BootsTAP: Bootstrapped Training for Tracking-Any-Point
Carl Doersch
Yi Yang
Dilara Gokay
Pauline Luc
Skanda Koppula
Ankush Gupta
Joseph Heyward
Ignacio Rocco
João Carreira
Andrew Zisserman
To endow models with greater understanding of physics and motion, it is useful to enable them to perceive how solid surfaces move and deform… (voir plus) in real scenes. This can be formalized as Tracking-Any-Point (TAP), which requires the algorithm to track any point on solid surfaces in a video, potentially densely in space and time. Large-scale groundtruth training data for TAP is only available in simulation, which currently has a limited variety of objects and motion. In this work, we demonstrate how large-scale, unlabeled, uncurated real-world data can improve a TAP model with minimal architectural changes, using a selfsupervised student-teacher setup. We demonstrate state-of-the-art performance on the TAP-Vid benchmark surpassing previous results by a wide margin: for example, TAP-Vid-DAVIS performance improves from 61.3% to 67.4%, and TAP-Vid-Kinetics from 57.2% to 62.5%. For visualizations, see our project webpage at https://bootstap.github.io/
Leveraging Data Characteristics for Bug Localization in Deep Learning Programs
Ruchira Manke
Mohammad Wardat
Hridesh Rajan
Deep Learning (DL) is a class of machine learning algorithms that are used in a wide variety of applications. Like any software system, DL p… (voir plus)rograms can have bugs. To support bug localization in DL programs, several tools have been proposed in the past. As most of the bugs that occur due to improper model structure known as structural bugs lead to inadequate performance during training, it is challenging for developers to identify the root cause and address these bugs. To support bug detection and localization in DL programs, in this paper, we propose Theia, which detects and localizes structural bugs in DL programs. Unlike the previous works, Theia considers the training dataset characteristics to automatically detect bugs in DL programs developed using two deep learning libraries, Keras and PyTorch . Since training the DL models is a time-consuming process, Theia detects these bugs at the beginning of the training process and alerts the developer with informative messages containing the bug's location and actionable fixes which will help them to improve the structure of the model. We evaluated Theia on a benchmark of 40 real-world buggy DL programs obtained from Stack Overflow . Our results show that Theia successfully localizes 57/75 structural bugs in 40 buggy programs, whereas NeuraLint, a state-of-the-art approach capable of localizing structural bugs before training localizes 17/75 bugs.
Leveraging Data Characteristics for Bug Localization in Deep Learning Programs
Ruchira Manke
Mohammad Wardat
Hridesh Rajan
Deep Learning (DL) is a class of machine learning algorithms that are used in a wide variety of applications. Like any software system, DL p… (voir plus)rograms can have bugs. To support bug localization in DL programs, several tools have been proposed in the past. As most of the bugs that occur due to improper model structure known as structural bugs lead to inadequate performance during training, it is challenging for developers to identify the root cause and address these bugs. To support bug detection and localization in DL programs, in this paper, we propose Theia, which detects and localizes structural bugs in DL programs. Unlike the previous works, Theia considers the training dataset characteristics to automatically detect bugs in DL programs developed using two deep learning libraries, Keras and PyTorch . Since training the DL models is a time-consuming process, Theia detects these bugs at the beginning of the training process and alerts the developer with informative messages containing the bug's location and actionable fixes which will help them to improve the structure of the model. We evaluated Theia on a benchmark of 40 real-world buggy DL programs obtained from Stack Overflow . Our results show that Theia successfully localizes 57/75 structural bugs in 40 buggy programs, whereas NeuraLint, a state-of-the-art approach capable of localizing structural bugs before training localizes 17/75 bugs.
