Knowledge catalogue
arXiv:2610.20999v1 Announce Type: cross Abstract: Diffusion models are notoriously expensive to train, requiring large-scale datasets to learn how to gradually reverse the noise from images over multi
arXiv:2610.22289v1 Announce Type: new Abstract: Stronger language models may increasingly construct useful procedures for themselves, reducing the advantage of developer-supplied scaffolding. We inves
arXiv:2610.13944v2 Announce Type: replace Abstract: Diffusion/flow models have emerged as the de facto paradigms for image generation, giving rise to a diverse family of modern generators with increas
arXiv:2610.20634v1 Announce Type: new Abstract: Retrieval-augmented generation asks one question at volume: does this evidence support this claim? The answer is one bit, yet most pipelines obtain it f
arXiv:2610.22080v1 Announce Type: new Abstract: A language model can generate several solutions to the same problem, some leading to correct answers and others to incorrect ones. Many post-training me
arXiv:2406.07243v4 Announce Type: replace Abstract: Generative large language models (LLMs) have been shown to exhibit harmful biases and stereotypes. While safety fine-tuning typically takes place in
arXiv:2610.20967v1 Announce Type: cross Abstract: State-of-the-art text-to-music models increasingly rely on scaling model capacity, data, and compute, while still learning musical structure directly
arXiv:2610.20965v1 Announce Type: new Abstract: Large multimodal models have achieved remarkable progress by scaling model capacity and training on massive paired multimodal data. However, this paradi
arXiv:2610.22249v1 Announce Type: new Abstract: Recurring expressions in model-written text are often treated as signatures of machine authorship, yet most of them serve legitimate functions. Whether
arXiv:2610.21438v1 Announce Type: new Abstract: Existing deepfake detection models are built upon manipu- lated images that are tampered with either exclusively fully swapped or fully synthesised face
arXiv:2610.20665v1 Announce Type: new Abstract: Large language model (LLM) agents can solve complex interactive tasks, yet reasoning and tool calls take time. In continuously changing environments, an
arXiv:2610.20764v1 Announce Type: new Abstract: This paper challenges the understanding capabilities of existing AI paradigms and emerging world models by asking a fundamental question: How quickly ca
I saw the 4x R9700 build for a 10-person startup here a few days ago and wanted to share my results, since I opted to spend most of the money on the cards. I went with a super cheap used EPYC instead
arXiv:2610.15956v1 Announce Type: new Abstract: Vision-language-action models for embodied navigation typically rely on RGB observations, limiting their applicability in lights-out industrial environm
arXiv:2610.18860v1 Announce Type: new Abstract: Generating information-rich visual artifacts such as slides, posters, and dashboards as code is appealing because the outputs are structured, editable,
arXiv:2609.33196v2 Announce Type: replace Abstract: Evaluating large language models (LLMs) relies heavily on benchmark scores, yet aggregate metrics can obscure whether individual items serve their i
arXiv:2610.20331v1 Announce Type: new Abstract: Diffusion and flow matching are now dominant frameworks for generative modeling in continuous domains, but they typically require multiple network evalu
arXiv:2610.19951v1 Announce Type: new Abstract: Agent skills adapt frozen models through editable external instructions. Revising several rules at once makes changes difficult to inspect, while judgin
models : add maion-coder (#29778) Add Support to maion-coder arch iAdd Support to support Draft models Address comments Remove maion context shift function Co-authored-by: Karthik Vijayan kavijay@micr
arXiv:2610.19367v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for multi-turn agentic tasks that require interactions with users and environments over extended sequ
arXiv:2610.19709v1 Announce Type: new Abstract: Mamba models underperform Transformers on in-context retrieval. This gap is usually attributed to Mamba's fixed-size recurrent state, which loses inform
arXiv:2607.11414v2 Announce Type: replace Abstract: Large language models (LLMs) in financial applications fail most consequentially when they are confidently wrong. Hedged, uncertain answers invite s
arXiv:2610.14826v1 Announce Type: cross Abstract: Recent alignment-free Text-to-Speech (TTS) models achieve high synthesis quality by removing explicit alignment modules and simplifying training. Howe
arXiv:2610.20272v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated multilingual capabilities across diverse language generation and understanding tasks. Yet effective code-
arXiv:2610.14763v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) can reproduce sensitive, copyrighted, or unsafe information from their training data. Effective unlearning must
arXiv:2610.20483v1 Announce Type: new Abstract: We study how to improve LLM reasoning at inference time without updating model weights or using external reward models. Recent reward-free power-samplin
arXiv:2610.17331v1 Announce Type: new Abstract: General-purpose coding agents use standard shell and file interactions, yet formal theorem-proving agents often rely on specialized, ad-hoc tooling. Thi
arXiv:2603.00578v2 Announce Type: replace-cross Abstract: Long chain-of-thought~(CoT) reasoning improves the problem-solving capability of large reasoning models~(LRMs), but often incurs substantial i
arXiv:2610.17523v1 Announce Type: cross Abstract: With recent developments in Artificial Intelligence (AI), the adoption of distributed learning paradigms such as Federated Learning (FL) has emerged.
