Knowledge catalogue
arXiv:2607.25933v1 Announce Type: cross Abstract: Clinical diagnostic evaluation should not only assess whether models can provide correct diagnoses, but also reflect the realities of clinical practic
arXiv:2607.25364v1 Announce Type: new Abstract: Tool-using agents expose structured calls but commonly attach free-form rationales. Such rationales are neither authorization nor reliable introspection
arXiv:2607.24960v1 Announce Type: cross Abstract: We present a neural network surrogate model that emulates the NRSur7dq4 gravitational waveform model for precessing binary black hole mergers. The sur
arXiv:2607.25484v1 Announce Type: new Abstract: In some real applications a plan may later become unfeasible due to newly imposed budget constraints, yet, at the same time, using only the original act
arXiv:2607.24762v1 Announce Type: new Abstract: Machine learning models are increasingly embedded in everyday software, and most of their runtime is spent in a small set of compute kernels such as mat
arXiv:2607.25956v1 Announce Type: new Abstract: Multi-warehouse inventory allocation is typically formulated as a mixed-integer programming (MIP) problem, yet no single formulation consistently matche
arXiv:2510.22863v2 Announce Type: replace-cross Abstract: Reliable long-term forecasting of PM2.5 concentrations is critical for public health early-warning systems, yet existing deep learning approac
arXiv:2607.25199v1 Announce Type: cross Abstract: Automated code generation is becoming an important tool in quantitative finance, where large language models can generate option pricing implementatio
arXiv:2607.25886v1 Announce Type: cross Abstract: Recursive self-improvement requires turning evidence of model failures into better models. Data-centric post-training research entails diagnosing capa
arXiv:2607.25026v1 Announce Type: cross Abstract: In this work, we present a simulation-based parameter estimation framework for a model defined by a computational simulation of a physical system. We
arXiv:2607.25798v1 Announce Type: new Abstract: An often overlooked factor of robot manipulation performance is the embodiment of the robot itself. Motivated by this problem, we study motion-condition
arXiv:2607.23869v1 Announce Type: cross Abstract: Randomized features provide a scalable approximation to kernel machines, but their performance depends strongly on the choice of feature distribution.
arXiv:2607.23784v1 Announce Type: cross Abstract: While vision-language-action models have demonstrated impressive zero-shot manipulation capabilities, they remain fundamentally black box policies tha
arXiv:2602.00575v2 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) provides a promising pathway for continuously advancing GUI agents, yet existing reward modeli
arXiv:2607.23647v1 Announce Type: cross Abstract: Large language models (LLMs) can summarize heterogeneous user evidence in natural language, but current LLM recommenders often collapse enduring prefe
arXiv:2607.22577v1 Announce Type: new Abstract: Scaling large language models (LLMs) has driven their success, yet dense Transformers couple capacity and computation: every parameter is activated for
arXiv:2607.23835v1 Announce Type: new Abstract: Attribution methods are widely used to characterize the evidence underlying model predictions, yet their potential to improve model behavior remains und
Hey fellow llamas. we have something new for Strix Halo owners we thought would be useful to share. i'll keep it short: We were able to fit DeepSeek V4 Flash plus its speculative draft on a single Ryz
arXiv:2607.23361v1 Announce Type: cross Abstract: Language generation in the limit is an elegant model introduced by Kleinberg and Mullainathan [KM24] to formally study language generation by an algor
arXiv:2607.24653v1 Announce Type: new Abstract: We introduce Kimi K3, a 2.8T parameter Mixture-of-Experts model with 104 billion activated parameters, native vision capabilities, and a 1-million-token
arXiv:2607.24435v1 Announce Type: cross Abstract: Large language models may easily assign personality labels from text, but model interpretability remains an open problem. To address this gap, we intr
arXiv:2607.15166v2 Announce Type: replace Abstract: Most medical AI benchmarks measure whether a model knows the correct answer. MedFailBench asks a different question: which safety boundary failed? W
arXiv:2607.24665v1 Announce Type: new Abstract: Modern large language models scale successfully by pairing capacity growth with efficiency, keeping per-token and deployment costs under control as capa
arXiv:2607.24369v1 Announce Type: new Abstract: This work presents a motion planning framework for UAV navigation in non-convex urban air corridors. The planner is based on a mixed-integer tracking mo
arXiv:2607.22729v1 Announce Type: cross Abstract: Backchannels, which signal listener states like empathy and understanding, are fundamental to natural human interaction. However, current approaches r
arXiv:2607.22964v1 Announce Type: new Abstract: Tactile gloves digitize contact and force during hand-object interactions, enabling robotics applications in dexterous manipulation, teleoperation, and
arXiv:2607.22699v1 Announce Type: new Abstract: As Large Language Models (LLMs) grow more capable across diverse tasks, their (in)ability to generalize remains difficult to quantify and poorly underst
arXiv:2607.22758v1 Announce Type: cross Abstract: The integration of iterative LLMs within multi-agent diagnostic frameworks requires a rigorous quantitative reevaluation of underlying communication t
arXiv:2607.23492v1 Announce Type: new Abstract: Concept erasure techniques (CETs) edit text-to-image diffusion models to erase undesired targets such as NSFW content or copyrighted styles, while prese
arXiv:2607.22610v1 Announce Type: new Abstract: When a language model produces a response in a multi-turn conversation, which tokens from prior turns shaped that answer, and how did those dependencies
