Publications

Calibrated Value-Aware Model Learning with Stochastic Environment Models
Claas Voelcker
Anastasiia Pedan
Arash Ahmadian
Romina Abachi
Igor Gilitschenski
Amir-massoud Farahmand
The idea of value-aware model learning, that models should produce accurate value estimates, has gained prominence in model-based reinforcem… (see more)ent learning. The MuZero loss, which penalizes a model's value function prediction compared to the ground-truth value function, has been utilized in several prominent empirical works in the literature. However, theoretical investigation into its strengths and weaknesses is limited. In this paper, we analyze the family of value-aware model learning losses, which includes the popular MuZero loss. We show that these losses, as normally used, are uncalibrated surrogate losses, which means that they do not always recover the correct model and value function. Building on this insight, we propose corrections to solve this issue. Furthermore, we investigate the interplay between the loss calibration, latent model architectures, and auxiliary losses that are commonly employed when training MuZero-style agents. We show that while deterministic models can be sufficient to predict accurate values, learning calibrated stochastic models is still advantageous.
2025-05-28
ArXiv (preprint)
doi.org
arxiv.org
Calibrated Value-Aware Model Learning with Probabilistic Environment Models
Claas Voelcker
Anastasiia Pedan
Arash Ahmadian
Romina Abachi
Igor Gilitschenski
Amir-massoud Farahmand
The idea of value-aware model learning, that models should produce accurate value estimates, has gained prominence in model-based reinforcem… (see more)ent learning. The MuZero loss, which penalizes a model's value function prediction compared to the ground-truth value function, has been utilized in several prominent empirical works in the literature. However, theoretical investigation into its strengths and weaknesses is limited. In this paper, we analyze the family of value-aware model learning losses, which includes the popular MuZero loss. We show that these losses, as normally used, are uncalibrated surrogate losses, which means that they do not always recover the correct model and value function. Building on this insight, we propose corrections to solve this issue. Furthermore, we investigate the interplay between the loss calibration, latent model architectures, and auxiliary losses that are commonly employed when training MuZero-style agents. We show that while deterministic models can be sufficient to predict accurate values, learning calibrated stochastic models is still advantageous.
2025-05-28
ArXiv (preprint)
doi.org
arxiv.org
Calibrated Value-Aware Model Learning with Probabilistic Environment Models
Claas Voelcker
Anastasiia Pedan
Arash Ahmadian
Romina Abachi
Igor Gilitschenski
Amir-massoud Farahmand
The idea of value-aware model learning, that models should produce accurate value estimates, has gained prominence in model-based reinforcem… (see more)ent learning. The MuZero loss, which penalizes a model's value function prediction compared to the ground-truth value function, has been utilized in several prominent empirical works in the literature. However, theoretical investigation into its strengths and weaknesses is limited. In this paper, we analyze the family of value-aware model learning losses, which includes the popular MuZero loss. We show that these losses, as normally used, are uncalibrated surrogate losses, which means that they do not always recover the correct model and value function. Building on this insight, we propose corrections to solve this issue. Furthermore, we investigate the interplay between the loss calibration, latent model architectures, and auxiliary losses that are commonly employed when training MuZero-style agents. We show that while deterministic models can be sufficient to predict accurate values, learning calibrated stochastic models is still advantageous.