Leveraging Data Characteristics for Bug Localization in Deep Learning Programs
Ruchira Manke
Mohammad Wardat
Hridesh Rajan
Deep Learning (DL) is a class of machine learning algorithms that are used in a wide variety of applications. Like any software system, DL p… (voir plus)rograms can have bugs. To support bug localization in DL programs, several tools have been proposed in the past. As most of the bugs that occur due to improper model structure known as structural bugs lead to inadequate performance during training, it is challenging for developers to identify the root cause and address these bugs. To support bug detection and localization in DL programs, in this paper, we propose Theia, which detects and localizes structural bugs in DL programs. Unlike the previous works, Theia considers the training dataset characteristics to automatically detect bugs in DL programs developed using two deep learning libraries, Keras and PyTorch . Since training the DL models is a time-consuming process, Theia detects these bugs at the beginning of the training process and alerts the developer with informative messages containing the bug's location and actionable fixes which will help them to improve the structure of the model. We evaluated Theia on a benchmark of 40 real-world buggy DL programs obtained from Stack Overflow . Our results show that Theia successfully localizes 57/75 structural bugs in 40 buggy programs, whereas NeuraLint, a state-of-the-art approach capable of localizing structural bugs before training localizes 17/75 bugs.
Leveraging Data Characteristics for Bug Localization in Deep Learning Programs
Ruchira Manke
Mohammad Wardat
Hridesh Rajan
Deep Learning (DL) is a class of machine learning algorithms that are used in a wide variety of applications. Like any software system, DL p… (voir plus)rograms can have bugs. To support bug localization in DL programs, several tools have been proposed in the past. As most of the bugs that occur due to improper model structure known as structural bugs lead to inadequate performance during training, it is challenging for developers to identify the root cause and address these bugs. To support bug detection and localization in DL programs, in this paper, we propose Theia, which detects and localizes structural bugs in DL programs. Unlike the previous works, Theia considers the training dataset characteristics to automatically detect bugs in DL programs developed using two deep learning libraries, Keras and PyTorch. Since training the DL models is a time-consuming process, Theia detects these bugs at the beginning of the training process and alerts the developer with informative messages containing the bug's location and actionable fixes which will help them to improve the structure of the model. We evaluated Theia on a benchmark of 40 real-world buggy DL programs obtained from Stack Overflow. Our results show that Theia successfully localizes 57/75 structural bugs in 40 buggy programs, whereas NeuraLint, a state-of-the-art approach capable of localizing structural bugs before training localizes 17/75 bugs.
The Responsible Foundation Model Development Cheatsheet: A Review of Tools&Resources
Shayne Longpre
Stella Biderman
Alon Albalak
Hailey Schoelkopf
Daniel McDuff
Sayash Kapoor
Kevin Klyman
Kyle Lo
Gabriel Ilharco
Nay San
Maribeth Rauh
Aviya Skowron
Bertie Vidgen
Laura Weidinger
Arvind Narayanan
Victor Sanh
Percy Liang
Rishi Bommasani
Peter Henderson … (voir 3 de plus)
Sasha Luccioni
Yacine Jernite
Luca Soldaini
The BrowserGym Ecosystem for Web Agent Research
Thibault Le Sellier de Chezelles
Alexandre Lacoste
Massimo Caccia
Léo Boisvert
Megh Thakkar
Tom Marty
Rim Assouel
Sahar Omidi Shayegan
Lawrence Jang
Xing Han Lu
Ori Yoran
Dehan Kong
Frank F. Xu
Graham Neubig
Ruslan Salakhutdinov
The BrowserGym ecosystem addresses the growing need for efficient evaluation and benchmarking of web agents, particularly those leveraging a… (voir plus)utomation and Large Language Models (LLMs) for web interaction tasks. Many existing benchmarks suffer from fragmentation and inconsistent evaluation methodologies, making it challenging to achieve reliable comparisons and reproducible results. BrowserGym aims to solve this by providing a unified, gym-like environment with well-defined observation and action spaces, facilitating standardized evaluation across diverse benchmarks. Combined with AgentLab, a complementary framework that aids in agent creation, testing, and analysis, BrowserGym offers flexibility for integrating new benchmarks while ensuring consistent evaluation and comprehensive experiment management. This standardized approach seeks to reduce the time and complexity of developing web agents, supporting more reliable comparisons and facilitating in-depth analysis of agent behaviors, and could result in more adaptable, capable agents, ultimately accelerating innovation in LLM-driven automation. As a supporting evidence, we conduct the first large-scale, multi-benchmark web agent experiment and compare the performance of 6 state-of-the-art LLMs across all benchmarks currently available in BrowserGym. Among other findings, our results highlight a large discrepancy between OpenAI and Anthropic's latests models, with Claude-3.5-Sonnet leading the way on almost all benchmarks, except on vision-related tasks where GPT-4o is superior. Despite these advancements, our results emphasize that building robust and efficient web agents remains a significant challenge, due to the inherent complexity of real-world web environments and the limitations of current models.
