We use cookies to analyze the browsing and usage of our website and to personalize your experience. You can disable these technologies at any time, but this may limit certain functionalities of the site. Read our Privacy Policy for more information.
Setting cookies
You can enable and disable the types of cookies you wish to accept. However certain choices you make could affect the services offered on our sites (e.g. suggestions, personalised ads, etc.).
Essential cookies
These cookies are necessary for the operation of the site and cannot be deactivated. (Still active)
Analytics cookies
Do you accept the use of cookies to measure the audience of our sites?
Multimedia Player
Do you accept the use of cookies to display and allow you to watch the video content hosted by our partners (YouTube, etc.)?
Publications
Spectral State Space Model for Rotation-Invariant Visual Representation Learning
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.
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.
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.
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.
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.
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
