Knowledge catalogue
arXiv:2610.09478v1 Announce Type: new Abstract: Referring Expression Segmentation (RES) links natural-language descriptions to pixel-level object masks. Yet standard evaluation provides limited insigh
arXiv:2610.09920v1 Announce Type: cross Abstract: Prevailing multi-vector visual document retrievers store each page as about a thousand patch vectors, often in vector databases run by a third party.
arXiv:2610.09517v1 Announce Type: new Abstract: Frozen vision-language models increasingly provide safety signals for reinforcement learning. Their use assumes that similarity to language describing d
Classification is one of the oldest problems in machine learning. Unlike modern decoding transformers, most classification models were non-autoregressive by nature. Before Jev, the common approaches w
The other week I posted about Jev vs. Kev compared and since then, OpenAI released the decisions endpoint, Cloudflare released Clef and many here asked about Laya as well. This time we compared six po
arXiv:2610.09788v1 Announce Type: new Abstract: Reward modeling often requires jointly representing and reasoning over multiple evaluation criteria, yet verbalizing this process token by token can inc
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:2610.10473v1 Announce Type: new Abstract: Cell viability assessment is a core requirement in cell culture systems, with critical applications in biopharmaceutical manufacturing and drug developm
arXiv:2610.09283v1 Announce Type: new Abstract: Robot co-design couples morphology search with policy learning, yet training every new design from scratch discards acquired control experience. We pres
arXiv:2410.11687v4 Announce Type: replace Abstract: In-context learning lets a sequence model adapt to a new task from examples in its input. A prominent line of work shows how self-attention can be c
arXiv:2610.09045v1 Announce Type: cross Abstract: We study the problem of learning transition kernels for time-homogeneous jump-diffusion processes using conditional diffusion models, with the goal of
arXiv:2610.09872v1 Announce Type: cross Abstract: Evaluating agents by outcomes alone can obscure the capabilities that produce them. This problem is especially pronounced in evolving environments, wh
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:2605.24928v2 Announce Type: replace Abstract: Sonar imaging is the primary modality for underwater target detection, yet small targets remain difficult to detect due to insufficient pixel covera
arXiv:2610.09985v1 Announce Type: cross Abstract: We study a sequential pricing problem in which a seller jointly posts a price and an advertisement generated by a large language model (LLM). The sell
arXiv:2610.10351v1 Announce Type: cross Abstract: Differentiable quantum architecture search (DQAS) is a promising framework for the automated design of quantum circuits, particularly for variational
arXiv:2610.09652v1 Announce Type: cross Abstract: Autonomous navigation in dynamic environments requires computing spatiotemporal trajectories that satisfy non-holonomic motion constraints. When the t
arXiv:2610.09795v1 Announce Type: new Abstract: The demand for personalized LLMs is shifting from style imitation toward content quality. We investigate whether self-distillation can bridge this gap i
arXiv:2610.09473v1 Announce Type: new Abstract: Time-series anomaly detection (TSAD) identifies deviations from patterns learned from historical data. In non-stationary settings, distribution drift an
arXiv:2610.09830v1 Announce Type: new Abstract: Video deepfakes targeting a specific individual, the Person-of-Interest (POI), are the most harmful ones, and, since a public figure is abundantly recor
arXiv:2610.10087v1 Announce Type: new Abstract: Offline MARL increasingly relies on generative policies to model multimodal joint behavior, typically by distilling a centralized teacher into decentral
arXiv:2610.09020v1 Announce Type: new Abstract: Modern neural networks are often miscalibrated, with a tendency to overconfidence. Existing train-time calibration methods largely modify task losses or
arXiv:2610.10387v1 Announce Type: new Abstract: In robotics, scene representation plays a pivotal role in understanding and interacting with the environment. The advent of Neural Radiance Fields (NeRF
arXiv:2610.09185v1 Announce Type: new Abstract: Cine cardiovascular magnetic resonance (CMR) captures the cardiac cycle as a four-dimensional (4D) sequence, but standard acquisition requires electroca
arXiv:2610.09397v1 Announce Type: new Abstract: Cine cardiovascular magnetic resonance (CMR) analysis relies on multi-frame sequences capturing the full cardiac cycle. However, standard multi-frame ac
arXiv:2610.09577v1 Announce Type: new Abstract: We study finite-horizon online resource allocation with i.i.d. requests and an endogenous Markov state on a finite state space: each action affects the
OpenDocRouter is basically OpenRouter for document OCR You can compare and use all your favorite OCR models under a single API / billing interface. They range from some of the lightweight/OSS models (
arXiv:2610.09040v1 Announce Type: new Abstract: Constraint handling methods typically intervene before the optimizer acts, by modifying the objective or the gradient. Yet momentum, adaptive scaling, a
arXiv:2610.09837v1 Announce Type: cross Abstract: Universal machine learning force-field generalization to multicomponent environments generated by compositional design remains insufficiently assessed
arXiv:2610.10018v1 Announce Type: new Abstract: Effective long-range propagation remains a central challenge in graph neural networks, as increasing a model's propagation depth does not guarantee that
arXiv:2610.09071v1 Announce Type: new Abstract: Layout-to-Image generation has made substantial progress in spatial and object-level control. However, existing methods still struggle with complex scen
