Knowledge catalogue
arXiv:2610.04255v1 Announce Type: cross Abstract: Robotic manipulation often requires inferring task-relevant states from past interactions when the current observation alone is insufficient to determ
arXiv:2610.05450v1 Announce Type: new Abstract: Preference-based alignment methods such as reinforcement learning from human feedback (RLHF) and Nash learning from human feedback (NLHF) aggregate pair
arXiv:2610.04651v1 Announce Type: cross Abstract: Neural audio codecs compress waveforms into compact discrete tokens that underpin speech language models, real-time communication, and large-scale aud
arXiv:2610.06688v1 Announce Type: new Abstract: Factories, museums and surveyors photograph the same space months apart and need to know which objects changed. When each visit is reconstructed with 3D
arXiv:2604.00385v2 Announce Type: replace Abstract: Type 1 diabetes (T1D) management requires continuous adjustment of insulin and lifestyle behaviors to maintain blood glucose within a safe target ra
arXiv:2610.06805v1 Announce Type: new Abstract: Long-horizon planning with latent world models requires reasoning across timescales and levels of abstraction. Existing task-agnostic JEPA world models
Cybersecurity training company Hack The Box Ltd. today introduced AI Range Enterprise Edition to let security teams test whether their own artificial intelligence agents can do the jobs they have been
Tamara Djurickovic / Tech.eu: Hadrian, an agentic AI offensive security service, raised 40M co-led by Forgepoint Capital International and SmartFin, taking its total funding to 65M — Hadrian will use
Dutch offensive security startup Hadrian Security B.V. today announced that it has raised 40 million in new funding to expand its business internationally. Hadrian’s software points artificial intelli
arXiv:2610.04969v1 Announce Type: new Abstract: Optimization in machine learning is usually expressed through iterative rules that update model parameters using information from the loss landscape. In
arXiv:2409.18778v2 Announce Type: replace Abstract: Efficiently determining the satisfiability of a boolean equation -- known as the SAT problem for brevity -- is crucial in various industrial problem
arXiv:2610.06503v1 Announce Type: new Abstract: Text-to-image generative models can produce highly realistic imagery but also raise concerns about harmful misuse. While safety mechanisms exist, system
arXiv:2610.06394v1 Announce Type: new Abstract: Human-object interaction (HOI) detection aims to localize human-object pairs and recognize their interactions. Traditional supervised methods perform st
Here's a benchmark that uses Lilypond https://x.com/aug5thmusic/status/2096030719156089029 GPT-6 Astra has the best result yet on the Bach Benchmark. Its chorale contains no voice-leading errors, and
arXiv:2610.06437v1 Announce Type: new Abstract: We introduce Heuristic-Guided Fourier Fine-Tuning (HeuFouFT), a task-guided framework for selecting trainable frequency coordinates in Fourier fine-tuni
arXiv:2610.05139v1 Announce Type: new Abstract: Code large language model (Code LLM) assistants generate code from heterogeneous development contexts, including open files, imported modules, pasted sn
arXiv:2610.05834v1 Announce Type: new Abstract: Broad Learning System (BLS) supports analytical training and incremental expansion, but its growth needs guidance on which inputs new blocks should lear
arXiv:2610.04344v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has been shown to improve the reasoning capability of large language models (LLMs) across diverse
arXiv:2610.05855v1 Announce Type: new Abstract: A bipedal robot cannot deviate from its path to avoid an obstacle without disturbing its balance, and this coupling is most severe on underactuated plat
arXiv:2610.05446v1 Announce Type: new Abstract: Off-policy hierarchical reinforcement learning must estimate the values of high-level decisions while the low-level policy changes. HIRO adapts replay d
arXiv:2603.26954v2 Announce Type: replace Abstract: The trend towards larger training setups has brought a renewed interest in partially asynchronous two-phase optimizers which optimize locally and th
arXiv:2610.05739v1 Announce Type: new Abstract: Long-horizon video world models require persistent memory to preserve scene consistency over extended rollouts. Softmax attention retains the full gener
arXiv:2610.04499v1 Announce Type: new Abstract: Radiology report generation (RRG) aims to convert medical images into diagnostic texts to assist in clinical decision-making and alleviate the workload
arXiv:2610.05994v1 Announce Type: cross Abstract: Vision-language-action (VLA) models currently demonstrate strong performance in a wide range of real-world robotics tasks. However, they often still l
DOCA GPUNetIO delivers a unified GPU‑directed networking (GDA‑KI) foundation that lets CUDA kernels drive Ethernet, RDMA, Verbs and DMA operations without the CPU entering the application path. It shi
arXiv:2610.05135v1 Announce Type: new Abstract: Under a fixed physical law, the visible geometry of a scene determines how motion must change. We ask how video generators realize this relationship. We
arXiv:2610.05077v1 Announce Type: new Abstract: Backtests of LLM trading agents often assume that every order fills at the closing price. We ask whether this choice changes only reported returns or al
arXiv:2610.04988v1 Announce Type: new Abstract: Latent world models plan by rolling a frozen predictor forward under candidate action sequences and ranking the candidates by the latent distance betwee
arXiv:2610.04158v1 Announce Type: new Abstract: Recent studies on reinforcement learning (RL) report seemingly conflicting evidence about large language model (LLM) reasoning. Training on mathematics
arXiv:2610.04950v1 Announce Type: new Abstract: On-policy distillation (OPD) improves the reasoning capabilities of small language models through token-level teacher supervision on student-generated t
