Knowledge catalogue
arXiv:2605.20515v1 Announce Type: new Abstract: Modern artificial intelligence systems require calibrated uncertainty estimates that remain reliable in sequential and non-stationary environments. Onli
arXiv:2605.20539v1 Announce Type: new Abstract: The advent of machine learning (ML) and computer vision has significantly accelerated seismic inversion workflows by reducing the computational cost of
arXiv:2605.20289v1 Announce Type: new Abstract: ANN-to-SNN conversion offers a practical, training-free route to spiking large language models. However, current pipelines primarily focus on spike-driv
arXiv:2603.10726v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) rely on optimizations like Automatic Prefix Caching (APC) to accelerate inference. APC works by reusing previousl
arXiv:2605.20195v1 Announce Type: new Abstract: A target-oriented proactive dialogue system is designed to steer conversations toward predefined targets while actively providing suggestions. The core
arXiv:2605.20295v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed on mobile devices, where Neural Processing Units (NPUs) necessitate fully static quantization for
arXiv:2605.20654v1 Announce Type: new Abstract: While Large Language Models (LLMs) demonstrate remarkable capabilities, they remain susceptible to sophisticated, multi-step jailbreak attacks that circ
arXiv:2605.21257v1 Announce Type: new Abstract: Planning through crowded environments under uncertain obstacle motions remains difficult, as stochastic interactions often induce overly conservative be
arXiv:2508.09001v2 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly deployed in long-context tasks such as reasoning, code generation, and multi-turn dialogue. However, i
arXiv:2603.10718v2 Announce Type: replace Abstract: Flow Matching enables simulation-free training of generative models on Riemannian manifolds, yet sampling typically still relies on numerically inte
Listen to the session or watch below AI companies want to build systems that understand the external world and overcome the limitations of LLMs. Recent developments have brought world models to the fo
.@RowanCheung anchored our Podcast Porch and interviewed @SundarPichai about what AI will look like in three years, his advice to young people experiencing the AI shift, our new Omni model and more. 🎤
Elon Musk posted a personal message expressing his enduring affection for two entities denoted as 'S & X,' likely referring to Tesla's Model S vehicle and X (formerly Twitter), the social media platfo
arXiv:2605.20998v1 Announce Type: new Abstract: Aspect-Term Sentiment Analysis (ATSA) in multi-aspect sentences faces a fundamental tradeoff between efficiency and expressiveness. Existing models eith
arXiv:2605.20272v1 Announce Type: new Abstract: While humans readily generalize abstract concepts to more complex or larger tasks, building Reinforcement Learning (RL) systems with this ability remain
arXiv:2605.21075v1 Announce Type: new Abstract: Earth observation (EO) foundation models (FMs) are increasingly trained on multisensor data, spanning multispectral imagery (MSI), synthetic aperture ra
arXiv:2605.20760v1 Announce Type: new Abstract: Automated segmentation of the vertebral column in Computed Tomography (CT) scans is a prerequisite for pathological assessment and surgical planning. Ho
arXiv:2508.12247v2 Announce Type: replace Abstract: Recently, spatio-temporal time-series prediction has developed rapidly, yet existing deep learning methods struggle with learning complex long-term
arXiv:2605.21466v1 Announce Type: new Abstract: Although existing video editing methods are generally feasible, they often require many costly iterations and still struggle to deliver high-quality yet
arXiv:2605.21132v1 Announce Type: new Abstract: Understanding surgical workflow in real time is fundamental for intelligent surgical embodiment, where AI systems continuously perceive and respond as s
arXiv:2605.20916v1 Announce Type: new Abstract: Implicit sentiment analysis is challenging because sentiment toward an aspect is often inferred from events rather than expressed through explicit opini
arXiv:2605.20290v1 Announce Type: cross Abstract: Recent generative video models achieve impressive visual quality but remain constrained by limited physical consistency and controllability. Existing
arXiv:2605.21318v1 Announce Type: new Abstract: Large language models (LLMs) are highly sensitive to the prompts used to specify task objectives and behavioral constraints. Many recent prompt optimiza
arXiv:2605.20767v1 Announce Type: new Abstract: Large language models (LLMs) show potential as simulators of human behavior, offering a scalable way to study responses to interventions. However, becau
AI is turning digital trust from a security function into an operating model. That shift is putting new pressure on the systems enterprises have long used to verify identity, protect data and keep dig
arXiv:2605.21070v1 Announce Type: new Abstract: Amos et al. (2024) showed that the accuracy of Transformer models in sequence classification can be significantly improved by first pretraining with a m
arXiv:2605.21489v1 Announce Type: cross Abstract: Pretrained diffusion models serve as frozen teachers feeding downstream pipelines such as text-to-3D, single-step distillation, and data attribution.
