 | Block-level Text Spotting with LLMs | Ganesh Bannur,Bharadwaj Amrutur, Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text | |
 | Scaling Rectified Flow Transformers for High-Resolution Image Synthesis | Patrick Esser,Sumith Kulal,Andreas Blattmann,Rahim Entezari,Jonas Müller,Harry Saini,Yam Levi,Dominik Lorenz,Axel Sauer,Frederic Boesel,Dustin Podell,Tim Dockhorn,Zion English,Kyle Lacey,Alex Goodwin,Yannik Marek,Robin Rombach, Patrick Esser, Sumith Kulal, Andreas Blattmann, Rahim Entezari, Jonas Müller, Harry Saini, Yam Levi, Dominik Lorenz, Axel Sauer, | |
 | Black-Box vs. Gray-Box: A Case Study on Learning Table Tennis Ball Trajectory Prediction with Spin and Impacts | Jan Achterhold,Philip Tobuschat,Hao Ma,Dieter Buechler,Michael Muehlebach,Joerg Stueckler, SCENE-Net V2 is a gray-box model that pairs geometric interpretability and | |
 | Whispering Experts: Neural Interventions for Toxicity Mitigation in Language Models | average of [PIQA, SIQA, TriviaQA, TruthfuGA, Hellaswag), Whispering Experts: Neural Interventions for Toxicity Mitigation in Language Models | |
 | Spinning Down a Black Hole With Scalar Fields | Chris M. Chambers,William A. Hiscock,Brett Taylor, HumanTOMATO: Text-aligned Whole-body Motion Generation | |
 | The effects of Gribov copies in 2D gauge theories | D. Dudal,S. P. Sorella,N. Vandersickel,H. Verschelde, Vid3D: Synthesis of Dynamic 3D | |
 | Efficient Regularized Piecewise-Linear Regression Trees | Leonidas Lefakis,Oleksandr Zadorozhnyi,Gilles Blanchard, Piecewise Constant and Linear Regression Trees | |
 | fine-tuning using the input restoration shape can improve the solution signifi- | [3] Angel X. Chang, Thomas A. Funkhouser, Leonidas J. Guibas, Pat Hanrahan, Qi-Xing Huang, Zimo Li, Silvio, fine-tuning using the input restoration shape can improve the solution signifi- | |
 | SceneCraft: An LLM Agent for Synthesizing 3D Scene as Blender Code | Ziniu Hu,Ahmet Iscen,Aashi Jain,Thomas Kipf,Yisong Yue,David A. Ross,Cordelia Schmid,Alireza Fathi, Agent for Synthesizing | |
 | Position: Key Claims in LLM Research Have a Long Tail of Footnotes | Anna Rogers,Alexandra Sasha Luccioni, Key Claims in LLM Research Have a Long Tail of Footnotes* | |
 | Large Language Models are Geographically Biased | Rohin Manvi,Samar Khanna,Marshall Burke,David Lobell,Stefano Ermon, Large Language Models are Geographically Biased | |
 | MISGENDERED: Limits of Large Language Models in Understanding Pronouns | Tamanna Hossain,Sunipa Dev,Sameer Singh, in the weights of GPT-Neo-1.3B using | |
 | layer 6 | partners (Backpack, Book, Bottle, Opener, Candle, Sandal)., layer 6 | |
 | MMOne: Representing Multiple Modalities in One Scene | Zhifeng Gu,Bing Wang, POSITION: MISSION CRITICAL - SATELLITE DATA IS A DISTINCT MODALITY IN MACHINE LEARNING | |
 | Human vs. Generative AI in Content Creation Competition: Symbiosis or Conflict? | Fan Yao,Chuanhao Li,Denis Nekipelov,Hongning Wang,Haifeng Xu, Human vs. Generative Al in Content Creation Competition: | |
 | Multimodal Crop Type Classification Fusing Multi-Spectral Satellite Time Series with Farmers Crop Rotations and Local Crop Distribution | Valentin Barriere,Martin Claverie, QUANTiFpiNG LiKENESS | |
 | Privacy Backdoors: Stealing Data with Corrupted Pretrained Models | Shanglun Feng,Florian Tramèr, Privacy Backdoors: Stealing Data with Corrupted Pretrained Models | |
