Knowledge catalogue
arXiv:2608.19025v1 Announce Type: new Abstract: Accurately extracting nuanced, contextualized data from research articles is laborious and time intensive. Here, we investigate the performance of front
arXiv:2608.18282v1 Announce Type: cross Abstract: Stochastic mean-field control (MFC) provides a fundamental framework for coordinating large populations of interacting agents under uncertainty, with
arXiv:2603.05202v2 Announce Type: replace Abstract: Medical image segmentation is critical for computer-aided diagnosis. However, dense pixel-level annotation is time-consuming and costly, and medical
arXiv:2608.18560v1 Announce Type: cross Abstract: Fine-grained control over continuous semantic attributes of 3D objects is essential for 3D content creation, but is not well supported by conventional
arXiv:2606.15091v3 Announce Type: replace-cross Abstract: Brain-computer interfaces (BCIs) can restore sensory and motor function in individuals with severe neurological impairment, but the literature
arXiv:2608.18303v1 Announce Type: new Abstract: LLM-as-judge evaluation reduces response quality assessment to a single holistic A/B preference choice, providing no mechanism to isolate which quality
arXiv:2608.18545v1 Announce Type: new Abstract: Multilingual large language models often generalize across languages, and prior work suggests that their internal mechanisms can overlap cross-lingually
arXiv:2608.18863v1 Announce Type: cross Abstract: We study Bayesian optimization in a time-varying environment where the unknown reward function evolves according to a Gaussian process drift model. Ex
Should you use Codex, Claude, or ChatGPT? If I’m a business professional wondering TODAY whether to use ChatGPT or Claude or Claude Cowork or Claude Code or Codex, here is what AI I would use under di
arXiv:2608.18779v1 Announce Type: cross Abstract: Semantic-ID mappings are reusable interfaces between item tokenizers and generative recommenders, yet released mappings rarely state whether they are
arXiv:2608.18263v1 Announce Type: new Abstract: Traffic signal control is a complex sequential decision-making problem requiring real-time adaptation and trade-offs among throughput, delay fairness, s
arXiv:2608.18915v1 Announce Type: new Abstract: Hardware shifts, color variations, and changing patient characteristics between development and deployment routinely break trained medical image classif
arXiv:2608.18319v1 Announce Type: new Abstract: Neural networks trained on nonstationary tasks frequently lose the ability to fit new targets, a phenomenon referred to as loss of plasticity. We identi
arXiv:2608.18933v1 Announce Type: cross Abstract: Large language model (LLM) based agents have demonstrated remarkable proficiency in automated software issue resolution, yet they often struggle to re
arXiv:2608.18852v1 Announce Type: new Abstract: Agent frameworks increasingly package procedural knowledge as skills: instruction files an agent reads on demand, while public libraries now hold thousa
arXiv:2603.04448v2 Announce Type: replace Abstract: Current AI agents can flexibly invoke tools and execute complex tasks, yet their long-term advancement is hindered by the lack of systematic accumul
arXiv:2608.18921v1 Announce Type: cross Abstract: Existing LRM-DoS methods rely heavily on model feedback to synthesize attack queries, requiring either repeated queries to the target model or trainin
this screenshot is without MTP usage , fully offloaded onto the GPU. using LM STUDIO i wanted to ask you guys if theres a way to make it even faster , as MTP really didnt help and is infact slower due
So @swyx and team are still judging his amazing “Kill My SaaS in one weekend” contest, where you could win 10K to replace his 40K/year conference submission (CFP) and scheduling SaaS. I think 68 peopl
arXiv:2608.18237v1 Announce Type: cross Abstract: Estimating the difference of two Stein's score functions is a fundamental problem in generative modeling. In particular, score differences arise natur
arXiv:2608.18701v1 Announce Type: new Abstract: Physical interaction quality is central to deformable-object manipulation, yet most benchmarks evaluate task success alone. A policy may complete the ta
arXiv:2608.18111v1 Announce Type: new Abstract: Foundation models such as GPT and Claude now solve olympiad-level mathematics with remarkable proficiency, so much so that geometry problem solving has
Marina Temkin / TechCrunch: Source: AI training data startup Micro1's gross annual run rate grew from 100M to 500M in the past eight months, putting net annual run rate at 150M-200M — The near-bottoml
Rachel Metz / Bloomberg: Source: Anthropic plans a safety system this year that still requires enterprises to retain data for 30 days but lets them do so on their own cloud systems — Anthropic PBC pla
Bloomberg: Sources: Broadcom is in talks with a group of lenders to raise 60B+ in debt for an AI chip financing deal that will benefit Anthropic and other companies — Broadcom Inc. is in talks with a
Qianer Liu / The Information: Sources: Nvidia plans to begin small-batch shipments of an LPU tailored for Chinese customers by the end of 2026; the chip complies with US export control rules — Nvidia
Newcomer: Sources: Poolside struck a non-exclusive 6B licensing deal with Nvidia, plus a 1B investment at a $12B pre-money valuation; 109 staffers get Nvidia job offers — EXCLUSIVE TO NEWCOMER: Poolsi
arXiv:2608.19197v1 Announce Type: cross Abstract: Continuous self-improvement requires an ever-expanding pool of self-generated, diverse, adaptive goals. For language agents, existing training environ
arXiv:2608.18616v1 Announce Type: new Abstract: Fetal cardiac MRI (fCMR) provides valuable diagnostic information complementary to echocardiography, particularly for complex congenital heart disease (
arXiv:2608.18585v1 Announce Type: new Abstract: Vision-based industrial anomaly detectors are calibrated on one distribution but may be deployed on another that differs in illumination, fixture placem
