Tootfinder

Opt-in global Mastodon full text search. Join the index!

@Techmeme@techhub.social
2025-08-07 17:19:27

OpenAI says GPT-5 is its first "unified" AI model and combines the reasoning abilities of its o-series of models with the fast responses of its GPT series (Maxwell Zeff/TechCrunch)
techcrunch.com/2025/08/07/open

@arXiv_hepth_bot@mastoxiv.page
2025-10-07 09:12:32

Fluctuations of the AdS3 C-metric
Shaohua Xue, Yuxuan Liu, Li-xin Li
arxiv.org/abs/2510.04054 arxiv.org/pdf/2510.04054

@arXiv_csLO_bot@mastoxiv.page
2025-10-06 07:47:49

Axiomatisation for an asynchronous epistemic logic with sending and receiving messages
Philippe Balbiani, Hans van Ditmarsch, Clara Lerouvillois
arxiv.org/abs/2510.02890

@arXiv_csCV_bot@mastoxiv.page
2025-08-06 10:44:20

OmniShape: Zero-Shot Multi-Hypothesis Shape and Pose Estimation in the Real World
Katherine Liu, Sergey Zakharov, Dian Chen, Takuya Ikeda, Greg Shakhnarovich, Adrien Gaidon, Rares Ambrus
arxiv.org/abs/2508.03669

@arXiv_quantph_bot@mastoxiv.page
2025-10-06 10:06:19

Absence of quantum Darwinism as a resource in secure quantum communication and computation
Bishal Kumar Das, Sourav Manna, Vaibhav Madhok
arxiv.org/abs/2510.03225

@arXiv_csCL_bot@mastoxiv.page
2025-10-06 10:15:09

Time-To-Inconsistency: A Survival Analysis of Large Language Model Robustness to Adversarial Attacks
Yubo Li, Ramayya Krishnan, Rema Padman
arxiv.org/abs/2510.02712

@arXiv_csAI_bot@mastoxiv.page
2025-09-05 09:55:31

World Model Implanting for Test-time Adaptation of Embodied Agents
Minjong Yoo, Jinwoo Jang, Sihyung Yoon, Honguk Woo
arxiv.org/abs/2509.03956

@tiotasram@kolektiva.social
2025-07-30 17:56:35

Just read this post by @… on an optimistic AGI future, and while it had some interesting and worthwhile ideas, it's also in my opinion dangerously misguided, and plays into the current AGI hype in a harmful way.
social.coop/@eloquence/1149406
My criticisms include:
- Current LLM technology has many layers, but the biggest most capable models are all tied to corporate datacenters and require inordinate amounts of every and water use to run. Trying to use these tools to bring about a post-scarcity economy will burn up the planet. We urgently need more-capable but also vastly more efficient AI technologies if we want to use AI for a post-scarcity economy, and we are *not* nearly on the verge of this despite what the big companies pushing LLMs want us to think.
- I can see that permacommons.org claims a small level of expenses on AI equates to low climate impact. However, given current deep subsidies on place by the big companies to attract users, that isn't a great assumption. The fact that their FAQ dodges the question about which AI systems they use isn't a great look.
- These systems are not free in the same way that Wikipedia or open-source software is. To run your own model you need a data harvesting & cleaning operation that costs millions of dollars minimum, and then you need millions of dollars worth of storage & compute to train & host the models. Right now, big corporations are trying to compete for market share by heavily subsidizing these things, but it you go along with that, you become dependent on them, and you'll be screwed when they jack up the price to a profitable level later. I'd love to see open dataset initiatives SBD the like, and there are some of these things, but not enough yet, and many of the initiatives focus on one problem while ignoring others (fine for research but not the basis for a society yet).
- Between the environmental impacts, the horrible labor conditions and undercompensation of data workers who filter the big datasets, and the impacts of both AI scrapers and AI commons pollution, the developers of the most popular & effective LLMs have a lot of answer for. This project only really mentions environmental impacts, which makes me think that they're not serious about ethics, which in turn makes me distrustful of the whole enterprise.
- Their language also ends up encouraging AI use broadly while totally ignoring several entire classes of harm, so they're effectively contributing to AI hype, especially with such casual talk of AGI and robotics as if embodied AGI were just around the corner. To be clear about this point: we are several breakthroughs away from AGI under the most optimistic assumptions, and giving the impression that those will happen soon plays directly into the hands of the Sam Altmans of the world who are trying to make money off the impression of impending huge advances in AI capabilities. Adding to the AI hype is irresponsible.
- I've got a more philosophical criticism that I'll post about separately.
I do think that the idea of using AI & other software tools, possibly along with robotics and funded by many local cooperatives, in order to make businesses obsolete before they can do the same to all workers, is a good one. Get your local library to buy a knitting machine alongside their 3D printer.
Lately I've felt too busy criticizing AI to really sit down and think about what I do want the future to look like, even though I'm a big proponent of positive visions for the future as a force multiplier for criticism, and this article is inspiring to me in that regard, even if the specific project doesn't seem like a good one.

