Publications

Zero-Shot Anomaly Detection with Dual-Branch Prompt Selection

Zero-shot anomaly detection (ZSAD) enables identifying and localizing defects in unseen categories by relying solely on generalizable featur… (voir plus)es rather than requiring any labeled examples of anomalies. However, existing ZSAD methods, whether using fixed or learned prompts, struggle under domain shifts because their training data are derived from limited training domains and fail to generalize to new distributions. In this paper, we introduce PILOT, a framework designed to overcome these challenges through two key innovations: (1) a novel dual-branch prompt learning mechanism that dynamically integrates a pool of learnable prompts with structured semantic attributes, enabling the model to adaptively weight the most relevant anomaly cues for each input image; and (2) a label-free test-time adaptation strategy that updates the learnable prompt parameters using high-confidence pseudo-labels from unlabeled test data. Extensive experiments on 13 industrial and medical benchmarks demonstrate that PILOT achieves state-of-the-art performance in both anomaly detection and localization under domain shift.

2025-08-01

ArXiv (prépublication)

arxiv.org

Zero-Shot Anomaly Detection with Dual-Branch Prompt Selection

Zihan Wang

Samira Ebrahimi Kahou

Narges Armanfard

Zero-shot anomaly detection (ZSAD) enables identifying and localizing defects in unseen categories by relying solely on generalizable featur… (voir plus)es rather than requiring any labeled examples of anomalies. However, existing ZSAD methods, whether using fixed or learned prompts, struggle under domain shifts because their training data are derived from limited training domains and fail to generalize to new distributions. In this paper, we introduce PILOT, a framework designed to overcome these challenges through two key innovations: (1) a novel dual-branch prompt learning mechanism that dynamically integrates a pool of learnable prompts with structured semantic attributes, enabling the model to adaptively weight the most relevant anomaly cues for each input image; and (2) a label-free test-time adaptation strategy that updates the learnable prompt parameters using high-confidence pseudo-labels from unlabeled test data. Extensive experiments on 13 industrial and medical benchmarks demonstrate that PILOT achieves state-of-the-art performance in both anomaly detection and localization under domain shift.

2025-08-01

ArXiv (prépublication)

arxiv.org

Advancing science- and evidence-based AI policy.

Rishi Bommasani

Sanjeev Arora

Jennifer Chayes

Yejin Choi

Mariano-Florentino Cuéllar

Li Fei-Fei

Daniel E. Ho

Dan Jurafsky

Sanmi Koyejo

Hima Lakkaraju

Arvind Narayanan

Alondra Nelson

Emma Pierson

Joelle Pineau

Scott R. Singer

Gael Varoquaux

Suresh Venkatasubramanian

Ion Stoica

Percy Liang

Dawn Song

Policy must be informed by, but also facilitate the generation of, scientific evidence.

2025-07-31

ArXiv (prépublication)

doi.org

arxiv.org

Advancing science- and evidence-based AI policy.

Rishi Bommasani

Sanjeev Arora

Jennifer Chayes

Yejin Choi

Mariano-Florentino Cuéllar

Li Fei-Fei

Daniel E. Ho

Dan Jurafsky

Sanmi Koyejo

Hima Lakkaraju

Arvind Narayanan

Alondra Nelson

Emma Pierson

Joelle Pineau

Scott Singer

Gael Varoquaux

Suresh Venkatasubramanian

Ion Stoica

Percy Liang

Dawn Song

2025-07-31

Science (publié)

doi.org

arxiv.org

Audio Prototypical Network for Controllable Music Recommendation

Traditional recommendation systems represent user preferences in dense representations obtained through black-box encoder models. While thes… (voir plus)e models often provide strong recommendation performance, they lack interpretability for users, leaving users unable to understand or control the system’s modeling of their preferences. This limitation is especially challenging in music recommendation, where user preferences are highly personal and often evolve based on nuanced qualities like mood, genre, tempo, or instrumentation. In this paper, we propose an audio prototypical network for controllable music recommendation. This network expresses user preferences in terms of prototypes representative of semantically meaningful features pertaining to musical qualities. We show that the model obtains competitive recommendation performance compared to popular baseline models while also providing interpretable and controllable user profiles.