 | by Linear Regression: | Objective: given some sub-sequence (x,” …,x() predict the*, by Linear Regression: | |
 | Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution | Chrisantha Fernando,Dylan Banarse,Henryk Michalewski,Simon Osindero,Tim Rocktäschel, Promptbreeder: Self-Referential Self-Improvement via Prompt Evolution | |
 | Solving Poisson Equations using Neural Walk-on-Spheres | Hong Chul Nam’”, Julius Berner?”, Anima Anandkumar2, Solving Poisson Equations using Neural Walk-on-Spheres | |
 | MagicLens % : Next-Generation Image Retrieval Models | Kai Zhang, Yi Luan, Hexiang Hu, Kenton Lee, Siyuan Qiao, Wenhu Chen, Yu Su, and Ming-Wei Chang, MagicLens % : Next-Generation Image Retrieval Models | |
 | Local vs. Global Interpretability: A Computational Complexity Perspective | Shahaf Bassan,Guy Amir,Guy Katz, Local vs. Global Interpretability: A Computational Complexity Perspective | |
 | 9$8000089 | nn. Convld(25, 25, 3, stride=2, padding=1),, 9$8000089 | |
 | Integrated Information-induced quantum collapse | Kobi Kremnizer,André Ranchin, Mean-field Chaos Diffusion Models | |
 | Adversarial Perturbations Cannot Reliably Protect Artists From Generative AI | Robert Hönig,Javier Rando,Nicholas Carlini,Florian Tramèr, Adversarial Perturbations Cannot Reliably | |
 | A Geometric Explanation of the Likelihood OOD Detection Paradox | Hamidreza Kamkari,Brendan Leigh Ross,Jesse C. Cresswell,Anthony L. Caterini,Rahul G. Krishnan,Gabriel Loaiza-Ganem, A Geometric Explanation of the Likelihood OOD Detection Paradox | |
 | Scalable Pre-training of Large Autoregressive Image Models | Alaaeldin El-Nouby,Michal Klein,Shuangfei Zhai,Miguel Angel Bautista,Alexander Toshev,Vaishaal Shankar,Joshua M Susskind,Armand Joulin, Scalable Pre-training of Large Autoregressive Image Models | |
 | A Circuit Domain Generalization Framework for Efficient Logic Synthesis in Chip Design | Zhihai Wang,Lei Chen,Jie Wang,Xing Li,Yinqi Bai,Xijun Li,Mingxuan Yuan,Jianye Hao,Yongdong Zhang,Feng Wu, A Circuit Domain Generalization Framework for | |
 | Strategies To Evaluate The Riemann Zeta Function | Alois Pichler, 20202200227012021 | |
 | Quantum circuit design for universal distribution using a superposition of classical automata | Aritra Sarkar,Zaid Al-Ars,Koen Bertels, Superposition Prompting: Improving and Accelerating Retrieval-Augmented Generation | |
 | Audio Flamingo: A Novel Audio Language Model with | [8] Gong, Yuan, et al. Listen, Think, and Understand. ICLR 2024., Audio Flamingo: A Novel Audio Language Model with | |
 | Using AI Uncertainty Quantification to Improve Human Decision-Making | Laura R. Marusich,Jonathan Z. Bakdash,Yan Zhou,Murat Kantarcioglu, USING AI UNCERTAINTY INFORMATION TO | |
 | About Geometry and Initial Phase of Cloud-to-Ground Lightning | Aleš Berkopec, Craft ox | |
 | Data-free Distillation of Diffusion Models with Bootstrapping | Fo (21, t, c) = fó(xt, t, n) + w. (foxt, t, c) - foxt, t, n)), Data-free Distillation of Diffusion Models with Bootstrapping | |
 | High-accuracy high-mass ratio simulations for binary neutron stars and their comparison to existing waveform models | Maximiliano Ujevic,Alireza Rashti,Henrique Gieg,Wolfgang Tichy,Tim Dietrich, Flow: Differentiable Simulations with 10x less code | |
 | Flow Rounding | Donggu Kang,James Payor, MusicFlow: Cascaded Flow Matching for | |
 | WebLINX | WebLINX: Real-World […], WebLINX | |
