Knowledge catalogue
arXiv:2608.21794v1 Announce Type: cross Abstract: GUI grounding evaluations that expose UI elements as text metadata often treat high instruction-element embedding similarity as evidence of semantic g
arXiv:2608.22370v1 Announce Type: new Abstract: Task-specific LoRA adapters offer a modular way to specialize large language and vision-language models. However, existing adapter composition methods a
arXiv:2608.23058v1 Announce Type: new Abstract: Large language models (LLMs) now support forecasting systems that combine language-based reasoning with temporal data, evidence retrieval, external tool
Hi, I’m having fun using “huihui_ai/Qwen3.6-abliterated:35b-Claude-4.7” for pen testing. It’s uncensored so it does whatever I want. I’m on M4 Pro 14 core 64GB. Just wondering if there are some models
arXiv:2510.11358v3 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) is typically optimized for topical relevance, yet its success ultimately depends on whether retrieved pas
arXiv:2608.21836v1 Announce Type: new Abstract: Large language models have become increasingly capable agents for low-level code and kernel optimization, but isolated kernel benchmarks provide only a
arXiv:2608.21858v1 Announce Type: cross Abstract: The rapid evolution of energy structures has positioned microgrids as pivotal components of next-generation power systems, offering enhanced resilienc
arXiv:2608.22417v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to support text analysis in qualitative research, yet evidence on their performance in inductive cont
Hey everyone, I'm trying to set up a local LLM on my machine. My goal is to use it with Qwen Code or OpenCode to help me out with small to medium sized tasks, but nothing too big. I tested many differ
arXiv:2607.16327v2 Announce Type: replace Abstract: Medical image segmentation is essential for modern computer-aided medicine. Recently, text-guided segmentation has shown promise by incorporating cl
arXiv:2608.23200v1 Announce Type: new Abstract: Large language models are increasingly expected to execute complex workflows whose success depends on maintaining interdependent constraints and produci
arXiv:2608.23090v1 Announce Type: new Abstract: Looping videos are essential for practical applications such as web graphics, game development, and social media. However, existing approaches typically
arXiv:2608.21561v1 Announce Type: new Abstract: Fisher width measures the Gaussian width of a probe set after deformation by the local Fisher geometry. We study its evolution along learning trajectori
arXiv:2608.22465v1 Announce Type: new Abstract: High-fidelity free-viewpoint video (FVV) and interactive rendering increasingly rely on explicit Gaussian representations, yet practical deployment rema
I’ve been going back and forth on this for a week and I can’t settle it, so I’m hoping someone here has hands-on numbers. The two configs (German prices, dealer quote, incl. VAT): Config Price Mac Stu
At $10k, you could get - 6.2B tokens with Qwen 3.8 Max (Qwen Pro plan) - 5.7B tokens with DeepSeek V4 Pro OpenRouter - 100B tokens with DeepSeek V4 Flash OpenRouter As a firm believer of local inferen
arXiv:2601.20996v2 Announce Type: replace Abstract: Existing benchmarks for computational materials discovery primarily evaluate static predictive tasks or isolated computational sub-tasks. While valu
arXiv:2608.21407v1 Announce Type: cross Abstract: Vision-language-action (VLA) models face a crucial tradeoff between their task success rate and the policy-call frequency. Executing a single action p
arXiv:2608.22460v1 Announce Type: new Abstract: Public mass-shooting databases differ substantially in coverage, feature availability, and reporting practices, creating challenges for machine-learning
arXiv:2509.23705v2 Announce Type: replace Abstract: Multi-robot coverage path planning commonly balances geometric area or path length under a constantspeed assumption. This assumption is inadequate w
arXiv:2608.21664v1 Announce Type: new Abstract: Safe deployment of increasingly capable models will likely come to rely on latent-space monitoring as a complement to behavioral evaluations, especially
arXiv:2608.23397v1 Announce Type: new Abstract: Interactive clinical agents must gather decisive evidence and convert it into grounded actions under partial observability. A correct final diagnosis al
arXiv:2608.22323v1 Announce Type: new Abstract: The application of Large Language Models (LLMs) to diagnostic decision-making has garnered growing interest. However, existing benchmarks largely focus
arXiv:2608.21867v1 Announce Type: new Abstract: LLM agents are moving from single-prompt use to long task streams in which reusable memory becomes a core capability for terminal, software-engineering,
arXiv:2608.22061v1 Announce Type: new Abstract: Personal AI agents routinely consume external content while performing tasks such as web browsing, email processing, and SNS feed summarization, and the
arXiv:2608.22149v1 Announce Type: cross Abstract: LLMs generate fluent plans for robots but routinely violate the syntactic and se8mantic constraints they must satisfy to execute, and existing remedie
arXiv:2509.19005v2 Announce Type: replace-cross Abstract: The Minimum Bisection Problem is a fundamental, computationally hard graph partitioning problem with applications in parallel computing, netwo
arXiv:2608.23497v1 Announce Type: new Abstract: Reasoning-Induced Misalignment, where fine-tuning on reasoning data containing no harmful content, including mathematics, code, and problem-solving with
arXiv:2507.09924v2 Announce Type: replace-cross Abstract: Continually updating model-based indexes in generative retrieval with new documents remains challenging, as full retraining is computationally
arXiv:2608.23035v1 Announce Type: new Abstract: As on-device LLM agents evolve into personal copilots, the mobile operating system has become a key testbed for this paradigm, making rigorous capabilit
