Search: “research”

arXiv:2610.09958v1 Announce Type: new Abstract: Training can drive a transformer into a rank collapse: all token representations point in one direction, and learning stops. In a related collapse of at

arXiv:2610.09769v1 Announce Type: cross Abstract: Large language models are increasingly contributing to mathematical research, where progress often depends on efficient proof search, incremental impr

arXiv:2610.10396v1 Announce Type: new Abstract: This paper proposes a novel crowd counting approach, the Gaussian Density Splatting Network (GDSNet). Unlike methods that rely on conventional, grid-bas

arXiv:2610.10033v1 Announce Type: cross Abstract: A theoretical understanding of multi-head self-attention is fundamental to the study of modern neural networks. Using random matrix theory, we establi

arXiv:2610.08866v1 Announce Type: cross Abstract: Sparse-view computed tomography (CT) reduces radiation dose and acquisition time and may mitigate motion artifacts. However, angular undersampling pro

arXiv:2610.09356v1 Announce Type: new Abstract: We prove global exponential (linear) convergence with an explicit rate in the rich scaling for wide two-layer linear networks trained with smooth Polyak

arXiv:2610.09579v1 Announce Type: new Abstract: Trajectory optimisation for cone-beam computed tomography (CT) determines which information sparse-view scans acquire. Fixed candidate pools prevent off

arXiv:2610.10423v1 Announce Type: new Abstract: Adversarial example detectors are often tied to the classifier backbone they were trained on, limiting reuse when the protected model is replaced or upg

arXiv:2610.09068v1 Announce Type: new Abstract: Reliable robotic disassembly requires part-level representations that distinguish genuine component geometry from scanning and reconstruction artifacts.

arXiv:2610.10346v1 Announce Type: new Abstract: Robotic minimally invasive surgery has revolutionized surgical practice. However, as the surgeons are mechanically separated from the surgical tools, lo

arXiv:2606.19156v2 Announce Type: replace Abstract: Dynamic 3D hand reconstruction from egocentric videos is essential for next-generation computing platforms such as AR/VR and AI glasses. Despite its

arXiv:2510.01335v2 Announce Type: replace Abstract: The manifold hypothesis suggests that data lies on manifolds with smaller intrinsic dimension (ID) than their ambient dimension. However there is no

arXiv:2610.10196v1 Announce Type: new Abstract: LiDAR point clouds of humans are extremely expensive to collect and annotate, thus represent a scarce resource that hinders the development of human ana

I find it odd watching armchair critics rush to nitpick @MistralAI’s plans or obsess over whether they’re #1 on every leaderboard. Having a team with this level of conviction building frontier models

arXiv:2610.10092v1 Announce Type: new Abstract: For better or worse, LLMs are by now used routinely for scientific writing.footnote{This paper is no exception; we did use AI to assist with writing som

arXiv:2610.09889v1 Announce Type: new Abstract: Human learning is a dissipative dynamical process: mastery accumulates through practice, decays through forgetting, and propagates across interdependent

arXiv:2610.08818v1 Announce Type: cross Abstract: Spatio-temporal forecasting is a cornerstone of logistics, urban planning, and intelligent transportation systems. However, constrained by deployment

arXiv:2610.09927v1 Announce Type: new Abstract: Knowledge graph embedding (KGE) models encode the entities and relations of a knowledge graph into a low-dimensional latent space, enabling tasks such a

arXiv:2610.10187v1 Announce Type: cross Abstract: Split Gibbs sampling (SGS) is a popular framework for posterior sampling in Bayesian imaging inverse problems. It decouples a Gaussian data-fidelity t

arXiv:2610.10366v1 Announce Type: new Abstract: Feature caching accelerates diffusion sampling by replacing expensive network evaluations with predictions from previously computed activations. However

arXiv:2610.09305v1 Announce Type: cross Abstract: Benchmarks for measuring the quality of action-conditioned world models are still evolving and shifting away from visual similarity-based metrics to a

arXiv:2610.08811v1 Announce Type: new Abstract: As context windows scale to tens or hundreds of thousands of tokens, KV cache compression has become essential for efficient LLM inference. Existing met

arXiv:2610.09179v1 Announce Type: cross Abstract: As data propagates through a Transformer, the norm of its hidden states grows by orders of magnitude with depth, a phenomenon framed as 'curse of dept

