Knowledge catalogue
arXiv:2609.16366v1 Announce Type: cross Abstract: When foundation models describe people, recent work in AI fairness, accessibility, and ethics recommends avoiding inferred identity labels (e.g., 'she
arXiv:2609.16222v1 Announce Type: new Abstract: Stopgrads are widely used in training machine learning models, but stopgrads can alter the gradient, stationary points and convergence guarantees of the
At Orange, the leading France-based multinational telecom provider, there are days when engineering teams set aside their delivery backlogs and spend the day cleaning up cloud spend together. There's
Agentic AI workflows using NVIDIA Omniverse libraries automate preparation of Blender scenes for robotics simulation by adding semantic labels, sensor definitions, physics properties and validating th
arXiv:2609.17094v1 Announce Type: new Abstract: Multimodal representation learning seeks shared representations for cross-modal retrieval and knowledge transfer. Hub-based binding reduces pairwise sup
Customer relationship management vendor HubSpot Inc. is using its annual Unbound conference in Boston today to unveil what it calls its most significant product release in years: a rebuilt CRM platfor
Hugging Face CEO @ClementDelangue, whose company was the victim of an AI-led cyberattack, said existing cyber laws are likely sufficient to govern advanced AI. “I’m not even sure that we need to reinv
arXiv:2609.16964v1 Announce Type: new Abstract: Rapid extraction of structured information from social media is important for humanitarian response, yet existing disaster tweet resources mainly provid
arXiv:2609.17168v1 Announce Type: cross Abstract: Autonomous systems require reliable place recognition for efficient and effective simultaneous localisation and mapping (SLAM). Traditional geometric
arXiv:2609.17358v1 Announce Type: new Abstract: Variational quantum circuits (VQCs) are parameterized quantum circuits optimized classically. We propose a hybrid variational quantum circuit (HVQC) ext
arXiv:2609.16925v1 Announce Type: new Abstract: Hyperbolic geometry provides a natural inductive bias for genomic representation learning, but existing hyperbolic genomic models primarily use Lorentz
arXiv:2609.16811v1 Announce Type: new Abstract: Event cameras have shown great potential for robust visual perception, yet scaling event representation learning remains challenging due to the scarcity
arXiv:2609.16207v1 Announce Type: new Abstract: Spatial Transcriptomics (ST) has transformed biomedical research by enabling the spatial mapping of gene expression across tissue sections. However, hig
I've been working on something that started as the training backend for my Hierarchos architecture, but it has grown into a much broader project: https://github.com/necat101/Hierarchos-Native Hierarch
I think Claude Managed Agents strikes the right balance here, the sandbox is optional and can be spun up independently of the rest of the agent loop. I recently ported an old project that was focused
If you build agent harnesses, this is important. Should you avoid subagents, or can they be useful? My thoughts as a harness builder: I remember using subagents in Claude Code, and I mostly found them
arXiv:2609.16696v1 Announce Type: new Abstract: Autonomous excavator control is challenged by coupled kinematics, actuation lag, and uncertainty. We propose imitation learning and adaptive Cartesian t
arXiv:2609.16403v1 Announce Type: cross Abstract: Goldwasser et al. showed that undetectable backdoors can be planted in machine learning models trained with the Random Fourier Features (RFF) algorith
arXiv:2609.16816v1 Announce Type: cross Abstract: Language model-generated rubrics are increasingly used as reward signals for rubric-based reinforcement learning, LLM-as-a-judge evaluation, and autom
AI agents on foundation models often misapply healthcare and life sciences decision frameworks, citing the right guideline but applying it incorrectly. This post shares 38 open-source agent skills acr
arXiv:2609.16237v1 Announce Type: cross Abstract: Rotating detonation engines (RDEs) exhibit strongly nonlinear, multiscale wave dynamics that set the observed thermal field. High-fidelity simulations
arXiv:2609.16775v1 Announce Type: new Abstract: Annotating large radiology datasets is bottlenecked by the manual effort of delineating structures slice-by-slice in 3D volumes. Interactive methods red
Ina Fried / Axios: In an essay, Mustafa Suleyman says Anthropic's training of Claude to imitate consciousness is a mistake that could make advanced AI harder to control — Microsoft AI chief Mustafa Su
arXiv:2609.16827v1 Announce Type: new Abstract: High-capacity associative memories based on Kernel Logistic Regression (KLR) exhibit exceptional storage capabilities and robustness. Previous empirical
arXiv:2609.17218v1 Announce Type: new Abstract: Label-free clustering of frozen pretrained visual embeddings offers a scalable route to biodiversity monitoring, but image-only fine-grained taxonomy ex
arXiv:2609.16779v1 Announce Type: new Abstract: LLMs are increasingly employed in a wide range of decision-making tasks. However, the opacity of their internal reasoning makes it difficult to validate
arXiv:2609.16295v1 Announce Type: cross Abstract: Interaction techniques (IxTs) are the low-level, reusable components out of which user interfaces are designed, including menus, scroll bars, text inp
arXiv:2609.17088v1 Announce Type: new Abstract: Recent advancements in large language models have significantly enhanced the capabilities of agents in modeling long-term conversations. Despite these s
Interesting safety paper from Microsoft. They find that a weaker, unaligned model can split a harmful task into harmless-looking subquestions, ask an aligned frontier model each one in a separate sess
arXiv:2609.16436v1 Announce Type: cross Abstract: Simulations based on large language models (LLMs) have proven to be powerful for understanding human behavior, making them valuable additions to the s