2025-07-31

ArXiv (prépublication)

openreview.net

Computing Approximate Nash Equilibria for Integer Programming Games

Aloïs Duguet

Margarida Carvalho

Gabriele Dragotto

Sandra-ulrich Ngueveu

2025-07-31

Optimization Letters (publié)

doi.org

arxiv.org

Co-Producing AI: Toward an Augmented, Participatory Lifecycle

Rashid A. Mushkani

Hugo Berard

Toumadher Ammar

Cassandre Chatonnier

Shin (Alexandre) Koseki

Despite efforts to mitigate the inherent risks and biases of artificial intelligence (AI) algorithms, these algorithms can disproportionatel… (voir plus)y impact culturally marginalized groups. A range of approaches has been proposed to address or reduce these risks, including the development of ethical guidelines and principles for responsible AI, as well as technical solutions that promote algorithmic fairness. Drawing on design justice, expansive learning theory, and recent empirical work on participatory AI, we argue that mitigating these harms requires a fundamental re-architecture of the AI production pipeline. This re-design should center co-production, diversity, equity, inclusion (DEI), and multidisciplinary collaboration. We introduce an augmented AI lifecycle consisting of five interconnected phases: co-framing, co-design, co-implementation, co-deployment, and co-maintenance. The lifecycle is informed by four multidisciplinary workshops and grounded in themes of distributed authority and iterative knowledge exchange. Finally, we relate the proposed lifecycle to several leading ethical frameworks and outline key research questions that remain for scaling participatory governance.

2025-07-31

ArXiv (prépublication)

arxiv.org

Evaluating and Improving LitLLMs with Deep Research

Gaurav Sahu

Shubham Agarwal

Abhay Puri

Issam Hadj Laradji

Krishnamurthy Dj Dvijotham

Jason Stanley

Laurent Charlin

Chris Pal

Literature reviews are an essential component of scientific research, but they remain time-intensive and challenging to write, especially du… (voir plus)e to the recent influx of research papers. This paper explores the zero-shot abilities of recent Large Language Models (LLMs) in assisting with the writing of literature reviews based on an abstract. We decompose the task into two components: (1) Retrieving related works given a query abstract and (2) Writing a literature review based on the retrieved results. We analyze how effective LLMs are for both components. For retrieval, we introduce a novel two-step search strategy that first uses an LLM to extract meaningful keywords from the abstract of a paper and then retrieves potentially relevant papers by querying an external knowledge base. Additionally, we study a prompting-based re-ranking mechanism with attribution and show that re-ranking doubles the normalized recall compared to naive search methods while providing insights into the LLM's decision-making process. In the generation phase, we propose a two-step approach that first outlines a plan for the review and then executes steps in the plan to generate the actual review. To evaluate different LLM-based literature review methods, we create test sets from arXiv papers using a protocol designed for rolling use with newly released LLMs to avoid test set contamination in zero-shot evaluations. We release this evaluation protocol to promote additional research and development in this regard. Our empirical results suggest that LLMs show promising potential for writing literature reviews when the task is decomposed into smaller components of retrieval and planning. Particularly, our ``Deep Research" retrieval variant improves coverage by over 5x compared to standard keyword search, addressing a key bottleneck in the pipeline. Further, we demonstrate that our planning-based approach achieves higher-quality reviews by minimizing hallucinated references in the generated review by 18-26\% compared to existing simpler LLM-based generation methods.

2025-07-31

colmweb.org/COLM/2025/Workshop/LM4Sci (publié)

openreview.net

Towards a General Recipe for Combinatorial Optimization with Multi-Filter GNNs

Michael Perlmutter

2025-07-30

Proceedings of the Third Learning on Graphs Conference (publié)

proceedings.mlr.press

openreview.net

Capacity-Constrained Continual Learning

Zheng Wen

Doina Precup

Benjamin Van Roy

Satinder Singh

Any agents we can possibly build are subject to capacity constraints, as memory and compute resources are inherently finite. However, compar… (voir plus)atively little attention has been dedicated to understanding how agents with limited capacity should allocate their resources for optimal performance. The goal of this paper is to shed some light on this question by studying a simple yet relevant continual learning problem: the capacity-constrained linear-quadratic-Gaussian (LQG) sequential prediction problem. We derive a solution to this problem under appropriate technical conditions. Moreover, for problems that can be decomposed into a set of sub-problems, we also demonstrate how to optimally allocate capacity across these sub-problems in the steady state. We view the results of this paper as a first step in the systematic theoretical study of learning under capacity constraints.

2025-07-29

ArXiv (prépublication)

arxiv.org