2025-05-28
ArXiv (preprint)
arxiv.org
arxiv.org
From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space Regularization
Shoaib Ahmed Siddiqui
Adrian Weller
David Scott Krueger
Gintare Karolina Dziugaite
Michael Curtis Mozer
Eleni Triantafillou
Recent unlearning methods for LLMs are vulnerable to relearning attacks: knowledge believed-to-be-unlearned re-emerges by fine-tuning on a s… (see more)mall set of (even seemingly-unrelated) examples. We study this phenomenon in a controlled setting for example-level unlearning in vision classifiers. We make the surprising discovery that forget-set accuracy can recover from around 50% post-unlearning to nearly 100% with fine-tuning on just the retain set -- i.e., zero examples of the forget set. We observe this effect across a wide variety of unlearning methods, whereas for a model retrained from scratch excluding the forget set (gold standard), the accuracy remains at 50%. We observe that resistance to relearning attacks can be predicted by weight-space properties, specifically,
2025-05-28
ArXiv (preprint)
doi.org
arxiv.org
From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space Regularization
Shoaib Ahmed Siddiqui
Adrian Weller
David Krueger 0001
Gintare Karolina Dziugaite
M. C. Mozer
Eleni Triantafillou
Recent unlearning methods for LLMs are vulnerable to relearning attacks: knowledge believed-to-be-unlearned re-emerges by fine-tuning on a s… (see more)mall set of (even seemingly-unrelated) examples. We study this phenomenon in a controlled setting for example-level unlearning in vision classifiers. We make the surprising discovery that forget-set accuracy can recover from around 50% post-unlearning to nearly 100% with fine-tuning on just the retain set -- i.e., zero examples of the forget set. We observe this effect across a wide variety of unlearning methods, whereas for a model retrained from scratch excluding the forget set (gold standard), the accuracy remains at 50%. We observe that resistance to relearning attacks can be predicted by weight-space properties, specifically,
2025-05-28
ArXiv (preprint)
arxiv.org
arxiv.org
Jailbreak Distillation: Renewable Safety Benchmarking
Jingyu Zhang
Ahmed Elgohary
Xiawei Wang
A S M Iftekhar
Ahmed Magooda
Benjamin Van Durme
Daniel Khashabi
Kyle Jackson
JBDistill Benchmark JBDistill Benchmark
Marah Ihab Abdin
Jyoti Aneja
Harkirat Singh Behl
Sébastien Bubeck
Ronen Eldan
S. Gunasekar
Michael Harrison
Russell J. Hewett
Mojan Javaheripi
Piero Kauffmann
James R. Lee … (see 484 more)
Yin Tat Lee
Yuanzhi Li
Weishung Liu
Caio C. T. Mendes
Anh Nguyen
Eric Price
Gustavo de Rosa
Olli Saarikivi
Adil Salim
Tim Beyer
Sophie Xhonneux
Simon Geisler
Gauthier Gidel
Leo Schwinn
Stephan Günnemann. 2025
Blake Bullwinkel
Amanda Minnich
Shiven Chawla
Gary Lopez
Martin Pouliot
Whitney Maxwell
Patrick Chao
Edoardo Debenedetti
Alexander Robey
Maksym Andriushchenko
Francesco Croce
Vikash Sehwag
Edgar Dobriban
Nicolas Flammarion
George J. Pappas
Florian Tramèr
Hamed Hassani
Eric Wong
Jailbreakbench
Zora Che
Stephen Casper
Robert Kirk
Anirudh Satheesh
Stewart Slocum
