Publications

The BrowserGym Ecosystem for Web Agent Research
Thibault Le Sellier de Chezelles
Maxime Gasse
Alexandre Lacoste
Massimo Caccia
Alexandre Drouin
Léo Boisvert
Megh Thakkar
Tom Marty
Rim Assouel
Sahar Omidi Shayegan
Lawrence Keunho Jang
Xing Han Lu
Ori Yoran
Dehan Kong
Frank F. Xu
Siva Reddy
Graham Neubig
Quentin Cappart
Russ Salakhutdinov
Nicolas Chapados
The BrowserGym ecosystem addresses the growing need for efficient evaluation and benchmarking of web agents, particularly those leveraging a… (see more)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.
2025-03-08
TMLR (accepted)
doi.org
openreview.net
NNetNav: Unsupervised Learning of Browser Agents Through Environment Interaction in the Wild
Shikhar Murty
Hao Zhu
Dzmitry Bahdanau
Christopher D Manning
We introduce NNetNav, a method for unsupervised interaction with websites that generates synthetic demonstrations for training browser agent… (see more)s. Given any website, NNetNav produces these demonstrations by retroactively labeling action sequences from an exploration policy. Most work on training browser agents has relied on expensive human supervision, and the limited prior work on such interaction-based techniques has failed to provide effective search through the exponentially large space of exploration. In contrast, NNetNav exploits the hierarchical structure of language instructions to make this search more tractable: Complex instructions are typically decomposable into simpler sub-tasks, allowing NNetNav to automatically prune interaction episodes when an intermediate trajectory cannot be annotated with a meaningful sub-task. \texttt{LLama-3.1-8b} finetuned on 10k NNetNav self-generated demonstrations obtains over 16\% success rate on WebArena, and 35\% on WebVoyager, an improvement of 15pts and 31pts respectively over zero-shot \texttt{LLama-3.1-8b}, outperforming zero-shot GPT-4 and reaching the state-of-the-art among unsupervised methods, for both benchmarks.
2025-03-07
ICLR.cc/2025/Workshop/SSI-FM (poster)
openreview.net
openreview.net
Towards Graph Foundation Models: A Study on the Generalization of Positional and Structural Encodings
Billy Joe Franks
Moshe Eliasof
Semih Cantürk
Guy Wolf
Carola-Bibiane Schönlieb
Sophie Fellenz
Marius Kloft
Recent advances in integrating positional and structural encodings (PSEs) into graph neural networks (GNNs) have significantly enhanced thei… (see more)r performance across various graph learning tasks. However, the general applicability of these encodings and their potential to serve as foundational representations for graphs remain uncertain. This paper investigates the fine-tuning efficiency, scalability with sample size, and generalization capability of learnable PSEs across diverse graph datasets. Specifically, we evaluate their potential as universal pre-trained models that can be easily adapted to new tasks with minimal fine-tuning and limited data. Furthermore, we assess the expressivity of the learned representations, particularly, when used to augment downstream GNNs. We demonstrate through extensive benchmarking and empirical analysis that PSEs generally enhance downstream models. However, some datasets may require specific PSE-augmentations to achieve optimal performance. Nevertheless, our findings highlight their significant potential to become integral components of future graph foundation models. We provide new insights into the strengths and limitations of PSEs, contributing to the broader discourse on foundation models in graph learning.
2025-03-07
TMLR (accepted)
openreview.net
openreview.net
GradTune: Last-layer Fine-tuning for Group Robustness Without Group Annotation
Patrik Joslin Kenfack
Ulrich Aivodji
Samira Ebrahimi Kahou
This work addresses the limitations of deep neural networks (DNNs) in generalizing beyond training data due to spurious correlations. Recent… (see more) research has demonstrated that models trained with empirical risk minimization learn both core and spurious features, often upweighting spurious ones in the final classification, which can frequently lead to poor performance on minority groups. Deep Feature Reweighting alleviates this issue by retraining the model's last classification layer using a group-balanced held-out validation set. However, relying on spurious feature labels during training or validation limits practical application, as spurious features are not always known or costly to annotate. Our preliminary experiments reveal that ERM-trained models exhibit higher gradient norms on minority group samples in the hold-out dataset. Leveraging these insights, we propose an alternative approach called GradTune, which fine-tunes the last classification layer using high-gradient norm samples. Our results on four well-established benchmarks demonstrate that the proposed method can achieve competitive performance compared to existing methods without requiring group labels during training or validation.