arXiv:2610.08826v1 Announce Type: new Abstract: Full-sphere panoramic cameras let fixed monitoring systems and mobile robots track people in every direction, but a planar bounding box does not fully d
arXiv:2610.10324v1 Announce Type: new Abstract: Pretrained models for cell and nuclear instance segmentation differ substantially in architecture, pretraining data and objectives, parameter count, inf
arXiv:2610.09510v1 Announce Type: new Abstract: Physics-informed neural PDE solvers adapt their parameters to satisfy governing equations, yet their representational structure typically remains fixed
arXiv:2610.09479v1 Announce Type: new Abstract: Precise end-effector tracking during humanoid whole-body motion is challenging due to floating-base oscillations, gravity, dynamic coupling, and locomot
arXiv:2511.17776v2 Announce Type: replace Abstract: We present PrismSSL, a Python library that unifies state-of-the-art self-supervised learning (SSL) methods across audio, vision, graphs, and cross-m
arXiv:2603.11938v2 Announce Type: replace-cross Abstract: Structured radiology reporting promises faster, more consistent communication than free text, but automation remains difficult as models must
arXiv:2610.09941v1 Announce Type: new Abstract: Large vision-language models (LVLMs) are increasingly deployed in safety-critical applications, yet they remain vulnerable to backdoor attacks. Defendin
arXiv:2610.10497v1 Announce Type: new Abstract: We introduce QuadTok, a novel framework for visual tokenization and autoregressive image generation. Compared to traditional approaches using 2D grids o
arXiv:2610.09670v1 Announce Type: new Abstract: Unsupervised anomaly detection, which learns only from normal images, is a central task in medical image analysis and remains an open problem. Reconstru
arXiv:2610.08954v1 Announce Type: new Abstract: Video large language models (Vid-LLMs) excel at diverse video-language tasks by reasoning over selected frames. However, frame selection for long videos
arXiv:2610.09173v1 Announce Type: new Abstract: 3D foundation models enable efficient novel view synthesis by carrying a Gaussian head on the representation they already use for reconstruction. Howeve
arXiv:2610.09780v1 Announce Type: new Abstract: Diffusion models excel at image synthesis, but they remain limited in their ability to reliably satisfy structured spatial reasoning constraints. In con
arXiv:2610.09613v1 Announce Type: cross Abstract: Shallow models are special cases of deep models, and deep models theoretically have the potential to outperform the shallow ones. However, the existin
arXiv:2610.10381v1 Announce Type: new Abstract: Looped Transformers improve parameter efficiency by repeatedly applying shared Transformer blocks over multiple recurrent loops, increasing computationa
arXiv:2610.09455v1 Announce Type: new Abstract: Recently, approaches that leverage human video datasets for robot policy training have become increasingly prevalent. However, most existing hand tracke
arXiv:2510.00154v2 Announce Type: replace Abstract: Despite rapid progress in robotics, complex or long-horizon tasks remain a fundamental challenge. Most current approaches follow an open-loop paradi
arXiv:2610.10388v1 Announce Type: cross Abstract: Recent advances in multimodal foundation models have made them capable generalist physical agents for a range of manipulation tasks. However, successf
arXiv:2610.08978v1 Announce Type: new Abstract: Streaming 3D reconstruction requires more than a sequence of geometric predictions: it requires a persistent scene state that can incorporate new eviden
arXiv:2610.09875v1 Announce Type: new Abstract: Infrared small target detection aims to accurately identify and locate dim targets in complex backgrounds and supports applications such as maritime sur
arXiv:2610.09665v1 Announce Type: new Abstract: On-policy post-training can improve large language models by learning from their own trajectories, but requires costly rollout generation. We ask whethe
arXiv:2610.09591v1 Announce Type: cross Abstract: Conditional density estimation targets the full distribution of a response given covariates, as required, for example, for per-galaxy photometric reds
arXiv:2610.10013v1 Announce Type: new Abstract: Self-supervised learning (SSL) at scale produces powerful visual representations. However, most scalable SSL methods rely on ad hoc combinations of mult
arXiv:2610.10513v1 Announce Type: cross Abstract: Language-model agents are increasingly asked to carry out open-ended scientific research, yet their results are usually graded against a known answer,
arXiv:2610.10400v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have made significant progress in visual understanding and generation. However, generating interleaved image--t
arXiv:2610.10274v1 Announce Type: new Abstract: Token-based world models enable fine-grained latent planning, but repeatedly processing large spatial token grids makes action search expensive. We intr
arXiv:2610.09886v1 Announce Type: cross Abstract: Bayesian neural networks need not be fully stochastic to be universal conditional density approximators, but it remains open which parameters should b
arXiv:2610.05685v2 Announce Type: replace Abstract: Reasoning models write most of their KV cache while decoding long chains of thought (CoT), so the cache has to be compressed online under a fixed me
arXiv:2610.09025v1 Announce Type: new Abstract: Indexer-based sparse attention reduces the cost of core attention by passing only a fixed, small number of important tokens to it. However, the indexer
arXiv:2610.09514v1 Announce Type: new Abstract: Physical world modeling requires predicting how interactions change a scene, not merely generating coherent motion. We propose STRIKE, a framework that