Lev E McKinney
Rohit Gandikota
Aidan Ewart
Domenic Rosati
Zichu Wu
Zikui Cai
Daya Guo
Dejian Yang
Haowei Zhang
Jun-Mei Song
Ruoyu Zhang
Runxin Xu
Qihao Zhu
Shirong Ma
Peiyi Wang
Xiaoling Bi
Xiaokang Zhang
Xingkai Yu
Yu Wu
Z. F. Wu
Zhibin Gou
Zhihong Shao
Zhuoshu Li
Ziyi Gao
A. Liu
Bing Xue
Bingxuan Wang
Bo WU
Bei Feng
Chenggang Lu
Chenggang Zhao
Chengqi Deng
Chenyu Zhang
C. Ruan
Damai Dai
Deli Chen
Dong-Li Ji
Erhang Li
Fangyun Lin
Fucong Dai
Fuli Luo
Guangbo Hao
Guanting Chen
Guowei Li
Han Bao
Hanwei Xu
Haocheng Wang
Honghui Ding
Huajian Xin
Huazuo Gao
Hui Qu
Hui Li
Jianzhong Guo
Jiashi Li
Jiawei Wang
Jingchang Chen
Jingyang Yuan
Junjie Qiu
Junlong Li
J. Cai
J. Ni
Jian Liang
Jin Chen
Kai Dong
Kai Hu
Kaige Gao
Kang Guan
Kexin Huang
Kuai Yu
Lean Wang
Lecong Zhang
Liang Zhao
Litong Wang
Liyue Zhang
Lei Xu
Leyi Xia
Mingchuan Zhang
Minghua Zhang
Min Tang
Meng Li
Miaojun Wang
Mingming Li
Ning Tian
Panpan Huang
Peng Zhang
Qiancheng Wang
Qinyu Chen
Qiushi Du
Ruiqi Ge
Ruisong Zhang
Ruizhe Pan
Runji Wang
R. J. Chen
Rong Jin
Ruyi Chen
Shanghao Lu
Shangyan Zhou
Shanhuang Chen
Shengfeng Ye
Shiyu Wang
Shuiping Yu
Shunfeng Zhou
Shuting Pan
S. S. Li
Shuang Zhou
Shao-Ping Wu
Tao Yun
Tian Pei
Tianyu Sun
T. Wang
Wangding Zeng
Wanjia Zhao
Wen Liu
Wenfeng Liang
Wenjun Gao
Wen-Xuan Yu
Wentao Zhang
Wei Xiao
Wei An
Xiaodong Liu
Xiaohan Wang
Xiaokang Chen
Xiaotao Nie
Xin Cheng
Jian Li
Xinfeng Xie
Xingchao Liu
Xinyu Yang
Xinyuan Li
Xuecheng Su
Xuheng Lin
Xiangyu Jin
Xi-Cheng Shen
Xiaosha Chen
Xiaowen Sun
Xiaoxi-ang Wang
Xinnan Song
Xinyi Zhou
Xianzu Wang
Xinxia Shan
Y. K. Li
Y. Q. Wang
Y. X. Wei
Yang Zhang
Yanhong Xu
Yao Zhao
Yaofeng Sun
Yaohui Wang
Yi Yu
Yichao Zhang
Yifan Shi
Yi Xiong
Ying He
Yishi Piao
Yisong Wang
Yi Chern Tan
Yiyang Ma
Yiyuan Liu
Yongqiang Guo
Yuan Ou
Yuduan Wang
Yue Gong
Yuheng Zou
Yuzi He
Yunfan Xiong
Yuxiang Luo
Yuxiang You
Yu-mei You
Yuxuan Liu
Yuyang Zhou
Y. X. Zhu
Yanping Huang
Yaohui Li
Yao Li
Yi Zheng
Yunxiang Ma
Ying Tang
Yukun Zha
Yuting Yan
Z. Z. Ren
Zehui Ren
Zhangli Sha
Zhe Fu
Zhean Xu
Zhenda Xie
Zhengyan Zhang
Zhewen Hao
Zhicheng Ma
Zhigang Yan
Zhiyu Wu
Zihui Gu
Zijia Zhu
Zijun Liu
Zi-An Li
Ziwei Xie
Ziyang Song
Deep Ganguli
Liane Lovitt
Jackson Kernion
Amanda Askell
Yuntao Bai
Saurav Kadavath
Benjamin Mann
Ethan Perez
Nicholas Schiefer
Kamal Ndousse
Andy Jones
Sam Bowman
Anna Chen
Tom Con-erly
Nova Dassarma
Dawn Drain
Nelson Elhage Sheer
Stanislav Fort
Zac Hatfield-Dodds
T. Henighan
Danny Hernandez
Tristan Hume
Josh Jacobson
Scott Johnston
Shauna Kravec
Catherine Olsson
Sam Ringer
Eli Tran-Johnson
Dario Amodei
Tom Brown
Nicholas Joseph
Sam McCandlish
Chris Olah
Jared Kaplan
Jack Clark. 2022. Red
Aaron Grattafiori
Abhimanyu Dubey
Abhinav Jauhri
Abhinav Pandey
Abhishek Kadian
Ahmad Al-Dahle
Aiesha Letman
Akhil Mathur
Alan Schel-ten
Alex Vaughan
Amy Yang
Angela Fan
Anirudh Goyal
A. Hartshorn
Aobo Yang
Archi Mitra
Archie Sravankumar
Artem Korenev
Arthur Hinsvark
Arun Rao
Aston Zhang
Aurelien Ro-driguez
Austen Gregerson
Ava Spataru
Baptiste Rozière
Bethany Biron
Binh Tang
Bobbie Chern
Charlotte Caucheteux
Chaya Nayak