 | Evaluating Copyright Takedown Methods for Language Models | Boyi Wei), Weljia Shiz, Yangsibo Huang1, Noah A. Smithz, Chiyuan Zhang, Luke Zettlemoyer2, Kai Lit, Peter Henderson1*, Evaluating Copyright Takedown Methods for Language Models | |
 | Auxiliary Knowledge-Induced Learning for Automatic Multi-Label Medical Document Classification | Xindi Wang,Robert E. Mercer,Frank Rudzicz, OAK: Enriching Document Representations using Auxiliary Knowledge for Extreme Classification | |
 | Topological Uncertainty for Anomaly Detection in the Neural-network EoS Inference with Neutron Star Data | Kenji Fukushima,Syo Kamata, SECOND-ORDER UNCERTAINTY QUANTIFICATION: | |
 | Demonstrating and Reducing Shortcuts in Vision-Language Representation Learning | Maurits Bleeker,Mariya Hendriksen,Andrew Yates,Maarten de Rijke, Revisiting the Role of Language Priors in Vision-Language Models | |
 | Tactics and Tallies: A Study of the 2016 U.S. Presidential Campaign Using Twitter ‘Likes’ | Yu Wang,Xiyang Zhang,Jiebo Luo, A Taxonomy of Tactics and Insights from Media Data | |
 | Grad-ECLIP: Gradient-based Visual and Textual Explanations for CLIP | Chenyang Zhao,Kun Wang,Janet H. Hsiao,Antoni B. Chan, Gradient-based Visual Explanation for Transformer-based CLIP | |
 | Bringing motion taxonomies to continuous domains via GPLVM on hyperbolic manifolds | Noémie Jaquier,Leonel Rozo,Miguel González-Duque,Viacheslav Borovitskiy,Tamim Asfour, Bringing Motion Taxonomies to Continuous Domains via GPLVM on Hyperbolic Manifolds | |
 | Better & Faster Large Language Models via Multi-token Prediction | Fabian Gloeckle,Badr Youbi Idrissi,Baptiste Rozière,David Lopez-Paz,Gabriel Synnaeve, Better & Faster Large Language Models via Multi-token Prediction | |
 | TJ-FlyingFish: Design and Implementation of an Aerial-Aquatic Quadrotor with Tiltable Propulsion Units | Xuchen Liu,Minghao Dou,Dongyue Huang,Biao Wang,Jinqiang Cui,Qinyuan Ren,Lihua Dou,Zhi Gao,Jie Chen,Ben M. Chen, University of Science and Technology of China Microsoft Research & Microsoft Azure The Chinese University of Hong Kong, Shenzhen | |
 | Position: Tensor Networks are a Valuable Asset for Green AI | Eva Memmel,Clara Menzen,Jetze Schuurmans,Frederiek Wesel,Kim Batselier, Position: Tensor Networks are a Valuable Asset for Green Al | |
 | Spectral lens enables a minimalist framework for hyperspectral imaging | Zhou Zhou,Yiheng Zhang,Yingxin Xie,Tian Huang,Zile Li,Peng Chen,Yanqing Lu,Shaohua Yu,Shuang Zhang,Guoxing Zheng, School of Engineering | |
 | Dual Convexified Convolutional Neural Networks | Site Bai,Chuyang Ke,Jean Honorio, Parameter Recovery of Neural Networks | |
 | Luban: Building Open-Ended Creative Agents via Autonomous Embodied Verification | Yuxuan Guo,Shaohui Peng,Jiaming Guo,Di Huang,Xishan Zhang,Rui Zhang,Yifan Hao,Ling Li,Zikang Tian,Mingju Gao,Yutai Li,Yiming Gan,Shuai Liang,Zihao Zhang,Zidong Du,Qi Guo,Xing Hu,Yunji Chen, Creative Text-to-Audio Generation Via Synthesizer Programming | |
 | TRUSTWORTHY ACTIONABLE PERTURBATIONS -“ | Department of ECE, University of Arizona, Tucson, AZ, USA, TRUSTWORTHY ACTIONABLE PERTURBATIONS -” | |
 | Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews | Weixin Liang,Zachary Izzo,Yaohui Zhang,Haley Lepp,Hancheng Cao,Xuandong Zhao,Lingjiao Chen,Haotian Ye,Sheng Liu,Zhi Huang,Daniel A. McFarland,James Y. Zou, Monitoring Al-Modified Content at Scale: | |