Search: “index”

arXiv:2610.13527v1 Announce Type: cross Abstract: Multimodal language models (MLLMs) exhibit promising spatial reasoning capabilities, yet the internal mechanisms supporting them remain poorly underst

arXiv:2610.12544v1 Announce Type: new Abstract: Masked diffusion models (MDMs) generate discrete data by iteratively unmasking multiple tokens in parallel using a learned mask predictor. Their output

arXiv:2610.10135v1 Announce Type: cross Abstract: Sparse attention mechanisms estimate attention over n tokens using a small subset of keys. Many existing approaches use maximum inner product search (

arXiv:2610.10310v1 Announce Type: new Abstract: Recursive self-improvement requires carrying accepted changes into later improvement cycles, while studying agent-proposed changes also requires substan

arXiv:2610.07059v1 Announce Type: new Abstract: Yield forecasts help planners and farmers decide on inputs, storage and imports, but small agricultural tables can make reported accuracy fail on a new

arXiv:2610.07388v1 Announce Type: cross Abstract: Joint Models simultaneously model longitudinal and survival outcomes, leveraging patterns in patients' longitudinal trajectory to improve the predicti

arXiv:2610.07928v1 Announce Type: cross Abstract: Dynamic multimodal learning aims to learn robust representations by adaptively modeling information discrepancies across modalities. However, existing

arXiv:2610.07676v1 Announce Type: cross Abstract: Research on transformer expressivity shows whether a transformer is capable of solving a given task, but gives little indication of whether the soluti

arXiv:2603.21276v2 Announce Type: replace-cross Abstract: The growing demand for on-device large language model (LLM) services on mobile edge devices has driven the adoption of Mixture-of-Experts (MoE

arXiv:2606.31429v2 Announce Type: cross Abstract: We introduce a geometric formulation of statistical feature learning for supervised regression. Feature learning is defined through a base--fiber deco

arXiv:2610.08089v1 Announce Type: cross Abstract: In semantic query engines, predicates are evaluated by machine-learned models, and the choice of a query plan affects not only the cost of a query but

arXiv:2610.04708v1 Announce Type: new Abstract: Operator learning methods such as DeepONets and FNOs often struggle with PDE families featuring sharp interfaces, heterogeneous coefficients, and locali

arXiv:2610.04195v1 Announce Type: cross Abstract: Personal AI agents in enterprise multi-tenant deployments share a common vector store for long-term memory. Shared embedding spaces create a surface f

arXiv:2610.06686v1 Announce Type: new Abstract: Long context inference with large language models becomes increasingly expensive as attention must operate over an ever growing KV cache. Page sparse at

arXiv:2610.04162v1 Announce Type: new Abstract: Selecting the best k items out of m candidates is a critical component of modern large language model systems, such as document selection in Retrieval-A

arXiv:2610.06691v1 Announce Type: cross Abstract: Embedding enhancement improves speaker verification under acoustic mismatch without modifying a frozen backbone. Recent work has established a practic

arXiv:2610.05891v1 Announce Type: new Abstract: Post-hoc class activation maps (CAMs) are a standard tool for inspecting the evidence behind an image classifier's predictions, yet nothing in ordinary

arXiv:2610.06610v1 Announce Type: cross Abstract: We study contextual bandits in which a surrogate is observed after the action but before the learner decides whether to acquire the primary outcome th

arXiv:2610.05700v1 Announce Type: new Abstract: Recurrent sequence models must decide how strongly to overwrite their memory at each token. Read as Bayesian filtering, this write is the gain of a Kalm

arXiv:2610.03400v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has substantially advanced multimodal reasoning, yet it remains fundamentally limited by ambiguous token-

arXiv:2610.02875v1 Announce Type: cross Abstract: Multilingual encoders can exhibit reduced retrieval effectiveness when queries and relevant documents differ in language, despite strong same-language

arXiv:2610.03087v1 Announce Type: cross Abstract: Deterministic data loading is important for foundation model development: model researchers need confidence that differences they observe across costl

arXiv:2610.00069v1 Announce Type: cross Abstract: Long-horizon ego/exo data contains rich procedural evidence, but are redundant, noisy, and costly to process or retain. We propose a compact framework