Chloe Bi
Chris Marra
Chris McConnell
Christian Keller
Christophe Touret
Chunyang Wu
Corinne Wong
Cris-tian Cantón Ferrer
Cyrus Nikolaidis
Damien Al-lonsius
Daniel Song
Danielle Pintz
Danny Livshits
Danny Wyatt
David Esiobu
Dhruv Choudhary
Dhruv Mahajan 0001
Diego Garcia-Olano
Diego Perino
Dieuwke Hupkes
Egor Lakomkin
Ehab A. AlBadawy
Elina Lobanova
Emily Dinan
Eric Michael Smith
Filip Radenovic
Francisco Guzmán
Frank Zhang
Gabriele Synnaeve
Gabrielle Lee
Georgia Lewis
G. Thattai
Graeme Nail
Gregoire Mi-alon
Guan Pang
Guillem Cucurell
Hailey Nguyen
Han-nah Korevaar
Hu Xu
Hugo Touvron
Imanol Iliyan Zarov
Arrieta Ibarra
Is-abel Kloumann
Ishan Misra
Ivan Evtimov
Jack Zhang
Jade Copet
Jaewon Lee
Jan Geffert
Jana Vranes
Jason Park
Jay Mahadeokar
Jeet Shah
Jelmer van der Linde
Jennifer Billock
Jenny Hong
Jenya Lee
Jeremy Fu
J. Fu
Jianfeng Chi
Jianyu Huang
Jiawen Liu
Jie Wang
Jiecao Yu
Joanna Bitton
Joe Spisak
Jongsoo Park
Joseph Rocca
J. Johnstun
Joshua Saxe
Junteng Jia
Kalyan Vasuden Alwala
Karthik Prasad
Kartikeya Upasani
Kate Plawiak
Keqian Li
K. Heafield
Kevin R. Stone
Khalid El-Arini
Krithika Iyer
Kshitiz Malik
Kuen-ley Chiu
Kunal Bhalla
Kushal Lakhotia
Lauren Rantala-Yeary
Laurens van der Maaten
Lawrence Chen
Liang Tan
Liz Jenkins
Louis Martin
Lovish Madaan
Lubo Malo
Lukas Blecher
Lukas Landzaat
Luke de Oliveira
Madeline Muzzi
Mahesh Pasupuleti
Mannat Singh
Manohar Paluri
Marcin Kardas
Maria Tsimpoukelli
Mathew Oldham
Mathieu Rita
Maya Pavlova
Melanie Kam-badur
Mike Lewis
Mitesh Min Si
Kumar Singh
Mona Hassan
Naman Goyal
Narjes Torabi
Niko-lay Bashlykov
Nikolay Bogoychev
Niladri S. Chatterji
Ning Zhang
Olivier Duchenne
Onur Çelebi
Patrick Alrassy
Petar Pengwei Li
Peter Weng
Prajjwal Bhargava
Pratik Dubal
Punit Praveen Krishnan
Singh Koura
Puxin Xu
Qing He
Qingxiao Dong
Ragavan Srinivasan
Raj Ganapathy
Ramon Calderer
Ricardo Silveira Cabral
Robert Stojnic
Roberta Raileanu
Rohan Maheswari
Rohit Girdhar
Rohit Patel
Ro-main Sauvestre
Ron-nie Polidoro
Roshan Sumbaly
Ross Taylor
Ruan Silva
Rui Hou
Rui Wang
S. Hosseini
Sa-hana Chennabasappa
Sanjay Singh
Sean Bell
Seo-hyun Sonia Kim
Sergey Edunov
Shaoliang Nie
Sharan Narang
Sharath Chandra Raparthy
Sheng Shen
Shengye Wan
Shruti Bhosale
Shun Zhang
Simon Van-denhende
Soumya Batra
Spencer Whitman
Sten Sootla
Stephane Collot
Suchin Gururangan
S. Borodinsky
Tamar Herman
Tara Fowler
Tarek Sheasha
Thomas Georgiou
Thomas Scialom
Tobias Speckbacher
Todor Mihaylov
Tong Xiao
Ujjwal Karn
Vedanuj Goswami
Vibhor Gupta
Vignesh Ramanathan
Viktor Kerkez
Vincent Gonguet
Vir-ginie Do
Vish Vogeti
Vitor Albiero
Vladan Petro-vic
Weiwei Chu
Wenhan Xiong
Wenyin Fu
2025-05-28
ArXiv (preprint)
doi.org
arxiv.org
One Demo Is All It Takes: Planning Domain Derivation with LLMs from A Single Demonstration
Jinbang Huang
Yixin Xiao
Zhanguang Zhang
Mark Coates
Jianye Hao
Yingxue Zhang
