Simulation of the Background from $^{13}$C$(\alpha, n)^{16}$O Reaction in the JUNO Scintillator
Juno Collaboration Thomas Adam
Kai Adamowicz
Shakeel Ahmad
Rizwan Ahmed
Sebastiano Aiello
Fengpeng An
C. Andreopoulos
Giuseppe Andronico
Nikolay Anfimov
Vito Antonelli
Tatiana Antoshkina
João Pedro Athayde Marcondes de André
Didier Auguste
Weidong Bai
Nikita Balashov
Andrea Barresi
Davide Basilico
Eric Baussan
Marco Beretta
Antonio Bergnoli … (see 481 more)
Nikita Bessonov
Daniel Bick
Lukas Bieger
Svetlana Biktemerova
Thilo Birkenfeld
Simon Blyth
Anastasia Bolshakova
Mathieu Bongrand
Matteo Borghesi
Dominique Breton
Augusto Brigatti
Riccardo Brugnera
Riccardo Bruno
Marcel Buchner
Antonio Budano
Jose Busto
Anatael Cabrera
Barbara Caccianiga
Hao Cai
Xiao Cai
Yanke Cai
Zucong Cai
Stéphane Callier
Steven Calvez
Antonio Cammi
C. Cao
Guofu Cao
Jun Cao
Yaoqi Cao
Rossella Caruso
Cédric Cerna
Vanessa Cerrone
Jinfan Chang
Yunling Chang
Auttakit Chatrabhuti
Chao Chen
Guoming Chen
Jiahui Chen
Jian Chen
Jing Chen
Junyou Chen
Pingping Chen
Shaomin Chen
Shiqiang Chen
Xin Chen
Yiming Chen
Yixue Chen
Yu Chen
Ze Chen
Zhangming Chen
Zhiyuan Chen
Jie Cheng
Yaping Cheng
Yuanyuan Zhang
Alexander Chepurnov
Alexey Chetverikov
Davide Chiesa
Pietro Chimenti
Po-Lin Chou
Ziliang Chu
Artem Chukanov
Gérard Claverie
Catia Clementi
Barbara Clerbaux
C. Coletta
Selma Conforti Di Lorenzo
Simon Csakli
Chenyang Cui
Olivia Dalager
C. Taille
Zhi Deng
Ziyan Deng
Xiaoyu Ding
Xuefeng Ding
Yayun Ding
Bayu Dirgantara
Carsten Dittrich
Sergey Dmitrievsky
David Doerflinger
Dmitry Dolzhikov
Haojie Dong
Jianmeng Dong
Evgeny Doroshkevich
Marcos Dracos
Frédéric Druillole
Ran Du
Shuxian Du
Yujie Duan
K. Dugas
Stefano Dusini
Hongyue Duyang
J. Eck
Timo Enqvist
Andrea Fabbri
Ulrike Fahrendholz
Lei Fan
Jian Fang
W. X. Fang
Dmitry Fedoseev
Li-Cheng Feng
Qichun Feng
Federico Ferraro
Daniela Fetzer
Marcellin Fotz'e
Amélie Fournier
Aaron Freegard
Feng Gao
Alberto Garfagnini
Arsenii Gavrikov
Marco Giammarchi
Nunzio Giudice
Maxim Gonchar
Guanghua Gong
Hui Gong
Yuri Gornushkin
Marco Grassi
Maxim Gromov
Vasily Gromov
Minghao Gu
X. Gu
Yunting Gu
M. Guan
Yuduo Guan
Nunzio Guardone
Rosa Maria Guizzetti
Cong Guo
Wanlei Guo
Caren Hagner
Hechong Han
Ran Han
Yang Han
Jinhong He
Miao He
Wei He
Xinhai He
Ziou He
Tobias Heinz
Patrick Hellmuth
Yuekun Heng
Yuenkeung Hor
Shaojing Hou
Yee Hsiung
Bei-Zhen Hu
Hang Hu
Jun Hu
T. Hu
Yuxiang Hu
Guihong Huang
Jinhao Huang
Jun-Hao Huang
Kai Huang
Shengheng Huang
Tao Huang
Xingtao Huang
Yongbo Huang
Jiaqi Hui
Lei Huo
Cédric Huss
Safeer Hussain
Leonard Imbert
Ara Ioannisian
Adrienne Jacobi
Arshak Jafar
Beatrice Jelmini
Xiangpan Ji
Xiaolu Ji
Huihui Jia
Junji Jia
Cailian Jiang
Wei Jiang
Xiaoshan Jiang
Xiaozhao Jiang
Yi-Nong Jiang
Yixuan Jiang
Xiao-Ying Jing
Cécile Jollet
Li Kang
Rebin Karaparabil
Narine Kazarian