arXiv:2609.17325v1 Announce Type: new Abstract: Biological cells can be viewed as individual, interacting agents whose collective dynamics give rise to adaptive behaviour at multiple levels of organis
arXiv:2609.17115v1 Announce Type: cross Abstract: Vision-language-action (VLA) systems already bring together two valuable resources for robot learning: rich visual representations and demonstrations
arXiv:2609.17175v1 Announce Type: new Abstract: We present IRENE (Italian Radar Ensemble Nowcasting Experiment), a deep learning model for probabilistic short-range precipitation nowcasting over the I
arXiv:2609.16085v1 Announce Type: cross Abstract: Eight-bit integer (INT8) post-training quantization is the default recipe for edge deployment, under a widely held assumption: INT8 makes inference fa
arXiv:2512.15020v3 Announce Type: replace Abstract: Vision-based imitation learning has enabled impressive robotic manipulation skills, but action imitation alone provides limited supervision of the g
Jack & Jill, operated by Tinker Tailor Talent Ltd., a hiring platform powered by conversational generative artificial intelligence, said Tuesday it has raised 40 million in early funding to build a jo
arXiv:2609.16739v1 Announce Type: new Abstract: Background: Large language models (LLMs) have achieved physician-comparable performance on multiple-choice medical knowledge examinations, but their cap
arXiv:2609.16626v1 Announce Type: new Abstract: Virtual try-on (VTON) enables customers to visualize how fashion products appear when worn and has become an important technology for online shopping. W
Just went on BBC TV and they opened with clips today from Altman, Huang, and Sanders. Altman and Huang want us to believe that the AI companies have the public interest at heart and will happily just
arXiv:2609.17475v1 Announce Type: new Abstract: Capable open-weight models make local coding and reasoning attractive, but their context and execution state strain laptop memory. We present JustFit, a
arXiv:2609.17147v1 Announce Type: cross Abstract: Autonomous racing confronts significant challenges in safely overtaking Opponent Vehicles (OVs) that exhibit uncertain trajectories, stemming from unk
arXiv:2609.17417v1 Announce Type: cross Abstract: Finite knowledge is usually stored extensionally, one code or vector per item. We ask whether a finite collection can instead be stored intensionally,
It turns out Krea 2 was trained on a number of different pixel art resolutions. These loras help you get some of these resolutions more consistently and avoid ugly 'mixel' resolutions with inconsisten
arXiv:2609.17509v1 Announce Type: cross Abstract: Neural audio codecs are a key component in speech language modeling. However, their high frame rates lead to long sequence lengths, increasing computa
arXiv:2609.16458v1 Announce Type: cross Abstract: Audio deepfake detectors need to transfer to languages absent from training, as multilingual speech synthesis outpaces labeled anti-spoofing resources
GitHub: https://github.com/pfekin/LARA I've been working on LARA (Lightweight Additive Residual Adaptation), a research project on making post-training modular for frozen language models. I've also de
arXiv:2609.17376v1 Announce Type: cross Abstract: Large language models (LLMs) trained on next-token prediction exhibit remarkable in-context learning (ICL) abilities, yet the representations that sup
arXiv:2609.16599v1 Announce Type: cross Abstract: Modern networked control systems (NCSs), cyber-physical systems (CPSs), and complex multi-agent network systems (CNSs) increasingly rely on large lang
arXiv:2609.15994v1 Announce Type: new Abstract: LLMs handle ordinary typing variation fluently: a typo or missing punctuation leaves both user intent and the model's response substantively unchanged.
arXiv:2609.16795v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) can answer knowledge-intensive visual questions by combining visual evidence from images with facts retrieved f
arXiv:2609.16823v1 Announce Type: new Abstract: Photonic neural networks (PNNs) offer efficient analog inference, but parameters optimized under ideal device models can degrade after fabrication, crea
arXiv:2609.16440v1 Announce Type: cross Abstract: Classification and regression trees are typically constructed using a greedy splitting rule that maximizes the immediate reduction in prediction error
arXiv:2603.08283v2 Announce Type: replace Abstract: Complex constraints often make real-world optimization computationally prohibitive at the scale and speed required for operational decision-making.
arXiv:2609.17429v1 Announce Type: cross Abstract: Many learned sequential decision systems map the current state directly to an action. That shortcut becomes brittle when candidate actions are numerou
arXiv:2609.17042v1 Announce Type: new Abstract: Learning flexible motor primitives is a hallmark of skilled motor control. Recent neuroscience theory proposes that motor primitives may be implemented
arXiv:2609.16629v1 Announce Type: new Abstract: UAVs have emerged as highly flexible platforms for data sensing in Wireless Sensor Networks (WSNs). Path planning for UAVs in such tasks plays a key rol
arXiv:2609.16672v1 Announce Type: new Abstract: Background and Objective: Colonoscopy recording practice preserves text reports and still photographs, while the spatial information already present in
arXiv:2609.17145v1 Announce Type: new Abstract: In this paper, we study 3D LiDAR scan alignment in challenging scenarios with degeneracies, such as straight corridors or flat fields, where the alignme
arXiv:2609.17488v1 Announce Type: new Abstract: We introduce LimiX-2, a new model in the LimiX family, developed through model and data scaling guided by our previously established scaling laws. LimiX
arXiv:2609.16912v1 Announce Type: new Abstract: We describe tus-nlp's Lit3R (Retrieve-Relate-Read) system for LitTraceQA, a shared task for literature-grounded question answering that requires systems