All entries

arXiv:2604.20869v1 Announce Type: cross Abstract: Background: More than 80% of U.S. cancer care is delivered in community settings, where survival remains worse than at academic centers. Clinicians mu

arXiv:2604.21060v1 Announce Type: new Abstract: Accurate diagnosis of pediatric brain tumors, starting with histopathology, presents unique challenges for deep learning, including severe data scarcity

arXiv:2604.20924v1 Announce Type: new Abstract: Timely and interpretable early warning of sepsis remains a major clinical challenge due to the complex temporal dynamics of physiological deterioration.

Cloud-hosted models will become more niche/seldom-used as much cheaper local models fulfill that which 90% of consumers need from AI. Lots of models to buy/use, but very few hardware options upon whic

arXiv:2604.21270v1 Announce Type: cross Abstract: There has been remarkable progress over the past decade in establishing finite-sample, non-asymptotic bounds on recovering unknown system parameters f

arXiv:2604.20987v1 Announce Type: new Abstract: Long horizon interactive environments are a testbed for evaluating agents skill usage abilities. These environments demand multi step reasoning, the cha

arXiv:2604.21584v1 Announce Type: new Abstract: Feature discovery from complex unstructured data is fundamentally a reasoning problem: it requires identifying abstractions that are predictive of a tar

Artificial intelligence coding assistant startup Cognition AI Inc. is engaged in discussions with investors over another massive funding round that would more than double its valuation to 25 billion,

arXiv:2603.18677v2 Announce Type: replace-cross Abstract: Artificial intelligence is increasingly embedded in human decision making. In some cases, it enhances human reasoning. In others, it fosters e

Coined by Sonal Choksi (@smc90) The McClusky Curve outlines the tension between being first in the cycle, or going later and adding a deeper in depth take. We asked @gbrl_dick Co-Founder of @MTSlive a

This post from Swyx appears to be a humorous or provocative invitation directed at Anthropic AI, suggesting a particular country has the highest per-capita adoption or focus on AI technology and encou

ComfyUI is an open-source platform for creative AI that has become widely used by millions of artists, developers, and studios to create images, videos, 3D assets, and audio. The company raised $17 mi

Marina Temkin / TechCrunch: ComfyUI, which gives creators granular control over image, video, and audio outputs from diffusion models, raised 30M at a 500M valuation — ComfyUI, a startup that helps cr

ComfyUI announced $17 million in funding from investors including Pace Capital, Chemistry, and Abstract Ventures . The funding will be used to scale Comfy Cloud, improve the local user experience, and

arXiv:2604.21789v1 Announce Type: cross Abstract: Competing firms that serve shared customer populations face a fundamental information aggregation problem: each firm holds fragmented signals about ri

arXiv:2604.21546v1 Announce Type: new Abstract: Out-of-Distribution (OOD) detection requires sensitivity to subtle shifts without overreacting to natural In-Distribution (ID) diversity. However, from

arXiv:2509.23744v3 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) promise enhanced reasoning by integrating diverse inputs such as text, vision, and audio. Yet cross-m

arXiv:2512.16001v2 Announce Type: replace-cross Abstract: Measuring the statistical dependence between observed signals is a primary tool for scientific discovery. However, biological systems often ex

arXiv:2604.21462v1 Announce Type: new Abstract: In this paper, we consider the problem of conditional anomaly detection that aims to identify data instances with an unusual response or a class label.

arXiv:2603.27189v2 Announce Type: replace-cross Abstract: Conformal prediction provides rigorous distribution-free finite-sample guarantees for marginal coverage under the assumption of exchangeabilit

Congrats to @deepseek_ai team! Doing the numbers I would estimate: Pro < 14m for the final training run Flash < 4m Ratio of active params x total training tokens vs v3 Total compute costs (data prep,

arXiv:2604.21380v1 Announce Type: cross Abstract: Since software performance requirements are documented in natural language, quantifying them into mathematical forms is essential for software enginee

arXiv:2509.21361v2 Announce Type: replace-cross Abstract: Large language model (LLM) providers boast big numbers for maximum context window sizes. To test the real world use of context windows, we 1)

arXiv:2604.21921v1 Announce Type: new Abstract: We present Omni, a unified multimodal model natively trained on diverse modalities, including text, images, videos, 3D geometry, and hidden representati

arXiv:2602.00931v2 Announce Type: replace-cross Abstract: Large language model reasoning is often treated as a monolithic capability, relying on binary preference supervision that fails to capture par

arXiv:2303.03237v4 Announce Type: replace-cross Abstract: Sampling from Gibbs distributions and computing their log-partition function are fundamental tasks in statistics, machine learning, and statis