The BrowserGym Ecosystem for Web Agent Research
Thibault Le Sellier de Chezelles
Alexandre Lacoste
Massimo Caccia
Léo Boisvert
Megh Thakkar
Tom Marty
Rim Assouel
Sahar Omidi Shayegan
Lawrence Jang
Xing Han Lu
Ori Yoran
Dehan Kong
Frank F. Xu
Graham Neubig
Ruslan Salakhutdinov
The BrowserGym ecosystem addresses the growing need for efficient evaluation and benchmarking of web agents, particularly those leveraging a… (voir plus)utomation and Large Language Models (LLMs) for web interaction tasks. Many existing benchmarks suffer from fragmentation and inconsistent evaluation methodologies, making it challenging to achieve reliable comparisons and reproducible results. BrowserGym aims to solve this by providing a unified, gym-like environment with well-defined observation and action spaces, facilitating standardized evaluation across diverse benchmarks. Combined with AgentLab, a complementary framework that aids in agent creation, testing, and analysis, BrowserGym offers flexibility for integrating new benchmarks while ensuring consistent evaluation and comprehensive experiment management. This standardized approach seeks to reduce the time and complexity of developing web agents, supporting more reliable comparisons and facilitating in-depth analysis of agent behaviors, and could result in more adaptable, capable agents, ultimately accelerating innovation in LLM-driven automation. As a supporting evidence, we conduct the first large-scale, multi-benchmark web agent experiment and compare the performance of 6 state-of-the-art LLMs across all benchmarks currently available in BrowserGym. Among other findings, our results highlight a large discrepancy between OpenAI and Anthropic's latests models, with Claude-3.5-Sonnet leading the way on almost all benchmarks, except on vision-related tasks where GPT-4o is superior. Despite these advancements, our results emphasize that building robust and efficient web agents remains a significant challenge, due to the inherent complexity of real-world web environments and the limitations of current models.
The BrowserGym Ecosystem for Web Agent Research
Thibault Le Sellier de Chezelles
Alexandre Lacoste
Massimo Caccia
Léo Boisvert
Megh Thakkar
Tom Marty
Rim Assouel
Sahar Omidi Shayegan
Lawrence Jang
Xing Han Lu
Ori Yoran
Dehan Kong
Frank F. Xu
Graham Neubig
Ruslan Salakhutdinov
The BrowserGym ecosystem addresses the growing need for efficient evaluation and benchmarking of web agents, particularly those leveraging a… (voir plus)utomation and Large Language Models (LLMs) for web interaction tasks. Many existing benchmarks suffer from fragmentation and inconsistent evaluation methodologies, making it challenging to achieve reliable comparisons and reproducible results. BrowserGym aims to solve this by providing a unified, gym-like environment with well-defined observation and action spaces, facilitating standardized evaluation across diverse benchmarks. Combined with AgentLab, a complementary framework that aids in agent creation, testing, and analysis, BrowserGym offers flexibility for integrating new benchmarks while ensuring consistent evaluation and comprehensive experiment management. This standardized approach seeks to reduce the time and complexity of developing web agents, supporting more reliable comparisons and facilitating in-depth analysis of agent behaviors, and could result in more adaptable, capable agents, ultimately accelerating innovation in LLM-driven automation. As a supporting evidence, we conduct the first large-scale, multi-benchmark web agent experiment and compare the performance of 6 state-of-the-art LLMs across all benchmarks currently available in BrowserGym. Among other findings, our results highlight a large discrepancy between OpenAI and Anthropic's latests models, with Claude-3.5-Sonnet leading the way on almost all benchmarks, except on vision-related tasks where GPT-4o is superior. Despite these advancements, our results emphasize that building robust and efficient web agents remains a significant challenge, due to the inherent complexity of real-world web environments and the limitations of current models.
