Knowledge catalogue
arXiv:2609.34786v1 Announce Type: new Abstract: Longer histories can improve time-series foundation models (TSFMs), but require substantially higher inference cost. We therefore ask whether contextual
arXiv:2602.04952v2 Announce Type: replace-cross Abstract: We study the sample complexity of shadow tomography in the high-precision regime under realistic measurement constraints. Given an unknown d-d
arXiv:2609.32201v1 Announce Type: cross Abstract: On-Policy Context Distillation (OPCD) has recently emerged as a powerful technique for transferring context to student models and for self-improvement
arXiv:2609.31701v1 Announce Type: new Abstract: A Hybrid Residual Attention Network is proposed for accurately classifying silkworm images into six different classes, including healthy and diseased st
arXiv:2609.31997v1 Announce Type: new Abstract: Decoding imagined speech is an important goal for brain-computer interfaces but remains challenging due to weak neural responses, low signal-to-noise ra
arXiv:2609.33951v1 Announce Type: new Abstract: The increasing adoption of robotic systems in surgery, together with the expanding range of procedures they can support and the growing level of autonom
arXiv:2609.32048v1 Announce Type: new Abstract: Model misspecification poses a fundamental challenge in multi-agent reinforcement learning, where transition uncertainty can be amplified by strategic i
arXiv:2609.35351v1 Announce Type: new Abstract: Interference is commonly treated as geometric overlap between learned features. We introduce effective interference, which combines feature geometry and
arXiv:2603.14528v2 Announce Type: replace Abstract: In recent years, 3D visual foundation models, pioneered by pointmap-based approaches such as DUSt3R, have attracted a lot of interest, achieving imp
arXiv:2609.32539v1 Announce Type: cross Abstract: Deep learning models can achieve high accuracy for indoor localization, but their black-box nature limits interpretability and the reuse of learned in
arXiv:2609.35073v1 Announce Type: new Abstract: Graph visualization methods and agglomerative clustering have been frequently considered in data analysis and pattern recognition. Because these approac
arXiv:2609.32660v1 Announce Type: new Abstract: Table images preserve structural information that are often lost in text serialization, and reasoning over them requires locating relevant rows, columns
arXiv:2609.32619v1 Announce Type: new Abstract: Large self-supervised vision models learn representations that support scene segmentation and the semantic decomposition of physical objects. We ask whe
arXiv:2609.33416v1 Announce Type: new Abstract: In this paper, a methodology to design fair graph convolutional neural networks (GCNs) is developed and tested over several application data sets. The g
arXiv:2609.32857v1 Announce Type: new Abstract: Predicting spatial gene expression from routine H&E histology offers a scalable route toward spatial molecular profiling. Recent work has pursued increa
arXiv:2609.32004v1 Announce Type: new Abstract: Encoded demographic information in internal model representations is a commonly assumed risk factor for algorithmic bias, with demographic representatio
arXiv:2609.33049v1 Announce Type: new Abstract: Behavior cloning (BC) is vulnerable to covariate shift during closed-loop execution, where small prediction or execution errors can drive the robot towa
arXiv:2609.33585v1 Announce Type: new Abstract: The rapid proliferation of highly realistic AI-Generated Content (AIGC) necessitates robust and interpretable detection mechanisms. However, existing de
arXiv:2609.35350v1 Announce Type: cross Abstract: While Large Reasoning Models (LRMs) excel at complex reasoning, alignment through reinforcement learning often induces systemic overconfidence. In pro
arXiv:2609.34931v1 Announce Type: cross Abstract: Machine learning has made strong progress on music tasks, both as assistive tools and as creative partners. However, most systems train on multitrack
arXiv:2609.32481v1 Announce Type: new Abstract: Joint-embedding predictive architectures are unusually sensitive to how the input is masked: block masks work, scattered masks do not, and the explanati
arXiv:2609.33874v1 Announce Type: new Abstract: JET uses pretrained language and vision-language models to select among a finite set of answers without additional training. It evaluates candidate like
arXiv:2609.34024v1 Announce Type: cross Abstract: Jev is a non-generative 'System One' model that assigns probabilities to predefined answer options and cannot answer outside them. Its accuracy and ca
arXiv:2609.33906v1 Announce Type: cross Abstract: Generative models often suffer from mode collapse and limited sample diversity. While prior works attempt to mitigate this by jointly generating a bat
arXiv:2609.34381v1 Announce Type: new Abstract: Video and audio are perceived together, yet most generative models treat them in isolation. We examine methods that model the two modalities jointly, ge
arXiv:2603.20984v2 Announce Type: replace Abstract: Gaussian process surrogates dominate constrained multi-objective optimization because they are effective in data-scarce regimes, but their cubic sca
arXiv:2609.35032v1 Announce Type: cross Abstract: In complex embodied visual reasoning scenarios, an agent often has only a limited field of view, and the evidence needed to answer a question may be d
arXiv:2609.34385v1 Announce Type: cross Abstract: Memory is critical for AI agents. Many existing agent-memory systems follow an Ahead-of-Time (AOT) design, constructing memory before a specific reque
arXiv:2609.34972v1 Announce Type: new Abstract: Long visual token sequences often account for a substantial fraction of the computational overhead in multimodal large language models~(MLLMs). Existing
arXiv:2609.34082v1 Announce Type: cross Abstract: Interpreting architecture, engineering, and construction (AEC) drawings is hard for general Multimodal Large Language Models (MLLMs) and vision-langua
