Knowledge catalogue
Microsoft Corp. today pulled back the curtains on Maia 300, its newest internally developed artificial intelligence accelerator. The chip is optimized for inference. Microsoft estimates that it can pr
Tom Warren / The Verge: Microsoft unveils its third-gen in-house AI chip, the Maia 300, built on TSMC's N2P process node and aimed at serving as its “primary AI inference system” — The new Maia 300 ch
Microsoft is announcing its third-generation Maia in-house AI chip today, designed to be the 'primary AI inference system' for Microsoft's products and services. Maia 300 not only improves the cost an
arXiv:2610.12881v1 Announce Type: new Abstract: Understanding and manipulating spatial relations is fundamental to AI systems that reason about physical environments and construct grounded world model
arXiv:2610.12575v1 Announce Type: cross Abstract: Modern video-language models are increasingly treated as general-purpose video reasoners, yet it remains unclear whether they robustly capture tempora
https://preview.redd.it/f7ytj63103vh1.jpg?width=2996&format=pjpg&auto=webp&s=4f5ff97fae270d5b912fcb4193dd75b865604dce Since my last post has been deleted unfortunately (due to a mega-link), here we go
arXiv:2610.12740v1 Announce Type: cross Abstract: We study the two-sample estimation of the powered Sliced Wasserstein functional under projected r-th moment assumptions. Let N=nwedge m, where n and m
arXiv:2610.12970v1 Announce Type: cross Abstract: The increasing demand for GPU-accelerated machine learning inference has exposed limitations in centralized GPU infrastructures, including high cost,
Ambient intelligence startup Mistlabs Ltd. today brought its Ambi artificial intelligence system out of beta test on Apple Inc. devices, backed by 26 million in new funding. Ambi is designed to act wi
arXiv:2610.12855v1 Announce Type: new Abstract: On-Policy Self-distillation is a self-improvement paradigm that enables large language models (LLMs) to improve their capabilities by leveraging the sam
arXiv:2510.03151v2 Announce Type: replace Abstract: This paper uses classical high-rate quantization theory to provide new insights into mixture-of-experts (MoE) models for regression tasks. Our MoE i
arXiv:2610.13637v1 Announce Type: cross Abstract: Machine learning models are increasingly used for automated feature extraction from weakly annotated bioimaging data, such as microscopy and cytomorph
arXiv:2610.13397v1 Announce Type: cross Abstract: We develop a model-free, noise-aware Bayesian clustering framework that constructs a martingale posterior over clusterings from a predictive Bayesian
arXiv:2610.12522v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used in molecular discovery and structure elucidation, where decisions depend on physical observations.
arXiv:2610.13215v1 Announce Type: new Abstract: Learning new tasks in multimodal continual instruction tuning can cause catastrophic forgetting of previously acquired knowledge. Although multi-expert
arXiv:2610.13386v1 Announce Type: new Abstract: Stance detection remains challenging for large language models (LLMs) due to implicit opinions, sarcasm, and context-dependent expressions of stance. Al
arXiv:2610.13305v1 Announce Type: new Abstract: We introduce MORAD, an online reinforcement learning framework for backbone-conditioned RNA diffusion models that trains a single shared policy across d
arXiv:2610.12963v1 Announce Type: cross Abstract: Video editing models achieve strong performance in modifying appearance, backgrounds, styles, and motions, empowered by large-scale training data. Bey
arXiv:2609.35664v2 Announce Type: replace-cross Abstract: Gated Linear Attention (GLA) Transformers advance linear recurrent models through data-dependent gating, but face a core limitation: the fixed
The blog post “Multi‑Agent Self‑Supervision: Recursive self‑improvement through collective intelligence” by @hardmaru describes how multiple AI agents can jointly supervise and refine each other’s lea
arXiv:2610.13630v1 Announce Type: new Abstract: Attention Residuals (AttnRes) enables content-dependent retrieval over network depth, which can be viewed as single-stream softmax attention along the d
arXiv:2510.00375v3 Announce Type: replace Abstract: While adaptive experimental design has outgrown one-dimensional, staircase-based adaptations, most cognitive experiments still control a single fact
arXiv:2610.12780v1 Announce Type: new Abstract: This paper presents the computational architecture and quantitative preclinical evaluation of MIRAGE, a multimodal image-guided robotic surgery framewor
Must-read paper on the effectiveness of multi-agent systems and persistent memory. We have recently seen many viral examples of multi-agent systems scaled via persistent memory. This work takes a clos
arXiv:2610.12961v1 Announce Type: cross Abstract: We introduce MVGraph, a benchmark for evaluating large vision-language models (LVLMs) on multi-graph reasoning where the evidence required by a query
arXiv:2604.00333v3 Announce Type: replace-cross Abstract: Collective behaviors that emerge from interactions are fundamental to numerous biological systems. To learn such interacting forces from obser
My AI agent doing proactive customer service: Someone emailed me that, after subscribing to my Substack, they were automatically signed up for others (which shouldn't happen) Without my asking, my Dot
arXiv:2610.12741v1 Announce Type: new Abstract: We interpret Transformer networks as learned approximations to a hybrid probabilistic-inference procedure that combines max-product Loopy Belief Propaga
arXiv:2610.12842v1 Announce Type: new Abstract: Neural networks routinely develop representations in which individual neurons contribute to multiple distinct functions, leading to the widespread view
arXiv:2610.13258v1 Announce Type: new Abstract: Neural surrogates provide computationally efficient auto-regressive modeling of wave propagation, enabling e.g. fast inverse solutions. Despite recent p