2025-03-06
ICLR.cc/2025/Workshop/SCSL (published)
openreview.net
openreview.net
A Joint Space-Time Encoder for Geographic Time-Series Data
David Mickisch
Konstantin Klemmer
Mélisande Teng
David Rolnick
Many real-world processes are characterized by complex spatio-temporal dependencies, from climate dynamics to disease spread. Here, we intro… (see more)duce a new neural network architecture to model such dynamics at scale: the \emph{Space-Time Encoder}. Building on recent advances in \emph{location encoders}, models that take as inputs geographic coordinates, we develop a method that takes in geographic and temporal information simultaneously and learns smooth, continuous functions in both space and time. The inputs are first transformed using positional encoding functions and then fed into neural networks that allow the learning of complex functions. We implement a prototype of the \emph{Space-Time Encoder}, discuss the design choices of the novel temporal encoding, and demonstrate its utility in climate model emulation. We discuss the potential of the method across use cases, as well as promising avenues for further methodological innovation.
2025-03-06
ICLR.cc/2025/Workshop/MLMP (poster)
openreview.net
openreview.net
Mitigating Shortcut Learning with Diffusion Counterfactuals and Diverse Ensembles
Luca Scimeca
Alexander Rubinstein
Damien Teney
Seong Joon Oh
Armand Mihai Nicolicioiu
Yoshua Bengio
Spurious correlations in the data, where multiple cues are predictive of the target labels, often lead to a phenomenon known as shortcut lea… (see more)rning, where a model relies on erroneous, easy-to-learn cues while ignoring reliable ones. In this work, we propose
2025-03-06
ICLR.cc/2025/Workshop/SCSL (published)
openreview.net
openreview.net
Towards personalized healthcare without harm via bias modulation
Frank Ngaha
Patrik Joslin Kenfack
Ulrich Aivodji
Samira Ebrahimi Kahou
Personalized machine learning models have gained significant importance in various domains, including healthcare. However, designing efficie… (see more)nt personalized models remains a challenge. Traditional approaches often involve training multiple sub-models for different population sub-groups, which can be costly and does not always guarantee improved performance across all sub-groups. This paper presents a novel approach to improving model performance at the sub-group level by leveraging bias and training a joint model. Our method involves a two-step process: first, we train a model to predict group attributes, and then we use this model to learn data-dependent biases to modulate a second model for diagnosis prediction. Our results demonstrate that this joint architecture achieves consistent performance gains across all sub-groups in the Heart dataset. Furthermore, in the mortality dataset, it improves performance in two of the four sub-groups. A comparison of our method with the traditional decoupled personalization method demonstrated a greater performance gain in the sub-groups with less harm. This approach offers a more effective and scalable solution for personalization of models, which could have positive impact in healthcare and other areas that require predictive models which take sub-group information into account.
2025-03-06
ICLR.cc/2025/Workshop/SCSL (published)
openreview.net
openreview.net
Who is your ideal peer mentor? A qualitative study to identify cancer patient preferences for a digital peer support app
Loes Knaapen
Andrea M. Laizner
Kelly Agnew
Xiao Jian Du
Douaa El Abiad
Luc Galarneau
Susie Judd
James Manalad
Ridhi Mittal
Tristan Williams
Brandon Woolfson
Angele Wen
John Kildea
2025-03-06
Supportive Care in Cancer (published)
doi.org
Adaptive Local Training in Federated Learning
Donald Shenaj
Eugene Belilovsky
Pietro Zanuttigh
Federated Learning is a machine learning paradigm where multiple clients collaboratively train a global model by exchanging their locally tr… (see more)ained model weights instead of raw data. In the standard setting, every client trains the local model for the same number of epochs. We introduce ALT (Adaptive Local Training), a simple yet effective feedback mechanism that could be introduced at the client side to limit unnecessary and degrading computations. ALT dynamically adjusts the number of training epochs for each client based on the similarity between their local representations and the global one, ensuring that well-aligned clients can train longer without experiencing client drift. We evaluated ALT on federated partitions of the CIFAR-10 and TinyImageNet datasets, demonstrating its effectiveness in improving model convergence and stability.