arXiv:2609.34045v1 Announce Type: cross Abstract: Between them, the members of a research group or a circle of friends own several consumer computers, none large enough to run a capable large language
arXiv:2609.32203v1 Announce Type: new Abstract: Large vision-language models (VLMs) can judge visual similarity, but their judgments are not directly available as compact image embeddings for efficien
arXiv:2609.33074v1 Announce Type: new Abstract: High-performance GPU kernels are essential to modern machine learning systems, yet automatically generating kernels that are both correct and efficient
arXiv:2609.32182v1 Announce Type: new Abstract: Vision-language models are increasingly used to understand long videos and continuous streams. However, dense visual tokens accumulate with video durati
arXiv:2609.34507v1 Announce Type: cross Abstract: Financial candlestick forecasting is fundamental to quantitative investment, yet it remains exceptionally challenging due to extremely low signal-to-n
arXiv:2609.31888v1 Announce Type: cross Abstract: X-ray diffraction (XRD) is a experimental technique for determining the phase composition and structure of crystalline materials. However, interpretin
arXiv:2407.20737v3 Announce Type: cross Abstract: This study explores the application of Kolmogorov-Arnold networks (KANs) in predicting nuclear binding energies, leveraging their ability to decompose
arXiv:2609.33350v1 Announce Type: new Abstract: Learning population dynamics from temporally sparse, unpaired distribution snapshots is a fundamental challenge in developmental biology. Recent approac
arXiv:2609.32610v1 Announce Type: cross Abstract: Large language models represent context with a key-value (KV) cache. Caches are model-specific: for the same text, models with different architectures
arXiv:2609.35750v1 Announce Type: new Abstract: Scaling the horizon of agentic LLMs is bottlenecked by the need to fit ever longer context traces in GPU memory. Context compaction has been the most po
arXiv:2609.34060v1 Announce Type: new Abstract: Prompt-specialized multi-agent systems enable multiple agents to share a model while performing complementary roles to solve complex tasks. However, age
arXiv:2609.35710v1 Announce Type: new Abstract: We introduce LHFM, a geometric framework for learning image dynamics. Drawing on structures central to classical mechanics, symplectic geometry, and geo
arXiv:2609.31988v1 Announce Type: new Abstract: We investigate the applicability of Lagrangian and Hamiltonian Neural Network models to a dissipative system that has explicit time dependence in its La
arXiv:2609.35288v1 Announce Type: cross Abstract: Joint-embedding self-supervised learning typically combines an invariance objective across augmented views with additional mechanisms to prevent repre
arXiv:2609.32556v1 Announce Type: cross Abstract: Based on an analysis of the role of language in thought and communication, this article proposes a new concept for designing corporate knowledge bases
arXiv:2609.31665v1 Announce Type: new Abstract: Action anticipation predicts future human actions from partial video under incomplete context and temporal uncertainty. Recent systems introduce large l
arXiv:2609.33630v1 Announce Type: cross Abstract: Differentiable optimization brings the structural guarantees of mathematical optimization to network pipelines, allowing them to be trained end-to-end
arXiv:2609.35335v1 Announce Type: new Abstract: Machine learning task type identification is essential for constructing valid ML pipelines, yet in practice it is typically specified manually. We inves
arXiv:2609.33423v1 Announce Type: new Abstract: Large Language Models (LLMs) can contribute useful engineering knowledge to robot design, but directly generated designs may rely on implicit assumption
arXiv:2609.32933v1 Announce Type: new Abstract: In safety-critical applications, deployment uses a single policy, whose performance and constraint satisfaction should hold directly rather than only fo
arXiv:2609.35260v1 Announce Type: new Abstract: Spiking neural networks are attractive for low-power speech command recognition, yet their latency has received far less attention than their energy eff
arXiv:2609.32132v1 Announce Type: new Abstract: In cross-silo split learning, Parallel Split Learning with Global Sampling forms representative pooled batches when class distributions differ across cl
arXiv:2609.32794v1 Announce Type: new Abstract: Latent generative models make 3D medical image synthesis computationally practical by generating in a compressed space. However, we show that the common
arXiv:2609.31720v1 Announce Type: new Abstract: Transferring deformation between characters with different geometry and topology is challenging because conventional rigs encode behaviour through chara
arXiv:2609.33843v1 Announce Type: cross Abstract: The shipped Laya Typed-Decisions checkpoint, a 421M-parameter ModernBERT-large assessor that answers typed choice/noul/score questions over workflow s
arXiv:2609.33136v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student to match a teacher's next-token distributions on student-generated trajectories. However, privileged infor
arXiv:2609.34478v1 Announce Type: new Abstract: Task-specific fine-tuning can rewrite a language model's answers beyond the training task, complicating updates that must preserve existing behavior. We
arXiv:2609.35665v1 Announce Type: cross Abstract: Interior-point methods (IPMs) are among the most widely used algorithms for constrained optimization, yet their Newton-based search directions require
arXiv:2605.06050v2 Announce Type: replace Abstract: Graph-based learning from functional magnetic resonance imaging (fMRI) has shown strong potential for brain network analysis. However, existing meth
arXiv:2609.35598v1 Announce Type: cross Abstract: We introduce the Functional Spectral-Newton Method (FSNM) for learning the leading singular structure of a conditional expectation operator without fi