Ali Khan
Amina Khatun
Khanchai Khosonthongkee
Denis Korablev
Konstantin Kouzakov
Alexey Krasnoperov
Sergey Kuleshov
S. Kumaran
Nikolay Kutovskiy
Loïc Labit
Tobias Lachenmaier
Haojing Lai
Cecilia Landini
Sébastien Leblanc
M. Lecocq
Frederic Lefevre
Rui Li
Rupert Leitner
Jason Leung
Demin Li
Fule Li
Gaosong Li
Hongjian Li
Huang Li
Jiajun Li
Min Li
Nan Li
Qingjiang Li
Ruhui Li
Ruiting Lei
Shanfeng Li
Tao Li
Teng Li
Weidong Li
Xiaonan Li
Yi Li
Yichen Li
Yifan Li
Yufeng Li
Zhaohan Li
Zhibing Li
Zifeng Li
Zonghai Li
An-An Liang
Jiajun Liao
Minghua Liao
Yilin Liao
Ayut Limphirat
Bohan Lin
Guey-Lin Lin
Shengxin Lin
Tao Lin
Xianhao Lin
Xingyi Lin
Jiajie Ling
Xin Ling
Ivano Lippi
Caimei Liu
Yang Liu
Feng Liu
Haidong Liu
Haotian Liu
Hongbang Liu
Hongjuan Liu
Hongtao Liu
Hongyang Liu
Jianglai Liu
Jiaxi Liu
Jinchang Liu
Kainan Liu
Min Liu
Qian Liu
Runxuan Liu
Shenghui Liu
Shulin Liu
Xiaowei Liu
Xiwen Liu
Xuewei Liu
Yankai Liu
Zhen Liu
Lorenzo Loi
Alexey Lokhov
Paolo Lombardi
Claudio Lombardo
Kai Loo
Haoqi Lu
Junguang Lu
Meishu Lu
Peizhi Lu
Shu-Min Lu
Xianguo Lu
Bayarto Lubsandorzhiev
Sultim Lubsandorzhiev
Livia Ludhova
Arslan Lukanov
F. Luo
Guang Luo
Jianyi Luo
Shu Luo
Wuming Luo
Xiaojie Luo
Vladimir Lyashuk
B. Ma
Bangzheng Ma
Bing Ma
R. Q. Ma
Si Ma
W.Y. Ma
Wing Yan Ma
Xiaoyan Ma
Xubo Ma
Jihane Maalmi
Jingyu Mai
Marco Malabarba
Yury Malyshkin
Roberto Carlos Mandujano
Fabio Mantovani
Xin Mao
S. M. Mari
Agnese Martini
Matthias Mayer
Davit Mayilyan
Yu Meng
Anselmo Meregaglia
Lino Miramonti
Marta Colomer Molla
Michele Montuschi
Cristobal Morales Reveco
Iwan Morton-blake
M. Nastasi
Dmitry V. Naumov
Elena Naumova
Igor Nemchenok
Elisabeth Neuerburg
Minh Thuan Nguyen Thi
Alexey Nikolaev
F. Ning
Zhe Ning
Yujie Niu
Hiroshi Nunokawa
Juan Pedro Ochoa-Ricoux
Sebastian Olivares
Alexander Olshevskiy
Domizia Orestano
Fausto Ortica
Rainer Othegraven
Yifei Pan
A. Paoloni
George Parker
Y. P. Pei
Luca Pelicci
Anguo Peng
Yuefeng Peng
Zhaoyuan Peng
Z-R Peng
Elisa Percalli
Willy Perrin
Frédéric Perrot
P. Petitjean
Fabrizio Petrucci
Oliver Pilarczyk
Artyom Popov
Pascal Poussot
Ezio Previtali
F. Qi
M. Qi
Xiaohui Qi
Sen Qian
X. Qian
Zhonghua Qin
S. Qiu
Manhao Qu
Zhe Qu
Gioacchino Ranucci
Thomas Raymond
A. Re
Abdel Rebii
Mariia Redchuk
Bin Ren
Yuhan Ren
Barbara Ricci
Komkrit Rientong
Mariam Rifai
Mathieu Roche
Narongkiat Rodphai
Fernanda de Faria Rodrigues
Aldo Romani
Bedřich Roskovec
Arseniy Rybnikov
Andrey Sadovsky
Paolo Saggese
Deshan Sandanayake
Anut Sangka
G. Sava
Utane Sawangwit
Michaela Schever
Cédric Schwab
Konstantin Schweizer
Alexandr Selyunin
Andrea Serafini
M. Settimo
Junyu Shao
V. Sharov
Hangyu Shi
Hexi Shi
Jingyang Shi
Yanan Shi
Vitaly Shutov
Andrey Sidorenkov
Fedor Šimkovic
Apeksha Singhal
Chiara Sirignano
Jaruchit Siripak
Monica Sisti
Oleg Smirnov
Sergey Sokolov
Julanan Songwadhana