@arXiv_econTH_bot@mastoxiv.page
2025-08-06 07:55:30

An Evolutionary Analysis of Narrative Selection
Federico Innocenti, Roberto Rozzi
arxiv.org/abs/2508.03540 arxiv.org/pdf/2508.03540

@arXiv_mathCO_bot@mastoxiv.page
2025-09-05 09:01:51

On the $Z_q$-forcing number: computational approach and exact values
Aida Abiad, Maryam Moghaddas
arxiv.org/abs/2509.03967 arxiv.org/pdf/25…

@Techmeme@techhub.social
2025-08-05 14:31:01

Google DeepMind releases its Genie 3 model, which can generate 3D worlds from a prompt and has enough visual memory for a few minutes of continuous interaction (Jay Peters/The Verge)
theverge.com/news/718723/googl

@arXiv_csLG_bot@mastoxiv.page
2025-09-05 10:28:01

When three experiments are better than two: Avoiding intractable correlated aleatoric uncertainty by leveraging a novel bias--variance tradeoff
Paul Scherer, Andreas Kirsch, Jake P. Taylor-King
arxiv.org/abs/2509.04363

@arXiv_csIT_bot@mastoxiv.page
2025-08-05 08:51:00

Robust Detection of Planted Subgraphs in Semi-Random Models
Dor Elimelech, Wasim Huleihel
arxiv.org/abs/2508.02158 arxiv.org/pdf/2508.02158…

@arXiv_csCV_bot@mastoxiv.page
2025-10-06 10:07:19

PocketSR: The Super-Resolution Expert in Your Pocket Mobiles
Haoze Sun, Linfeng Jiang, Fan Li, Renjing Pei, Zhixin Wang, Yong Guo, Jiaqi Xu, Haoyu Chen, Jin Han, Fenglong Song, Yujiu Yang, Wenbo Li
arxiv.org/abs/2510.03012

@arXiv_csCL_bot@mastoxiv.page
2025-10-06 10:14:09

Uncertainty as Feature Gaps: Epistemic Uncertainty Quantification of LLMs in Contextual Question-Answering
Yavuz Bakman, Sungmin Kang, Zhiqi Huang, Duygu Nur Yaldiz, Catarina G. Bel\'em, Chenyang Zhu, Anoop Kumar, Alfy Samuel, Salman Avestimehr, Daben Liu, Sai Praneeth Karimireddy
arxiv.org/abs/2510.02671

@arXiv_qbioPE_bot@mastoxiv.page
2025-09-05 08:39:01

Sensitivity analysis of an epidemic model with a mass vaccination program of a homogeneous population
Ma. Cristina R. Bargo
arxiv.org/abs/2509.04188

@arXiv_eessSY_bot@mastoxiv.page
2025-10-06 08:22:39

Data-Driven Stochastic Distribution System Hardening Based on Bayesian Online Learning
Wenlong Shi, Hongyi Li, Zhaoyu Wang
arxiv.org/abs/2510.02485

@arXiv_quantph_bot@mastoxiv.page
2025-09-04 10:09:41

Identifiability and minimality bounds of quantum and post-quantum models of classical stochastic processes
Paul M. Riechers, Thomas J. Elliott
arxiv.org/abs/2509.03004

@arXiv_csCE_bot@mastoxiv.page
2025-08-05 07:32:09

Finance Agent Benchmark: Benchmarking LLMs on Real-world Financial Research Tasks
Antoine Bigeard, Langston Nashold, Rayan Krishnan, Shirley Wu
arxiv.org/abs/2508.00828

@arXiv_csSE_bot@mastoxiv.page
2025-09-03 09:49:33

Aligning Requirement for Large Language Model's Code Generation
Zhao Tian, Junjie Chen
arxiv.org/abs/2509.01313 arxiv.org/pdf/2509.0131…

@arXiv_csLO_bot@mastoxiv.page
2025-09-05 08:05:11

Simplicity Lies in the Eye of the Beholder: A Strategic Perspective on Controllers in Reactive Synthesis
Mickael Randour
arxiv.org/abs/2509.04129

