Knowledge catalogue
Something I have been thinking about: in the past, the best engineers I knew spent a lot of time automating their work in various ways. Better vim/emacs automations, writing lint rules to catch repeat
Cybersecurity firm Sophos Ltd. today launched Sophos Fusion, a single platform that ties together its security operations, endpoint, network, identity, email and cloud protection. Sophos calls it the
arXiv:2607.12094v1 Announce Type: cross Abstract: Reliable detection of out-of-distribution (OOD) samples is crucial for the safe deployment of machine learning models. Neural networks often produce o
arXiv:2607.11990v1 Announce Type: cross Abstract: Feedforward network (FFN) blocks account for a large fraction of the parameters and computation in Transformer architectures, yet their internal struc
arXiv:2209.14125v3 Announce Type: replace-cross Abstract: Diffusion models have proven to be a flexible and effective framework for modelling probability distributions on finite-dimensional spaces. Ho
arXiv:2607.12236v1 Announce Type: cross Abstract: Speculative execution accelerates LLM agents by using a smaller, cheaper model to predict and pre-launch the next step while the environment is idle.
arXiv:2603.08503v2 Announce Type: replace Abstract: Omnidirectional images are increasingly used in robotics and vision due to their wide field of view. However, extending 3D Gaussian Splatting (3DGS)
arXiv:2607.11986v1 Announce Type: new Abstract: Perineural invasion (PNI) is associated with poor prognosis in cholangiocarcinoma (CCA). However, its detection from 3D MRI remains challenging due to t
arXiv:2602.12783v3 Announce Type: replace-cross Abstract: Spoken query retrieval is an important interaction mode in modern information retrieval. However, existing evaluation datasets are often limit
arXiv:2607.12866v1 Announce Type: new Abstract: Reconstruction-based methods are a cornerstone of unsupervised image anomaly detection, but they remain vulnerable to outlier leakage, where standard me
arXiv:2607.12464v1 Announce Type: new Abstract: When labeled data are scarce, off-the-shelf diffusion models can augment training sets for few-shot medical image classification, but not all generated
arXiv:2506.21324v3 Announce Type: replace-cross Abstract: Neuromorphic and quantum computing have recently emerged as promising paradigms for advancing artificial intelligence, each offering complemen
arXiv:2607.12370v1 Announce Type: new Abstract: This paper proposes StratMamba, a dual-stream Mamba-based temporal modeling architecture, to more efficiently capture long-horizon temporal dependencies
arXiv:2607.12604v1 Announce Type: new Abstract: Purpose: Marker-based tracking of surgical robots is occlusion-prone in cluttered operating rooms. We evaluate stereo differentiable rendering for marke
arXiv:2606.16241v3 Announce Type: replace Abstract: Visual anagram is an intriguing form of art creation wherein a single image presents different conceptual interpretations under transformations such
Suno data obtained in a hacking incident has exposed that the AI music generator was trained by scraping millions of songs and lyrics from online audio platforms, including YouTube Music, Deezer, and
arXiv:2607.12042v1 Announce Type: new Abstract: Visual generation is increasingly ubiquitous in diverse domains, from text-to-image/video synthesis to multimodal interactive creation. Yet prevailing m
arXiv:2603.05995v2 Announce Type: replace-cross Abstract: Off-road autonomous driving poses significant challenges such as navigating unmapped, variable terrain with uncertain and diverse dynamics. Ad
arXiv:2607.11898v1 Announce Type: new Abstract: Large-scale text corpora have become a quiet bottleneck in modern NLP, not just in storage, but in the accumulated cost of training, fine-tuning, and co
Introduction RxBrain (Hy-Embodied-RxBrain-1.0) is a unified multimodal foundation model for embodied cognition — a single model that couples language reasoning with visual imagination to deliver three
arXiv:2607.12497v1 Announce Type: new Abstract: Beyond perception, reasoning is essential in remote sensing for advanced interpretation, inference, and decision-making. Recent advances in large langua
arXiv:2607.13028v1 Announce Type: cross Abstract: Training robust autonomous driving agents requires a simulator that is fast enough for reinforcement learning at scale, realistic enough to ground beh
arXiv:2607.12678v1 Announce Type: cross Abstract: Computer-Aided Design (CAD) floor plan drawings contain both graphical primitives and textual annotations, which provide complementary geometric and s
That’s progress, it’s the future. George Lucas says AI makes it 'much easier for us to make movies' and 'there’s nothing you can do about it. That’s progress, it’s the future.” “Artificial intelligenc
arXiv:2607.12208v1 Announce Type: cross Abstract: We show that the Benjamini--Hochberg procedure can fail to control the false discovery rate (FDR) at its nominal level for correlated two-sided Gaussi
The best base model for training isn't about someone else's benchmarks. Excited to offer @thinkymachines' first open-weights model: Inkling. 975B MoE, multimodal, with Apache 2.0. A great foundation f
The Blender MCP is now part of the Hermes Agent MCP Catalog! Easily activate and install the Blender MCP by running `hermes mcp install blender` and ask your agent to start using blender. Hermes will
arXiv:2607.12079v1 Announce Type: new Abstract: Decoding continuous language from fMRI signals remains a core challenge in non-invasive brain-computer interface research. We present two complementary
arXiv:2607.12447v1 Announce Type: cross Abstract: Reliable confidence -- the probability that a model's own answer is correct -- is essential for the trustworthy deployment of language models. Existin
The creation of a regulatory body to enforce and implement standards, as suggested here by @demishassabis or by @AnthropicAI last month, would be a huge step in the right direction to make AI developm
