Knowledge catalogue
It’s a really special time to be alive…some thoughts from training this model 🧵 Today, we share a breakthrough on the planar unit distance problem, a famous open question first posed by Paul Erdős in
arXiv:2605.19371v1 Announce Type: cross Abstract: Diffusion models are widely used in image generation, with most relying on noise-based corruption and denoising. A distinct branch instead uses blur a
An OpenAI general-purpose reasoning model autonomously disproved a conjecture posed by Paul Erdos in 1946, overturning 80 years of mathematical belief. The breakthrough concerns the planar unit distan
Reuters: Russia's Sberbank says it hopes to use Chinese chips to power its flagship GigaChat AI model, as sanctions continue to block the country's access to hardware — Russia hopes to power its flags
arXiv:2605.18835v1 Announce Type: new Abstract: Traditional sheet metal forming relies on time-consuming and expensive Finite Element Analysis (FEA) for design validation, a process that significantly
arXiv:2605.19319v1 Announce Type: new Abstract: Visual prediction has emerged as a promising paradigm for embodied control, where future observations are generated and then translated into actions. Ho
arXiv:2509.24143v2 Announce Type: replace Abstract: In this paper, we propose a new modeling approach and a fast algorithm for 3D motion planning, applicable for fixed-wing unmanned aerial vehicles. T
Agentmw is an open-source middleware framework designed to enhance AI agent reliability and efficiency across different models and frameworks. It addresses key operational challenges including mid-run
arXiv:2605.17435v1 Announce Type: new Abstract: Biomedical question answering often requires decisions from retrieved literature whose relevance, quality, and support for candidate answers are uneven.
arXiv:2604.04932v3 Announce Type: replace Abstract: The misuse of large language models (LLMs) requires precise detection of synthetic text. Existing works mainly follow binary or ternary classificati
arXiv:2605.18036v1 Announce Type: cross Abstract: Trust calibration -- aligning user trust judgment with model capability -- is crucial for safe deployment of explainable AI (XAI), yet is often evalua
arXiv:2602.20200v2 Announce Type: replace-cross Abstract: Hierarchical Vision-Language-Action (VLA) models have rapidly become a dominant paradigm for robotic manipulation. It typically comprising a V
arXiv:2506.23287v3 Announce Type: replace Abstract: In single-cell research, tracing and analyzing high-throughput single-cell differentiation trajectories is crucial for understanding biological proc
Walk through running quality, cost, and latency evaluations for the Foundry model router using an open-source GitHub repo designed for router-aware eval pipelines. The post How to run evals for the mo
arXiv:2605.17761v1 Announce Type: cross Abstract: Insider threats often reveal early anomalies through disruptions in behavioral statistics-such as altered recurrence patterns or short-versus long-ter
arXiv:2605.18128v1 Announce Type: new Abstract: Existing Multivariate Time Series Anomaly Detection (MTSAD) frameworks increasingly rely on integrating Graph Neural Networks (GNNs) with sequence model
arXiv:2605.16991v1 Announce Type: cross Abstract: Response-free item difficulty modelling promises to reduce reliance on response-based calibration but is intrinsically difficult on reading-comprehens
arXiv:2509.22061v2 Announce Type: replace-cross Abstract: Speech Continuation (SC) is the task of generating a coherent extension of a spoken prompt while preserving both semantic context and speaker
arXiv:2504.13217v3 Announce Type: replace-cross Abstract: Large language models (LLMs) have become increasingly embedded in organizational workflows. This has raised concerns over their energy consump
arXiv:2605.06506v2 Announce Type: replace Abstract: Language-model (LM) surprisal is widely used as a proxy for contextual predictability and has been reported to correlate with metaphor novelty judgm
arXiv:2605.17113v1 Announce Type: cross Abstract: Existing deception datasets label completed outputs as honest or deceptive, treating deception as a property of the final response rather than a funct
arXiv:2605.17821v1 Announce Type: cross Abstract: Large Language Model (LLM) training is frequently interrupted by a heterogeneous spectrum of failures, from common GPU crashes to catastrophic cluster
At Google I/O, we introduced a unified development toolkit featuring Antigravity 2.0 and the Managed Agents API, giving developers better ways to build locally and deploy securely to the cloud on a sh
arXiv:2509.15267v2 Announce Type: replace-cross Abstract: The costs of generative model compute rekindled promises and hopes for efficient data curation. In this work, we investigate whether recently
arXiv:2605.15905v1 Announce Type: cross Abstract: Modeling long-term user interests with massive historical user behaviors enhances click-through rate (CTR) prediction performance in advertising and r
Introducing Composer 2.5, our most powerful model yet. It's more intelligent, better at sustained work on long-running tasks, and more reliable at following complex instructions. For the next week, we
Note that as of last summer Waymo said that LLMs/VLMs were experimental, and that their foundation model then could “process only a small amount of image frames, does not incorporate accurate 3D sensi
Together with SpaceXAI, we’re training a significantly larger model from scratch, using 10x more total compute. With Colossus 2’s million H100-equivalents and our combined data and training techniques
arXiv:2605.16079v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have shown significant progress in video understanding, yet they face substantial challenges in tasks requiring p
The best feature of @xai Grok Build right now is how it handles subagents and personas. Most people still treat the model like one very smart intern that has to do everything at once. Grok Build took
Interesting interpretability paper on tool-using agents. The authors probe hidden states and find the model often recognizes it should call a tool, but fails to actually call one. The mismatch ranges
arXiv:2605.14242v1 Announce Type: cross Abstract: The monitoring of fetal heart rate (FHR) and the assessment of its variability are crucial for preventing fetal compromise and adverse outcomes. Howev
arXiv:2603.14851v3 Announce Type: replace Abstract: Integrating vision-language models (VLMs) into end-to-end (E2E) autonomous driving (AD) systems has shown promise in improving scene understanding.
