The Archive

ORCH applies organizational theory to multi-agent embodied AI, constructing task-specific hierarchies for collective coordination.

Quantum spectral features from Ising DOS applied to signed graph learning; no direct LLM or foundation model relevance.

Reflex-informed reinforcement learning for muscle-driven locomotion balances physiological plausibility with adaptive control.

Neural controlled differential equations improve duration-aware acoustic modeling in TTS by treating phone representations as continuous-time control paths.

Eloquence team applies LoRA fine-tuning and multimodal in-context learning to Voxtral models for multilingual MCQA across 21 languages at Interspeech 2026 challenge.

Universal Music Group is launching a new AI-powered platform that will allow users to draw from its catalog of licensed music to create song remixes, mashups, and new takes on tracks, according to an announcement on Thursday. The record label is developing the platform through a multiyear licensing agreement with ElevenLabs, a company that specializes in AI voice and music generation. Artists can choose whether to participate in UMG and ElevenLabs' upcoming platform, which marks yet another AI deal for the record label. UMG is currently developing an AI music platform with Udio and has struck...

Post-training quantization works on LLMs because pretrained weights have spectral properties that limit error accumulation across layers, unlike random initialization.

Voltage-to-time conversion readout for memristive spiking neural network crossbar arrays reduces area and power overhead in analog VMM implementations.

Theoretical analysis of distributed kernel-based robust gradient descent establishes optimal learning rates and alleviates saturation in DKRGD algorithms.

Bayesian backward reasoning resolves LLM agent disagreements by constructing reverse posteriors, avoiding correlated errors in forward-only voting methods.

Language-augmented semantic priors integrate NLP design intent into B-spline surface fitting for CAD geometry kernels.

Negative Self-Distillation preserves uncertainty and self-correction by penalizing confident reasoning traces, improving LLM performance on complex reasoning over OPSD.

ActSafeGuard enforces differentiable hard constraints on flow-matching robotic policies during training to ensure safe, feasible actions at deployment.

Geospatial foundation models from 2022 satellite data capture health-relevant physical place features beyond conventional socioeconomic risk indices.

Biomolecular structure prediction is now often run at proteome scale, where the goal is to move an entire worklist through the pipeline efficiently. NVIDIA... Biomolecular structure prediction is now often run at proteome scale, where the goal is to move an entire worklist through the pipeline efficiently. NVIDIA BioNeMo Inference Runtime (BioIR) helps accelerate supported biomolecular structure-prediction models on NVIDIA GPUs while keeping the familiar PyTorch workflow. It uses optimized kernels and, where applicable, CUDA Graphs to speed model… Source

OpenAI launches Data agent in ChatGPT Work, enabling natural-language data connection, insight discovery, and dashboard creation.

I turned my Muse assistant into a purple cat. | Screenshot: The Verge Meta has launched its new Muse assistant, marking the company's first real foray into AI-powered productivity tools. The company says its AI agent can "take the busywork off your plate" by helping you with online shopping, emails, trip-planning, and more. I decided to try out the new tool and see how well it performed - especially from a company that previously prioritized entertainment over productivity. Though the AI assistant generally worked as I expected it to, the unnerving amount of information it autonomously gleane...

“The vast majority of cases we find are people who are entitled to claim for something, claiming for that thing,” the researcher told TechCrunch.

Maven Robotics emerged from stealth today with a $100 million Series A and active deployments.

This interview has been lightly edited for length and clarity. Nick Statt: Hello and welcome to Decoder, Nilay’s show about big ideas and other problems. This is Nick Statt, senior producer. And I’m joined by our brand-new supervising producer, Greg Ott. Greg Ott: Good day, everyone. And Hi, Nilay. Nilay is here too. He is the person who hosts the show, and his name is also in the show. So it makes sense. Nilay Patel: It’s true. We don’t consistently say my name in the show enough. We should do it all the time. I should do it. Welcome to Decoder with Nilay Patel. GO: Like Nick was saying, thi...

OpenAI establishes independent advisory board on mathematics and AI to review and communicate emerging research findings.

Sam Altman, chief executive officer of OpenAI, during a media tour of the Stargate AI data center. | Bloomberg via Getty Images Another researcher is challenging OpenAI about the data driving its increasingly impressive array of mathematical discoveries. Just days after a bitter row erupted over whether the company's models benefited from unpublished work, a second mathematician has come forward accusing the AI giant of unethical and "dishonest" behavior and a lack of transparency about the origins of its training data. In a series of posts on Mastodon, mathematician Andreas Thom raised conce...

On July 22, 2026, a transmission line fault in Ashburn, Virginia—the heart of the world’s largest data center cluster—knocked more than 3 gigawatts of load off the grid in seconds. And it wasn’t the first time. Two years earlier, a single failed surge arrester dropped roughly 60 Virginia facilities and 1,500 megawatts at once. No…

Stratechery opinion on Apple's hardware-software integration strategy and potential AI limitations in app-centric design.

NVIDIA has one of the largest and most complex supply chains in the world, and its performance is measured from wafer-out to first token. The interval is in two... NVIDIA has one of the largest and most complex supply chains in the world, and its performance is measured from wafer-out to first token. The interval is in two parts. Time-to-rack runs from silicon leaving the fab to an assembled system arriving on a data center floor. Time-to-token covers everything thereafter: power, cooling, networking, and the software stack that makes the infrastructure… Source

OpenAI and GSA offer zero license fees, 50% usage discount, and cyber defense support to U.S. federal, state, local, and tribal governments.

OpenAI releases ChatGPT for Financial Services with integrated financial data and GPT-6 Astra for research and modeling.

No substantive AI news reported.

Calif Research demonstrates WeWorm, a zero-click iOS/Android worm spreading via WeChat calls, developed in ~9 days using AI-assisted vulnerability discovery and RCE exploit generation.

Listen Labs walked away from a signed Series C term sheet from Menlo Ventures, sources say.