded in images into visual question-answering tasks, approaches to these tasks generally rely on optical character recognition or masked language modeling, thus reducing the task to mainly text-based processing. However, text-based processing becomes ineffective in VCR as accurate text restoration depends on the combined information from provided images, context, and subtle cues from the tiny exposed areas of masked texts. We develop a pipeline to generate synthetic images for the VCR task using image-caption pairs, with adjustable caption visibility to control the task difficulty. With this pipeline, we construct a dataset for VCR called VCR-Wiki using images with captions from Wikipedia, comprising 2.11M English and 346K Chinese entities in both easy and hard split variants. Our results reveal that current vision language models significantly lag behind human performance in the VCR task, and merely fine-tuning the models on our dataset does not lead to notable improvements. We release VCR-Wiki and the data construction code to facilitate future research.
2024-10-09
NeurIPS.cc/2024/Workshop/Sys2-Reasoning (poster)
doi.org
openreview.net
VinePPO: Accurate Credit Assignment in RL for LLM Mathematical Reasoning
Amirhossein Kazemnejad
Milad Aghajohari
Eva Portelance
Alessandro Sordoni
Siva Reddy
Aaron Courville
Nicolas Le Roux
Large language models (LLMs) are increasingly required to solve complex reasoning tasks, like mathematical problems, that involve multiple r… (voir plus)easoning steps before feedback is received. Effectively identifying and prioritizing key steps by accurately assigning credit to these intermediate steps is essential for enhancing model performance. Proximal Policy Optimization (PPO), a state-of-the-art reinforcement learning algorithm for finetuning LLMs, addresses the credit assignment problem by employing value networks to predict the expected cumulative rewards of intermediate states. In this work, we identify significant limitations with this value estimation method. To address this, we propose \methodname that leverages the flexibility of language environments to compute unbiased Monte Carlo-based estimates of the intermediate values. VinePPO consistently outperforms standard PPO, doing so more efficiently and with lower divergence from the reference model. Our findings underscore the critical importance of accurate credit assignment in LLM post-training and present a simple, yet effective solution.
2024-10-09
NeurIPS.cc/2024/Workshop/MATH-AI (accepté)
openreview.net
openreview.net
VinePPO: Accurate Credit Assignment in RL for LLM Mathematical Reasoning
Amirhossein Kazemnejad
Milad Aghajohari
Eva Portelance
Alessandro Sordoni
Siva Reddy
Aaron Courville
Nicolas Le Roux
Large language models (LLMs) are increasingly required to solve complex reasoning tasks, like mathematical problems, that involve multiple r… (voir plus)easoning steps before feedback is received. Effectively identifying and prioritizing key steps by accurately assigning credit to these intermediate steps is essential for enhancing model performance. Proximal Policy Optimization (PPO), a state-of-the-art reinforcement learning algorithm for finetuning LLMs, addresses the credit assignment problem by employing value networks to predict the expected cumulative rewards of intermediate states. In this work, we identify significant limitations with this value estimation method. To address this, we propose \methodname that leverages the flexibility of language environments to compute unbiased Monte Carlo-based estimates of the intermediate values. VinePPO consistently outperforms standard PPO, doing so more efficiently and with lower divergence from the reference model. Our findings underscore the critical importance of accurate credit assignment in LLM post-training and present a simple, yet effective solution.
2024-10-09
NeurIPS.cc/2024/Workshop/MATH-AI (accepté)
openreview.net
openreview.net
Visual Story-Writing: Writing by Manipulating Visual Representations of Stories
Damien Masson
Zixin Zhao
Fanny Chevalier
We define"visual story-writing"as using visual representations of story elements to support writing and revising narrative texts. To demonst… (voir plus)rate this approach, we developed a text editor that automatically visualizes a graph of entity interactions, movement between locations, and a timeline of story events. Interacting with these visualizations results in suggested text edits: for example, connecting two characters in the graph creates an interaction between them, moving an entity updates their described location, and rearranging events on the timeline reorganizes the narrative sequence. Through two user studies on narrative text editing and writing, we found that visuals supported participants in planning high-level revisions, tracking story elements, and exploring story variations in ways that encourage creativity. Broadly, our work lays the foundation for writing support, not just through words, but also visuals.
2024-10-09
ArXiv (prépublication)
doi.org
arxiv.org
Visual Story-Writing: Writing by Manipulating Visual Representations of Stories
Damien Masson
Zixin Zhao
Fanny Chevalier
We define"visual story-writing"as using visual representations of story elements to support writing and revising narrative texts. To demonst… (voir plus)rate this approach, we developed a text editor that automatically visualizes a graph of entity interactions, movement between locations, and a timeline of story events. Interacting with these visualizations results in suggested text edits: for example, connecting two characters in the graph creates an interaction between them, moving an entity updates their described location, and rearranging events on the timeline reorganizes the narrative sequence. Through two user studies on narrative text editing and writing, we found that visuals supported participants in planning high-level revisions, tracking story elements, and exploring story variations in ways that encourage creativity. Broadly, our work lays the foundation for writing support, not just through words, but also visuals.