Pre-trained Large Language Models (LLMs) have shown promise in solving planning problems but often struggle to ensure plan correctness, espe… (see more)cially for long-horizon tasks. Meanwhile, traditional robotic task and motion planning (TAMP) frameworks address these challenges more reliably by combining high-level symbolic search with low-level motion planning. However, TAMP relies on the availability of planning domains that typically involve substantial manual effort and domain expertise, limiting its generalizability. We introduce Planning Domain Derivation with LLMs (PDDLLM), a novel approach that combines simulated physical interaction with LLM reasoning to improve planning performance. The method reduces reliance on humans by inferring planning domains from a single annotated task-execution demonstration. Unlike prior domain-inference methods that rely on partially predefined or language descriptions of planning domains, PDDLLM constructs domains entirely from scratch and automatically integrates them with low-level motion planning skills, enabling fully automated long-horizon planning. PDDLLM is evaluated on over 1,200 diverse tasks spanning nine environments and benchmarked against six LLM-based planning baselines, demonstrating superior planning performance, lower token costs, and successful deployment on multiple robot platforms.
2025-05-28
thecvf.com/CVPR/2025/Workshop/FMEA (oral)
openreview.net
openreview.net
Artificial Neural Networks for Magnetoencephalography: A review of an emerging field
Arthur Dehgan
Hamza Abdelhedi
Vanessa Hadid
Irina Rish
Karim Jerbi
Magnetoencephalography (MEG) is a cutting-edge neuroimaging technique that measures the intricate brain dynamics underlying cognitive proces… (see more)ses with an unparalleled combination of high temporal and spatial precision. MEG data analytics has always relied on advanced signal processing and mathematical and statistical tools for various tasks ranging from data cleaning to probing the signals' rich dynamics and estimating the neural sources underlying the surface-level recordings. Like in most domains, the surge in Artificial Intelligence (AI) has led to the increased use of Machine Learning (ML) methods for MEG data classification. More recently, an emerging trend in this field is using Artificial Neural Networks (ANNs) to address many MEG-related tasks. This review provides a comprehensive overview of how ANNs are being used with MEG data from three vantage points: First, we review work that employs ANNs for MEG signal classification, i.e., for brain decoding. Second, we report on work that has used ANNs as putative models of information processing in the human brain. Finally, we examine studies that use ANNs as techniques to tackle methodological questions in MEG, including artifact correction and source estimation. Furthermore, we assess the current strengths and limitations of using ANNs with MEG and discuss future challenges and opportunities in this field. Finally, by establishing a detailed portrait of the field and providing practical recommendations for the future, this review seeks to provide a helpful reference for both seasoned MEG researchers and newcomers to the field who are interested in using ANNs to enhance the exploration of the complex dynamics of the human brain with MEG.