arXiv:2607.24081v1 Announce Type: cross Abstract: Brain-machine interfaces (BMIs) can assist individuals with limited mobility, such as stroke survivors or amputees. One of the key challenges in devel
arXiv:2607.22727v1 Announce Type: new Abstract: Medical image segmentation models often report high benchmark accuracy under ideal imaging conditions, yet their failures under clinical degradation can
common: fix explicit -md precedence over draft sidecar resolution (#26165) common: fix explicit -md precedence over draft sidecar resolution Follow-up of #25955, an explicit --model-draft file given w
arXiv:2607.21806v1 Announce Type: new Abstract: Predictive machine learning (ML) models are increasingly used to aid human decision-makers across various high-risk domains such as healthcare and crimi
arXiv:2607.22035v1 Announce Type: new Abstract: Currently, most foundation models can reproduce or strongly depend on copyrighted training content, but output similarity alone is insufficient for infr
arXiv:2607.21941v1 Announce Type: new Abstract: Chemists and materials scientists increasingly use machine learning models, such as graph neural networks (GNNs), to predict properties of molecules and
arXiv:2602.05988v2 Announce Type: replace Abstract: Pre-training Large Language Models (LLMs) on web-scale datasets becomes fundamental for advancing general-purpose AI. In contrast, enhancing their p
arXiv:2508.12393v3 Announce Type: replace Abstract: The rapid expansion of medical literature challenges the scalable structuring of domain knowledge. Knowledge Graphs (KGs) offer a solution, yet curr
I was refreshing my youtube and found out my favourite reviewer uploaded a battery test of 78 smartphones: https://youtu.be/MpgUFrsIWSQ the author said they started using robotic arm to simulate a per
Instead of 2T+ models, continuing to release highly capable small to medium size LLMs would really help to keep this community vibrant. Hardly anyone can even dream of running the recent 1.5-2T+ beast
When I released Inflect v2 last week, I thought most people would ask whether a TTS model this small actually sounded decent. Instead, I kept getting two questions: “Can I train it on my own voice?” “
This was my Bachelor's Final Project: implementing YOLO26n inference completely from scratch using ARM64 Assembly Language and C, without relying on existing inference frameworks. The goal was to unde
Very happy to support this on behalf of Google. We have long benefited from open source, are big contributors to open source and in fact have consistently made open weights models with Gemma available
arXiv:2607.21403v1 Announce Type: new Abstract: Mobile-health interventions increasingly use online learning and decision making algorithms to personalize when to nudge users toward healthier behavior
Am I supposed to interpret that it's better than Fable 5 from the benchmarks? Or it's ~close but cheaper? Introducing Claude Opus 5. It's a thoughtful and proactive model that comes close to the front
arXiv:2607.21340v1 Announce Type: new Abstract: In capital-markets workflows the question is rarely whether a large language model can produce a fluent draft, but whether the draft is bankable: defens
arXiv:2604.25077v2 Announce Type: replace Abstract: Weak-to-strong alignment offers a promising route to scalable supervision, but it can fail when a strong model becomes confidently wrong on examples
arXiv:2607.20583v1 Announce Type: cross Abstract: The function of many genes is still unknown, and conventional driver-discovery methods, which rely on how frequently a gene is mutated, cannot assess
OpenAI GPT-5.6 Sol, Terra, and Luna are now generally available on Amazon Bedrock. Learn how to select a model, run inference through the Responses API on the bedrock-mantle endpoint, reduce cost with
arXiv:2607.20982v1 Announce Type: new Abstract: As large language model agents increasingly operate autonomously with access to tools and external environments, ensuring their safe and reliable behavi
arXiv:2607.21208v1 Announce Type: new Abstract: Pearl famously argues that causal knowledge enables the prediction of intervention effects. By contrast, purely descriptive knowledge supports only conc
arXiv:2607.20539v1 Announce Type: cross Abstract: While deep learning has accelerated drug discovery, its impact on biomanufacturing has been considerably more limited. The reason is data scarcity. Bi
arXiv:2607.20642v1 Announce Type: new Abstract: Computer aided design (CAD) is ubiquitous: virtually any modern object was designed using editable CAD tools. However, with the shortage of available CA
'The NVIDIA Qwen-Image-Flash model generates images from text prompts using a four-step, DMD2-distilled version of Qwen/Qwen-Image. The distillation used DMD2 from NVIDIA FastGen, NVIDIA Model Optimiz
Open weights = freedom. You can run them on your own hardware. No vendor can pull the plug. No API can deprecate you. No company logs your private data. That's sovereignty. Closed models hand one comp
arXiv:2607.20532v1 Announce Type: cross Abstract: Many modern AI systems are designed to operate under diverse, open-ended, use-cases. To help generalize deployed systems, many deployed-system mainten
arXiv:2607.21063v1 Announce Type: new Abstract: Almost every large language model that reaches a broad audience is quantized: trained in full precision, then compressed for efficiency. This step is as
arXiv:2607.20652v1 Announce Type: cross Abstract: Language models are thought to exhibit the phenomenon of superposition, representing many more features than dimensions in their residual streams. Spa
arXiv:2602.19313v2 Announce Type: replace-cross Abstract: General-purpose robot learning requires dense, instruction-conditioned feedback that can distinguish meaningful task progress from stalled, fa
arXiv:2607.21325v1 Announce Type: cross Abstract: Autonomous AI agents increasingly execute actions, invoke tools, and operate on protected resources with limited human oversight. Existing authenticat