Clem Delangue from Hugging Face announced upcoming machine learning research from Shopify, though specific details about the research topic or findings are not provided in this teaser post. The post s

arXiv:2604.21241v1 Announce Type: cross Abstract: Vision--Language--Action (VLA) models often use intermediate representations to connect multimodal inputs with continuous control, yet spatial guidanc

arXiv:2411.14748v2 Announce Type: replace-cross Abstract: A major challenge in extracting information from current and upcoming surveys of cosmological Large-Scale Structure (LSS) is the limited avail

arXiv:2506.21546v4 Announce Type: replace-cross Abstract: Segmentation Vision-Language Models (VLMs) have significantly advanced grounded visual understanding, yet they remain prone to pixel-grounding

Public sector organizations are at an inflection point, one where the combination of domain-specific data and agentic enterprise intelligence is producing measurable, life-changing outcomes for the po

arXiv:2509.13576v2 Announce Type: replace-cross Abstract: Sparse-View CT (SVCT) reconstruction enhances temporal resolution and reduces radiation dose, yet its clinical use is hindered by artifacts du

arXiv:2604.21469v1 Announce Type: new Abstract: Automating the detection of regulatory compliance remains a challenging task due to the complexity and variability of legal texts. Models trained on one

arXiv:2604.21286v1 Announce Type: cross Abstract: Cacioli (2026) showed that the K-way energy probe on standard discriminative predictive coding networks reduces approximately to a monotone function o

arXiv:2604.21131v1 Announce Type: cross Abstract: AI-agent guardrails are memoryless: each message is judged in isolation, so an adversary who spreads a single attack across dozens of sessions slips p

arXiv:2603.26791v2 Announce Type: replace-cross Abstract: Assessing a cited paper's impact is typically done by analyzing its citation context in isolation within the citing paper. While this focuses

arXiv:2604.21416v1 Announce Type: cross Abstract: Poisoning-based backdoor attacks pose significant threats to deep neural networks by embedding triggers in training data, causing models to misclassif

Tesla's Cybercab autonomous taxi has entered production phase, according to an announcement by Elon Musk on X. The Cybercab is Tesla's purpose-built autonomous vehicle designed to operate without a st

arXiv:2604.20935v1 Announce Type: cross Abstract: Wastewater treatment plants (WWTPs) need digital-twin-style decision support tools that can simulate plant response under prescribed control plans, to

arXiv:2601.22703v2 Announce Type: replace Abstract: Detecting out-of-distribution (OOD) inputs is a critical safeguard for deploying machine learning models in the real world. However, most post-hoc d

🎉 Day-0 support for @deepseek_ai V4 Pro and Flash on vLLM — a new generation of DeepSeek model, purpose-built for tasks up to 1M tokens. Alongside the release, we're publishing a first-principles walk

arXiv:2604.21627v1 Announce Type: new Abstract: Advancing face morphing attack techniques is crucial to anticipate evolving threats and develop robust defensive mechanisms for identity verification sy

As enterprises pivot from AI experimentation to production deployment, AI storage infrastructure is emerging as the critical bottleneck determining whether massive chip investments deliver real return

arXiv:2604.21428v1 Announce Type: new Abstract: Modern large-scale language model pre-training relies heavily on the single program multiple data (SPMD) paradigm, which requires tight coupling across

arXiv:2604.21354v1 Announce Type: new Abstract: Behavior sequences, composed of executable steps, serve as the operational foundation for multi-constraint planning problems such as travel planning. In

Deep Agents middleware is a great invention. You get a really strong default harness and a clean way to customize every part of it DeepAgents - it’s all you need - batteries included if you want, but