2025-05-27
Journal of Neural Engineering (published)
doi.org
arxiv.org
Charting the Landscape of African NLP: Mapping Progress and Shaping the Road Ahead
Jesujoba Oluwadara Alabi
Michael A. Hedderich
David Ifeoluwa Adelani
Dietrich Klakow
2025-05-27
ArXiv (preprint)
doi.org
arxiv.org
Combining cortical and spinal stimulation maximizes improvement of gait after spinal cord injury
Roxanne Drainville
Marco Bonizzato
Davide Burchielli
Rose Guay-Hottin
Alexandre Sheasby
Marina Martinez
2025-05-27
bioRxiv (preprint)
doi.org
A Python Toolbox for Representational Similarity Analysis
Jasper JF van den Bosch
Tal Golan
Benjamin Peters
JohnMark Taylor
Mahdiyar Shahbazi
Baihan Lin
Ian Charest
Jörn Diedrichsen
Nikolaus Kriegeskorte
Marieke Mur
Heiko H. Schütt
2025-05-27
bioRxiv (preprint)
doi.org
Quantifying antimicrobial resistance in food-producing animals in North America
Mohamed Mediouni
Abdoulaye Banire Diallo
Vladimir Makarenkov
The global misuse of antimicrobial medication has further exacerbated the problem of antimicrobial resistance (AMR), enriching the pool of g… (see more)enetic mechanisms previously adopted by bacteria to evade antimicrobial drugs. AMR can be either intrinsic or acquired. It can be acquired either by selective genetic modification or by horizontal gene transfer that allows microorganisms to incorporate novel genes from other organisms or environments into their genomes. To avoid an eventual antimicrobial mistreatment, the use of antimicrobials in farm animal has been recently reconsidered in many countries. We present a systematic review of the literature discussing the cases of AMR and the related restrictions applied in North American countries (including Canada, Mexico, and the USA). The Google Scholar, PubMed, Embase, Web of Science, and Cochrane databases were searched to find plausible information on antimicrobial use and resistance in food-producing animals, covering the time period from 2015 to 2024. A total of 580 articles addressing the issue of antibiotic resistance in food-producing animals in North America met our inclusion criteria. Different AMR rates, depending on the bacterium being observed, the antibiotic class being used, and the farm animal being considered, have been identified. We determined that the highest average AMR rates have been observed for pigs (60.63% on average), the medium for cattle (48.94% on average), and the lowest for poultry (28.43% on average). We also found that Cephalosporines, Penicillins, and Tetracyclines are the antibiotic classes with the highest average AMR rates (65.86%, 61.32%, and 58.82%, respectively), whereas the use of Sulfonamides and Quinolones leads to the lowest average AMR (21.59% and 28.07%, respectively). Moreover, our analysis of antibiotic-resistant bacteria shows that Streptococcus suis (S. suis) and S. auerus provide the highest average AMR rates (71.81% and 69.48%, respectively), whereas Campylobacter spp. provides the lowest one (29.75%). The highest average AMR percentage, 57.46%, was observed in Mexico, followed by Canada at 45.22%, and the USA at 42.25%, which is most probably due to the presence of various AMR control strategies, such as stewardship programs and AMR surveillance bodies, existing in Canada and the USA. Our review highlights the need for better strategies and regulations to control the spread of AMR in North America.
2025-05-27
Frontiers in Microbiology (published)
doi.org