Knowledge catalogue
Quantising the K/V cache is the highest-leverage memory setting most people never touch, and it has one behaviour in the docs that catches almost everyone. Every number below is out of Ollama's own FA
arXiv:2608.25398v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have demonstrated strong abilities in solving diverse visual and textual reasoning tasks. However, their develo
arXiv:1902.10193v4 Announce Type: replace Abstract: While idiosyncrasies of the Chinese classifier system have been a richly studied topic among linguists (Adams and Conklin, 1973; Erbaugh, 1986; Lako
arXiv:2608.25034v1 Announce Type: new Abstract: Standard neural architectures often fail to generalize to longer inputs for dynamic programming (DP) targets. We investigate what makes this hard geomet
arXiv:2608.25609v1 Announce Type: new Abstract: We identify a previously unreported phenomenon in CLIP representations: human and AI-generated paintings spontaneously separate along the dominant princ
arXiv:2608.25904v1 Announce Type: new Abstract: Multilingual language models transfer knowledge across languages through shared subword vocabulary, a mechanism that breaks down when related languages
arXiv:2608.26058v1 Announce Type: new Abstract: Scaling generalist vision-language-action (VLA) policies is severely bottlenecked by the inherent heterogeneity of embodied data, which spans diverse ro
arXiv:2608.25936v1 Announce Type: cross Abstract: On-policy distillation trains a language model on its own generations while a teacher scores them token by token. It combines the dense supervision of
One way to think of current AI is as a big sponge for patterns. It absorbs and operationalizes any pattern it is exposed to (albeit with very low data efficiency at training time). Once you can progra
arXiv:2510.04938v2 Announce Type: replace-cross Abstract: Neural architecture search (NAS) automates the design process of high-performing architectures, but remains bottlenecked by expensive performa
OpenAI Group PBC today published an open letter signed by more than 100 technology companies, banks, insurers and security vendors warning that artificial intelligence-enabled cyberattacks will become
Sam Sabin / Axios: OpenAI, Anthropic, AWS, Microsoft, and 100+ companies warn there is “a limited window” to prepare for AI-enabled cyberattacks and call for “collective action” — OpenAI, Anthropic, A
Maxwell Zeff / Wired: OpenAI is testing a “Persistent mode” in Codex, designed to let AI agents “continue working until put to sleep” and proactively generate follow-up tasks — Code reviewed by WIRED
Ivan Mehta / TechCrunch: OpenAI launches ads on its ChatGPT Free and Go subscription tiers in India, where it has 100M+ weekly active users, and plans to launch an ad manager next month — It seems the
Today on Decoder, I’m talking to Verge senior AI reporter Hayden Field about some pure Decoder bait: the seemingly-endless org chart changes at OpenAI, and how all of them seem to consolidate power un
arXiv:2608.25274v1 Announce Type: new Abstract: Fine-grained Cross-View Localization (CVL) estimates the precise position and orientation of a ground-level image by aligning it with geo-referenced aer
arXiv:2603.11051v2 Announce Type: replace-cross Abstract: We release OpenSanctions Pairs, the first large-scale public benchmark for entity matching on sanctions and OSINT data. The dataset includes 7
arXiv:2608.25515v1 Announce Type: new Abstract: Finger vein verification is a promising biometric modality for secure authentication because vascular patterns are internal, difficult to observe extern
arXiv:2608.25674v1 Announce Type: new Abstract: This work proposes a Deep Learning Enhanced PVT algorithm to mitigate multipath interference in dense urban areas. A supervised objective jointly predic
arXiv:2410.10368v3 Announce Type: replace Abstract: We present the first linear time complexity randomized algorithms for unbiased approximation of the celebrated family of general random walk kernels
🚨Our new research examines agentic shopping: can you consistently predict (or, using marketing, influence) what an agent chooses? Nope. We found that even small differences (viewing order of pages, me
arXiv:2608.25231v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models appear to encode moral content as robustly as dense models, yet prove far more fragile in their encoding. In OLMoE-1B-
I was using UD-Q3_K_XL until now with more than 140000 context. Quality wise it's very good, very few erroneous tool calls. Then I saw many others here reporting good results with IQ3_XXS, so I gave i
arXiv:2608.25662v1 Announce Type: new Abstract: In 2026, we held the fourth iteration of the SHROOM Shared Task series: SHROOM-Visions (extbf{S}hared-task on extbf{H}allucinations and extbf{R}elated e
arXiv:2608.24907v1 Announce Type: cross Abstract: In health and nutrition consulting, widely used prompting methods pass the user profile as an unstructured block without a dedicated analysis step, le
arXiv:2608.25038v1 Announce Type: new Abstract: We introduce grounded glossary generation, a structured task requiring models to recover semantically meaningful Sanskrit phrases and produce translatio
arXiv:2608.25472v1 Announce Type: new Abstract: Photoacoustic computed tomography (PACT) combines optical absorption contrast with acoustic detection for high-resolution deep-tissue imaging. A persist
arXiv:2608.25970v1 Announce Type: new Abstract: Multimodal medical prediction often faces incomplete pairing: auxiliary modalities with complementary signal are available for only a subset of subjects
arXiv:2608.24905v1 Announce Type: cross Abstract: Service robots may encounter ambiguous user requests that require context-aware inference. Users may also have unique preferences with certain tasks w
arXiv:2608.25365v1 Announce Type: new Abstract: Noisy node classification problem is a fundamental yet challenging task for real-world graph-related web services, where node labels are often corrupted
