Publications

Understanding the impact of IoT security patterns on CPU usage and energy consumption: a dynamic approach for selecting patterns with deep reinforcement learning

Saeid Jamshidi

Amin Nikanjam

Kawser Wazed Nafi

Foutse Khomh

2025-03-09

International Journal of Information Security (publié)

What makes a theory of consciousness unscientific?

IIT-Concerned

Derek H. Arnold

Mark G. Baxter

Tristan A. Bekinschtein

Yoshua Bengio

James W. Bisley

Jacob Browning

Dean V. Buonomano

David Carmel

Marisa Carrasco

Peter Carruthers

Olivia Carter

Dorita H. F. Chang

Ian Charest

Mouslim Cherkaoui

Axel Cleeremans

Michael A. Cohen

Philip R. Corlett

Kalina Christoff

Sam Cumming … (voir 80 de plus)

Cody A. Cushing

Beatrice de Gelder

Felipe De Brigard

Daniel C. Dennett

Nadine Dijkstra

Adrien Doerig

Paul E. Dux

Stephen M. Fleming

Keith Frankish

Chris Frith

Sarah Garfinkel

Melvyn A. Goodale

Jacqueline Gottlieb

Jake R. Hanson

Ran R. Hassin

Michael H. Herzog

Cecilia Heyes

Po‐Jang Hsieh

Shao‐Min Hung

Robert W. Kentridge

Tomas Knapen

Nikos Konstantinou

Konrad P. Kording

Timo L. Kvamme

Sze Chai Kwok

Renzo C. Lanfranco

Hakwan Lau

Joseph E. LeDoux

Alan Lee

Camilo Libedinsky

Matthew D. Lieberman

Ying-Tung Lin

Kayuet Liu

Maro G. Machizawa

Julio Martínez-Trujillo

Janet Metcalfe

Matthias Michel

Kenneth D. Miller

Partha P. Mitra

Dean Mobbs

Robert M. Mok

Jorge Morales

Myrto Mylopoulos

Brian Odegaard

Charles C.-F. Or

Adrian M. Owen

David Pereplyotchik

Franco Pestilli

Megan A. K. Peters

Ian Phillips

Rosanne L. Rademaker

Dobromir Rahnev

Geraint Rees

Dario L. Ringach

Adina L. Roskies

Daniela Schiller

Aaron Schurger

D. Samuel Schwarzkopf

R. B. Y. Scott

Aaron R. Seitz

Joshua Shepherd

Juha Silvanto

Heleen A. Slagter

Barry Smith

Guillermo Solovey

David Soto

Hugo J. Spiers

Timo Stein

Vincent Taschereau‐Dumouchel

Frank Tong

Peter U. Tse

Jonas Vibell

Sebastian Watzl

Taylor W. Webb

Josh Weisberg

Thalia Wheatley

Michał Wierzchoń

Martijn E. Wokke

Karen Yan

Michał Klincewicz

2025-03-09

Nature Neuroscience (inconnu)

A Taxonomy of Inefficiencies in LLM-Generated Python Code

Altaf Allah Abbassi

Leuson Da Silva

Amin Nikanjam

Foutse Khomh

Large Language Models (LLMs) are widely adopted for automated code generation with promising results. Although prior research has assessed L… (voir plus)LM-generated code and identified various quality issues- such as redundancy, poor maintainability, and sub-optimal performance- a systematic understanding and categorization of these inefficiencies remain unexplored. Therefore, we empirically investigate inefficiencies in LLM-generated Python code by state-of-the-art models, i.e., CodeLlama, DeepSeek-Coder, and CodeGemma. To do so, we manually analyze 492 generated Python code snippets in the HumanEval+ dataset. We then construct a taxonomy of inefficiencies in LLM-generated Python code that includes 5 categories (General Logic, Performance, Readability, Maintainability, and Errors) and 19 subcategories of inefficiencies. We validate the obtained taxonomy through an online survey with 58 LLM practitioners and researchers. The surveyed participants affirmed the completeness of the proposed taxonomy, and the relevance and the popularity of the identified code inefficiency patterns. Our qualitative findings indicate that inefficiencies are diverse and interconnected, affecting multiple aspects of code quality, with logic and performance-related inefficiencies being the most frequent and often co-occurring while impacting overall code quality. Our taxonomy provides a structured basis for evaluating the quality of LLM-generated code and guiding future research to improve code generation efficiency.