2025-03-05
ICLR.cc/2025/Workshop/MCDC (accepted)
openreview.net
openreview.net
AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Understanding
Ahmed Masry
Juan A. Rodriguez
Tianyu Zhang
Suyuchen Wang
Chao Wang
Aarash Feizi
Akshay Kalkunte Suresh
Abhay Puri
Xiangru Jian
Pierre-Andre Noel
Sathwik Tejaswi Madhusudhan
Marco Pedersoli
Bang Liu
Nicolas Chapados
Yoshua Bengio
Enamul Hoque
Chris Pal
Issam Hadj Laradji
David Vazquez
Perouz Taslakian … (see 2 more)
Spandana Gella
Sai Rajeswar
Aligning visual features with language embeddings is a key challenge in vision-language models (VLMs). The performance of such models hinges… (see more) on having a good connector that maps visual features generated by a vision encoder to a shared embedding space with the LLM while preserving semantic similarity. Existing connectors, such as multilayer perceptrons (MLPs), often produce out-of-distribution or noisy inputs, leading to misalignment between the modalities. In this work, we propose a novel vision-text alignment method, AlignVLM, that maps visual features to a weighted average of LLM text embeddings. Our approach leverages the linguistic priors encoded by the LLM to ensure that visual features are mapped to regions of the space that the LLM can effectively interpret. AlignVLM is particularly effective for document understanding tasks, where scanned document images must be accurately mapped to their textual content. Our extensive experiments show that AlignVLM achieves state-of-the-art performance compared to prior alignment methods. We provide further analysis demonstrating improved vision-text feature alignment and robustness to noise.
2025-03-05
ICLR.cc/2025/Workshop/Re-Align (poster)
doi.org
openreview.net
Cracking the Code of Action: A Generative Approach to Affordances for Reinforcement Learning
Lynn Cherif
Flemming Kondrup
David Venuto
Ankit Anand
Doina Precup
Khimya Khetarpal
Agents that can autonomously navigate the web through a graphical user interface (GUI) using a unified action space (e.g., mouse and keyboar… (see more)d actions) can require very large amounts of domain-specific expert demonstrations to achieve good performance. Low sample efficiency is often exacerbated in sparse-reward and large-action-space environments, such as a web GUI, where only a few actions are relevant in any given situation. In this work, we consider the low-data regime, with limited or no access to expert behavior. To enable sample-efficient learning, we explore the effect of constraining the action space through intent-based affordances -- i.e., considering in any situation only the subset of actions that achieve a desired outcome. We propose **Code as Generative Affordances**
2025-03-05
ICLR.cc/2025/Workshop/DL4C (published)
openreview.net
openreview.net
Exploring Sparse Adapters for Scalable Merging of Parameter Efficient Experts
Samin Yeasar Arnob
Zhan Su
Minseon Kim
Oleksiy Ostapenko
Doina Precup
Lucas Caccia
Alessandro Sordoni
Merging parameter-efficient task experts has recently gained growing attention as a way to build modular architectures that can be rapidly a… (see more)dapted on the fly for specific downstream tasks, without requiring additional fine-tuning. Typically, LoRA (Low-Rank Adaptation) serves as the foundational building block of such parameter-efficient modular architectures, leveraging low-rank weight structures to reduce the number of trainable parameters. In this paper, we study the properties of sparse adapters, which train only a subset of weights in the base neural network, as potential building blocks of modular architectures. First, we propose a simple method for training highly effective sparse adapters, which is conceptually simpler than existing methods in the literature and surprisingly outperforms both LoRA and full fine-tuning in our setting. Next, we investigate the merging properties of these sparse adapters by merging adapters for up to 20 natural language processing tasks, thus scaling beyond what is usually studied in the literature. Our findings demonstrate that sparse adapters yield superior in-distribution performance post-merging compared to LoRA or full model merging. Achieving strong held-out performance remains a challenge for all methods considered.
2025-03-05
ICLR.cc/2025/Workshop/MCDC (accepted)
openreview.net
openreview.net