arXiv:2607.12177v1 Announce Type: new Abstract: The analysis of satellite and aerial imagery has entered a new era with the advent of foundation models. This paper describes the concept of Geospatial
arXiv:2607.12616v1 Announce Type: new Abstract: Continuous-time generative frameworks construct probability paths between base and target domains by optimizing time-dependent velocity fields. While th
arXiv:2607.12231v1 Announce Type: new Abstract: We present the GEST-Engine, a complete system that goes from natural-language text to fully-annotated multi-actor video. At its core is an explicit worl
arXiv:2607.12963v1 Announce Type: new Abstract: As large language models (LLMs) grow more capable, they are increasingly deployed in context-rich settings where task inputs are often accompanied by lo
arXiv:2405.11667v2 Announce Type: replace Abstract: Local SGD is a popular optimization method in distributed learning, often outperforming other algorithms in practice, including mini-batch SGD. Desp
arXiv:2607.12520v1 Announce Type: new Abstract: What a frontier model recalls about a person or tool from its own weights -- before any retrieval step -- often shapes the first description a human see
arXiv:2607.12796v1 Announce Type: cross Abstract: When a language model must pick one answer from a large space of equally valid options, which does it pick -- and how often is it the same answer ever
Written by: Corné de Jong Introduction Mandiant security assessments frequently identify publicly exposed serverless applications that lack authentication, often as a result of specific business requi
arXiv:2607.13031v1 Announce Type: cross Abstract: When one ball strikes another, then another, video models should predict the consequences of each bounce. In controlled experiments on multi-ball hard
arXiv:2607.12290v1 Announce Type: cross Abstract: Audio-language embedding models such as CLAP are widely evaluated on matching present sound events, but rarely on negation. We show this affirmation-o
arXiv:2607.13006v1 Announce Type: new Abstract: A growing family of indices scores how predictable a series is from its spectrum. Practitioners increasingly read these scores as answering a different
arXiv:2312.17670v5 Announce Type: replace Abstract: The Circle of Willis (CoW) is an important network of arteries connecting major circulations of the brain. Its vascular architecture is believed to
Thinking Machines just dropped a ~1T Omni model 🔥 > 1M context window, trained on 48T tokens of image, text, audio 🤯 > comes with a drafter, NVFP4 weights and Unsloth quants > transformers, llama.cpp
Thinking Machines Lab: Thinking Machines Lab debuts Inkling, an open-weight MoE model with 975B total and 41B active parameters, trained to be broad rather than optimized for one area — Try on Tinker
Thinky with a ~1T param, 41B active, apache-2 model Benchmarks are a clear step up from Nemotron Ultra (55B active), new best American model, and omni input. A bit behind GLM 5.2 on agentic benchies,
This AI recursive self improvement (RSI) paper shows no sign of fast takeoff. The AI model advances at about [Intelligence]^0.075, or the the 13th root of input intelligence [1,2]. That means the inte
This is for pretraining based on nemotron nvp4 figures, mfu etc Large context, multimodal, long RL we are seeing now could make it a multiple of this Worth noting how good the lite model is, similar t
This is insane! We've just started the challenge, and already 73 papers from ICML are partially or fully reproduced thanks to the community! Join the effort here 👉 https://huggingface.co/spaces/ICML-2
This piece by @GavinSBaker makes me wonder if @elonmusk might consider making future @grok models 'open.' 1- Like @nvidia they have the resources to maintain an open model. 2- They have activity in ma
this was such a fun talk with Cat and Simon, hope you get to check it out if you missed it 🆕This Year In Claude https://www.youtube.com/watch?v=uU5Gv2h8-9g @simonw chats with @_catwu and @trq212 about
🆕This Year In Claude https://www.youtube.com/watch?v=uU5Gv2h8-9g @simonw chats with @_catwu and @trq212 about the state of: - @claudeai Code - Claude Fable - @anthropicai culture & product strategy -
arXiv:2607.12389v1 Announce Type: cross Abstract: We consider Bayesian bandit models and prove that Thompson sampling makes at most twice the expected number of mistakes (selections of a suboptimal ar
arXiv:2602.01700v3 Announce Type: replace Abstract: In this work, we present Tilt-Ropter, a fully actuated hybrid aerial-terrestrial vehicle (HATV) that integrates tilt rotors with passive wheels to e
Today, we are introducing Inkling. Inkling reasons efficiently across text, image, and audio modalities. We are making the full weights available. https://thinkingmachines.ai/news/introducing-inkling/
arXiv:2511.18089v2 Announce Type: replace Abstract: Multimodal survival analysis aims to improve cancer prognosis using heterogeneous biomedical data, such as histopathology images and genomic profile
arXiv:2607.12161v1 Announce Type: new Abstract: Context-reduction layers for API-based coding agents, including command-output compressors, retrieval rankers, and payload-optimizing proxies, are usual
arXiv:2607.12863v1 Announce Type: cross Abstract: Transformer language models are increasingly used as software components, yet biased outputs remain difficult to localize and repair inside the model.
arXiv:2502.11554v3 Announce Type: replace-cross Abstract: Metaphors play a critical role in shaping user experiences with Voice User Interfaces (VUIs), yet existing designs often rely on static, human
arXiv:2607.10467v2 Announce Type: replace-cross Abstract: Healthcare organizations often cannot freely centralize patient data because medical records are sensitive, regulated, and institutionally con
arXiv:2607.12113v1 Announce Type: cross Abstract: One year ago, the AISLE roadmap argued that autonomous laboratories operated as isolated islands and proposed a grassroots network organized around fi