@arXiv_csCL_bot@mastoxiv.page
2025-08-07 10:23:14

Unveiling the Landscape of Clinical Depression Assessment: From Behavioral Signatures to Psychiatric Reasoning
Zhuang Chen, Guanqun Bi, Wen Zhang, Jiawei Hu, Aoyun Wang, Xiyao Xiao, Kun Feng, Minlie Huang
arxiv.org/abs/2508.04531

@arXiv_csCY_bot@mastoxiv.page
2025-10-03 09:05:31

Small is Sufficient: Reducing the World AI Energy Consumption Through Model Selection
Tiago da Silva Barros, Fr\'ed\'eric Giroire, Ramon Aparicio-Pardo, Joanna Moulierac
arxiv.org/abs/2510.01889

@arXiv_condmatdisnn_bot@mastoxiv.page
2025-10-07 08:28:52

Learning Linear Regression with Low-Rank Tasks in-Context
Kaito Takanami, Takashi Takahashi, Yoshiyuki Kabashima
arxiv.org/abs/2510.04548 a…

@arXiv_csGR_bot@mastoxiv.page
2025-09-05 08:15:01

ContraGS: Codebook-Condensed and Trainable Gaussian Splatting for Fast, Memory-Efficient Reconstruction
Sankeerth Durvasula, Sharanshangar Muhunthan, Zain Moustafa, Richard Chen, Ruofan Liang, Yushi Guan, Nilesh Ahuja, Nilesh Jain, Selvakumar Panneer, Nandita Vijaykumar
arxiv.org/abs/2509.03775

@tante@tldr.nettime.org
2025-09-15 12:00:05

"The understanding that the total supremacy of the “data” discourse was always a problematic, neoliberal way of seeing and structuring the world, of legitimizing violence according to the needs of those in power."
(Original title: The “Data” Narrative eats itself)
tante.cc/2025/09/15/…

@arXiv_statME_bot@mastoxiv.page
2025-09-05 09:20:01

How many patients could we save with LLM priors?
Shota Arai, David Selby, Andrew Vargo, Sebastian Vollmer
arxiv.org/abs/2509.04250 arxiv.or…

@arXiv_physicssocph_bot@mastoxiv.page
2025-08-05 08:37:20

Collective contributions to polarization in political voting
Gavin Rees, Edward D. Lee
arxiv.org/abs/2508.02496 arxiv.org/pdf/2508.02496

@arXiv_astrophEP_bot@mastoxiv.page
2025-07-29 08:51:01

The Impact of Different Haze Types on the Atmosphere and Observations of Hot Jupiters: 3D Simulations of HD 189733b, HD209458b and WASP-39b
Mei Ting Mak, Denis Sergeev, Nathan Mayne, Maria Zamyatina, Maria E. Steinrueck, James Manners, Eric Hebrard, David K. Sing, Krisztian Kohary
arxiv.org/abs/2507.20366

@arXiv_csCR_bot@mastoxiv.page
2025-10-03 08:58:01

Evaluating the Robustness of a Production Malware Detection System to Transferable Adversarial Attacks
Milad Nasr, Yanick Fratantonio, Luca Invernizzi, Ange Albertini, Loua Farah, Alex Petit-Bianco, Andreas Terzis, Kurt Thomas, Elie Bursztein, Nicholas Carlini
arxiv.org/abs/2510.01676

@arXiv_csAI_bot@mastoxiv.page
2025-09-05 07:57:50

CausalARC: Abstract Reasoning with Causal World Models
Jacqueline Maasch, John Kalantari, Kia Khezeli
arxiv.org/abs/2509.03636 arxiv.org/pd…

@arXiv_csRO_bot@mastoxiv.page
2025-09-03 13:15:53

Fail2Progress: Learning from Real-World Robot Failures with Stein Variational Inference
Yixuan Huang, Novella Alvina, Mohanraj Devendran Shanthi, Tucker Hermans
arxiv.org/abs/2509.01746

@arXiv_csCL_bot@mastoxiv.page
2025-10-06 10:15:29

TravelBench : Exploring LLM Performance in Low-Resource Domains
Srinivas Billa, Xiaonan Jing
arxiv.org/abs/2510.02719 arxiv.org/pdf/2510.02…

@arXiv_csHC_bot@mastoxiv.page
2025-08-01 08:59:41

Toward the Autonomous AI Doctor: Quantitative Benchmarking of an Autonomous Agentic AI Versus Board-Certified Clinicians in a Real World Setting
Hashim Hayat, Maksim Kudrautsau, Evgeniy Makarov, Vlad Melnichenko, Tim Tsykunou, Piotr Varaksin, Matt Pavelle, Adam Z. Oskowitz
arxiv.org/abs/2507.22902

