Knowledge catalogue
arXiv:2605.13744v1 Announce Type: new Abstract: Image restoration is an inherently ill posed inverse problem. Equivariant networks that embed geometric symmetry priors can mitigate this ill posedness
all of their ideas now are like “should we dissolve the government, imprison our opponents, and seize every lever of power in the country? we’re the good guys remember, if we don’t do this the bad guy
almost all LLM “thought” is derivative. below just sounds like hype to me 📁 Jensen Huang, CEO of NVIDIA, says GPT was never just about generating images or text but about generating thought itself. Th
Atsuko Fukase / Bloomberg: Alphabet sold 3.6B of bonds in its debut yen-denominated bond sale, the largest by a non-Japanese company, as AI-driven capital spending accelerates — Alphabet Inc. sold ¥57
also all this: Codex is getting easier to automate and customize around your code. 🪝 Hooks customize the Codex loop with scripts that run at key points in a task: • Run validators before or after work
Over 70 percent of Americans oppose AI data center construction in their area, according to a new Gallup survey. Just 7 percent said they were 'strongly' in favor of new data centers. According to Gal
arXiv:2605.13010v1 Announce Type: cross Abstract: We study image inpainting with generative diffusion models. Existing methods typically either train dedicated task-specific models, or adapt a pretrai
arXiv:2605.13128v1 Announce Type: cross Abstract: This paper introduces an algorithm-agnostic approach to feature-based time series clustering via amortized neural inference. By training neural networ
arXiv:2605.13785v1 Announce Type: cross Abstract: Cognitive operations are a rising concern in the geopolitical sphere, a quiet yet rigorous fight for public perception and decision making. While such
arXiv:2605.13221v1 Announce Type: new Abstract: In cloud manufacturing, unmanned aerial vehicles (UAVs) can support both product collection and mobile edge computing (MEC). This joint operation forms
arXiv:2605.13046v1 Announce Type: new Abstract: Mental health disorders affect millions worldwide, and healthcare systems are increasingly overwhelmed by the volume of clinical data generated from ele
arXiv:2601.16806v3 Announce Type: replace Abstract: In this work we develop a novel insect-inspired model for visual point-goal navigation. This combines abstracted models of two insect brain structur
arXiv:2410.22643v2 Announce Type: replace Abstract: Generating overtaking trajectories in high-speed scenarios is typically addressed through hierarchical planning, which often suffers from local opti
arXiv:2605.12929v1 Announce Type: cross Abstract: Retinal diagnosis is inherently bilateral: clinicians compare homologous structures across eyes (e.g., optic disc asymmetry), yet most deep models ope
Anima is a 2 billion parameter text-to-image model focused on anime concepts, characters, and styles, with capability for non-photorealistic content. Preview versions are intermediate model checkpoint
Nous Research announced the release of a new model available for free to Hermes agent users through the Nous Portal. The post suggests this is a significant model release from Nous Research, their org
Anthropic PBC, the developer and provider of the Claude artificial intelligence model family, said it’s offering a special credit pool for users who want to use agentic tools with its large language m
Anthropic PBC today launched an offering called Claude for Small Business that is designed to expand the adoption of its chatbot among entrepreneurs. The feature bundle is the fifth market-specific ve
any time a model router company drops data, its worth browsing. here we learn that gemini leads in education and personal assistants (?!), ant leads in vibecoding and koding and back office (?!), and
arXiv:2605.13724v1 Announce Type: cross Abstract: Few-step video generation has been significantly advanced by consistency distillation. However, the performance of consistency-distilled models often
APPLEBAUM: Russia's war in Ukraine is sometimes described, including recently by American Vice President, as if it were nothing more than territorial dispute, kind of scuffle over lines on map. But wh
This article discusses designing and implementing data pipelines capable of processing large-scale multimodal datasets (combining text, images, video, audio, etc.) using Ray, an open-source distribute
arXiv:2605.13517v1 Announce Type: cross Abstract: Vector Quantized Variational Autoencoder (VQ-VAE) has become a fundamental framework for learning discrete representations in image modeling. However,
arXiv:2605.12575v1 Announce Type: cross Abstract: Whole-slide image (WSI) multiple instance learning (MIL) classifiers can achieve strong slide-level AUC while leaving the full-bag prediction opaque.