Boonrucksar Soonthornthum
Albert Sotnikov
Warintorn Sreethawong
Achim Stahl
Luca Stanco
E. S. Farilla
Konstantin Stankevich
Hans Steiger
Jochen Steinmann
Tobias Sterr
Virginia Strati
Mikhail Strizh
Alexander Studenikin
Aoqi Su
Jun Su
Guangbao Sun
Mingxia Sun
Shifeng Sun
Xilei Sun
Yongzhao Sun
Zhengyang Sun
Narumon Suwonjandee
Akira Takenaka
Xiaohan Tan
Jingzhe Tang
Qiang Tang
Quan Tang
Xiaodong Tang
Vidhya Thara Hariharan
Yuxin Tian
Igor Tkachev
Tomas Tmej
M. Torri
Andrea Triossi
Wladyslaw Trzaska
Yu-Chen Tung
Cristina Tuve
Nikita Ushakov
Carlo Venettacci
Giuseppe Verde
Maxim Vialkov
Benoit Viaud
Cornelius Moritz Vollbrecht
Vit Vorobel
Dmitriy Voronin
Lucia Votano
Caishen Wang
Chung-Hsiang Wang
En Wang
Y. H. Wang
Jiabin Wang
Jun Wang
Li Wang
Meng Wang
Mingyuan Wang
Qianchuan Wang
Ruiguang Wang
Sibo Wang
Tianhong Wang
Wei Wang
Wenshuai Wang
Xi Wang
Yangfu Wang
Yaoguang Wang
Yi Wang
Yifang Wang
Yuan Wang
Yuyi Wang
Zhe Wang
Zheng Wang
Zhimin Wang
Apimook Watcharangkool
Wei Wei
Yadong Wei
Yuehuan Wei
Zhengbao Wei
Kaile Wen
Jun Weng
Christopher Wiebusch
Rosmarie Wirth
Bi Wu
Chengxin Wu
Diru Wu
Qun Wu
AI Automatons: AI Systems Intended to Imitate Humans
Solon Barocas
Su Lin Blodgett
Lisa Egede
Alicia DeVrio
Myra Cheng
There is a growing proliferation of AI systems designed to mimic people's behavior, work, abilities, likenesses, or humanness -- systems we … (see more)dub AI automatons. Individuals, groups, or generic humans are being simulated to produce creative work in their styles, to respond to surveys in their places, to probe how they would use a new system before deployment, to provide users with assistance and companionship, and to anticipate their possible future behavior and interactions with others, just to name a few applications. The research, design, deployment, and availability of such AI systems have, however, also prompted growing concerns about a wide range of possible legal, ethical, and other social impacts. To both 1) facilitate productive discussions about whether, when, and how to design and deploy such systems, and 2) chart the current landscape of existing and prospective AI automatons, we need to tease apart determinant design axes and considerations that can aid our understanding of whether and how various design choices along these axes could mitigate -- or instead exacerbate -- potential adverse impacts that the development and use of AI automatons could give rise to. In this paper, through a synthesis of related literature and extensive examples of existing AI systems intended to mimic humans, we develop a conceptual framework to help foreground key axes of design variations and provide analytical scaffolding to foster greater recognition of the design choices available to developers, as well as the possible ethical implications these choices might have.