@arXiv_physicsoptics_bot@mastoxiv.page
2025-10-03 08:30:11

BIFROST: A First-Principles Model of Polarization Mode Dispersion in Optical Fiber
Patrick R. Banner, Steven L. Rolston, Joseph W. Britton
arxiv.org/abs/2510.01212

@arXiv_econGN_bot@mastoxiv.page
2025-09-03 08:14:33

Exploring Trade Openness and Logistics Efficiency in the G20 Economies: A Bootstrap ARDL Analysis of Growth Dynamics
Haibo Wang, Lutfu Sua
arxiv.org/abs/2509.00368

@Techmeme@techhub.social
2025-08-03 01:36:03

A profile of Robinhood CEO Vlad Tenev, whose personal fortune has surged 6x over the past year to $6.1B, as the company leans into tokenized stock derivatives (Nina Bambysheva/Forbes)
forbes.com/sites/ninabambyshev

@arXiv_csCV_bot@mastoxiv.page
2025-09-05 10:16:01

TriLiteNet: Lightweight Model for Multi-Task Visual Perception
Quang-Huy Che, Duc-Khai Lam
arxiv.org/abs/2509.04092 arxiv.org/pdf/2509.0409…

@arXiv_csDC_bot@mastoxiv.page
2025-09-03 08:24:53

DSDE: Dynamic Speculative Decoding with KLD Stability for Real-World Serving
Mingyu Yang, Jae-Young Choi, Kihyo Moon, Minsung Jang, Eunjoo Joen
arxiv.org/abs/2509.01083

@arXiv_hepph_bot@mastoxiv.page
2025-07-30 10:13:31

BSM: Extended Scalar Sectors
Tania Robens, Rui Santos
arxiv.org/abs/2507.21910 arxiv.org/pdf/2507.21910

@midtsveen@social.linux.pizza
2025-09-16 15:14:19

I have to agree with Hofmann, LSD really lets you connect with nature in a way that’s unlike anything else. It’s not just seeing trees or animals differently, it’s like the walls between you and the world around you come down, and you feel everything’s alive and connected.
That experience makes it impossible to ignore how fragile and important all of this is, the plants, animals, the earth itself, and us too. It’s a reminder that we’re part of something bigger, and that caring for natu…

Black and white photo of Albert Hofmann in a lab, holding a molecular model. Beside the photo is a quote: 'Through my LSD experience and my new picture of reality, I became aware of the wonder of creation, the magnificence of nature and of the animal and plant kingdom. I became very sensitive to what will happen to all this and all of us.' Albert Hofmann.
@arXiv_csLG_bot@mastoxiv.page
2025-09-04 10:33:31

LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence
Xingxuan Zhang, Gang Ren, Han Yu, Hao Yuan, Hui Wang, Jiansheng Li, Jiayun Wu, Lang Mo, Li Mao, Mingchao Hao, Ningbo Dai, Renzhe Xu, Shuyang Li, Tianyang Zhang, Yue He, Yuanrui Wang, Yunjia Zhang, Zijing Xu, Dongzhe Li, Fang Gao, Hao Zou, Jiandong Liu, Jiashuo Liu, Jiawei Xu, Kaijie Cheng, Kehan Li, Linjun Zhou, Qing Li, Shaohua Fan, Xiaoyu Lin, Xinyan Han, Xuanyue Li, Yan Lu, Yuan Xue, Yuanyuan Jiang, Zi…

@arXiv_csGT_bot@mastoxiv.page
2025-10-01 07:37:25

Information Design With Large Language Models
Paul Duetting, Safwan Hossain, Tao Lin, Renato Paes Leme, Sai Srivatsa Ravindranath, Haifeng Xu, Song Zuo
arxiv.org/abs/2509.25565

@arXiv_csAI_bot@mastoxiv.page
2025-07-31 07:31:41

CoEx -- Co-evolving World-model and Exploration
Minsoo Kim, Seung-won Hwang
arxiv.org/abs/2507.22281 arxiv.org/pdf/2507.22281

@arXiv_hepth_bot@mastoxiv.page
2025-09-29 10:09:57

Holographic defect CFTs with Dirichlet end-of-the-world branes
Haruki Nakayama, Tatsuma Nishioka
arxiv.org/abs/2509.22270 arxiv.org/pdf/250…

@arXiv_eessSY_bot@mastoxiv.page
2025-10-03 10:08:21

Game-theoretic Social Distancing in Competitive Bi-Virus SIS Epidemics
Benjamin Catalano, Keith Paarporn, Sebin Gracy
arxiv.org/abs/2510.02269

@arXiv_mathOC_bot@mastoxiv.page
2025-09-03 13:25:33

Bilevel Mixed-Integer Linear Program with Binary Tender
Bo Zhou, Ruiwei Jiang, Siqian Shen
arxiv.org/abs/2509.02370 arxiv.org/pdf/2509.0237…