2024-10-09
ArXiv (prépublication)
doi.org
arxiv.org
Visual Writing: Writing by Manipulating Visual Representations of Stories
Damien Masson
Zixin Zhao
Fanny Chevalier
We introduce"visual writing", an approach to writing stories by manipulating visuals instead of words. Visual writing relies on editable vis… (voir plus)ual representations of time, entities, events, and locations to offer representations more suited to specific editing tasks. We propose a taxonomy for these representations and implement a prototype software supporting the visual writing workflow. The system allows writers to edit the story by alternating between modifying the text and manipulating visual representations to edit entities, actions, locations, and order of events. We evaluate this workflow with eight creative writers and find visual writing can help find specific passages, keep track of story elements, specify edits, and explore story variations in a way that encourages creativity.
2024-10-09
ArXiv (prépublication)
doi.org
arxiv.org
Visual Writing: Writing by Manipulating Visual Representations of Stories
Damien Masson
Zixin Zhao
Fanny Chevalier
We introduce "visual writing", an approach to writing stories by manipulating visuals instead of words. Visual writing relies on editable vi… (voir plus)sual representations of time, entities, events, and locations to offer representations more suited to specific editing tasks. We propose a taxonomy for these representations and implement a prototype software supporting the visual writing workflow. The system allows writers to edit the story by alternating between modifying the text and manipulating visual representations to edit entities, actions, locations, and order of events. We evaluate this workflow with eight creative writers and find visual writing can help find specific passages, keep track of story elements, specify edits, and explore story variations in a way that encourages creativity.
2024-10-09
ArXiv (prépublication)
doi.org
arxiv.org
Differentiation Through Black-Box Quadratic Programming Solvers
Connor W. Magoon
Fengyu Yang
Noam Aigerman
Shahar Kovalsky
2024-10-08
ArXiv (prépublication)
doi.org
arxiv.org
Path-filtering in path-integral simulations of open quantum systems using GFlowNets
Jeremy Lackman-Mincoff
Moksh J. Jain
Nikolay Malkin
Yoshua Bengio
Lena Simine
2024-10-08
Journal of Chemical Physics (publié)
doi.org
Beyond FVD: Enhanced Evaluation Metrics for Video Generation Quality
Ge Ya Luo
Gian Mario Favero
Zhi Hao Luo
Alexia Jolicoeur-Martineau
Chris Pal
The Fr\'echet Video Distance (FVD) is a widely adopted metric for evaluating video generation distribution quality. However, its effectivene… (voir plus)ss relies on critical assumptions. Our analysis reveals three significant limitations: (1) the non-Gaussianity of the Inflated 3D Convnet (I3D) feature space; (2) the insensitivity of I3D features to temporal distortions; (3) the impractical sample sizes required for reliable estimation. These findings undermine FVD's reliability and show that FVD falls short as a standalone metric for video generation evaluation. After extensive analysis of a wide range of metrics and backbone architectures, we propose JEDi, the JEPA Embedding Distance, based on features derived from a Joint Embedding Predictive Architecture, measured using Maximum Mean Discrepancy with polynomial kernel. Our experiments on multiple open-source datasets show clear evidence that it is a superior alternative to the widely used FVD metric, requiring only 16% of the samples to reach its steady value, while increasing alignment with human evaluation by 34%, on average.
2024-10-07
ArXiv (prépublication)
doi.org
arxiv.org
Beyond FVD: Enhanced Evaluation Metrics for Video Generation Quality
Ge Ya Luo
Gian Favero
Zhi Hao Luo
Alexia Jolicoeur-Martineau
Chris Pal
The Fr\'echet Video Distance (FVD) is a widely adopted metric for evaluating video generation distribution quality. However, its effectivene… (voir plus)ss relies on critical assumptions. Our analysis reveals three significant limitations: (1) the non-Gaussianity of the Inflated 3D Convnet (I3D) feature space; (2) the insensitivity of I3D features to temporal distortions; (3) the impractical sample sizes required for reliable estimation. These findings undermine FVD's reliability and show that FVD falls short as a standalone metric for video generation evaluation. After extensive analysis of a wide range of metrics and backbone architectures, we propose JEDi, the JEPA Embedding Distance, based on features derived from a Joint Embedding Predictive Architecture, measured using Maximum Mean Discrepancy with polynomial kernel. Our experiments on multiple open-source datasets show clear evidence that it is a superior alternative to the widely used FVD metric, requiring only 16% of the samples to reach its steady value, while increasing alignment with human evaluation by 34%, on average.
2024-10-07
ArXiv (prépublication)
doi.org
arxiv.org
An Effective Theory of Bias Amplification
Arjun Subramonian
Samuel J. Bell
Levent Sagun
Elvis Dohmatob
Machine learning models may capture and amplify biases present in data, leading to disparate test performance across social groups. To bette… (voir plus)r understand, evaluate, and mitigate these possible biases, a deeper theoretical understanding of how model design choices and data distribution properties could contribute to bias is needed. In this work, we contribute a precise analytical theory in the context of ridge regression, both with and without random projections, where the former models neural networks in a simplified regime. Our theory offers a unified and rigorous explanation of machine learning bias, providing insights into phenomena such as bias amplification and minority-group bias in various feature and parameter regimes. For example, we demonstrate that there may be an optimal regularization penalty or training time to avoid bias amplification, and there can be fundamental differences in test error between groups that do not vanish with increased parameterization. Importantly, our theoretical predictions align with several empirical observations reported in the literature. We extensively empirically validate our theory on diverse synthetic and semi-synthetic datasets.
2024-10-07
ArXiv (prépublication)
doi.org
arxiv.org