Knowledge catalogue
arXiv:2603.09493v2 Announce Type: replace-cross Abstract: The adaptation of large-scale vision-language models (VLMs) to downstream tasks with limited labeled data remains a significant challenge. Whi
arXiv:2606.04197v1 Announce Type: cross Abstract: How much should an LLM agent remember, and how should multi-agent systems be connected when trying to reach consensus? We show these two design choice
arXiv:2510.20042v3 Announce Type: replace Abstract: Generative image models produce striking visuals yet often misrepresent culture. Prior work has examined cultural bias mainly in text-to-image (T2I)
Finally! the first eval ship from cog!!!!!!!!!! 👼🏼 To contextualize: @METR_Evals cap out at ~16 hours. Cog has private enterprise evals up to 100hrs, and is confident enough to put a financial guarant
arXiv:2606.04282v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are predominantly evaluated on free-form vision-language tasks such as visual question answering, captioning, a
arXiv:2603.19225v3 Announce Type: replace-cross Abstract: Real-world financial decision-making is a challenging problem that requires reasoning over heterogeneous signals, including company fundamenta
arXiv:2509.23385v5 Announce Type: replace-cross Abstract: Simulation-based inference (SBI) is transforming experimental sciences by enabling parameter estimation in complex non-linear models from simu
arXiv:2606.04986v1 Announce Type: new Abstract: Recent studies have explored Vision-Language Models (VLMs) for food analysis. However, most existing methods rely primarily on supervised fine-tuning (S
foom! Our internal data shows Claude is accelerating AI development—a possible path to recursive self-improvement, or AI autonomously building a more capable successor. It’s happening faster than we t
Tom Dotan / Newcomer: Founders Fund launches a TV-style game show featuring A-list founders and investors, including Sam Altman and Palmer Luckey, playing a game of Mafia — Do people want to watch the
arXiv:2606.04381v1 Announce Type: cross Abstract: Recent large language models (LLMs) often appear to exhibit spatial reasoning ability; however, this capability is largely symbolic, arising from patt
arXiv:2606.04329v1 Announce Type: cross Abstract: Memory is a core component of AI agents, enabling them to accumulate knowledge across interactions and improve performance. However, persistent memory
arXiv:2606.05142v1 Announce Type: cross Abstract: Recent developments in multi-view image editing with generative models have brought us a step closer toward general 3D content generation and customiz
arXiv:2606.04525v1 Announce Type: new Abstract: Progress in genomic foundation models is difficult to assess due to fragmented benchmarks, incompatible evaluation protocols, and task-specific reportin
arXiv:2601.06196v3 Announce Type: replace-cross Abstract: Large language models (LLMs) frequently generate factually incorrect or unsupported content, commonly referred to as hallucinations. Prior wor
arXiv:2606.05124v1 Announce Type: cross Abstract: After the success of 3D Gaussian Splatting (3DGS) for novel view synthesis, many works have explored how to also use it for geometric surface represen
arXiv:2606.04385v1 Announce Type: new Abstract: Foundation models have driven rapid progress in computer vision, yet the two dominant paradigms, vision-language foundation models (VLMs) and vision-onl
A security researcher spent 1,500 running 13+ AI models against a deliberately vulnerable app, with GPT-5.5 achieving a 70% solve rate while Gemini refused to engage almost entirely. The test app cont
arXiv:2604.02121v2 Announce Type: replace-cross Abstract: Stochastic kinetic models are ubiquitous in physics, yet inferring their parameters from experimental data remains challenging. For determinis
arXiv:2606.05116v1 Announce Type: new Abstract: We introduce the Graph Set Transformer (GST), a neural network architecture for learning on sets of graphs, designed for tasks in which per-element pred
arXiv:2606.04019v1 Announce Type: cross Abstract: Recent studies on sensor-language alignment have shown that two-stage frameworks can improve the semantic modeling ability of wearable-sensor human ac
arXiv:2606.04184v1 Announce Type: new Abstract: True general intelligence requires not only a model of the physical world but also a social world model: the capacity to infer how individual mental sta
arXiv:2606.04888v1 Announce Type: new Abstract: Traditional Chinese Medicine (TCM) ocular inspection provides empirical cues for assessing scleral surface anomalies, but its clinical use remains subje
arXiv:2503.10629v2 Announce Type: replace Abstract: Adversarial attacks pose significant challenges for vision models in critical fields like healthcare, where reliability is essential. Although adver
arXiv:2402.02555v2 Announce Type: replace-cross Abstract: In this work, we propose ESG, a pipeline for high-quality entity segmentation and grounding supported by a new dataset EntitySeg. At first, th
Highlighting recent advances in multi-GPU and tensor parallel support in llama.cpp Over the last few months llama.cpp maintainers and engineers from NVIDIA collaborated to improve the multi-GPU perfor
arXiv:2606.04126v1 Announce Type: cross Abstract: We introduce HighTide, an evolving AI-assisted benchmark suite. Specifically, the contributions are: (i) a diverse open-source suite spanning multiple
arXiv:2606.05143v1 Announce Type: new Abstract: Scaling robust robot policies requires more than broader randomization, because physical-domain experience must remain organized and learnable throughou
Dynamic workflows in Claude Code enable the model to handle complex, multi-step tasks by allowing execution flows to adapt based on intermediate results rather than following fixed paths. This capabil
This guide explains how to adapt NVIDIA's Nemotron 3.5 Automatic Speech Recognition (ASR) model to specific languages, domains, or accents through fine-tuning techniques. It likely covers the fine-tun