@arXiv_csSD_bot@mastoxiv.page
2025-07-28 09:15:01

The Eloquence team submission for task 1 of MLC-SLM challenge
Lorenzo Concina, Jordi Luque, Alessio Brutti, Marco Matassoni, Yuchen Zhang
arxiv.org/abs/2507.19308

@arXiv_csRO_bot@mastoxiv.page
2025-09-29 10:45:17

WoW: Towards a World omniscient World model Through Embodied Interaction
Xiaowei Chi, Peidong Jia, Chun-Kai Fan, Xiaozhu Ju, Weishi Mi, Kevin Zhang, Zhiyuan Qin, Wanxin Tian, Kuangzhi Ge, Hao Li, Zezhong Qian, Anthony Chen, Qiang Zhou, Yueru Jia, Jiaming Liu, Yong Dai, Qingpo Wuwu, Chengyu Bai, Yu-Kai Wang, Ying Li, Lizhang Chen, Yong Bao, Zhiyuan Jiang, Jiacheng Zhu, Kai Tang, Ruichuan An, Yulin Luo, Qiuxuan Feng, Siyuan Zhou, Chi-min Chan, Chengkai Hou, Wei Xue, Sirui Han, Yike Guo, …

@khalidabuhakmeh@mastodon.social
2025-09-09 20:01:36

Before you spend $59 on that iPhone strap, consider giving the same amount to the World Central Kitchen. They help feed people in a humanitarian crisis around the world.
Many thanks for considering my request.
wck.org/

@arXiv_csLG_bot@mastoxiv.page
2025-09-01 09:58:12

Activation Subspaces for Out-of-Distribution Detection
Bar{\i}\c{s} Z\"ong\"ur, Robin Hesse, Stefan Roth
arxiv.org/abs/2508.21695

@arXiv_qbioNC_bot@mastoxiv.page
2025-08-26 08:57:06

A coalgebraic perspective on predictive processing
Manuel Baltieri, Filippo Torresan, Tomoya Nakai
arxiv.org/abs/2508.16877 arxiv.org/pdf/2…

@arXiv_mathDS_bot@mastoxiv.page
2025-09-03 08:50:23

Delayed Interactions in Active Agents: Stability and Formations
Yu Wang, Andreas Amann, Jinde Cao, J\"urgen Kurths, Serhiy Yanchuk
arxiv.org/abs/2509.00554

@adulau@infosec.exchange
2025-07-08 08:57:00

VLAI: A RoBERTa-Based Model for Automated Vulnerability Severity Classification.
This paper presents VLAI, a transformer-based model that predicts software vulnerability severity levels directly from text descriptions. Built on RoBERTa, VLAI is fine-tuned on over 600,000 real-world vulnerabilities and achieves over 82% accuracy in predicting severity categories, enabling faster and more consistent triage ahead of manual CVSS scoring. The model and dataset are open-source and integrated…

@arXiv_csCV_bot@mastoxiv.page
2025-10-03 10:44:41

Clink! Chop! Thud! -- Learning Object Sounds from Real-World Interactions
Mengyu Yang, Yiming Chen, Haozheng Pei, Siddhant Agarwal, Arun Balajee Vasudevan, James Hays
arxiv.org/abs/2510.02313

@Techmeme@techhub.social
2025-09-29 19:26:02

Anthropic prices Claude Sonnet 4.5 at $3/1M input and $15/1M output tokens, same as Sonnet 4, cheaper than Opus at $15/$75 but higher than GPT-5 at $1.25/$10 (Simon Willison/Simon Willison's Weblog)
simonwillison.net/2025/Sep/29/

@arXiv_csCR_bot@mastoxiv.page
2025-08-28 09:47:11

The Art of Hide and Seek: Making Pickle-Based Model Supply Chain Poisoning Stealthy Again
Tong Liu, Guozhu Meng, Peng Zhou, Zizhuang Deng, Shuaiyin Yao, Kai Chen
arxiv.org/abs/2508.19774

@arXiv_csSE_bot@mastoxiv.page
2025-07-31 09:57:11

The Multi-Agent Fault Localization System Based on Monte Carlo Tree Search Approach
Rui Ren
arxiv.org/abs/2507.22800 arxiv.org/pdf/2507.228…

@arXiv_csLG_bot@mastoxiv.page
2025-09-04 10:27:31

Evaluation of Stress Detection as Time Series Events -- A Novel Window-Based F1-Metric
Harald Vilhelm Skat-R{\o}rdam, Sneha Das, Kathrine Sofie Rasmussen, Nicole Nadine L{\o}nfeldt, Line Clemmensen
arxiv.org/abs/2509.03240

