cs.AI · cs.CL · cs.LG · cs.CV · cs.CR · cs.SE · stat.ML · q-fin.TR · q-fin.ST · econ.GN · q-bio.QM · physics.soc-ph · math.OC · cs.RO · cs.HC
Noam Rotstein, Yoad Tewel, Chen Tessler, Haggai Maron, Gal Chechik and others · 2026-10-20
Video generation models can now depict remarkably realistic motion. Yet it is unclear how to use this motion beyond pixels: to animate a specific 3D asset and replay the animation in its 3D scene. For instance, a video model can show a monkey jumping over a crossbar, but it canno…
Yuxuan Kuang, Jiashun Wang, Yixuan Sun, Yufei Ye, Sungjae Park and others · 2026-10-20
Dexterous multi-finger hands hold promise to unlock diverse skills like functional grasps, in-hand reorientation, and dynamic handover that the human-designed world assumes, yet existing learning recipes force a trade-off. Goal-reaching reinforcement learning generalizes to arbit…
Michael Chen, Hong Chul Nam, Xi Deng, Anima Anandkumar · 2026-10-20
Planning under uncertain control execution noise requires reliable feedback policies across diverse environments. We introduce Planning Under Noise (PUN), a neural operator that learns noise-aware value fields for planning in unseen geometries. Building on an established screened…
Emile Anand, Mohammed Rehan Parwani, Xinyuan Cao · 2026-10-20
Multi-token prediction (MTP) can accelerate language-model decoding by drafting several tokens and verifying them in a single target-model pass. However, the best speculation horizon changes with context: longer drafts offer greater amortization when reliable, but can waste compu…
Vincent Jung, Alba Carballo-Castro, Yiming Qin, Lonneke van der Plas, Pascal Frossard · 2026-10-20
Graph generative models commonly use graph-specific Transformer architectures to jointly update node and edge features. However, these architectures do not directly benefit from recent hardware-aware attention implementations, limiting their scalability. The adaptation is, howeve…
Vasilii Feofanov, Zhenghan Tai, Andrei Ermakov, Irina Rish · 2026-10-20
TS2Vec is one of the strongest self-supervised methods for time series classification, introduced in 2022. It is designed to be trained anew on every dataset: self-supervised pre-training followed by linear probing. Since then, the field has shifted towards foundation models that…
Hrishikesh Viswanath, Md Ashiqur Rahman, Chi Lin, Damon Conover, Aniket Bera · 2026-10-20
Neural implicit representations provide memory-efficient signed distance field (SDF) parameterizations for large-scale LiDAR scenes, but the geometry recovered from sparse and often noisy inputs carries jitter and artifacts. Classical geometric optimization techniques resolve suc…
Arthur Bizzi, Márcio Marques, Kleyton Da Costa, Vitor Balestro, Tiago Novello and others · 2026-10-20
Neuro-spectral architectures (NeuSA) are a class of physics-informed neural networks (PINNs) that have proven effective for solving time-dependent PDEs in the frequency domain. However, training and inference often rely on costly numerical integration of the learned vector field,…
Yicheng Zhang, Yujie Jin, Ke Zhang, Jiaxin Wu · 2026-10-20
Camera-trap imagery presents substantial variation in animal appearance, illumination, background clutter, and visual degradation. Masked autoencoders (MAEs) offer a label-free framework for modeling such data through reconstruction of randomly hidden image patches. We present Wi…
Florestan Brunck, Christoph Hertrich, Kilian Ruess, Jack Stade, Amir Yehudayoff · 2026-10-20
We prove that every $\operatorname{ReLU}$ network can be exactly simulated by a $\operatorname{ReLU}$ network with two hidden layers. We present two proofs: one that is based on fillings in homological algebra and a direct combinatorial proof.