arXiv:2605.14305v1 Announce Type: new Abstract: Discrete diffusion language models improve generation efficiency through parallel token prediction, but standard X_0 prediction methods introduce factor
arXiv:2605.14712v1 Announce Type: cross Abstract: Robot imitation data are often multimodal: similar visual-language observations may be followed by different action chunks because human demonstrators
arXiv:2605.14805v1 Announce Type: new Abstract: Accurate dynamics models are critical for aerial manipulators operating under complex tasks such as payload transport. However, modeling these systems r
arXiv:2604.05306v2 Announce Type: replace-cross Abstract: Large language models (LLMs) often produce confident yet incorrect answers, which can lead to risky failures in real-world applications. We st
New Template Batch Drop SELFIE modeled by @paranoidream Classic Bedroom Mirror https://grok.com/imagine/templates/8a017403-bbad-428c-8900-5e338c7f3eb4 Post-Shower Fresh Look https://grok.com/imagine/t
Ollama 0.24 now supports integration with a Codex app, allowing users to run open-source models through the application after updating to the latest version. The feature enables users to select and ut
arXiv:2605.14765v1 Announce Type: cross Abstract: Persian music, with its unique tonalities, modal systems (Dastgah), and rhythmic structures, presents significant challenges for music generation mode
arXiv:2507.21433v3 Announce Type: replace-cross Abstract: Large Reasoning Models (LRMs) are becoming integral to many AI inference systems, enhancing their capabilities with advanced reasoning. Howeve
arXiv:2601.03630v2 Announce Type: replace Abstract: This paper presents the first systematic comparison investigating whether Large Reasoning Models (LRMs) are superior judges to non-reasoning LLMs. O
arXiv:2605.14551v1 Announce Type: new Abstract: Instance normalization (IN) is widely used in non-stationary multivariate time series forecasting to reduce distribution shifts and highlight common pat
arXiv:2605.14368v1 Announce Type: cross Abstract: Continuous diffusion language models lag behind autoregressive transformers, partly because diffusion is applied in spaces poorly suited to language d
arXiv:2605.13724v1 Announce Type: cross Abstract: Few-step video generation has been significantly advanced by consistency distillation. However, the performance of consistency-distilled models often
arXiv:2605.12952v1 Announce Type: new Abstract: Grad-ECLIP is published at ICML 2024 and represents a new Transformer interpretation technical route (intermediate features-based). First, this paper de
DID SOMEONE SAY FREE TOKENS IN FLEET???? Yes it's true. Fleet now has a built in model powered by @FireworksAI_HQ that's free for all Developer & Plus plan users. Try it out today (or before @hwchase1
arXiv:2605.12790v1 Announce Type: new Abstract: Modeling concentric tube robots (CTRs) involves complex nonlinear continuum mechanics, and despite recent progress, physics-based models often lack an a
LangSmith Fleet has introduced a free model option powered by Fireworks AI for users on Developer and Plus plans, lowering the barrier to entry for getting started with the platform. This update makes
arXiv:2602.23013v3 Announce Type: replace Abstract: Detecting visual anomalies in industrial inspection often requires training with only a few normal images per category. Recent few-shot methods achi
arXiv:2605.13158v1 Announce Type: new Abstract: Image restoration under multiple adverse weather conditions aims to develop a single model to recover the underlying scene with high visibility. Weather
you can see more here (color stuff is at bottom): http://colorfeelings.replit.app - changing embedding model may change results - the similarity range was pretty small so normalizing really stretched
arXiv:2605.11233v1 Announce Type: new Abstract: Effective model selection is critical in symbolic regression (SR) to identify mathematical expressions that balance accuracy and complexity, and have lo
Introducing GridSFM, a small foundation model that can predict AC optimal power flow in milliseconds, boosting efficiency and unlocking cost savings. Learn how GridSFM gives grid operators direct visi
arXiv:2605.11596v1 Announce Type: new Abstract: Closed-loop driving simulation requires real-time interaction beyond short offline clips, pushing current driving world models toward autoregressive (AR
arXiv:2605.10948v1 Announce Type: cross Abstract: Understanding how vegetation loss alters rainfall remains a major challenge in climate and hydrological science, as deforestation modifies precipitati
arXiv:2412.18594v3 Announce Type: replace Abstract: Gaussian graphical model selection is usually studied under independent sampling, but in many applications observations arise from dependent dynamic
arXiv:2511.06077v2 Announce Type: replace Abstract: Short-video recommenders such as Douyin must exploit extremely long user histories without breaking latency or cost budgets. We present an end-to-en
arXiv:2510.05497v5 Announce Type: replace-cross Abstract: Large-scale Mixture of Experts (MoE) Large Language Models (LLMs) have recently become the frontier open-weight models, achieving remarkable m
This article argues that infrastructure quality and architecture are more critical to AI/ML project success than the choice of underlying model. It likely explores how proper deployment, scaling, moni