arXiv:2610.00436v1 Announce Type: new Abstract: Online batch selection fine-tunes a language model on the most useful part of each candidate batch. Selectors that match the gradient of the candidate b

arXiv:2610.01288v1 Announce Type: new Abstract: Dynamic Movement Primitives (DMPs) provide a compact and stable formulation for trajectory representation and generalization in robot skill learning. Ho

arXiv:2610.00586v1 Announce Type: cross Abstract: Activation memory, not compute, limits CNN inference on constrained hardware such as microcontrollers. Direct in-place convolution removes the dual-bu

arXiv:2610.00384v1 Announce Type: cross Abstract: The Natural Image Quality Evaluator (NIQE) scores an image by its statistical distance from a model fitted on pristine images, and its distributed mod

arXiv:2610.00403v1 Announce Type: new Abstract: A network can fit its training examples while failing to recover the rule that generated their labels. We examine this separation in single-hidden-layer

arXiv:2609.38195v1 Announce Type: new Abstract: Operators for interfacial problems are trained on reference solutions produced by the solver they are intended to replace. This work develops a data-fre

arXiv:2609.39585v1 Announce Type: new Abstract: AI video generators have not only become harder to detect but are used to generate a diverse set of scenarios from landscapes to street views to animal

arXiv:2609.36835v1 Announce Type: new Abstract: Long-context large language model inference is bottlenecked by KV caches that grow linearly with sequence length. This burden is especially severe for l

arXiv:2609.19963v2 Announce Type: cross Abstract: Exploration in centralized serial-dictatorship matching bandits must use complete matchings, so learning one player-arm pair can impose regret on othe

arXiv:2601.11433v2 Announce Type: replace Abstract: Deep Differentiable Logic Gate Networks (LGNs) and Lookup Table Networks (LUTNs) are demonstrated to be suitable for the automatic classification of

arXiv:2609.37499v1 Announce Type: new Abstract: Historical archives are an under-used source for extending the instrumental climate record backward in time, and LLMs offer a way to extract the indices

arXiv:2609.35193v1 Announce Type: new Abstract: Understanding how two entities are connected often requires tracing multi-hop relations across documents to identify intermediate entities and supportin

arXiv:2609.33746v1 Announce Type: new Abstract: At each decoding step a language model attends over the key-value (KV) cache of every earlier token, so at long context the attention call is bounded by

arXiv:2609.31101v1 Announce Type: cross Abstract: The flatness of the loss landscape at a minimizer is a widely used heuristic for reasoning about neural-network generalization, yet evidence for this

arXiv:2609.30738v1 Announce Type: new Abstract: KV cache eviction methods such as SnapKV and PyramidKV rank tokens solely by mean attention over a small observation window. We study a unified score, m

arXiv:2609.30160v1 Announce Type: new Abstract: Automatic speech recognition is typically trained assuming that the reference transcript is the only valid labeling of an utterance, yet even nominally

arXiv:2609.29735v1 Announce Type: new Abstract: Long-horizon tasks require preserving and later recovering cross-session evidence under a bounded, query-blind memory budget. Existing compression can d

arXiv:2609.29709v1 Announce Type: cross Abstract: An LLM judge scores a bank of responses against a rubric, and the reliability comes back at 0.52. What has been measured? Judge evaluation has begun b

arXiv:2609.28399v1 Announce Type: new Abstract: Language models typically construct attention values from contextual hidden states, even when some of their content may be reusable across contexts. We

arXiv:2609.27526v1 Announce Type: new Abstract: Long-horizon navigation requires an agent to revise its intermediate objectives as evidence accumulates. Full visual histories are costly to process, wh

arXiv:2609.26605v1 Announce Type: cross Abstract: Foundation model embeddings of screening mammograms may encode pre-diagnostic tissue change without task-specific adaptation. We tested whether embedd

arXiv:2602.02940v2 Announce Type: replace-cross Abstract: Formal semantics and distributional semantics are distinct approaches to linguistic meaning: the former models meaning as reference via model-

arXiv:2609.23769v1 Announce Type: new Abstract: The disambiguation of semantically similar statutory text across jurisdictions is a retrieval problem that existing methods do not solve. This inter-con