All entries

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

arXiv:2604.21006v1 Announce Type: new Abstract: We introduce Deep FinResearch Bench, a practical and comprehensive evaluation framework for deep research (DR) agents in financial investment research.

arXiv:2604.20861v1 Announce Type: cross Abstract: Generative Recommendation (GR) has demonstrated remarkable performance in next-token prediction paradigms, which relies on Semantic IDs (SIDs) to comp

arXiv:2604.21572v1 Announce Type: new Abstract: This work focuses on per-video unsupervised action segmentation, which is of interest to applications where storing large datasets is either not possibl

DeepAgents is a framework or tool that provides comprehensive, ready-to-use components for building AI agents while maintaining flexibility for customization. The 'batteries included' approach suggest

DeepAgents Sandbox — a lightweight native Linux sandbox for deepagents It gives full isolation for safely running LLM/agent-generated code — no Docker, no VMs, no cloud dependency. Super fast and secu

Chinese artificial intelligence developer DeepSeek today released a new series of open-source large language models. V4, as the algorithm family is called, comprises two LLMs on launch. There’s the fl

Bloomberg: DeepSeek releases its new flagship models V4 Pro and V4 Flash in preview, saying V4 Pro trails the performance of state-of-the-art models by about 3 to 6 months — DeepSeek rolled out previe

Chinese AI lab DeepSeek's last model release was V3.2 (and V3.2 Speciale) last December. They just dropped the first of their hotly anticipated V4 series in the shape of two preview models, DeepSeek-V

DeepSeek-V4 is an advanced language model featuring a million-token context window that enables practical agentic applications beyond simple retrieval. The model demonstrates improved efficiency and u

DeepSeek V4 by @deepseek_ai just dropped! SGLang is ready on Day 0 with a full stack of optimizations from architectures to low-level kernels. We also deliver a verified RL training pipeline in Miles

deepseek-v4-flash is now available on Ollama's cloud! Hosted in the US. Try it with Claude Code: ollama launch claude --model deepseek-v4-flash:cloud Try it with OpenClaw: ollama launch openclaw --mod

DeepSeek-V4 is a newly released AI model announced by Clem Delangue on X (formerly Twitter). The release likely represents an updated version of the DeepSeek model series with improvements in capabili

DeepSeek has released v4, its latest model iteration. The announcement was made by Clem Delangue on X (formerly Twitter). This likely represents a significant update to DeepSeek's AI capabilities, tho

DeepSeek-V4, a new model release from DeepSeek AI, has been made available on Hugging Face's model hub. The release was announced by Clem Delangue and includes model weights and resources accessible t

🚀 DeepSeek-V4 Preview is officially live & open-sourced! Welcome to the era of cost-effective 1M context length. 🔹 DeepSeek-V4-Pro: 1.6T total / 49B active params. Performance rivaling the world's top

DeepSeek-V4-Pro is a Mixture-of-Experts language model with 1.6 trillion total parameters and 49 billion activated per token, supporting a 1 million token context length. Released under the MIT Licens

Simon Willison / Simon Willison's Weblog: DeepSeek V4 Pro costs 1.74/1M input tokens and 3.48/1M output tokens, while V4 Flash costs 0.14/1M and 0.28/1M; both models are the cheapest in their class —

Vincent Chow / South China Morning Post: DeepSeek V4 Pro has 1.6T total parameters, its largest model by the metric, and V4 Flash has 284B parameters; both models have a context window of 1M tokens —

DeepSeek V4 Pro is now available through Together AI's model platform, with the faster DeepSeek V4 Flash variant expected to launch soon. Together AI is offering users the ability to access and test D

As AI accelerates enterprise transformation, it is simultaneously widening the attack surface organizations must defend — and compressing the time defenders have to respond. The convergence of geopoli

arXiv:2502.03484v2 Announce Type: replace-cross Abstract: Dementia encompasses a group of syndromes that impair cognitive functions such as memory, reasoning, and the ability to perform daily activiti

arXiv:2602.23408v2 Announce Type: replace-cross Abstract: The specification of the action space plays a pivotal role in imitation-based robotic manipulation policy learning, fundamentally shaping the

arXiv:2604.20852v1 Announce Type: cross Abstract: Learning to rank (LTR) is one of the core tasks in Machine Learning. Traditional LTR models have made great progress, but nearly all of them are imple

arXiv:2501.02576v2 Announce Type: replace Abstract: Monocular depth estimation within the diffusion-denoising paradigm demonstrates impressive generalization ability but suffers from low inference spe

arXiv:2604.20893v1 Announce Type: new Abstract: Wrist exoskeletons play a vital role in rehabilitation and assistive applications, yet conventional actuation mechanisms such as electric motors or pneu

arXiv:2604.20857v1 Announce Type: cross Abstract: Recent advances in autonomous ``AI scientist'' systems have demonstrated the ability to automatically write scientific manuscripts and codes with exec

arXiv:2604.21152v1 Announce Type: cross Abstract: As state-of-the-art Large Language Models (LLMs) have become ubiquitous, ensuring equitable performance across diverse demographics is critical. Howev

arXiv:2604.21421v1 Announce Type: cross Abstract: Protecting patient privacy in clinical narratives is essential for enabling secondary use of healthcare data under regulations such as GDPR and HIPAA.

arXiv:2604.20985v1 Announce Type: cross Abstract: In machine learning applications, privacy requirements during inference or deployment time could change constantly due to varying policies, regulation

arXiv:2604.21518v1 Announce Type: cross Abstract: Neural representations (NRs), such as neural fields and 3D Gaussians, effectively model volumetric data in computed tomography (CT) but suffer from se

arXiv:2604.21651v1 Announce Type: cross Abstract: Denoising of periodic signals and accurate waveform estimation are core tasks across many signal processing domains, including speech, music, medical

Raphael Satter / Reuters: Diplomatic cable: US State Department has ordered a global push to bring attention to what it says are efforts by Chinese companies to steal IP from US AI labs — The U.S. Sta

arXiv:2604.21909v1 Announce Type: new Abstract: Humans and modern vision models can reach similar classification accuracy while making systematically different kinds of mistakes - differing not in how

arXiv:2604.21712v1 Announce Type: new Abstract: 3D human mesh recovery from monocular RGB images aims to estimate anatomically plausible 3D human models for downstream applications, but remains challe

arXiv:2509.22321v2 Announce Type: replace Abstract: An associative memory (AM) enables cue-response recall, and associative memorization has recently been noted to underlie the operation of modern neu

arXiv:2604.21814v1 Announce Type: cross Abstract: Capsule endoscopy (CE) enables non-invasive gastrointestinal screening, but current CE research remains largely limited to frame-level classification

arXiv:2602.11871v2 Announce Type: replace Abstract: Large Language Models (LLMs) are a powerful tool for statistical text analysis, with derived sequences of next-token probability distributions offer

arXiv:2604.21276v1 Announce Type: cross Abstract: As pretrained large language models replace task-specific decoders in speech recognition, a critical question arises: do their text-derived priors mak