arXiv:2605.21483v1 Announce Type: cross Abstract: Precise measurement of the kinematic Sunyaev-Zel'dovich (kSZ) effect - a probe of the large-scale distribution of baryonic matter, a key observable fo
Secure access service edge firm Versa Networks Inc. today introduced a zero-trust architecture for the Model Context Protocol that validates every action an artificial intelligence agent takes inside
Latest face swapping methods are expanding toward 3D-consistent video swapping and identity-preserving generation systems that control portraits and clips . Improvements in diffusion models and neural
arXiv:2605.19316v1 Announce Type: new Abstract: Recent studies in difficulty-controlled reading comprehension item generation have leveraged large language models (LLMs) to produce items by adjusting
arXiv:2605.19595v1 Announce Type: cross Abstract: The inspection of electrical power line insulators is essential for ensuring grid reliability and preventing failures caused by damaged or degraded in
arXiv:2605.19178v1 Announce Type: cross Abstract: The great success of neural networks in recognizing hidden patterns and correlations in complex data lies in the way they take advantage of the large
arXiv:2605.19677v1 Announce Type: new Abstract: Cryomicroneedles offer a route to minimally invasive intradermal delivery of living cells, but their cryogenic formulations must reconcile cell protecti
arXiv:2605.18762v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) is widely used to augment large language models with external knowledge retrieval to improve reliability and gene
Today, Amazon SageMaker AI introduces OpenAI-compatible API support for real-time inference endpoints. If you use the OpenAI SDK, LangChain, or Strands Agents, you can now invoke models on SageMaker A
arXiv:2605.19285v1 Announce Type: cross Abstract: The rapid spread of misinformation on social media platforms has become a formidable challenge. To mitigate its proliferation, Misinformation Detectio
b9244 is an intermediate build release of llama.cpp, a C/C++ implementation framework for running large language models with GGUF format support. The release includes pre-compiled binaries for multipl
arXiv:2605.19249v1 Announce Type: new Abstract: Time-series forecasting is critical in various scenarios, such as energy, transportation, and public health. However, most existing forecasters rely pri
arXiv:2605.20032v1 Announce Type: new Abstract: Text-attributed graph fraud detection (TAGFD) plays a critical role in preventing fraudulent activities on online social and e-commerce platforms. Howev
HiDream-O1-Image is a unified image generative foundation model that supports text-to-image and instruction-based image editing with support for multiple reference images. The sampler accepts up to 12
arXiv:2511.13588v2 Announce Type: replace-cross Abstract: Model Predictive Control (MPC) is a powerful framework for optimal control but can be too slow for low-latency applications. We present a data
arXiv:2511.12158v3 Announce Type: replace Abstract: Research in bioacoustics, neuroscience, and linguistics often uses birdsong as a proxy to acquire knowledge across diverse areas. This requires audi
arXiv:2605.18892v1 Announce Type: cross Abstract: Federated learning (FL) enables collaborative learning of computer vision models, where privacy and regulatory constraints prevent centralizing data a
arXiv:2605.19322v1 Announce Type: new Abstract: Recent advances in Video Large Language Models (Video-LLMs) have greatly expanded multimodal reasoning capabilities. However, the massive number of visu
arXiv:2602.04279v2 Announce Type: replace Abstract: Electrocardiography (ECG) serves as an indispensable diagnostic tool in clinical practice, yet existing multimodal large language models (MLLMs) rem
arXiv:2605.19394v1 Announce Type: cross Abstract: Adapting small instruction-tuned models to specialized domains often relies on supervised fine-tuning (SFT) on curated instruction-response examples,
arXiv:2605.19947v1 Announce Type: new Abstract: This work addresses the problem of learning directed acyclic graphs (DAGs) from nodal observations generated by a linear structural equation model. DAG
arXiv:2510.13727v2 Announce Type: replace Abstract: Generative AI systems are increasingly assisting and acting on behalf of end users in practical settings, from digital shopping assistants to next-g
arXiv:2605.20145v1 Announce Type: cross Abstract: Bayesian optimization (BO) selects evaluation points for expensive black-box objectives using Gaussian process (GP) predictive distributions. Kernel c
Grok Build 0.1 has been released and is now accessible through the Vercel AI Gateway, enabling developers to integrate Grok's capabilities into their applications via Vercel's platform. This release p
arXiv:2510.00054v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have made significant strides in visual understanding tasks. However, their performance on high-resol
How fast is 10 tokens per second really? Neat little HTML app by Mike Veerman (source code here) which simulates LLM token output speeds from 5/second to 800/second. Useful if you see a model advertis
AI repeals the Mythical Man Month: 'Rather than requiring large teams across multiple subsystems that need to coordinate, AI models are developed by smaller teams whose output increases in quality as
Enterprise AI needs agentic transformation to turn scattered experiments into measurable business outcomes. The next phase of AI adoption is less about picking models and more about making enterprise
arXiv:2605.18759v1 Announce Type: cross Abstract: Artificial intelligence (AI), exemplified by large language models (LLMs), is rapidly approaching and in some cases surpassing human performance acros
It’s pretty funny that I can’t tell whether the intelligent comments are from people who actually read the book or whether they are bots that know a lot about The Culture. AIs, even small models, love
arXiv:2605.19805v1 Announce Type: cross Abstract: Irregular multivariate time series impose a trade-off for long-horizon forecasting: discrete methods can distort temporal structure via re-gridding, w
arXiv:2605.19074v1 Announce Type: cross Abstract: The rapid global expansion of solar photovoltaic (PV) capacity-reaching a record 597 GW in 2024-highlights the urgent need for robust forecasting mode
Mercedes-AMG has unveiled the all-electric GT 4-Door, the first all-electric model in AMG history , powered by three axial flux motors with a 106-kWh battery and featuring a rear-biased all-wheel-driv