Knowledge catalogue
arXiv:2610.11583v1 Announce Type: cross Abstract: End-to-end autonomous driving demands trajectory planners that are both highly accurate and cheap enough for edge deployment. State-of-the-art artific
arXiv:2610.10768v1 Announce Type: cross Abstract: The global challenge of climate change has driven significant steps to reduce CO2 emissions, guided by international agreements like the Paris Agreeme
arXiv:2610.11136v1 Announce Type: new Abstract: Presupposing the boundaries of bias is itself a form of bias. We study closed-loop bias governance for Dutch government documents, where a system must d
arXiv:2610.10620v1 Announce Type: cross Abstract: When an assistant encounters a message for another AI, does it tell its user? Four fixed model-provider deployments perform simulated source tasks in
arXiv:2610.10622v1 Announce Type: cross Abstract: Large language models can now write complete, interactive 3D worlds as code, but grading those worlds automatically is unreliable. Existing judges tak
arXiv:2610.09770v1 Announce Type: cross Abstract: Deep learning has made rapid advances in weather forecasting: autoregressive models trained on atmospheric reanalyses now rival dynamical models acros
Awesome day, @satyanadella! Windows sparked a platform shift that created a new industry for NVIDIA. Then we invented programmable shading GPUs for DirectX, which led to CUDA. Then we partnered to bri
arXiv:2505.06592v2 Announce Type: replace Abstract: In this paper, we propose batch augmentation with unimodal fine-tuning for multimodal learning. We start with pre-trained unimodal models. We fine-t
Big new paper nobody is talking about ‼️ 🌎 Robot world models now have scaling laws. Meta trained an 8B-parameter JEPA on 15,000 hours of robot video to prove it. RoboJEPA (FAIR at Meta + Mila) imagin
arXiv:2610.08917v1 Announce Type: new Abstract: While vision-language-action (VLA) models have advanced rapidly, running them at every control step remains expensive. Prior work accelerates VLA infere
arXiv:2610.09219v1 Announce Type: cross Abstract: Direct Preference Optimization (DPO) treats all constraint violations equally: a 1 budget overshoot and a 1,000 overshoot induce the same training sig
arXiv:2610.09228v1 Announce Type: new Abstract: Vision-language-action (VLA) policies trained on large datasets are capable within their training domains, yet they still fail to generalize to the vari
arXiv:2610.10206v1 Announce Type: cross Abstract: Links are disjoint unions of circles smoothly embedded in S^3. We use reinforcement learning and Bayesian optimisation to obtain new upper bounds on s
arXiv:2610.09552v1 Announce Type: cross Abstract: Watermarking enables language model providers to identify text generated by their models. However, its desired properties can conflict (ie~stronger wa
arXiv:2610.10527v1 Announce Type: cross Abstract: Heavy-tailed noise has been widely observed in modern machine learning, motivating the use of methods like gradient clipping and normalization. While
arXiv:2610.10378v1 Announce Type: new Abstract: Document-level text simplification involves transformations that go beyond sentence-internal edits, addressing discourse coherence, anaphora resolution,
arXiv:2610.10203v1 Announce Type: new Abstract: Model organisms of alignment-relevant behaviors (e.g., backdoors, sycophancy, spurious correlations) have emerged as a key tool for evaluating whitebox
arXiv:2610.10368v1 Announce Type: cross Abstract: Adaptive computation aims to improve language-model inference by tailoring execution to each input. For layer programs, oracle evaluations use known a
Write-up + demo: https://drksci.com/labs-phosphene So this started as a bit of a gripe. Modern terminal renderers are seriously impressive and seriously complicated. GPU glyph atlases, texture caches,
arXiv:2610.10473v1 Announce Type: new Abstract: Cell viability assessment is a core requirement in cell culture systems, with critical applications in biopharmaceutical manufacturing and drug developm
arXiv:2610.09285v1 Announce Type: cross Abstract: Many applications of physical AI run within finite or closed physical worlds with a limited set of physical laws governing object behavior. Examples i
arXiv:2610.10232v1 Announce Type: new Abstract: Large language models (LLMs) have already been shown to match or exceed human experts in persuasion. While their persuasive capabilities hold promise fo
arXiv:2610.09795v1 Announce Type: new Abstract: The demand for personalized LLMs is shifting from style imitation toward content quality. We investigate whether self-distillation can bridge this gap i
arXiv:2610.09063v1 Announce Type: cross Abstract: Multi-label topic assignment for user-generated content (UGC) -- including product reviews and buyer-seller conversations -- poses unique scalability
arXiv:2610.10515v1 Announce Type: cross Abstract: Latent world models have shown a remarkable ability to predict future states and to plan in the real world. In practice, however, we lack a principled
arXiv:2604.03315v2 Announce Type: replace Abstract: Storyboarding is a core skill in visual storytelling for film, animation, and games. However, automating this process requires a system to achieve t
arXiv:2610.09313v1 Announce Type: new Abstract: Vision-language models (VLMs) often miss small objects in large images. We ask three questions: what limits them, which of these limits better models ca
arXiv:2610.07084v1 Announce Type: cross Abstract: An inaccurate expert can still provide useful information after correction. We study online learning to defer in which the learner chooses an expert a
arXiv:2610.07677v1 Announce Type: new Abstract: In this paper, we show that standard evaluations of high-resolution Model Inversion Attacks (MIAs) significantly underestimate training-data privacy lea
arXiv:2610.07029v1 Announce Type: cross Abstract: Resistive random-access memory (ReRAM)-based Processing-in-Memory (PIM) accelerator is a promising platform for processing massively memory intensive