Martin Hernandez, Xinyan Qing, Mo Zhou, Yuhua Zhu · 2026-10-20
Continuous-time reinforcement learning seeks an optimal policy under unknown dynamics driven by stochastic differential equations using observations collected at discrete times. We develop a policy gradient framework that combines rigorous convergence analysis with learning from …
Chenxu Niu, Batuhan Sencer, Wei Zhang, Yong Chen · 2026-10-20
Energy-efficient deployment of large language models requires understanding how model architecture, hardware, and serving settings shape energy per generated token. We introduce the Token-Energy Law, a compact, interpretable model of GPU-board energy per output token for dense, f…
Jinming Nian, Jyun-Yu Jiang, Henry Tsai, Yi Fang, Zhirong Liang · 2026-10-20
Generative retrieval (GR) casts search and recommendation as autoregressive generation of discrete semantic identifiers (SIDs). SID design largely determines GR quality, but its discrete, interdependent components (SID construction, collision handling, decoding, and training) can…
Yuzhi Liu, Enis Simsar, Giulia Lanzillotta, Thomas Hofmann · 2026-10-20
Text-to-image personalization aims to equip pretrained diffusion models with the ability to learn user-specific concepts from only a few reference images. Existing methods, however, typically train each concept independently or assume that all concepts are available simultaneousl…
Priyanka Sinha, Snigdhansu Chatterjee · 2026-10-20
Clustered federated learning (CFL) can suffer from cluster collapse. In particular, under unfavorable initialization, early client assignments concentrate heterogeneous groups on one cluster model, which is then trained toward a pooled compromise, while another model receives no …
Andrei Velichko, Imen Mahmoud · 2026-10-20
Online search activity is widely used as a digital trace of information seeking during epidemics, but its predictive value is often reduced to correlation, a selected lag, or a single forecast-error score. We examine eight pre-specified Google Trends-COVID-19 pairs in both direct…
Ma ZhenYao, Yue Liang, Jian-Qiao Zhu · 2026-10-20
Many scientific phenomena are best understood as outcomes of underlying optimization problems, yet automated scientific discovery has largely focused on recovering equations that describe observed input-output patterns. We introduce OptScientist, a novel automated framework for d…
Gabin Maxime Nguegnang, Bubacarr Bah, Holger Rauhut, Ulrich Terstiege · 2026-10-20
Stochastic gradient descent (SGD) is the cornerstone of modern deep learning, yet its theoretical convergence properties remain poorly understood in non-convex settings. To address this gap, we study SGD dynamics in deep linear neural networks - simplified models that retain key …
Fateme Memar, Dongjie Wang, Arvin Agah · 2026-10-20
Large language models (LLMs) can leverage semantic feature names alongside summary statistics for tabular feature selection, yet it remains unclear when such information improves subset selection relative to established statistical methods. We investigate this question within an …
Hangyu Zhou, Constantine Dovrolis, Stephen Mussmann · 2026-10-20
Statistical learning in high dimensions suffers from the curse of dimensionality. Fortunately, many functions of practical interest are compositionally sparse, meaning they admit a composition of local functions, each depending on only a few variables, allowing sample complexity …
Qiyuan Wang, Ke Xiao, Christos Anagnostopoulos · 2026-10-20
Decentralised federated learning (DFL) trains personalised models on devices that average with their neighbours rather than with a central server. Real devices, however, are often offline for hours or days, and a client returning from an outage can recover only by aggregating the…
Rodrigo Casado Noguerales, Dimitri von Rütte, Bernhard Schölkopf, Thomas Hofmann, Aran Raoufi · 2026-10-20
Discrete diffusion models iteratively denoise a noisy sequence of categorical data such as text, enabling any-order generation with self-correction and in-filling capabilities. This makes them promising candidates for reasoning, planning, and constrained-generation tasks like cod…
Ilya Vilkoviskiy, Liang-Hong Mo, Suozhi Huang, Dmitry A. Abanin · 2026-10-20
Unresolved atmospheric processes can introduce history dependence beyond the short input windows used by many weather forecasting models. We introduce GraphCast--Mamba, which augments a frozen, pretrained $1^\circ$ GraphCast backbone with a trainable Mamba correction branch combi…
Wei Jiang, Dingzhi Yu, Zechao Li · 2026-10-20
We study variance reduction for non-convex optimization when gradient evaluations return with a delay. The server can update the parameter while earlier evaluations remain unfinished. We first analyze an ordered recursive momentum estimator for stochastic optimization. Under aver…
Walentin Palanchuk · 2026-10-20
Laboratory measurements are essential for clinical decision making but typically require invasive blood sampling. Recent research suggests that ECG recordings may contain information beyond cardiac rhythm and provide information related to laboratory values. This thesis investiga…
Ning Zhang, Shihao Wang, Jinrui Zhang, Chaodong Xiao, Lei Zhang · 2026-10-20
