PHBA: Prefix-State Hybrid Block Attention
arXiv:2610.08527v1 Announce Type: new Abstract: Hybrid architectures combining linear sequence models with softmax attention provide an effective balance between efficient long-context modeling and pr
Knowledge catalogue
arXiv:2610.08527v1 Announce Type: new Abstract: Hybrid architectures combining linear sequence models with softmax attention provide an effective balance between efficient long-context modeling and pr
arXiv:2610.06923v1 Announce Type: new Abstract: Artificial intelligence has advanced individual radiotherapy tasks, yet these capabilities remain separated across clinical stages, software environment
arXiv:2610.07962v1 Announce Type: cross Abstract: Where generalization capacity--the ability to extract context-invariant relational structures--first emerges remains a central question in AI and neur
arXiv:2512.23073v2 Announce Type: replace-cross Abstract: Fine-tuning has become the dominant paradigm for adapting Vision-Language Models (VLMs), yet most approaches rely on explicit weight updates t
arXiv:2610.08319v1 Announce Type: new Abstract: In proof assistants such as Lean, a generated proof must pass machine compilation checks, so evaluation needs no human scoring. Direct generation fails
arXiv:2610.08678v1 Announce Type: cross Abstract: Speculative decoding accelerates inference for a large language model (LLM), referred to as the target model, by first using a smaller model, referred
arXiv:2610.07745v1 Announce Type: new Abstract: Pose error in precision assembly can corrupt not only what a robot observes but also the coordinate frame in which it acts. On the FORGE benchmark, the
arXiv:2610.07385v1 Announce Type: new Abstract: Fine-tuning vision-language models (VLMs) is typically evaluated at a single downstream checkpoint, obscuring whether a semantic capability was never ac
arXiv:2610.07666v1 Announce Type: cross Abstract: This paper presents SENSE, a state-aware framework for generating playable branching visual novels with multi-track emotional navigation. Integrating
arXiv:2610.07091v1 Announce Type: new Abstract: The evolution of machine learning has progressively changed where intelligence resides in an AI system. In conventional machine learning the task, data
Today I’m excited to introduce OpenDocRouter - a unified API for document parsing with the latest frontier and open-weight models. There are a lot of VLMs and OCR models that can be used for document
arXiv:2610.07859v1 Announce Type: new Abstract: Conventional decentralized federated learning (DFL) often focuses on clients, with each client maintaining a model copy, performing updates individually
arXiv:2610.08463v1 Announce Type: new Abstract: Long-context inference and Retrieval-Augmented Generation (RAG) handle evidence selection at vastly different scales, from a single long prompt to an en
arXiv:2610.07261v1 Announce Type: new Abstract: A team of coding agents can look fine agent by agent yet fail as a team: each passes its own tests while the merged result is broken, and single-agent e
arXiv:2509.26189v2 Announce Type: replace Abstract: The rapid proliferation of Large Language Models has intensified the challenge of distinguishing LLM-generated text from human writing in non-Englis
arXiv:2610.07334v1 Announce Type: new Abstract: Interpretability methods for neural networks are predominantly reactive: they analyse activations produced during specific forward passes, requiring kno
arXiv:2610.07396v1 Announce Type: new Abstract: Navigation for humanoid robots is critical, yet large-scale evaluation on physical hardware is often impractical due to cost and safety concerns, making
arXiv:2610.07860v1 Announce Type: new Abstract: Multi-agent systems are increasingly deployed for complex knowledge work, yet their orchestration layers remain largely memoryless: each new task is dec
arXiv:2610.05166v1 Announce Type: cross Abstract: A safe action is not necessarily a viable one. Under a frozen vision-language-action (VLA) policy, an action can be likely and locally admissible yet
arXiv:2610.05782v1 Announce Type: cross Abstract: Agentic AI is emerging as a promising paradigm for automating complex cybersecurity decisions, yet its use in enforcing zero trust introduces signific
arXiv:2610.04391v1 Announce Type: new Abstract: Vision-language-action policies may predict a transferable manipulation strategy yet fail to realize it reliably on the encountered object: objects comp
arXiv:2610.06685v1 Announce Type: new Abstract: Clinical questions often depend on linking a patient's multimodal evidence to external biomedical knowledge, yet existing predictive systems rarely repr
arXiv:2610.06174v1 Announce Type: new Abstract: Can LLMs recognize degradation in their own computational substrate? Inspired by anosognosia, a neurological condition in which patients fail to recogni
arXiv:2412.14814v2 Announce Type: replace-cross Abstract: Although Answer Set Programming (ASP) allows constraining neural-symbolic (NeSy) systems, its employment is hindered by the prohibitive costs
arXiv:2610.05400v1 Announce Type: cross Abstract: Long-video agents can actively gather question-relevant evidence, but they typically leave a central decision implicit: when has the agent seen enough
arXiv:2610.05481v1 Announce Type: cross Abstract: Large language models for code generation often fail on execution, multilingual coverage, and contamination control, especially under frozen backbone
Maybe I'm mistaken, but wasn't one of the big pros of Ollama Cloud inference that it was all hosted by Ollama? If that's the case, why duplicate the Deepseek on-/off- hour premiums? Surely they do not
arXiv:2610.04792v1 Announce Type: cross Abstract: Missing modality remains a longstanding challenge in multimodal learning. Existing methods typically address this issue through modality recovery or a
arXiv:2610.05529v1 Announce Type: new Abstract: We present DynaMesh, a dynamic texture generation method for 3D meshes. Given a textureless shape and a text prompt describing an effect, our method pro