arXiv:2510.04724v2 Announce Type: replace Abstract: This paper introduces a methodology for task-specific design optimization of multirotor Micro Aerial Vehicles. By leveraging reinforcement learning,
arXiv:2601.17103v2 Announce Type: replace Abstract: Performance uncertainty quantification is essential for reliable validation and eventual clinical translation of medical imaging artificial intellig
arXiv:2608.26011v1 Announce Type: new Abstract: Redirecting unmanned aerial vehicles (UAVs) from their intended mission trajectories has been an active area of research. However, existing UAV redirect
arXiv:2602.18728v2 Announce Type: replace-cross Abstract: Unsupervised multi-view clustering (MVC) aims to partition data into meaningful groups by leveraging complementary information from multiple v
arXiv:2608.25275v1 Announce Type: cross Abstract: Learned traffic-behavior models are commonly trained separately for each intersection, creating model portfolios that cannot share evidence across sit
arXiv:2608.24970v1 Announce Type: new Abstract: Physics-Informed Neural Networks (PINNs) have emerged as an important class of numerical methods for solving partial differential equations (PDEs). Howe
arXiv:2608.25564v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) often rely on over-parameterized models to optimize coupled solution and differential-residual objectives, leav
arXiv:2608.25401v1 Announce Type: new Abstract: Neural radiance fields (NeRFs), 3D Gaussian Splatting (3DGS), and related novel-view synthesis methods are commonly evaluated under capture and reconstr
arXiv:2608.26088v1 Announce Type: cross Abstract: Addressing critical global challenges, from food security and disaster risk to disease outbreaks and socio-economic vulnerability, demands high-fideli
arXiv:2608.25622v1 Announce Type: cross Abstract: Practical video editing is not only pixel generation: an editor must turn a brief, a clip pool, music metadata, and hard constraints into an executabl
arXiv:2608.26091v1 Announce Type: cross Abstract: Civil infrastructure compliance checking has long relied on engineers manually reading legacy 2D plans; however, OCR-based automation strips away the
Plaud Inc., the maker of artificial intelligence-enabled note-taking devices, today introduced the Plaud One Explorer Edition, a pair of earbuds and a charging box that connect people to AI agents for
arXiv:2608.25735v1 Announce Type: cross Abstract: Hosted retrieval-augmented generation (RAG) and semantic search allow users to query valuable provider-held corpora, raising two competing demands: to
arXiv:2608.25299v1 Announce Type: new Abstract: Vision-language models (VLMs) increasingly rely on point coordinates as a compact and executable interface for visual grounding in GUI interaction, robo
arXiv:2608.25486v1 Announce Type: cross Abstract: Long Narrative Reasoning is an essential capability for processing and reasoning over complex narratives. While retrieval-augmented generation provide
arXiv:2608.25495v1 Announce Type: new Abstract: Human-robot interaction (HRI) requires robots to interpret human actions early in their execution in order to respond safely, efficiently, and naturally
arXiv:2608.25858v1 Announce Type: new Abstract: High-resolution precipitation fields are essential for hydrological impact assessment, yet global climate model outputs are too coarse and biased for di
arXiv:2608.25311v1 Announce Type: new Abstract: Diffusion Language Models (DLMs) have recently become increasingly competitive with autoregressive (AR) models, and even outperform them on certain task
arXiv:2608.26070v1 Announce Type: new Abstract: Test-time scaling uses extra test-time compute to improve performance, such as letting language models reason longer when solving a problem. As models k
arXiv:2511.05393v2 Announce Type: replace Abstract: Visual Quality Assessment (QA) seeks to predict human perceptual judgments of visual fidelity. While recent multimodal large language models (MLLMs)
arXiv:2608.25666v1 Announce Type: new Abstract: Bimanual manipulation in cluttered, contact-rich environments remains challenging because it requires coordinated motion generation, interaction-aware p
arXiv:2410.07632v3 Announce Type: replace Abstract: We study what provable privacy attacks can be shown for trained 2-layer ReLU neural networks, focusing on two types of attacks: membership inference
arXiv:2608.25336v1 Announce Type: new Abstract: Large language models (LLMs) can fluently verbalize statistical evidence, yet statistical reports can still drift numerical values, invert effect direct
Putting this tweet in the “scary” category of AI. Calling upon the non-technical business professionals that follow me to pay attention. I’m breaking down the key parts of the @RyanGreenblatt tweet on
arXiv:2608.25907v1 Announce Type: new Abstract: Driver behavior is heterogeneous, context-dependent, and changes over time, and these properties shape the traffic phenomena we observe. Most models, ho
arXiv:2602.17281v2 Announce Type: replace-cross Abstract: Quantum generative modeling, where the Born rule naturally defines probability distributions through measurement of parameterized quantum stat
arXiv:2608.25922v1 Announce Type: new Abstract: GNN-based Knowledge Graph Question Answering (KGQA) pipelines process queries through four discrete stages: entity linking, subgraph retrieval, GNN reas
Qwen3.8-Flash is now live on @OpenRouter! ⚡ Coding assistants, agentic workflows, long-video understanding, all one API call away. Qwen3.8 Flash from @Alibaba_Qwen is now live on OpenRouter. A multimo
Got the new Qwen3.8-Flash-Next (176B total, 6B active MoE) running locally and figured I'd share for anyone else wondering if their setup can handle it. **My hardware:** 192GB DDR5 RAM, RTX 5070 Ti (1
specs hardware: M4 Max 128GB Studio inference engine: oMLX & lllama.cpp insights it still very early, so had to disable oMLX K/V caching, qwen4_exp architectureis not yet supported + the obvious n-gra