Beyond Cosine Decay: On the effectiveness of Infinite Learning Rate Schedule for Continual Pre-training
Vaibhav Singh
Paul Janson
Paria Mehrbod
Adam Ibrahim
Benjamin Thérien
The ever-growing availability of unlabeled data presents both opportunities and challenges for training artificial intelligence systems. Whi… (see more)le self-supervised learning (SSL) has emerged as a powerful paradigm for extracting meaningful representations from vast amounts of unlabeled data, existing methods still struggle to adapt to the non-stationary, non-IID nature of real-world data streams without forgetting previously learned knowledge. Recent works have adopted a repeated cosine annealing schedule for large-scale continual pre-training; however, these schedules (1) inherently cause forgetting during the re-warming phase and (2) have not been systematically compared to existing continual SSL methods. In this work, we systematically compare the widely used cosine schedule with the recently proposed infinite learning rate schedule and empirically find the latter to be a more effective alternative. Our extensive empirical evaluation across diverse image and language datasets demonstrates that the infinite learning rate schedule consistently enhances continual pre-training performance compared to a repeated cosine decay without being restricted to a fixed iteration budget. For instance, in a small-scale MAE pre-training setup, it outperforms several strong baselines from the literature. We then scale up our experiments to larger MAE pre-training and autoregressive language model pre-training. Our results show that the infinite learning rate schedule remains effective at scale, surpassing repeated cosine decay for both MAE pre-training and zero-shot LM benchmarks.
Continual Pre-training of MoEs: How robust is your router?
Benjamin Thérien
Charles-Étienne Joseph
Zain Sarwar
Ashwinee Panda
Anirban Das
Shi-Xiong Zhang
Stephen Rawls
Sambit Sahu
DialEgg: Dialect-Agnostic MLIR Optimizer using Equality Saturation with Egglog
Abd-El-Aziz Zayed
MLIR’s ability to optimize programs at multiple levels of abstraction is key to enabling domain-specific optimizing compilers. However, ex… (see more)pressing optimizations remains tedious. Optimizations can interact in unexpected ways, making it hard to unleash full performance. Equality saturation promises to solve these challenges. First, it simplifies the expression of optimizations using rewrite rules. Secondly, it considers all possible optimization interactions, through saturation, selecting the best program variant. Despite these advantages, equality saturation remains absent from production compilers such as MLIR. This paper proposes to integrate Egglog, a recent equality saturation engine, with MLIR, in a dialect-agnostic manner. This paper shows how the main MLIR constructs such as operations, types or attributes can be modeled in Egglog. It also presents DialEgg, a tool that pre-defines a large set of common MLIR constructs in Egglog and automatically translates between the MLIR and Egglog program representations. This paper uses a few use cases to demonstrate the potential for combining equality saturation and MLIR.