Google’s new EmbeddingGemma 2 can run on a phone. The model travels light. The vectors need their own suitcase. At 10 million documents, full-size float32 vectors alone take 30.7 GB of RAM. We got ear
arXiv:2610.06677v1 Announce Type: new Abstract: Mixture-of-experts (MoE) routers typically apply softmax to the router scores and keep the top-K experts, making every token use exactly K experts. Spar
arXiv:2610.06784v1 Announce Type: cross Abstract: Much of the recent progress in machine learning domains such as language models has come from scaling laws that predict performance as a function of t
arXiv:2610.06034v1 Announce Type: cross Abstract: We consider the fusion of lung ultrasound images with routinely-collected clinical and demographic data for the purpose of automated tuberculosis (TB)
A small thing I noticed: full-size screenshots use far more AI tokens than the model needs, so usage limits run out sooner. I built a free Firefox add-on, TokenSaver, that shrinks images before they a
arXiv:2610.04366v1 Announce Type: new Abstract: Reliable safety evaluation of autonomous vehicles (AVs) is essential to improving road safety, yet it depends critically on realistic simulation of rare
arXiv:2610.05757v1 Announce Type: new Abstract: This paper introduces Hybrid DeepSEE (HDS), a Human-in-the-Loop (HITL) neuro-symbolic framework for proactive drift anticipation in Visual SLAM (V-SLAM)
arXiv:2610.05463v1 Announce Type: cross Abstract: Visual search is a fundamental cognitive ability. This study investigates whether Multimodal Large Language Models (MLLMs) exhibit human-like difficul
arXiv:2610.04238v1 Announce Type: cross Abstract: Humanoid robots could transport payloads substantially heavier than themselves by pulling passive wheeled vehicles instead of carrying the load. This
I've been working on native ComfyUI support for Tencent's HunyuanImage 3.0, the 80B mixture-of-experts image model (13B active per step). It isn't a wrapper around Tencent's pipeline: it uses the norm
arXiv:2610.05254v1 Announce Type: new Abstract: We propose Hybrid-Basis Feature Forecasting (HybridFF), a training-free, plug-and-play framework for accelerating diffusion sampling. To capture local s
arXiv:2610.06745v1 Announce Type: new Abstract: Hierarchical graphs embed in hyperbolic space with lower distortion than in Euclidean space owing to its negative curvature. However, their gradient-bas
arXiv:2610.04640v1 Announce Type: cross Abstract: Hypergraphs record multi-way interactions among entities. Extracting information from the combinatorial structure underlying observed multi-way intera
I asked Opus 5.5 to make an interactive website companion for the latest @AcquiredFM Home Depot episode. It came out pretty nice! Water color illustrations all drawn by Claude, too: https://claude.ai/
arXiv:2610.06129v1 Announce Type: new Abstract: Behavioral foundation models (BFMs) have recently shown that a single humanoid policy can support diverse whole-body control, but extending such general
I spent the last few weeks on a hobby research project and just made it public. The idea isn't new (product-key memory, Lample et al. 2019, and Meta's 'Memory Layers at Scale'): give a model a huge ta
On October 6 2026 Sophia Yang announced an “open‑source AI week.” She highlighted Monday’s event featuring @reflection_ai’s Beam and Tuesday’s unveiling of @MistralAI’s Mistral Large 4, indicating ant
Ideally I'd like to be able to run Qwen 3.8-Flash-Next with decent performance. I was thinking of just buying 2x Radeon AI R9700 (64GB VRAM), or maybe a DGX Spark but that was before the price hike. M
My YouTube feed was mostly songs, pranks and celebrity clips, so I built a filter that judges each video title with a small decision model running inside Chrome. Nothing is sent anywhere: no server, n
I've been working on an extension that runs MiniMax H3 inside Forge Neo. H3 makes the picture and the sound together, in one pass: footsteps, rain, engines, music and dialogue in pretty much any langu
I was tired of opening heavy photo editors just to tweak lighting or color-grade a folder of AI generations. So I built TinyLuma - an instant, lightweight photo editor designed specifically for finish
I recently led an AI workshop where the most jaw-dropping moment was toggling the desktop app from ChatGPT to Codex. That moment elicited the loudest “OHHHHH!!!” I heard all day. And these are incredi
Meet Bev. She is a decision model (the Jev / Nimble kind: you give her a situation and a question, she gives a probability for each answer), fine-tuned on Qwen3.5-9B to pick the worst answer on purpos
I wanted to build an offline bird/plant identifier that runs on a laptop with Ollama. Before building any UI, I tested it on 6 photos: Common Myna → gemma4:e2b said 'Jackdaw' (confidence: high). gemma
i was told we can't fundraise and grow at the same time. it turned out we grew monthly usage 400% during fundraising. we have never run this fast. while taking 60 investor calls a week, we shipped 20
arXiv:2607.11627v2 Announce Type: replace-cross Abstract: Both Remotely Operated underwater Vehicles (ROVs) and Autonomous Underwater Vehicles (AUVs) are frequently deployed to acquire geometric bathy
arXiv:2610.04142v1 Announce Type: new Abstract: Modern training on a new task often starts from a previously trained model rather than from scratch, raising the question of how this initialization aff
arXiv:2610.06778v1 Announce Type: cross Abstract: While modern AI detectors identify who wrote the words, emerging policies on AI use increasingly hinge on a different question: who came up with the i
If you are using Qwen3.8-27B + MTP, make sure to upgrade to DFlash for extra speed: llama serve -hf ggml-org/Qwen3.8-27B-GGUF --spec-type draft-dflash --spec-draft-n-max 7 Requires the latest llama.cp
arXiv:2610.06348v1 Announce Type: cross Abstract: Isogeometric analysis (IGA) solves partial differential equations accurately on exact NURBS geometry, whereas neural solvers are mesh-free but often o