arXiv:2608.21533v1 Announce Type: new Abstract: Robotic Fulfillment Centers (FCs) store inventory on shelves (pods) arranged in dense blocks. Retrieving a target pod that is buried deep in a block req
arXiv:2505.15798v2 Announce Type: replace Abstract: Certifying the IID generalisation ability of deep networks is the first of many requirements for trusting AI in high-stakes applications from medici
arXiv:2508.13533v2 Announce Type: replace Abstract: Within a model family, a smaller variant is often deployed as a drop-in replacement for a larger one when their performance is similar. However, per
arXiv:2608.22926v1 Announce Type: new Abstract: Gaze is increasingly used as an input signal for vision and multimodal models, yet no consensus exists on how to represent it across datasets. Raw trace
arXiv:2608.23238v1 Announce Type: new Abstract: We present Mover360, a controllable object manipulation framework for 360{eg} images. Unlike perspective images, 360{eg} images in equirectangular proje
arXiv:2608.22236v1 Announce Type: cross Abstract: Large audio-language models (LALMs) have shown promising progress in understanding speech, music, and general sound events, yet their ability to reaso
arXiv:2608.22045v1 Announce Type: cross Abstract: Modern scientific facilities and instruments generate datasets at scales that are difficult for individual researchers to discover, access, and explor
arXiv:2608.23484v1 Announce Type: new Abstract: We present Team Semiintelligencn's solution for the ACM RecSys 2026 TalkPlayData Challenge, addressing conversational music recommendation through a mul
arXiv:2608.21454v1 Announce Type: new Abstract: The same fruit appears in a bunch, unpicked, peeled, bagged in plastic, or sliced on a dish, so automated fruit classification in the wild (AFCW) must a
arXiv:2608.23323v1 Announce Type: cross Abstract: Continuous optimisation methods need to balance sharing information and maintaining alternative search directions. In this paper, we introduce Mycelia
arXiv:2412.04806v2 Announce Type: replace-cross Abstract: Adapting Large Language Models (LLMs) trained on discrete text data, to forecast continuous time series signals is challenging. While finetuni
arXiv:2608.23179v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly attractive for automating network configuration, yet their reliability and failure patterns are poo
arXiv:2608.23022v1 Announce Type: cross Abstract: The dynamics of particles in the early universe are described by Boltzmann equations, which involve high-dimensional phase-space integrals. Classical
arXiv:2608.22643v1 Announce Type: cross Abstract: Deploying large language models on edge devices is increasingly limited by a widening gap between model size and available memory. Existing approaches
We have been working on some performance optimisations for Qwen3.8 and other models. The main new feature that we introduced is adaptive speculation for Llama.cpp What is it? MTP and DFlash work well
arXiv:2608.22331v1 Announce Type: new Abstract: We audit measurement variability for 3 native tool-calling endpoints across 2 providers on the official BFCL multiple and parallel categories, using mat
Protecting capital in today's markets requires immense speed and precision. A financial analyst preparing a deal memo works across licensed market data, internal models, and confidential client files.
Few professions are as exacting as the practice of law. A team reviewing a contract or building a case works inside strictly privileged information, firm-specific playbooks, and a body of law that cha
Exposure management company Nucleus Security Inc. today unveiled Nucleus Helix, an artificial intelligence engine that now sits at the center of its platform. Three new capabilities run on the engine.
arXiv:2608.22757v1 Announce Type: cross Abstract: Unified models for visual understanding and generation have made rapid progress, yet they still lack the ability to understand and manipulate the spat
arXiv:2508.07173v3 Announce Type: replace Abstract: Omni-modal Large Language Models (OLLMs) that integrate visual, auditory, and textual processing face severe safety risks. They exhibit fragile defe
arXiv:2608.22637v1 Announce Type: new Abstract: Recent vision-language models (VLMs) show strong capabilities in robotic perception and spatial reasoning, yet their ability to reason about complex mec
arXiv:2608.22089v1 Announce Type: cross Abstract: Modern software systems require earlier and more scalable vulnerability severity assessment to reduce exposure to high-impact security flaws. Security
arXiv:2606.13610v2 Announce Type: replace-cross Abstract: Search-augmented LLMs increasingly mediate everyday consumer recommendations by retrieving live web content. This creates a new risk: LLM reco
arXiv:2608.22026v1 Announce Type: new Abstract: Accurate simulation of the long-time evolution of systems governed by partial differential equations (PDEs) is central to scientific computing. Among ex
Open models, open science. Qwen keeps growing steadily, and we'll always be right here with the research community.🙌 Thanks for the deep dive! @natolambert Over the weekend I had Codex parse 500K arXi
Emma Roth / The Verge: OpenAI says its Jalapeño chip delivered 1.5x-1.9x more AI work per watt and 1.7x-3.6x lower latency vs. Nvidia chips across GPT-OSS, DeepSeek R1, Kimi K2.5 1T — Jalapeño outperf
OpenWorker -- an open source agent that doesn't just chat but completes tasks on your laptop -- just released a new version with many features for security workflows. After our initial release, many u
arXiv:2608.22039v1 Announce Type: new Abstract: Structure-from-Motion (SfM) is a cornerstone of 3D perception, yet current methods often fail when applied to complex videos involving challenging camer
arXiv:2608.22279v1 Announce Type: cross Abstract: Recent vision language models (VLMs) have achieved strong progress in video understanding. However, most existing video QA research and benchmarks sti