Ensemble machine learning to accelerate industrial decarbonization: Prediction of Hansen solubility parameters for streamlined chemical solvent selection
Eslam G. Al-Sakkari
Ahmed Ragab
Mostafa Amer
Olumoye Ajao
Marzouk Benali
Daria C. Boffito
Mouloud Amazouz
Exploiting Instruction-Following Retrievers for Malicious Information Retrieval
Parishad BehnamGhader
Nicholas Meade
Instruction-following retrievers have been widely adopted alongside LLMs in real-world applications, but little work has investigated the sa… (see more)fety risks surrounding their increasing search capabilities. We empirically study the ability of retrievers to satisfy malicious queries, both when used directly and when used in a retrieval augmented generation-based setup. Concretely, we investigate six leading retrievers, including NV-Embed and LLM2Vec, and find that given malicious requests, most retrievers can (for >50% of queries) select relevant harmful passages. For example, LLM2Vec correctly selects passages for 61.35% of our malicious queries. We further uncover an emerging risk with instruction-following retrievers, where highly relevant harmful information can be surfaced by exploiting their instruction-following capabilities. Finally, we show that even safety-aligned LLMs, such as Llama3, can satisfy malicious requests when provided with harmful retrieved passages in-context. In summary, our findings underscore the malicious misuse risks associated with increasing retriever capability.
Feynman-Kac Correctors in Diffusion: Annealing, Guidance, and Product of Experts
Marta Skreta
Tara Akhound-Sadegh
Viktor Ohanesian
Roberto Bondesan
Alan Aspuru-Guzik
Arnaud Doucet
Rob Brekelmans
Alexander Tong
While score-based generative models are the model of choice across diverse domains, there are limited tools available for controlling infere… (see more)nce-time behavior in a principled manner, e.g. for composing multiple pretrained models. Existing classifier-free guidance methods use a simple heuristic to mix conditional and unconditional scores to approximately sample from conditional distributions. However, such methods do not approximate the intermediate distributions, necessitating additional 'corrector' steps. In this work, we provide an efficient and principled method for sampling from a sequence of annealed, geometric-averaged, or product distributions derived from pretrained score-based models. We derive a weighted simulation scheme which we call Feynman-Kac Correctors (FKCs) based on the celebrated Feynman-Kac formula by carefully accounting for terms in the appropriate partial differential equations (PDEs). To simulate these PDEs, we propose Sequential Monte Carlo (SMC) resampling algorithms that leverage inference-time scaling to improve sampling quality. We empirically demonstrate the utility of our methods by proposing amortized sampling via inference-time temperature annealing, improving multi-objective molecule generation using pretrained models, and improving classifier-free guidance for text-to-image generation. Our code is available at https://github.com/martaskrt/fkc-diffusion.
Implicit Generative Modeling by Kernel Similarity Matching
Shubham Choudhary
Demba Ba
Implicit Generative Modeling by Kernel Similarity Matching
Shubham Choudhary
Demba Ba
Understanding how the brain encodes stimuli has been a fundamental problem in computational neuroscience. Insights into this problem have le… (see more)d to the design and development of artificial neural networks that learn representations by incorporating brain-like learning abilities. Recently, learning representations by capturing similarity between input samples has been studied to tackle this problem. This approach, however, has thus far been used to only learn downstream features from an input and has not been studied in the context of a generative paradigm, where one can map the representations back to the input space, incorporating not only bottom-up interactions (stimuli to latent) but also learning features in a top-down manner (latent to stimuli). We investigate a kernel similarity matching framework for generative modeling. Starting with a modified sparse coding objective for learning representations proposed in prior work, we demonstrate that representation learning in this context is equivalent to maximizing similarity between the input kernel and a latent kernel. We show that an implicit generative model arises from learning the kernel structure in the latent space and show how the framework can be adapted to learn manifold structures, potentially providing insights as to how task representations can be encoded in the brain. To solve the objective, we propose a novel Alternate Direction Method of Multipliers (ADMM) based algorithm and discuss the interpretation of the optimization process. Finally, we discuss how this representation learning problem can lead towards a biologically plausible architecture to learn the model parameters that ties together representation learning using similarity matching (a bottom-up approach) with predictive coding (a top-down approach).
Improving clustering quality evaluation in noisy Gaussian mixtures
Renato Cordeiro De Amorim
Improving clustering quality evaluation in noisy Gaussian mixtures
Renato Cordeiro De Amorim