arXiv:2610.13134v1 Announce Type: new Abstract: We present Neurograf v1, an experimental end-to-end Romanian-first language-model pipeline developed to investigate the feasibility of training language
arXiv:2610.12471v1 Announce Type: cross Abstract: Satellite onboard computing faces an irreducible tension: mission intelligence requirements grow monotonically while power, mass, and radiation budget
arXiv:2603.16148v2 Announce Type: replace Abstract: Spiking neural networks promise brain-inspired neural dynamics, yet native large-scale spiking language-model pretraining remains largely unexplored
Compared to the original release, a large base anime dataset was used. Roughly 110k photos from nature to museums were also used. All photography photos that were added were scanned for humans. They a
New paper from Microsoft and colleagues on generating enterprise data for agents. If you train or evaluate agents on long-running business work, it's worth your time. (bookmark it) MiniCorp is an offi
New Show Announcement: High Taste Testers Good food and good ai convos Pilot episode 🔜 http://youtube.com/@latentspacepod ft: @davis7, @dexhorthy @AdjectiveAllison, @altryne, @benhylak on DevDay/Dots,
Nice paper on optimizing agents and their graders together. The key finding is that you want to update your LLM grader alongside the agent instead of keeping it fixed, because the agent's failure mode
On October 12, 2026, Gary Marcus (@GaryMarcus) posted on Twitter saying, “No Generative AI. Just one gorgeous building, beautiful light, and an Phone 16 Pro.” The tweet, timestamped 7:01 AM UTC, recei
arXiv:2610.13943v1 Announce Type: new Abstract: Pretrained vision-language-action (VLA) models encode broad manipulation priors, yet adapting them to specific tasks requires balancing limited robot in
arXiv:2610.12684v1 Announce Type: new Abstract: Non-prehensile manipulation with mobile robots has primarily targeted placement in coarse goal regions. Precision placement has been studied with manipu
arXiv:2610.13563v1 Announce Type: cross Abstract: Repository-level issue-resolution benchmarks such as SWE-bench evaluate submitted patches primarily based on whether they pass the correctness tests,
arXiv:2610.13674v1 Announce Type: cross Abstract: Linearizing softmax attention offers a route to efficient Transformer inference, but preserving pretrained attention remains challenging. We identify
arXiv:2610.13794v1 Announce Type: new Abstract: Discourse particles subtly shape the flow of discourse by reflecting conversational context and interlocutor attitudes, often leaving the truth-conditio
arXiv:2610.13309v1 Announce Type: cross Abstract: 6D pose estimation of novel objects without CAD models remains an open challenge: model-free methods must build the object representation from scratch
arXiv:2610.12985v1 Announce Type: cross Abstract: Neural-network variational Monte Carlo provides an accurate route to solving the electronic Schrodinger equation, but many neural wavefunctions are op
arXiv:2610.12754v1 Announce Type: new Abstract: We propose NV-Tesseract-AD, a curriculum learning-enhanced conditional diffusion framework for multivariate time-series anomaly detection. Our central h
Nvidia Corp. today announced new partnerships and contributions to the open-source community at the Open Compute Project Global Summit in San Jose, aimed at laying the foundation for the future of age
arXiv:2610.13790v1 Announce Type: cross Abstract: How well can vision-language models (VLMs) reason about what is missing from an image? We study this question with OccludeBench, a manually curated be
As AI factories grow from megawatts to gigawatts, building them takes more than advanced computing. Open standards are helping the industry scale AI infrastructure faster, more efficiently and more re
arXiv:2610.12914v1 Announce Type: new Abstract: Vision-language-action (VLA) models have shown strong promise in robotic manipulation, yet their post-training still predominantly relies on trajectory-
arXiv:2610.13447v1 Announce Type: cross Abstract: Speech recognition on low-cost microcontrollers is, in practice, limited to keyword spotting or a fixed list of commands. We present Oido, an inferenc
arXiv:2610.13834v1 Announce Type: new Abstract: Continuous diffusion language models (CDLMs) promise to bring the benefits of continuous flow modelling to language, including accelerated sampling and
arXiv:2610.13676v1 Announce Type: new Abstract: Time series foundation models (TSFMs) increasingly offer covariate support, with calendar information being the most common type of categorical covariat
arXiv:2603.02095v2 Announce Type: replace-cross Abstract: We study the convergence dynamics of Gradient Descent (GD) in a minimal binary classification setting, consisting of a two-neuron ReLU network
arXiv:2610.12582v1 Announce Type: new Abstract: A latent recurrent language model applies a shared block of layers repeatedly, so one checkpoint can trade inference compute for accuracy by changing th
arXiv:2610.12879v1 Announce Type: new Abstract: Diffusion language models generate tokens in parallel, but still require multiple sampling steps to produce high-quality text. In this paper, we investi
arXiv:2610.13430v1 Announce Type: cross Abstract: Time series causal discovery --- the process of detecting causation between time series --- has its roots in signal processing research from over a ha
Open standards are the foundation for AI factories that can scale from megawatts to gigawatts. At #OCPSummit26, we contributed the NVIDIA Vera Rubin NVL72 rack and compute tray designs to @OpenCompute
Gguf's: https://huggingface.co/openbmb/MiniCPM-V-4.7-1B-gguf 'MiniCPM-V 4.7 is the latest model in the MiniCPM-V series, available in a 1B variant. It builds on the family's single-image, multi-image,
gguf's: https://huggingface.co/openbmb/MiniCPM-V-4.7-35B-A3B-gguf 'MiniCPM-V 4.7 is the latest model in the MiniCPM-V series, available in a 35B-A3B variant, with 35B-A3B being the first MoE model in