All entries

Microsoft Corp. today introduced its first in-house cybersecurity model, MAI-Cyber-1-Flash, and a companion agentic system called Project Perception that fields teams of artificial intelligence agents

arXiv:2603.28956v2 Announce Type: replace-cross Abstract: The minimum-norm interpolator (MNI) framework has recently attracted considerable attention as a tool for understanding generalization in over

arXiv:2607.21922v1 Announce Type: new Abstract: Clinical irregular multivariate time series are shaped not only by physiological dynamics but also by the measurement process that determines when and w

The National Oceanic and Atmospheric Administration (NOAA) is embarking on a transformative journey to redefine how we understand and predict patterns in the Earth’s atmosphere that affect the weather

arXiv:2607.21978v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures have been widely adopted in large language models, yet parameter-efficient fine-tuning (PEFT) for MoE models rema

arXiv:2607.21653v1 Announce Type: cross Abstract: Agentic reinforcement learning research is constant algorithm modification, new estimators, new pipeline stages, new rollout schemes, and in mainstrea

moonshotai/Kimi-K3 As promised earlier this month, Moonshot have released the weights for their excellent 2.8 trillion parameter Kimi K3. They're a hefty 1.56TB on Hugging Face. Kimi introduced their

arXiv:2607.21634v1 Announce Type: new Abstract: Masked discrete diffusion for molecular graph generation typically applies a uniform corruption schedule to all tokens in a lossless graph-to-sequence r

arXiv:2606.18681v2 Announce Type: replace Abstract: Despite their remarkable performance, Vision Language Models (VLMs) incur substantial computational overhead due to the large number of visual token

arXiv:2607.21946v1 Announce Type: new Abstract: This technical report presents our approach to Challenge Track~3: SeePhys Pro at the 3rd AI for Math Workshop, where the task is to answer college-level

arXiv:2607.21645v1 Announce Type: new Abstract: Multi-horizon latent consistency is a common training knob in video predictors and world models, but practitioners rarely know what it does to transitio

I got tired of my Ollama server sitting idle between chat experiments, so I pointed it at my Navidrome library and made it run a radio station. The DJ is an agent, not a shuffler. Each turn it gets to

arXiv:2607.22083v1 Announce Type: cross Abstract: We present Nanbeige4.2-3B, a compact general agentic model with 3B non-embedding parameters. It delivers strong performance across code-agent, office-

arXiv:2607.21805v1 Announce Type: cross Abstract: We study the long-term behavior of the Multiplicative Weights Update (MWU) algorithm in game settings where learning dynamics frequently fail to conve

arXiv:2607.21671v1 Announce Type: new Abstract: Neural network compression and interpretability remain open challenges in modern deep learn- ing, where billion-parameter architectures deliver impressi

New research from NVIDIA. They just dropped a PyTorch-native training framework for agentic RL. (bookmark it) Paper summary: Molt is a PyTorch-native agentic RL framework with an unusual design target

Nexus connects to the agentic harnesses your teams already use, whether that’s Claude Code, Codex, OpenCode, or your own custom tooling. It gives you: → Intelligent routing, automatically matching eac

Nice little insights on doing autoresearch with coding agents. Hand a coding agent a dataset, an eval script, one editable file, and no supervision. That's autoresearch and it tries to optimize the nu

I just managed to get it running on windows and this thing is fucking insane. I get around 550-720t/s depending on task at hand. Previously to get to such numbers i would have to do batching and agent

arXiv:2510.21770v2 Announce Type: replace Abstract: Low-precision execution can induce substantial forward discrepancies in Transformers even for fixed weights and input, yet these discrepancies are u

Nvidia CEO Jensen Huang “Distillation - learning from AI, learning from other people, and learning from other sources of knowledge, is fundamental to intelligence. We are constantly learning from one

Nvidia Corp. is reportedly in talks to backstop a 250 billion loan for OpenAI Group PBC. The Wall Street Journal on Sunday cited sources as saying that the financing would cover the cost of a new data

Jaspreet Singh / Reuters: Nvidia forms the Open Secure AI Alliance, a coalition including CrowdStrike, Hugging Face, and Dell to develop and share tools for AI safety and cybersecurity — Nvidia (NVDA.