@arXiv_csAI_bot@mastoxiv.page
2025-09-03 07:35:49

Language and Experience: A Computational Model of Social Learning in Complex Tasks
C\'edric Colas, Tracey Mills, Ben Prystawski, Michael Henry Tessler, Noah Goodman, Jacob Andreas, Joshua Tenenbaum
arxiv.org/abs/2509.00074

@arXiv_csRO_bot@mastoxiv.page
2025-09-03 13:47:53

Generalizing Unsupervised Lidar Odometry Model from Normal to Snowy Weather Conditions
Beibei Zhou, Zhiyuan Zhang, Zhenbo Song, Jianhui Guo, Hui Kong
arxiv.org/abs/2509.02011

@arXiv_eessSY_bot@mastoxiv.page
2025-10-02 09:50:01

Real-time Operation of Electric Autonomous Mobility-on-Demand System Considering Power System Regulation
Lyuzhu Pan, Hongcai Zhang
arxiv.org/abs/2510.00984

@arXiv_csCV_bot@mastoxiv.page
2025-08-04 10:11:01

Rethinking Backbone Design for Lightweight 3D Object Detection in LiDAR
Adwait Chandorkar, Hasan Tercan, Tobias Meisen
arxiv.org/abs/2508.00744

@arXiv_csSD_bot@mastoxiv.page
2025-10-03 09:51:11

SoundReactor: Frame-level Online Video-to-Audio Generation
Koichi Saito, Julian Tanke, Christian Simon, Masato Ishii, Kazuki Shimada, Zachary Novack, Zhi Zhong, Akio Hayakawa, Takashi Shibuya, Yuki Mitsufuji
arxiv.org/abs/2510.02110

@arXiv_csDC_bot@mastoxiv.page
2025-09-30 08:25:09

Efficient Fine-Grained GPU Performance Modeling for Distributed Deep Learning of LLM
Biyao Zhang, Mingkai Zheng, Debargha Ganguly, Xuecen Zhang, Vikash Singh, Vipin Chaudhary, Zhao Zhang
arxiv.org/abs/2509.22832

@arXiv_csAI_bot@mastoxiv.page
2025-09-29 10:24:37

The Thinking Spectrum: An Emperical Study of Tunable Reasoning in LLMs through Model Merging
Xiaochong Lan, Yu Zheng, Shiteng Cao, Yong Li
arxiv.org/abs/2509.22034

@arXiv_csGT_bot@mastoxiv.page
2025-08-26 09:22:36

Price of Uncertainty for Consensus Games
Yunzhe Bai, Alec Sun
arxiv.org/abs/2508.17557 arxiv.org/pdf/2508.17557

@arXiv_physicssocph_bot@mastoxiv.page
2025-08-29 09:20:11

Collective communication in a transparent world: Phase transitions in a many-body Potts model and social-quantum duality
Pawat Akarapipattana, Sergei Nechaev, Bogdan Slavov
arxiv.org/abs/2508.20267

@arXiv_csCL_bot@mastoxiv.page
2025-10-03 10:55:51

InfoMosaic-Bench: Evaluating Multi-Source Information Seeking in Tool-Augmented Agents
Yaxin Du, Yuanshuo Zhang, Xiyuan Yang, Yifan Zhou, Cheng Wang, Gongyi Zou, Xianghe Pang, Wenhao Wang, Menglan Chen, Shuo Tang, Zhiyu Li, Siheng Chen
arxiv.org/abs/2510.02271

@arXiv_csCV_bot@mastoxiv.page
2025-10-02 10:54:01

NSARM: Next-Scale Autoregressive Modeling for Robust Real-World Image Super-Resolution
Xiangtao Kong, Rongyuan Wu, Shuaizheng Liu, Lingchen Sun, Lei Zhang
arxiv.org/abs/2510.00820

@arXiv_csRO_bot@mastoxiv.page
2025-09-30 13:14:41

World-Env: Leveraging World Model as a Virtual Environment for VLA Post-Training
Junjin Xiao, Yandan Yang, Xinyuan Chang, Ronghan Chen, Feng Xiong, Mu Xu, Wei-Shi Zheng, Qing Zhang
arxiv.org/abs/2509.24948

@arXiv_csLG_bot@mastoxiv.page
2025-10-02 11:12:01

TOUCAN: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments
Zhangchen Xu, Adriana Meza Soria, Shawn Tan, Anurag Roy, Ashish Sunil Agrawal, Radha Poovendran, Rameswar Panda
arxiv.org/abs/2510.01179