arXiv:2610.19240v1 Announce Type: new Abstract: Financial disclosures express the underlying relationships of double-entry accounting through unstructured text. While financial LLM benchmarks predomin
arXiv:2610.20417v1 Announce Type: new Abstract: Audits of large language model (LLM) extraction from full-length documents report severe unreliability, leaving two questions open: what the failures ac
arXiv:2610.15750v1 Announce Type: new Abstract: Google Earth AI is a family of geospatial AI models, together with an agent that orchestrates them. We present this agent, Google Earth AI's Geospatial
arXiv:2610.16790v1 Announce Type: cross Abstract: Language model APIs can expose token-specific biases while withholding logits and token probabilities. Existing bias-based extraction recovers relativ
arXiv:2610.20570v1 Announce Type: new Abstract: Brazilian Portuguese remains underserved by open-source language models, and the few that are safety-aligned rarely document what did not work or valida
arXiv:2610.14389v1 Announce Type: new Abstract: Benchmark scores tell us what an LLM can do, but not how much energy is required to deliver that capability. We directly measure this trade-off for 86 o
arXiv:2610.19728v1 Announce Type: cross Abstract: Video large language models (Video LLMs) often generate responses unsupported by the input video. Contrastive decoding (CD) can mitigate these halluci
Muse Spark Open is now rolled out to Pro, Max, Pay-as-you-go, and Teams plans. Muse Spark Open is now on Ollama. @Meta's open-weight model for coding and tool use, with a 1M-token context window. Run
arXiv:2610.16312v1 Announce Type: new Abstract: Explicit reasoning in large language models (LLMs) is often associated with reliability, yet it can still pose risks when a model infers harmful goals u
NVIDIA has made its Nemotron 3.5 Super VL model available on the Perplexity AI platform for users on Pro and Max subscription plans, as well as through a new Agent API endpoint. The release was announ
arXiv:2610.10358v2 Announce Type: replace Abstract: As multimodal large language models (MLLMs) become more capable and widely deployed, concerns about privacy and safety have become increasingly pres
arXiv:2610.16141v1 Announce Type: new Abstract: LLM agents increasingly operate over multiple entities, where reliable response generation requires not only retrieving relevant evidence but also prese
arXiv:2610.14570v1 Announce Type: new Abstract: Large language models (LLMs) support social simulation, but faithfully reproducing real users requires grounding both structured platform decisions and
arXiv:2610.17728v1 Announce Type: new Abstract: Egocentric multimodal assistants see through the user's eyes and guide what the user does next, so their outputs directly shape physical actions, includ
arXiv:2610.14089v1 Announce Type: cross Abstract: Smart glasses are a promising platform for vision-language assistants, but private split inference remains expensive: protecting visual representation
arXiv:2604.05656v2 Announce Type: replace Abstract: Vision-language-action (VLA) models with flow-matching action heads, such as {pi}0 and {pi}0.5, have become a standard recipe for generalist robot m
arXiv:2606.13497v2 Announce Type: replace-cross Abstract: This work introduces Spatial Annotations from Robot Demonstrations with Reliability Calibration (SPARC), a risk-aware framework that automatic
arXiv:2610.19636v1 Announce Type: cross Abstract: Large language models (LLMs) hold broad knowledge in one set of weights, but lack interpretability and trustworthy reasoning, especially in high-stake
arXiv:2610.15407v1 Announce Type: new Abstract: An end-to-end success rate alone cannot distinguish failure to learn an action from failure to apply it as task state changes. We study this distinction
arXiv:2610.15107v1 Announce Type: new Abstract: Chain-of-thought prompting enables reasoning in large language models but produces explanations that are difficult to verify, expensive to generate, and
arXiv:2601.21649v2 Announce Type: replace-cross Abstract: The deployment of coding agents in privacy-sensitive and resource-constrained environments drives the demand for capable open-weight Small Lan
arXiv:2610.14709v1 Announce Type: cross Abstract: Large language models are increasingly deployed in applications that act on users' long-term behavior histories, from personal assistants to recommend
arXiv:2610.19611v1 Announce Type: new Abstract: Modern vision-language models can accept multi-image contexts, but aggregate accuracy rarely reveals where a multi-image reasoning pipeline fails. We st
arXiv:2610.16615v1 Announce Type: new Abstract: Visual token compression has emerged as a critical technique for reducing the inference cost of Vision-Language Models. Existing methods select tokens b
arXiv:2610.19324v1 Announce Type: new Abstract: In large language models (LLMs), attention concentrates heavily on the first token. This 'attention sink' is believed to protect deep models against ove
arXiv:2610.16849v1 Announce Type: new Abstract: Face recognition systems often experience performance degradation under large pose variations due to changes in facial appearance and visibility of disc
arXiv:2610.14024v1 Announce Type: new Abstract: Physics time-series data are central to fundamental discoveries involving dark matter, neutrinos, and gravitational waves. Machine learning has shown st
arXiv:2610.18658v1 Announce Type: new Abstract: Generative models are often required to serve many downstream conditional tasks. In the training-free setting, a pretrained unconditional model is reuse
arXiv:2610.14746v1 Announce Type: cross Abstract: World Action Models (WAMs) commonly couple video and action experts through dense, layer-wise Mixture-of-Transformers (MoT) attention, exposing action
arXiv:2610.17306v1 Announce Type: cross Abstract: Explanations of LLM outputs are considered an important way to make model behavior legible, helping human users make good decisions on downstream task
arXiv:2610.17350v1 Announce Type: new Abstract: We use a frozen frontier vision-language model, GPT-6-Astra, directly as the robot policy on RoboMME, a benchmark of 16 memory-dependent manipulation ta