Nemotron-3-Ultra is a large language model available through Ollama's model library, likely representing an advanced iteration in NVIDIA's Nemotron model series optimized for performance and capabilit
arXiv:2606.04434v1 Announce Type: new Abstract: Multimodal In-Context Learning (ICL) has emerged as a practical inference paradigm for Multimodal Large Language Models, where a small set of interleave
I am hooked on Dynamic Workflows! The idea of generating harnesses on the fly is so compelling that I reverse-engineered it for my agent orchestrator. And then I built a monitoring dashboard (as an HT
arXiv:2601.17469v2 Announce Type: replace Abstract: Graph Neural Networks (GNNs) have shown remarkable capabilities in learning from graph-structured data with various applications such as social anal
Elon Musk shared a trailer for 'Iliad (Troy)' created using Grok Imagine 1.5, Xai's newly released text-to-image generation model. The post demonstrates the capabilities of the latest version of Grok'
arXiv:2606.04457v1 Announce Type: new Abstract: Incorporating visual semantic representations as an intermediate step before image generation can reduce the modeling difficulty between text and images
arXiv:2606.04545v1 Announce Type: new Abstract: Recent advances in generative image editing have improved the realism and controllability of localized image manipulation, raising new challenges for im
OpenAI Group PBC’s newly released proposal for how advanced artificial intelligence should be regulated differs slightly from the Trump administration’s executive order, also released this week. Relea
arXiv:2606.05071v1 Announce Type: new Abstract: Language-guided photo retouching aims to adjust color and tone while preserving geometry and texture. Recently, diffusion-based retouching shows a super
arXiv:2602.04101v2 Announce Type: replace Abstract: We present Interfaze, a native hybrid model that fuses task-specific deep neural networks (CNNs and DNNs) directly into a transformer decoder throug
Introducing NVIDIA Nemotron 3 Ultra. A frontier smart open model built for long-running agents that need to plan, reason, use tools and keep working across complex coding, research and enterprise work
Introducing two NVIDIA Nemotron models on Together AI: Nemotron 3 Ultra for high-throughput agentic workloads and Nemotron 3.5 ASR for low-latency multilingual speech recognition. AI natives can now b
arXiv:2606.05025v1 Announce Type: cross Abstract: Large language models (LLMs) suffer from shortcut learning: they systematically fail on out-of-distribution (OOD) inputs whose semantic surface differ
arXiv:2602.12147v4 Announce Type: replace Abstract: Time series foundation models (TSFMs) are revolutionizing the forecasting landscape from specific dataset modeling to generalizable task evaluation.
arXiv:2606.05104v1 Announce Type: new Abstract: Knowledge benchmarks for LLMs face three issues: scaling-driven designs that do not operationalize disciplinary representativeness; flat-payment annotat
arXiv:2606.04382v1 Announce Type: cross Abstract: Automated subject cataloging assigns controlledvocabulary headings to bibliographic records, but LCSH has no standard public benchmark. We introduce L
arXiv:2602.12215v2 Announce Type: replace Abstract: Recent robot foundation models largely rely on large-scale behavior cloning, which imitates expert actions but discards transferable dynamics knowle
arXiv:2606.04552v1 Announce Type: new Abstract: Genomic foundation models increasingly adopt large language model architectures, yet almost universally rely on fixed tokenization schemes such as k-mer
arXiv:2606.04672v1 Announce Type: cross Abstract: Continuous-time dynamic graphs (CTDGs) provide a richer framework to capture fine-grained temporal patterns in evolving relational data. Long-range in
arXiv:2603.03205v2 Announce Type: replace Abstract: Agentic language models operate in a fundamentally different safety regime than chat models: they must plan, call tools, and execute long-horizon ac
Leaving aside the question of consciousness, the Ted Chiang piece has a reasonable point about moral atrophy if you let AI make choices. But it is also interesting in light of the fact that repeated r
arXiv:2606.04660v1 Announce Type: new Abstract: Lifelong digital companions must integrate cross-session cues, continually update their understanding of users, and adapt to shifting privacy boundaries
arXiv:2606.04050v1 Announce Type: cross Abstract: Existing quantization methods are fundamentally limited by rigid, integer-based bit-widths (e.g., 2, 3-bit), resulting in a ``deployment gap' where La
arXiv:2606.04485v1 Announce Type: new Abstract: Tabular foundation models (TFMs) increasingly rival tree ensembles, but their performance is often compute-inefficient: with standard affine scalar toke
Listen to the OpenAI Podcast on— Spotify https://open.spotify.com/episode/3ca5s3o53D5xcEKmKgLLGj?si=4a9a555641fa4293 Apple https://podcasts.apple.com/us/podcast/how-a-reasoning-model-cracked-an-80-yea
arXiv:2606.04339v1 Announce Type: new Abstract: Computational models of epilepsy promise patient-specific treatment design, but most optimization workflows still search for parameters that perform wel
arXiv:2409.11901v2 Announce Type: replace Abstract: Personalization plays a critical role in numerous language tasks and applications, since users with the same requirements may prefer diverse outputs
arXiv:2606.04274v1 Announce Type: new Abstract: As large language models (LLMs) become default tools for online information verification, an implicit assumption follows them: that scale and general ca
arXiv:2505.17315v2 Announce Type: replace Abstract: Recent language models exhibit strong reasoning capabilities, yet the influence of long-context capacity on reasoning remains underexplored. In this
OpenAI's developer account posted this message on X (formerly Twitter), likely encouraging developers to explore additional features, updates, or resources available in OpenAI's Showcase platform or d