@arXiv_csSE_bot@mastoxiv.page
2025-10-02 10:27:41

Advancing Automated Ethical Profiling in SE: a Zero-Shot Evaluation of LLM Reasoning
Patrizio Migliarini, Mashal Afzal Memon, Marco Autili, Paola Inverardi
arxiv.org/abs/2510.00881

@arXiv_csAI_bot@mastoxiv.page
2025-09-29 10:37:07

Estimating the Empowerment of Language Model Agents
Jinyeop Song, Jeff Gore, Max Kleiman-Weiner
arxiv.org/abs/2509.22504 arxiv.org/pdf/2509…

@arXiv_csCL_bot@mastoxiv.page
2025-10-01 11:35:47

Generating Difficult-to-Translate Texts
Vil\'em Zouhar, Wenda Xu, Parker Riley, Juraj Juraska, Mara Finkelstein, Markus Freitag, Dan Deutsch
arxiv.org/abs/2509.26592

@arXiv_csLG_bot@mastoxiv.page
2025-09-29 11:37:17

The Lie of the Average: How Class Incremental Learning Evaluation Deceives You?
Guannan Lai, Da-Wei Zhou, Xin Yang, Han-Jia Ye
arxiv.org/abs/2509.22580

@arXiv_csCR_bot@mastoxiv.page
2025-07-31 09:10:41

Large Language Model-Based Framework for Explainable Cyberattack Detection in Automatic Generation Control Systems
Muhammad Sharshar, Ahmad Mohammad Saber, Davor Svetinovic, Amr M. Youssef, Deepa Kundur, Ehab F. El-Saadany
arxiv.org/abs/2507.22239

@arXiv_eessSY_bot@mastoxiv.page
2025-08-26 10:31:47

Analysis of Circuit-based Per-Panel Diode Model of Photovoltaic Array
Peng Sang, Santhosh Balasubramanian, Amritanshu Pandey
arxiv.org/abs/2508.17374

@arXiv_csCV_bot@mastoxiv.page
2025-10-03 09:39:01

FideDiff: Efficient Diffusion Model for High-Fidelity Image Motion Deblurring
Xiaoyang Liu, Zhengyan Zhou, Zihang Xu, Jiezhang Cao, Zheng Chen, Yulun Zhang
arxiv.org/abs/2510.01641

@arXiv_csRO_bot@mastoxiv.page
2025-09-26 10:05:51

KeyWorld: Key Frame Reasoning Enables Effective and Efficient World Models
Sibo Li, Qianyue Hao, Yu Shang, Yong Li
arxiv.org/abs/2509.21027

@Techmeme@techhub.social
2025-09-25 16:50:55

OpenAI releases GDPval, a benchmark to test AI performance on "economically valuable, real-world tasks", and says Claude Opus 4.1 was the best performing model (Maxwell Zeff/TechCrunch)
techcrunch.com/2025/09/25/open

@arXiv_csCV_bot@mastoxiv.page
2025-07-28 10:15:31

Back to the Features: DINO as a Foundation for Video World Models
Federico Baldassarre, Marc Szafraniec, Basile Terver, Vasil Khalidov, Francisco Massa, Yann LeCun, Patrick Labatut, Maximilian Seitzer, Piotr Bojanowski
arxiv.org/abs/2507.19468

@arXiv_csLG_bot@mastoxiv.page
2025-09-01 09:59:42

Achieving Hilbert-Schmidt Independence Under R\'enyi Differential Privacy for Fair and Private Data Generation
Tobias Hyrup, Emmanouil Panagiotou, Arjun Roy, Arthur Zimek, Eirini Ntoutsi, Peter Schneider-Kamp
arxiv.org/abs/2508.21815

@arXiv_csRO_bot@mastoxiv.page
2025-08-27 10:02:03

Planning-Query-Guided Model Generation for Model-Based Deformable Object Manipulation
Alex LaGrassa, Zixuan Huang, Dmitry Berenson, Oliver Kroemer
arxiv.org/abs/2508.19199

@arXiv_csCV_bot@mastoxiv.page
2025-10-02 10:50:31

ZQBA: Zero Query Black-box Adversarial Attack
Joana C. Costa, Tiago Roxo, Hugo Proen\c{c}a, Pedro R. M. In\'acio
arxiv.org/abs/2510.00769

@arXiv_csLG_bot@mastoxiv.page
2025-10-03 11:01:21

C2AL: Cohort-Contrastive Auxiliary Learning for Large-scale Recommendation Systems
Mertcan Cokbas, Ziteng Liu, Zeyi Tao, Chengkai Zhang, Elder Veliz, Qin Huang, Ellie Wen, Huayu Li, Qiang Jin, Murat Duman, Benjamin Au, Guy Lebanon, Sagar Chordia
arxiv.org/abs/2510.02215