arXiv:2610.05387v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated strong performance on coding and reasoning benchmarks; however, their ability to solve graph-structured m
arXiv:2610.06394v1 Announce Type: new Abstract: Human-object interaction (HOI) detection aims to localize human-object pairs and recognize their interactions. Traditional supervised methods perform st
I wanted to build an offline bird/plant identifier that runs on a laptop with Ollama. Before building any UI, I tested it on 6 photos: Common Myna → gemma4:e2b said 'Jackdaw' (confidence: high). gemma
arXiv:2610.04544v1 Announce Type: cross Abstract: Many groups now delegate label ontology and metadata harmonization to agentic LLM pipelines. We built one and audited it. Our aggregate scores looked
arXiv:2610.06052v1 Announce Type: new Abstract: Three-dimensional (3D) left ventricular (LV) reconstruction from sparse cardiac magnetic resonance (CMR) imaging remains challenging due to inter-slice
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:2610.04924v1 Announce Type: new Abstract: Visually identical containers can conceal loads that require different handling decisions. We present TANav, which uses a brief nudge to measure push re
arXiv:2610.06852v1 Announce Type: new Abstract: Pipeline figures in ML papers must be repurposed across many canvases, including paper columns, 16:9 slides, portrait posters, 1:1 social teasers, 9:16
arXiv:2610.05191v1 Announce Type: new Abstract: DETR-style detectors use one-to-one bipartite matching during training to assign object queries to ground-truth objects, enabling end-to-end set predict
arXiv:2603.09693v2 Announce Type: replace Abstract: Predicting interfacial degradation and microstructural evolution through phase-field modelling is computationally intensive, particularly for parame
arXiv:2610.04108v1 Announce Type: new Abstract: Accelerating the prediction of long-term behavior in chaotic systems is crucial in scientific computing. However, existing methods rely on numerical sol
arXiv:2610.05010v1 Announce Type: new Abstract: Portrait aesthetic assessment assigns comparable scores according to how effectively human-centered images fulfill their photographic intent. These scor
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
Reflection AI Inc. today introduced Beam, an open-source large language model with 501 billion parameters. The launch comes a few months after the startup raised funding at a 25 billion valuation. Aro
arXiv:2610.05066v1 Announce Type: new Abstract: Adapting step-distilled text-to-image (T2I) models through post-training incurs additional computational costs and affects native few-step generation be
arXiv:2610.03076v1 Announce Type: cross Abstract: Neural network-based approaches have emerged as efficient alternatives to traditional optimization-based procedures for the calibration of stochastic
arXiv:2610.05664v1 Announce Type: new Abstract: Vision-and-Language Navigation (VLN) policies increasingly benefit from strong semantic priors provided by large vision-language models (VLMs). However,
arXiv:2602.02180v2 Announce Type: replace Abstract: Linearizing pretrained large language models (LLMs) primarily relies on intra-layer hybrid attention mechanisms to alleviate the quadratic complexit
arXiv:2610.03773v1 Announce Type: cross Abstract: Soft tactile sensors elevate robotic touch through enhanced flexibility and adaptability, yet most existing designs depend on embedded electronics tha
Endpoint management and security company Tanium Inc. today expanded its Security Operations portfolio with new detection, response and threat-hunting tools built on its Tanium Atlas agentic artificial
arXiv:2610.04627v1 Announce Type: new Abstract: Object detection under image degradation can benefit from clean-image supervision, but aggregate gains do not imply that transferred representation chan
arXiv:2610.05925v1 Announce Type: new Abstract: Entropy-based selection objectives suffer from a fundamental degeneracy: minimizing Shannon entropy H(p_A) rewards confident selection regardless of whe
arXiv:2610.05310v1 Announce Type: cross Abstract: Frozen speech foundation models (SFMs) make downstream adaptation efficient: the backbone can stay fixed while a task learns layer fusion and a lightw
arXiv:2610.04925v1 Announce Type: new Abstract: Time-series forecasting informs critical decisions in energy dispatch, industrial operations, and environmental monitoring; understanding the patterns m
arXiv:2610.06317v1 Announce Type: cross Abstract: Article 50 (2) of the EU Artificial Intelligence Act requires providers of generative systems to make synthetic outputs machine-readable and detectabl
arXiv:2610.06274v1 Announce Type: new Abstract: Many agent runtimes give the agent a tool for editing its own configuration. Some of that configuration grants abilities, such as enabling a tool. Other
arXiv:2610.03289v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) achieve strong performance across vision-language tasks, yet the internal mechanisms by which visual and textua
arXiv:2610.02431v1 Announce Type: new Abstract: Deep neural networks achieve high accuracy through layered numerical transformations, yet their decisions remain difficult to audit because decision evi
arXiv:2610.03314v1 Announce Type: cross Abstract: Flow- and diffusion-based generative models have recently emerged as flexible and highly efficient forecasting models for dynamical systems. When comb
Disclosure: I made this. Sharing it here because it is fully local and small, and I want feedback from people who run models on their own machines. What it is: a 395M decision model (ModernBERT-large
arXiv:2610.02267v1 Announce Type: new Abstract: Agent harnesses make many small, typed decisions per task: which model to call, which tool to use, whether retrieved text is relevant, whether an input