Knowledge catalogue
arXiv:2609.27166v1 Announce Type: new Abstract: Capability and efficiency are two key dimensions of reasoning in large language models (LLMs). Capability refers to the ability to solve a given problem
Scribd, Inc. is home to one of the world's largest collections of human-created content. Scribd’s products leverage one of the world's largest collections of human-created content and intelligent tool
arXiv:2609.27175v1 Announce Type: cross Abstract: Multimedia verification requires not only accurate decisions but also traceable evidence, reliable human correction, and safe reuse of prior experienc
arXiv:2609.27671v1 Announce Type: new Abstract: 4D radar complements dense image semantics with long-range geometry and radial motion, but existing radar--camera detectors largely solve where to align
arXiv:2609.27717v1 Announce Type: new Abstract: Human-written agent skills encode rich workflows for real-world problem solving, but are typically used as external inference-time instructions rather t
arXiv:2609.26907v1 Announce Type: cross Abstract: Memes often derive their harmful, hateful, or sarcastic meaning from small but decisive visual, textual, or cross-modal cues. Existing multimodal clas
arXiv:2609.27904v1 Announce Type: new Abstract: As information technology advances, digital content has become widely adopted across diverse fields such as news broadcasting, entertainment, commerce,
arXiv:2609.27287v1 Announce Type: new Abstract: Real-time payment fraud detection is a non-stationary streaming prediction problem: adversaries adapt before supervised labels mature, and localized bur
arXiv:2606.18305v2 Announce Type: replace-cross Abstract: Operator learning is an emerging field at the intersection of machine learning and scientific computing. By learning mappings between function
arXiv:2609.27606v1 Announce Type: new Abstract: We introduce State-Grounded Conditioning (SGC), a design principle for user-facing LLM agents that must condition on live user state (game state, sessio
Knowledge management startup Stravito AB today introduced a Model Context Protocol server that lets people access the company’s consumer and market research from AI tools such as OpenAI Group PBC’s Ch
arXiv:2609.27227v1 Announce Type: new Abstract: Objective assessment of robotic surgery uses instrument kinematics, which must be reconstructed when only video is available. We introduce a kinematic r
arXiv:2609.27988v1 Announce Type: new Abstract: Methods operating on Vision Transformer (ViT) feature spaces typically rely on Euclidean distance or cosine similarity. This assumes that every directio
arXiv:2609.28077v1 Announce Type: new Abstract: Steel surface defect detection is critical for automated industrial quality control but remains challenging due to subtle inter-class texture difference
arXiv:2609.28029v1 Announce Type: cross Abstract: The key-value (KV) cache of autoregressive transformers can be viewed as a fourth-order tensor spanning attention heads, tokens, features, and grouped
arXiv:2609.27669v1 Announce Type: cross Abstract: Small language models (SLMs) are increasingly paired with knowledge graphs (KGs), yet end-to-end KG question answering conflates graph access, search,
arXiv:2609.27953v1 Announce Type: cross Abstract: Some LLM-based recommendation rerankers are evaluated under an oracle protocol that guarantees the ground-truth item is present in the scored set, eit
arXiv:2609.27250v1 Announce Type: cross Abstract: The Schrodinger bridge owes its computational power to a single structural fact: by Girsanov's theorem the controlled problem is a Kullback--Leibler (
arXiv:2609.28424v1 Announce Type: new Abstract: Catalog skin recolouring has to change pigment and leave shading alone. The classical Reinhard map does not make that split: it rescales lightness by th
arXiv:2609.25804v2 Announce Type: replace Abstract: LLM agents increasingly work on long-horizon tasks, and the decisions they make along the way, such as which hypothesis to test or which implementat
Google Cloud has become the platform of choice for startups building AI. Our uniquely complete stack — including a choice of first- and third-party compute and models; our platform for building and ma
arXiv:2609.27853v1 Announce Type: cross Abstract: A normal--inverse-gamma (NIG) latent hierarchy has four parameters, but its induced latent law does not identify all four. For sigma^2simInvGamma(alph
With the release of ThinkingCap-Qwen3.8-27B, I thought it would be worthwhile to do a comparison between the original Qwen3.8-27B, the new ThinkingCap, and Swift-Qwen3.8-27B. Both Swift which I alread
arXiv:2607.10669v2 Announce Type: replace Abstract: Bayesian optimization (BO) is widely used for expensive black-box problems, yet practical performance depends not only on high-level algorithmic cho
Today we establish that AI is as good as expert human tutors for immediate GRE learning gains (p=.015, n=2,383 students, study conducted July-Sep 2026). One hour with an expert GRE tutor: $75. One equ
arXiv:2609.26911v1 Announce Type: new Abstract: A single locally plausible tool call can derail an otherwise successful agent trajectory. Suspicion alone does not justify intervention, because the rep
Hey everyone, Jovan from UkisAI here! Today, we are introducing Swift, a family of efficient reasoning LLMs based on Qwen, trained by penalizing tokens related to pathological overthinking patterns an
arXiv:2609.27510v1 Announce Type: cross Abstract: Modern large language models are pretrained on massive datasets, making it difficult to prevent benchmark data from entering their training sets and u
arXiv:2603.08930v2 Announce Type: replace-cross Abstract: This paper introduces a benchmark for evaluating whether vision-language models (VLMs) can generate plant simulation configurations from image
arXiv:2609.26830v1 Announce Type: cross Abstract: Simulation success is not equivalent to structural correctness for LLM-generated circuits. We define and measure four evaluation levels -- schema vali