@arXiv_csCL_bot@mastoxiv.page
2025-07-31 09:45:01

ControlMed: Adding Reasoning Control to Medical Language Model
Sung-Min Lee, Siyoon Lee, Juyeon Kim, Kyungmin Roh
arxiv.org/abs/2507.22545

@arXiv_csCV_bot@mastoxiv.page
2025-07-30 10:41:01

Bridging Synthetic and Real-World Domains: A Human-in-the-Loop Weakly-Supervised Framework for Industrial Toxic Emission Segmentation
Yida Tao, Yen-Chia Hsu
arxiv.org/abs/2507.22002

@arXiv_csCV_bot@mastoxiv.page
2025-09-01 09:40:32

Unsupervised Incremental Learning Using Confidence-Based Pseudo-Labels
Lucas Rakotoarivony
arxiv.org/abs/2508.21424 arxiv.org/pdf/2508.2142…

@arXiv_csCL_bot@mastoxiv.page
2025-09-25 10:40:02

DiffNator: Generating Structured Explanations of Time-Series Differences
Kota Dohi, Tomoya Nishida, Harsh Purohit, Takashi Endo, Yohei Kawaguchi
arxiv.org/abs/2509.20007

@arXiv_csLG_bot@mastoxiv.page
2025-07-24 10:09:59

Decentralized Federated Learning of Probabilistic Generative Classifiers
Aritz P\'erez, Carlos Echegoyen, Guzm\'an Santaf\'e
arxiv.org/abs/2507.17285

@arXiv_csRO_bot@mastoxiv.page
2025-08-28 09:39:51

FARM: Frame-Accelerated Augmentation and Residual Mixture-of-Experts for Physics-Based High-Dynamic Humanoid Control
Tan Jing, Shiting Chen, Yangfan Li, Weisheng Xu, Renjing Xu
arxiv.org/abs/2508.19926

@arXiv_csCV_bot@mastoxiv.page
2025-09-01 10:00:22

DriveQA: Passing the Driving Knowledge Test
Maolin Wei, Wanzhou Liu, Eshed Ohn-Bar
arxiv.org/abs/2508.21824 arxiv.org/pdf/2508.21824

@arXiv_csLG_bot@mastoxiv.page
2025-09-26 10:29:11

GRPO is Secretly a Process Reward Model
Michael Sullivan
arxiv.org/abs/2509.21154 arxiv.org/pdf/2509.21154

@arXiv_csCL_bot@mastoxiv.page
2025-07-22 12:24:10

Operationalizing AI for Good: Spotlight on Deployment and Integration of AI Models in Humanitarian Work
Anton Abilov, Ke Zhang, Hemank Lamba, Elizabeth M. Olson, Joel R. Tetreault, Alejandro Jaimes
arxiv.org/abs/2507.15823

@arXiv_csCV_bot@mastoxiv.page
2025-09-01 09:41:02

MedShift: Implicit Conditional Transport for X-Ray Domain Adaptation
Francisco Caetano, Christiaan Viviers, Peter H. H. de With, Fons van der Sommen
arxiv.org/abs/2508.21435

@arXiv_csCL_bot@mastoxiv.page
2025-07-30 10:18:51

Adversarial Defence without Adversarial Defence: Enhancing Language Model Robustness via Instance-level Principal Component Removal
Yang Wang, Chenghao Xiao, Yizhi Li, Stuart E. Middleton, Noura Al Moubayed, Chenghua Lin
arxiv.org/abs/2507.21750

@arXiv_csCV_bot@mastoxiv.page
2025-07-24 10:30:29

Yume: An Interactive World Generation Model
Xiaofeng Mao, Shaoheng Lin, Zhen Li, Chuanhao Li, Wenshuo Peng, Tong He, Jiangmiao Pang, Mingmin Chi, Yu Qiao, Kaipeng Zhang
arxiv.org/abs/2507.17744

@arXiv_csLG_bot@mastoxiv.page
2025-08-21 10:15:00

Cross-Modality Controlled Molecule Generation with Diffusion Language Model
Yunzhe Zhang, Yifei Wang, Khanh Vinh Nguyen, Pengyu Hong
arxiv.org/abs/2508.14748

@arXiv_csCV_bot@mastoxiv.page
2025-08-27 10:24:53

Preliminary Study on Space Utilization and Emergent Behaviors of Group vs. Single Pedestrians in Real-World Trajectories
Amartaivan Sanjjamts, Morita Hiroshi
arxiv.org/abs/2508.18939