The complexity of modern chip design continues to grow as engineering teams work to develop increasingly sophisticated CPUs, GPUs and AI systems. To help meet that challenge, NVIDIA is collaborating w

Nvidia Corp. said tonight it’s now running the chip design software its engineers are using to design the next generation of its graphics processing units, on its own silicon. It’s partnering with Cad

NVIDIA Ising Calibration 1.5 is a 31‑billion‑parameter vision‑language model that diagnoses and tunes quantum processors, delivering state‑of‑the‑art zero‑shot and in‑context learning on the QCalEval

Nvidia on Monday said it is joining forces with Microsoft, SpaceX, IBM, and other tech companies to build and share open-source AI security tools. The new Open Secure AI Alliance said open tools are r

NVIDIA’s Nemotron 3 Ultra, when paired with the ACE‑RTL agent, achieves a 97.1 % average pass rate on the CVDP benchmark across nine RTL task categories—surpassing GLM 5.2 and Kimi K2.6 while using up

Keach Hagey / Wall Street Journal: Nvidia says it made a “substantial” investment in Safe Superintelligence, which will get access to Nvidia GPUs to up computing power by an “order of magnitude” — Par

arXiv:2507.18036v2 Announce Type: replace-cross Abstract: Securing intellectual property (IP) in Machine Learning as a Service is critical yet challenging. While deep neural network watermarking serve

“China is working hard to catch up, and the United States should take steps to keep its advantage. Most important, it should continue to prohibit American companies from selling the most advanced chip

arXiv:2607.22226v1 Announce Type: new Abstract: Foundation-model-based vision-language navigation (VLN) has advanced autonomous robot navigation by enabling robots to interpret natural-language instru

On FrontierCode 1.1 Extended, our benchmark for real-world engineering tasks that grades mergeability and quality, Kimi K3 scores 58.2% with a 63.6% pass rate. Within Devin, it excels on reproducing b

arXiv:2607.21961v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to generate long-form conversational content such as podcasts from textual sources. While these syste

arXiv:2607.21975v1 Announce Type: new Abstract: Low-rank adaptation (LoRA) optimizes J(B,A)=mathcal L(W_base+sBA) over two adapters B in R^{m imes r} and A in R^{r imes n} that form a low-rank update

arXiv:2607.21633v1 Announce Type: new Abstract: Logic Gate Networks (LGNs) implement computation through compositions of Boolean operations, yet unlike classical Boolean circuits, existing LGNs do not

arXiv:2607.22430v1 Announce Type: new Abstract: Learning world models that infer environment dynamics from high-dimensional observations and predict outcomes under candidate actions is central to plan

The artificial intelligence competition is no longer between large language models, but rather between AI systems. Advanced Micro Devices Inc. has shifted from being primarily a chip business to a sec

arXiv:2607.22119v1 Announce Type: cross Abstract: Multi-stream robot manipulation policies achieve unparalleled sample efficiency and generalization by modeling actions relative to environmental refer

One of the least explored questions in AI is how to build rich open-ended environments for learning. Benchmarks evaluate intelligence, environments shape it. iLands is interesting because it doesn't j

arXiv:2501.18049v3 Announce Type: replace Abstract: We study online learning for a seller that jointly chooses per-period inventory positions and a uniform price, then fulfills realized demand through

arXiv:2607.22513v1 Announce Type: cross Abstract: Commercial large language models are increasingly used as knowledge references, yet their stance on contested scientific claims is neither stable nor

This story originally appeared in The Algorithm, our weekly newsletter on AI. To get stories like this in your inbox first, sign up here. Reading OpenAI’s account last week of how some of its models b

arXiv:2601.12291v2 Announce Type: replace-cross Abstract: Scalable and maintainable maps are fundamental to large-scale navigation and the long-term deployment of robots in real-world environments. Ho

arXiv:2607.14193v2 Announce Type: replace-cross Abstract: The Helmholtz equation governs time-harmonic wave propagation, and in dissipative media a complex modulus renders its squared wavenumber kappa

arXiv:2501.18530v3 Announce Type: replace-cross Abstract: We consider a teacher-student model of supervised learning with a fully-trained two-layer neural network whose width k and input dimension d a