arXiv:2609.27778v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) has made real-time, high-fidelity 3D rendering practical, yet turning this explicit representation into a native generative
arXiv:2609.28099v1 Announce Type: new Abstract: Deep vision systems remain vulnerable to corruption, occlusion, and distribution shift despite strong benchmark performance. Existing reliability method
arXiv:2512.11490v2 Announce Type: replace Abstract: Satellite imagery differs from natural images in viewpoint, resolution, scale variation, and the prevalence of small objects -- demanding both regio
arXiv:2508.13680v5 Announce Type: replace Abstract: We introduce VMMU, a Vietnamese Multitask Multimodal Understanding and Reasoning Benchmark designed to evaluate how vision-language models (VLMs) in
arXiv:2510.01354v2 Announce Type: replace-cross Abstract: Multiple prompt injection attacks have been proposed against web agents. At the same time, various methods have been developed to detect gener
arXiv:2609.27064v1 Announce Type: new Abstract: A joint fact-verification score assesses answers and submitted evidence together. When the score improves, how much of the gain remains if the answers a
arXiv:2609.27822v1 Announce Type: cross Abstract: A common multi-agent design asks agents to report confidence and lets the highest-scoring agent speak next, implicitly using one scalar both to route
arXiv:2609.27679v1 Announce Type: new Abstract: What reusable computation should a tabular foundation model learn when every table defines a new supervised task? We develop in-situ representation refi
arXiv:2609.27408v1 Announce Type: cross Abstract: Benchmarks for vision-language models offer their answer choices in some convention: a letter, a color name, a pixel coordinate. That convention is tr
arXiv:2609.27819v1 Announce Type: new Abstract: Federated wearable models eventually serve people absent from source training, but favorable average accuracy does not establish that unlabeled onboardi
arXiv:2609.27124v1 Announce Type: cross Abstract: Federated Learning enables decentralized model training by exchanging model updates--rather than raw data--with a central parameter server (PS). While
arXiv:2609.27603v1 Announce Type: cross Abstract: In-Context Learning (ICL) has become a cornerstone of modern LLM deployment. However, existing ICL post-training methods have a critical blind spot: t
arXiv:2609.27411v1 Announce Type: new Abstract: Machine fault diagnosis from vibration requires learning from scarce labelled fault recordings while meeting the computational constraints of edge devic
arXiv:2609.26955v1 Announce Type: new Abstract: Fairness audits in production ML typically occur once, at deployment, on a single domain. Both fail in practice: fairness can shift after retraining or
arXiv:2609.27449v1 Announce Type: new Abstract: Generalist robot manipulation policies have developed rapidly, yet their reliable evaluation remains challenging due to fundamental flaws in existing si
arXiv:2609.27203v1 Announce Type: new Abstract: xlog is a CUDA-native logic programming engine integrating neural perception with deterministic Datalog, probabilistic inference, and epistemic world vi
arXiv:2609.27199v1 Announce Type: new Abstract: Sparse communication in decentralized zeroth-order learning requires compatible peer-state coordinates. We characterize this one-hop condition and devel
10,000 OpenAI agents worked 88 hours on the Navier-Stokes Clay prize problem Alas, open models fall off hard on long tasks With Zenith, @deepseek_ai's V4.1 Flash reaches the frontier & beats GPT-5.6 S
Almost everything is in the Title. For some reason I had to use a quantized version of the text encoder (NF4) but was able to run the BF16 version of the denoiser on my 5090. (BTW if I missed somethin
arXiv:2609.25511v1 Announce Type: new Abstract: Vision-based gesture control accepts commands from any hand in the camera field of view, which is unsafe in shared indoor spaces. This paper presents IG
arXiv:2609.22476v1 Announce Type: cross Abstract: Transmission system operators face rising complexity from renewable integration, reduced inertia, and tighter security margins. Large language models
In real-time streaming, every millisecond counts. For example, at 30 frames per second (fps), developers have a strict frame budget of just 33.3 ms (and only 16.6 ms at 60 fps) to ingest camera frames
arXiv:2609.25541v1 Announce Type: new Abstract: Tabular foundation models learn to predict cell values in context, whereas world-model self-supervision asks for prediction in representation space (LeC
arXiv:2609.25781v1 Announce Type: new Abstract: Graph Incremental Learning has garnered increasing attention as dynamic graph data continues to emerge across diverse fields. Conventional approaches pr
arXiv:2602.01163v2 Announce Type: replace Abstract: Safe UAV emergency landing requires more than just identifying flat terrain; it demands understanding complex semantic risks (e.g., crowds, temporar
arXiv:2609.26167v1 Announce Type: new Abstract: Activation-energy pruning -- removing weights whose product of magnitude and cumulative pre-synaptic spike count falls below a threshold -- was establis
arXiv:2609.26781v1 Announce Type: new Abstract: A multi-agent system can reduce latency on complex tasks by executing work concurrently. Several pioneering harness frameworks support multi-agent syste
arXiv:2609.23512v1 Announce Type: new Abstract: Large language model agents are typically deployed with predefined configurations, although the required model capability, context, tools, permissions,
arXiv:2609.25047v1 Announce Type: new Abstract: Autonomous agents that automatically build artificial intelligence (AI) models could broaden access to AI across science and engineering. A popular line
Alert: Apple just dropped a new model on Hugging Face. It's a Qwen3.5-9B finetune that turns long documents into small page images to save tokens, then pulls up the full text of only the pages relevan