This is gonna seem crazy off-topic, but I saw Spider-Man the other day and couldn’t help but notice how well executed E.V. is as an agentic system. compared to Jarvis, it felt much more grounded and c
arXiv:2608.19080v1 Announce Type: new Abstract: Object detectors often produce over-confident predictions for objects outside their training categories, leading to so-called out-of-distribution (OoD)
arXiv:2608.18102v1 Announce Type: new Abstract: The widespread adoption of large language models (LLMs) has intensified the demand for principled methods to distinguish human from machine-generated te
arXiv:2608.18532v1 Announce Type: new Abstract: Existing VLMs have achieved strong performance in video understanding, yet they struggle with long-video spatiotemporal reasoning when target objects be
arXiv:2608.18105v1 Announce Type: cross Abstract: StocksTalk is a voice-enabled conversational system for transforming spoken financial screening requests into executable and validated structured quer
Stop using your agent logs just for debugging. Use them to train your own model. Today we're launching Agnost AI (YC S26)'s first model: agnost-*******-0.1 Trained for our first customer on their exis
arXiv:2608.19003v1 Announce Type: new Abstract: We ask whether internal representation statistics can provide useful example-level difficulty signals for adaptive inference in multilingual African NLP
arXiv:2602.04083v3 Announce Type: replace-cross Abstract: Accurate channel state information in wideband MIMO systems is constrained by pilot overhead, a challenge intensifying as bandwidths scale tow
arXiv:2608.19078v1 Announce Type: new Abstract: Foundation models are increasingly adapted for downstream medical imaging tasks, yet the influence of the chosen adaptation strategy on subgroup fairnes
arXiv:2608.18087v1 Announce Type: cross Abstract: Existing subword tokenizers optimize statistical compression but ignore morphological structure, particularly the relationship between roots and affix
arXiv:2608.18899v1 Announce Type: new Abstract: Class expression learning often produces complex OWL class expressions that are difficult to interpret and reason over. However, by following theoretica
They released both GGUFs & custom llama.cpp fork today. 35B MOE in 7GB size which's good for Mobile & Edge devices(Also low memory systems). Up to 120 t/s on Consumer Laptop. GGUFs: https://huggingfac
arXiv:2608.18437v1 Announce Type: new Abstract: Tangut is an extinct language whose script does not explicitly mark word boundaries. We present the first systematic study of Tangut word segmentation u
arXiv:2608.18351v1 Announce Type: cross Abstract: Tool-using large language-model agents can complete a task while exercising authority that the user did not grant or the task does not need, causing e
arXiv:2605.05962v2 Announce Type: replace Abstract: This paper addresses end-to-end geospatial question answering over multilingual toponymic data. We introduce a bilingual (Russian-Tatar) dataset of
arXiv:2608.18602v1 Announce Type: new Abstract: Computer vision is increasingly used to automate recognition tasks in large ecological datasets, but more complex tasks such as multi-object tracking co
arXiv:2608.18667v1 Announce Type: new Abstract: Modern deep learning architectures have demonstrated strong performance in dental CBCT segmentation. One remaining crucial challenge is accurate tooth l
arXiv:2608.18115v1 Announce Type: cross Abstract: Token-level hallucination detectors score each token independently from a single signal, and fail exactly when the generating model is confidently wro
From the screenshots: Hy4 is now live, labeled 'Expert-Level Model' + 'Use Tools to Solve Problems' Hy3 is tagged with 'New Upgrade,' positioned as a brand-new general-purpose model DeepSeek, focused
arXiv:2608.18808v1 Announce Type: new Abstract: This paper introduces Tensor Field Models (TFMs), realization-level Mathematical Structures in which a learned Operator maps a product of admissible com
arXiv:2608.18931v1 Announce Type: cross Abstract: Test-time scaling (TTS) improves language model outputs by spending additional inference compute - generating multiple candidates, searching over part
Component Validated configuration Motherboard ASRock Rack SPC621D8U-2T/OVH CPU Xeon Gold 6330 (Get gold/platinum if interested in Optane Pmem gimmicks) GPU fabric Two Broadcom/PLX PEX88096 islands, ei
arXiv:2608.18144v1 Announce Type: cross Abstract: Modal auxiliaries such as must, should, and have to mark necessity and obligation within the contexts of speaker authority and interpersonal stance. W
the elephant in the room that no company wants to address: “OpenAI’s 69-page report on ChatGPT enterprise adoption doesn’t address the biggest question: ROI” by @EmilyForlini https://fortune.com/2026/
arXiv:2608.18433v1 Announce Type: new Abstract: Robot foundation models (RFMs), including vision-language-action (VLA) policies, are often discussed through a scaling view: more data, larger models, a
arXiv:2608.18715v1 Announce Type: cross Abstract: Ensuring not only high accuracy but also reliable and robust predictions is critical for the deployment of semantic segmentation models in safety-crit
“The Last Human Review” is where we are heading to, but, you do need to work a little or a lot to enbale it. Once we will get there, we won’t be able to go back Live now: our AI Architects, Show my Wo
arXiv:2608.18300v1 Announce Type: new Abstract: LLM-as-a-Judge, which leverages a large language model to evaluate natural language generated by another AI application or model, has become a standard,
The most important agentic workflows are the ones where you collaborate with the agent, verify its results, and encode them as a skill or verifier for reuse. This works for things like writing, resear
The real benchmark for an AI agent isn’t what it says. It’s what it gets done. AutoClaw, @Zai_org 's AI Agent for Work, is built to turn intent into finished output. Give it a complex task. AutoClaw b