Turncoat antibodies unmasked in a model of autoimmune demyelination: from biology to therapy
Reza Taghipour-Mirakmahaleh
Françoise Morin
Yu Zhang
Louis Bourhoven
Louis-Charles Béland
Qun Zhou
Julie Jaworski
Anna Park
Juan Manuel Dominguez
Eoin P Flanagan
Romain Marignier
Catherine Larochelle
Steven Kerfoot
Luc Vallières
Autoantibodies contribute to many autoimmune diseases, yet there is no approved therapy to neutralize them selectively. A popular mouse mode… (voir plus)l, experimental autoimmune encephalomyelitis (EAE), could serve to develop such a therapy, provided we can better understand the nature and importance of the autoantibodies involved. Here we report the discovery of autoantibody-secreting extrafollicular plasmablasts in EAE induced with specific myelin oligodendrocyte glycoprotein (MOG) antigens. Single-cell RNA sequencing reveals that these cells produce non-affinity-matured IgG antibodies. These include pathogenic antibodies competing for shared binding space on MOG’s extracellular domain. Interestingly, the synthetic anti-MOG antibody 8-18C5 can prevent the binding of pathogenic antibodies from either EAE mice or people with MOG antibody disease (MOGAD). Moreover, an 8-18C5 variant carrying the NNAS mutation, which inactivates its effector functions, can reduce EAE severity and promote functional recovery. In brief, this study provides not only a comprehensive characterization of the humoral response in EAE models, but also a proof of concept for a novel therapy to antagonize pathogenic anti-MOG antibodies.
Assessing and Learning Alignment of Unimodal Vision and Language Models
Le Zhang
Qian Yang
How well are unimodal vision and language models aligned? Although prior work have approached answering this question, their assessment meth… (voir plus)ods do not directly translate to how these models are used in practical vision-language tasks. In this paper, we propose a direct assessment method, inspired by linear probing, to assess vision-language alignment. We identify that the degree of alignment of the SSL vision models depends on their SSL training objective, and we find that the clustering quality of SSL representations has a stronger impact on alignment performance than their linear separability. Next, we introduce Swift Alignment of Image and Language (SAIL), a efficient transfer learning framework that aligns pretrained unimodal vision and language models for downstream vision-language tasks. Since SAIL leverages the strengths of pretrained unimodal models, it requires significantly fewer (6%) paired image-text data for the multimodal alignment compared to models like CLIP which are trained from scratch. SAIL training only requires a single A100 GPU, 5 hours of training and can accommodate a batch size up to 32,768. SAIL achieves 73.4% zero-shot accuracy on ImageNet (vs. CLIP's 72.7%) and excels in zero-shot retrieval, complex reasoning, and semantic segmentation. Additionally, SAIL improves the language-compatibility of vision encoders that in turn enhance the performance of multimodal large language models. The entire codebase and model weights are open-source: https://lezhang7.github.io/sail.github.io/
Assessing and Learning Alignment of Unimodal Vision and Language Models
Le Zhang
Qian Yang
How well are unimodal vision and language models aligned? Although prior work have approached answering this question, their assessment meth… (voir plus)ods do not directly translate to how these models are used in practical vision-language tasks. In this paper, we propose a direct assessment method, inspired by linear probing, to assess vision-language alignment. We identify that the degree of alignment of the SSL vision models depends on their SSL training objective, and we find that the clustering quality of SSL representations has a stronger impact on alignment performance than their linear separability. Next, we introduce Swift Alignment of Image and Language (SAIL), a efficient transfer learning framework that aligns pretrained unimodal vision and language models for downstream vision-language tasks. Since SAIL leverages the strengths of pretrained unimodal models, it requires significantly fewer (6%) paired image-text data for the multimodal alignment compared to models like CLIP which are trained from scratch. SAIL training only requires a single A100 GPU, 5 hours of training and can accommodate a batch size up to 32,768. SAIL achieves 73.4% zero-shot accuracy on ImageNet (vs. CLIP's 72.7%) and excels in zero-shot retrieval, complex reasoning, and semantic segmentation. Additionally, SAIL improves the language-compatibility of vision encoders that in turn enhance the performance of multimodal large language models. The entire codebase and model weights are open-source: https://lezhang7.github.io/sail.github.io/