arXiv:2610.09877v1 Announce Type: new Abstract: Mixed-precision post-training quantization is a network compression method that assigns bits layer by layer, under a global memory budget using a small

arXiv:2610.10332v1 Announce Type: new Abstract: Learning from large-model demonstrations offers a way to train small agents that can complete recurring tasks without calling a large model at every ste

arXiv:2610.09946v1 Announce Type: new Abstract: Traffic flow modeling is essential for understanding and predicting the collective dynamics of vehicles on road networks. Cellular automata provide a si

arXiv:2610.08835v1 Announce Type: new Abstract: The spread of fake news may cause severe social consequences. Existing fake news detection methods mainly focus on stylistic variations or incorporate e

arXiv:2610.10250v1 Announce Type: new Abstract: We study minimum-variance control of an unknown autoregressive system with exogenous inputs and coefficients that change at unknown times. Under bounded

arXiv:2610.10266v1 Announce Type: new Abstract: Dense self-expression matrices and full-affinity spectral clustering limit the scalability of subspace clustering. We introduce the Latent Orthogonal Op

arXiv:2610.09166v1 Announce Type: cross Abstract: Standard diffusion samplers generate samples through repeated evaluations of a learned score function. Parallel sampling methods seek to accelerate ge

arXiv:2610.10128v1 Announce Type: new Abstract: We show upper and lower bounds on the regret of m-set adversarial bandits for different utilities (winner reward or sum of rewards) and feedback models

arXiv:2601.01779v2 Announce Type: replace-cross Abstract: Based on a transformer based sequence-to-sequence architecture combined with a dynamic batching algorithm, this work introduces a machine lear

arXiv:2610.09536v1 Announce Type: new Abstract: Robotic grasping and surface exploration benefit from simultaneous measurement of normal and tangential forces and from surface information obtained thr

arXiv:2610.09723v1 Announce Type: new Abstract: Prior artisan mesh generation works largely predict face tokens autoregressively, which makes inference slow. Recent methods instead flow match continuo

arXiv:2610.09440v1 Announce Type: new Abstract: Pre-trained vision encoders contain layer-wise visual representations that differ in spatial granularity, semantic abstraction, and sensitivity to local

arXiv:2509.08483v2 Announce Type: replace Abstract: We analyze gradient descent with Polyak (1964) heavy-ball momentum (HB) whose fixed momentum hyperparameter eta in (0, 1) provides exponential decay

arXiv:2610.10245v1 Announce Type: new Abstract: Despite the ubiquity of sensors in wearable and mobile devices and the abundance of human movement data they generate, translating unlabeled recordings

arXiv:2610.09306v1 Announce Type: new Abstract: Naturalistic movie-fMRI provides a shared, temporally structured probe of brain dynamics, yet predictive models commonly rely on whole-run functional co

arXiv:2602.10137v2 Announce Type: replace Abstract: This work proposes MeCSAFNet, a multi-branch encoder-decoder architecture for land cover segmentation in multispectral imagery. The model separately

arXiv:2610.10278v1 Announce Type: cross Abstract: We propose a neural algorithm for sampling from distributions specified by unnormalized Boltzmann densities. Our approach is based on the Jordan--Kind

arXiv:2610.10538v1 Announce Type: new Abstract: As we move through the world and carry out everyday tasks, we encounter objects that may become relevant only later. We are capable of recalling where w

arXiv:2610.09297v1 Announce Type: new Abstract: In recent years, Graph Neural Networks (GNNs) and architecture search frameworks have gained extensive application in non-Euclidean data processing, att

arXiv:2610.09407v1 Announce Type: new Abstract: Pretrained diffusion models are powerful priors for inverse problems, but posterior sampling under nonlinear, non-differentiable forward models remain h

arXiv:2610.09145v1 Announce Type: cross Abstract: We revisit a standard accepted practice in the continuous diffusion language model literature of fixing conditioning prompt tokens clean during traini

arXiv:2610.09513v1 Announce Type: new Abstract: Camera trajectories control viewpoint changes in video generation, scene reconstruction, and robotic perception. Generating them from language requires

arXiv:2610.09104v1 Announce Type: cross Abstract: Identification is the task of recovering the parameters of an unknown ground-truth model from sampled data. When parameters other than the ground trut