Are scaling laws finally working for time series foundation models? Today, @datadoghq is releasing Toto 2.0 weights in Apache 2.0 on @huggingface. It's a family of open-weights TSFMs from 4M to 2.5B p
Ollama offers several memory management settings, including the ability to reduce context length (context window) to decrease VRAM usage, which can save 0.2-0.4GB for 7-8B models when reduced from 8K
Portable Reachy Mini is likely a compact, mobile robotic arm or manipulation device, with this post from Hugging Face's CEO Clem Delangue presumably announcing or promoting its availability or readine
AI trust infrastructure is quickly becoming a critical requirement as enterprises scale intelligent systems across their operations. The focus is shifting from simple data protection to securing, gove
arXiv:2605.12879v1 Announce Type: new Abstract: Doubly-stochastic attention has emerged as a transport-based alternative to row-softmax attention, with recent Transformer variants using it to reduce a
arXiv:2605.12845v1 Announce Type: cross Abstract: Assembling objects from parts requires understanding multimodal instructions, linking them to 3D components, and predicting physically plausible 6-DoF
arXiv:2605.13450v1 Announce Type: new Abstract: Measuring the creativity of large language models (LLMs) is essential for designing methods that can improve creativity and for enhancing our scientific
arXiv:2605.12964v1 Announce Type: new Abstract: Flow-based generation in high-dimensional spaces is difficult because velocity prediction requires modeling high-dimensional noise, even when data has s
arXiv:2605.13442v1 Announce Type: new Abstract: Autonomous robotic exploration in remote and extreme environments allows scientists to model complex transport phenomena and collective behaviors descri
arXiv:2512.10931v3 Announce Type: replace Abstract: Many state-of-the-art LLMs are trained to think before giving their answer. Reasoning can greatly improve language model capabilities, but it also m
arXiv:2605.13548v1 Announce Type: cross Abstract: Existing robotic foundation models, while powerful, are predicated on an implicit assumption of temporal homogeneity: treating all actions as equally
Attention @arxiv authors: Our Code of Conduct states that by signing your name as an author of a paper, each author takes full responsibility for all its contents, irrespective of how the contents wer
arXiv:2605.13784v1 Announce Type: new Abstract: Conventional transformer inference engines are request-driven, paying an O(n) prefill cost on every query. In streaming workloads, where data arrives co
arXiv:2602.02560v2 Announce Type: replace-cross Abstract: Lung cancer remains the leading cause of cancer mortality, driving the development of automated screening tools to alleviate radiologist workl
arXiv:2605.12937v1 Announce Type: cross Abstract: Anti-facial recognition (AFR) image filters alter images in ways that are subtle to people but blinding to computer vision. Yet, despite widespread in
Unified identity security platform provider Permiso Security Inc. today launched AI agent runtime security capabilities that give security teams continuous visibility into agent activity across cloud
arXiv:2605.06390v2 Announce Type: replace Abstract: A leading proposal for aligning artificial superintelligence (ASI) is to use AI agents to automate an increasing fraction of alignment research as c
arXiv:2601.15161v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly used for clinical decision support, where hallucinations and unsafe suggestions may pose direct
Automating AI research is the next major step in AI We let Claude Code (Opus 4.7) and Codex (GPT 5.5) run autonomously on the nanoGPT speedrun optimizer track using our idle compute. ~10k runs, ~14k H
The search did not return specific information about the b9140 release. Based on the context, b9140 is a specific build number from the llama.cpp project releases. llama.cpp is an LLM inference implem
Release b9142 is an intermediate build of llama.cpp, a C/C++ library for running large language model inference on consumer hardware. llama.cpp performs inference on various large language models and
The search results show releases near b9143 (specifically b9134 was the most recent) but do not contain specific details about b9143 itself. Based on the available information: llama.cpp is a C/C++ im
llama.cpp is an open source software library that performs inference on various large language models such as Llama. Build b9144 is an intermediate release version of the llama.cpp project from the gg
The search results show recent llama.cpp releases but don't contain specific details about the b9145 build. Based on the pattern of changes in recent releases, b9145 likely includes updates to SYCL/Le
Release b9148 of llama.cpp adds a non-backtracking tokenizer handler for Qwen3.5 to handle Unicode regex patterns for letters and combining marks, addressing stack overflow issues on long inputs. The
b9150 is a llama.cpp release that adds a custom Unicode regex handler for Qwen3.5's tokenizer to prevent stack overflows on long inputs. The release includes test vocabularies and updated test configu
Release b9151 of llama.cpp includes enhancements to Unicode regex handling for Qwen3.5's tokenizer, adding a custom non-backtracking handler to prevent stack overflows on long inputs. The release also
B9156 is a llama.cpp release that adds enhanced Unicode regex handling for Qwen3.5 tokenization, implementing a non-backtracking handler to prevent stack overflows on long inputs . The release include
B9158 is a llama.cpp release that adds a custom Unicode regex handler for Qwen3.5 tokenization to prevent stack overflows on long inputs. The release includes test vocabulary files and expected output
arXiv:2605.13381v1 Announce Type: new Abstract: As AI-generated synthetic images become increasingly realistic, Vision Transformers (ViTs) have emerged as a cornerstone of modern deepfake detection. H
arXiv:2605.13214v1 Announce Type: cross Abstract: Recent cryptographic results establish that neural networks can be backdoored such that no efficient algorithm can distinguish them from a clean model
Batching for vision models is now available in Beta with our latest MLX engine update 👾 The updated engine also brings major improvements to caching for faster inference overall. Turn on Developer Mod
arXiv:2605.13455v1 Announce Type: new Abstract: Synapses are densely packed submicron structures that dynamically reorganize during learning and memory formation. Longitudinal extit{in vivo} imaging o
arXiv:2605.12843v1 Announce Type: cross Abstract: Model merging aims to combine multiple task-specific expert models into a single model without joint retraining, offering a practical alternative to m
arXiv:2605.13088v1 Announce Type: new Abstract: Dynamical modelling is central to many scientific domains, including pharmacometrics, systems biology, physiology, and epidemiology. In these settings,
beautiful tech stack writeup, one of the best i've ever seen in my career. I always advocate that devtools companies write these up, because it fulfils multiple purposes: - tell users the care that go