arXiv:2610.06927v1 Announce Type: cross Abstract: The key-value (KV) cache of autoregressive transformers grows linearly with context length and dominates memory at long context. Most training-free re
arXiv:2603.15822v2 Announce Type: replace Abstract: Automated radiology report generation from 3D CT volumes often suffers from incomplete pathology coverage. We provide empirical evidence that this l
arXiv:2610.08123v1 Announce Type: cross Abstract: End-to-end planners based on waypoint regression achieve strong open-loop accuracy, but they primarily learn to mimic expert geometry and remain diffi
arXiv:2610.07939v1 Announce Type: new Abstract: Due to rapid advances in Generative AI, commercial video generation tools can be used to produce fabricated surveillance footage that can fool both huma
arXiv:2610.05828v2 Announce Type: replace Abstract: Large language models (LLMs) offer new opportunities for public opinion research by enabling early prediction of survey responses, potentially reduc
arXiv:2610.07984v1 Announce Type: cross Abstract: Multimodal assistants answer questions from long-term memories that contain images. After retrieval, each retrieved image reaches the answering model
On 15 September, TypeSafe released Jev, and within a few weeks about 10 companies had shipped something that works the same way. OpenAI, Liquid, Cloudflare, AWS and PostHog all launched one, and an op
arXiv:2610.07969v1 Announce Type: new Abstract: Scaling robotic foundation models requires diverse training data and reliable evaluation environments. Simulation offers a scalable solution, yet existi
arXiv:2610.07354v1 Announce Type: new Abstract: Deciding when to escalate a query from a small language model to a larger one requires a cheap signal that predicts, before the large model is called, w
NVIDIA cuPhoton is an open‑source CUDA‑X toolkit that keeps scientific image data on the GPU from ingestion through classification, providing modules such as xDataReader (direct FITS loading), xRep (a
arXiv:2604.00055v2 Announce Type: replace-cross Abstract: Existing robotic foundation policies are trained primarily via large-scale imitation learning. While such models demonstrate strong capabiliti
arXiv:2610.08350v1 Announce Type: cross Abstract: Visual world models enable goal-directed control through decision-time action search, but their deployment efficiency is often limited by conservative
arXiv:2610.07638v1 Announce Type: new Abstract: As part of learning to play complex games, human players develop develop abstractions for concepts and strategies of gameplay consistent with game rules
arXiv:2610.08033v1 Announce Type: new Abstract: World models are usually judged from the inside: by prediction loss, by the return a policy earns in imagination, or by how convincing their frames look
Running a model on your own machine used to be a privacy story with a quality tax. On this generation that trade has narrowed to where we can state it plainly: for daily work, the local model is good
arXiv:2610.07127v1 Announce Type: cross Abstract: Recent advances in multimodal foundation models yield strong performance on static perception and reasoning benchmarks, yet such evaluations largely o
arXiv:2610.07342v1 Announce Type: new Abstract: On-policy reinforcement learning has become a central paradigm for improving the reasoning abilities of large language models. However, its effectivenes
arXiv:2610.07894v1 Announce Type: new Abstract: Large language models (LLMs) are expected to answer questions faithfully based on the provided context, abstaining when the context information is insuf
arXiv:2610.08137v1 Announce Type: cross Abstract: AI systems create images and videos with image/video generation models or by writing code and graphics descriptions that are then rendered. These rout
arXiv:2610.06955v1 Announce Type: cross Abstract: Humans inherently understand the physical world through an active process. When sensory evidence is insufficient to infer physical properties, we natu
NVIDIA cuOpt’s Multi‑GPU Primal‑Dual Hybrid Gradient (mPDLP) solver distributes linear programming problems across NVLink‑connected GPUs, cutting per‑GPU peak memory by up to six times and handling up
arXiv:2610.08678v1 Announce Type: cross Abstract: Speculative decoding accelerates inference for a large language model (LLM), referred to as the target model, by first using a smaller model, referred
arXiv:2610.07650v1 Announce Type: new Abstract: Reusing a capability across heterogeneous robots still requires substantial human adaptation and verification: transferring a skill often means re-engin
arXiv:2610.06874v1 Announce Type: cross Abstract: Reinforcement-learning quadrotor controllers are usually trained under simplified wind models, yet the impact of wind-field fidelity, as opposed to ma
arXiv:2610.07527v1 Announce Type: new Abstract: We introduce Task-Space Imitation Guidance for Efficient Reinforcement Learning (TIGER), a reward-construction and pretraining framework for sparse-rewa
arXiv:2610.08747v1 Announce Type: new Abstract: A common approach to measuring bias in Large Language Models is to compare the log-likelihoods of two contrastive stereotype sentences. We argue that su
The power of OpenDocRouter is already working: Anthropic just dropped Haiku 5.5 and we already have initial benchmark results. I see pretty comparable results to Luna overal. Slightly better at tables
arXiv:2610.07798v1 Announce Type: new Abstract: People increasingly ask large language models what to do with their money, yet seldom describe their finances in full. This paper asks what a model does
arXiv:2610.07350v1 Announce Type: new Abstract: Long chain-of-thought reasoning increases sequential decoding cost while creating a growing history of potentially reusable continuations. We investigat
arXiv:2610.08225v1 Announce Type: new Abstract: In this work, we introduce Crazyflow, an accurate, differentiable simulator built on JAX. By leveraging jit compilation via XLA, Crazyflow unifies physi