2025-03-07

ArXiv (prépublication)

NNetscape Navigator: Complex Demonstrations for Web Agents Without a Demonstrator

Shikhar Murty

Dzmitry Bahdanau

Hao Zhu

Christopher D Manning

We introduce NNetscape Navigator (NNetnav), a method for training web agents entirely through synthetic demonstrations. These demonstrations… (voir plus) are collected by first interacting with a browser to generate trajectory rollouts, which are then retroactively labeled into instructions using a language model. Most work on training browser agents has relied on expensive human supervision, and the limited previous work on such interaction-first synthetic data techniques has failed to provide effective search through the exponential 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 subtasks, allowing NNetnav to automatically prune interaction episodes when an intermediate trajectory cannot be annotated with a meaningful sub-task. We use NNetnav demonstrations from a language model for supervised fine-tuning of a smaller language model policy, and find improvements of 6 points on WebArena and over 20 points on MiniWoB++, two popular environments for web-agents. Notably, on WebArena, we observe that language model policies can be further enhanced when fine-tuned with NNetnav demonstrations derived from the same language model. Finally, we collect and release a dataset of over 6k NNetnav demonstrations on WebArena, spanning a diverse and complex set of instructions.

2025-03-06

ICLR.cc/2025/Workshop/SSI-FM (poster)

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… (voir plus)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.

2025-03-06

TMLR (accepté)

Tractable Representations for Convergent Approximation of Distributional HJB Equations

Julie Alhosh

Harley Wiltzer

David Meger

2025-03-06

ArXiv (prépublication)

Cross-validation for training and testing co-occurrence network inference algorithms

Daniel Agyapong

Jeffrey Ryan Propster

Jane Marks

Toby Dylan Hocking

2025-03-05

BMC Bioinformatics (publié)

DASFormer: self-supervised pretraining for earthquake monitoring

Qianggang Ding

Zhichao Shen

Weiqiang Zhu

Bang Liu

Earthquake monitoring is a fundamental task to unravel the underlying physics of earthquakes and mitigate associated hazards for public safe… (voir plus)ty. Distributed acoustic sensing, or DAS, which transforms pre-existing telecommunication cables into ultra-dense seismic networks, offers a cost-effective and scalable solution for next-generation earthquake monitoring. However, current approaches for earthquake monitoring like PhaseNet and PhaseNet-2 primarily rely on supervised learning, while manually labeled DAS data is quite limited and it is difficult to obtain more annotated datasets. In this paper, we present DASFormer, a novel self-supervised pretraining technique on DAS data with a coarse-to-fine framework that models spatial-temporal signal correlation. We treat earthquake monitoring as an anomaly detection task and demonstrate DASFormer can be directly utilized as a seismic phase detector. Experimental results demonstrate that DASFormer is effective in terms of several evaluation metrics and outperforms state-of-the-art time-series forecasting, anomaly detection, and foundation models on the unsupervised seismic detection task. We also demonstrate the potential of fine-tuning DASFormer to downstream tasks through case studies.

2025-03-05

ICLR.cc/2025/Workshop/FM-Wild (publié)

EMA-Net: Efficient Multitask Affinity Learning for Dense Scene Predictions

Dimitrios Sinodinos

Narges Armanfard

2025-03-05

2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) (publié)

GradTune: Last-layer Fine-tuning for Group Robustness Without Group Annotation

Patrik Joslin Kenfack

Ulrich Matchi Aïvodji

S Ebrahimi Kahou

This work addresses the limitations of deep neural networks (DNNs) in generalizing beyond training data due to spurious correlations. Recent… (voir plus) 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.

2025-03-05

ICLR.cc/2025/Workshop/SCSL (publié)