For efficient deployment of large language models (LLMs), methods of ultra-low-bit backbones reduce weight storage, memory traffic, and linear-layer execution cost, while multi-token prediction (MTP) methods reduce sequential decoding steps by predicting multiple future tokens in…
Aur Shalev Merin · 2026-10-20
Probing studies of latent reasoning often read a model's state where the answer begins and take a failed probe as evidence that a value is absent. We test this with a digit copied from the question, in the looped model Ouro-1.4B and the standard transformer Qwen2.5-1.5B. Comparin…
Erik Stolt, Sanja Karilanova, Ayca Ozcelikkale · 2026-10-20
Deep State-Space Models (Deep SSMs) have shown promising performance and computational benefits in processing of time-series data with complex temporal dependencies. Spiking neural networks (SNNs) constitute a biologically inspired class of deep SSMs, where computing blocks commu…
Angeline Hu, Ava K. Tse, Kaitlyn S. Yasumura, Luciana Sarabia, Malcolm Yeung and others · 2026-10-20
We introduce a two-stage data-driven neural framework for discovering dynamically admissible extreme scenarios. Rather than assuming prior knowledge of the governing equations, the first stage infers the effective dynamical constraints directly from observational data. When the u…
Christoph Riedl, Fernando E. Rosas · 2026-10-20
When a language model develops capabilities not traceable to its individual components, when a multi-agent AI system outperforms each agent on its own, or when a human-AI pair succeeds where either fails in isolation, AI researchers describe it as a case of ``synergy'' or ``emerg…
Kartik Tandon, Alessio Borgi, Pavel Snopov, Inés García-Redondo, Davide D'Ascenzo and others · 2026-10-20
Joint-Embedding Predictive Architectures (JEPA) offer an appealing approach to self-supervised learning, but are typically prone to representation collapse. LeJEPA resolves this by introducing a theoretically grounded distribution-matching objective that drives the embedding towa…
Francesco Maria Guadagnuolo, Alessio Borgi, Dorina Thanou, Pietro Liò · 2026-10-20
We extend the Bochner-Weitzenböck decomposition to cellular sheaf Laplacians, splitting it into a positive semidefinite term, the Bochner sheaf Laplacian, and a block diagonal term, the Forman curvature. We show that the Bochner Laplacians form a class of cellular sheaves that ex…
Filip Postepski, Grzegorz M. Wojcik · 2026-10-20
This study examines whether short, minimally preprocessed EEG segments contain sufficient information to distinguish between individuals classified as extraverted or introverted according to the Myers--Briggs Type Indicator (MBTI). EEG recordings from 50 participants were divided…
Alvaro Ribot, Yulia Alexandr, Anna Seigal · 2026-10-20
A neural model is the set of functions that can be expressed by a given neural network architecture. Neural models contain natural submodels, such as those obtained by setting some neurons to be inactive. We study the geometry of neural models and ask whether they prefer their su…
Krzysztof Wrobel, Grzegorz M. Wojcik · 2026-10-20
We investigate whether a 2D Convolutional Neural Network (CNN) trained on minimally preprocessed EEG signals can classify hypnotic susceptibility across distinct brain regions. Sixty-two male participants (32 Control, 30 Guided Imagery / Hipno group) underwent a 20-minute EEG rec…
Dan Zlotnikov, Ohad Ben-Shahar · 2026-10-20
Vision-language trackers (VLTs) accept descriptions intended to assist tracking, but accepting text does not establish that its content changes tracking decisions, particularly as visual evidence deteriorates. We introduce DISTRACT, a matched-intervention benchmark that holds vid…
Spiros Maggioros, Guray Erus, Gareth Harman, George Aidinis, Alexander Getka and others · 2026-10-20
Deep learning models have become essential tools in medical imaging, yet training them end-to-end for diverse tasks remains challenging due to limited labeled data and computational constraints. To address this, we introduce Brain2Vec, a foundation model pre-trained on 74,425 T1-…
Tom A. Lamb, Adam Golinski, Eleonora Gualdoni, Sinead Williamson, Michael Kirchhof · 2026-10-20
Large language model agents are often given an inference budget and asked to maximise success within it. A multi-turn agent has to allocate this budget across many environment interactions. An external harness can enforce the budget, but it remains unclear whether the agent itsel…
Fangcong Yin, Ming Yin, Tanvi Bhandarkar, Aashu Singh, Eryk Helenowski and others · 2026-10-20
LLM agents are commonly trained with RLVR, but the sparse nature of typical RLVR rewards makes credit assignment challenging, especially for long-horizon tasks. We propose Self-Credit, an end-to-end agentic RL method that creates dense supervision signals from sparse outcome rewa…
Jakob Steimle, Thomas Elsken, Daniel Ehrhardt, Lukas Rinder, Daniel Cremers and others · 2026-10-20
A growing body of work proposes dynamic expert-skipping methods for Mixture-of-Experts (MoE) models that adjust the number of experts activated per token during inference, aiming to preserve model quality while further reducing the number of active parameters. These methods have …
GET https://store.agentexchange.work/gw/papers/latest?cat=cs.LG&limit=25 (0.003 USD per call). Catalogue