Knowledge catalogue
arXiv:2608.18419v1 Announce Type: cross Abstract: Recent work has shown that large language models (LLMs) exhibit strong numerical sequence modeling capabilities and show promise in time-series predic
arXiv:2608.18982v1 Announce Type: new Abstract: Bioassay activity prediction is often data-limited because drug-discovery datasets rely on time-consuming and expensive wet-lab experiments for data gen
arXiv:2608.18094v1 Announce Type: cross Abstract: Large pretrained language models have demonstrated remarkable capabilities across diverse languages, yet critically underrepresented low-resource lang
arXiv:2608.18495v1 Announce Type: cross Abstract: Radio maps are essential for wireless decision-making tasks such as access-point placement, coverage planning, and localization, but their fine spatia
arXiv:2608.18611v1 Announce Type: new Abstract: Electric power networks are increasingly exposed to weather-sensitive failure mechanisms that require asset-level, spatially explicit risk modelling for
arXiv:2608.17496v1 Announce Type: new Abstract: Vision-language-action policies generalize broadly but provide no execution-time guarantees; classical model-based planners respect kinematic and geomet
arXiv:2608.18027v1 Announce Type: new Abstract: Humans continuously learn from experience, whereas conventional large language model (LLM) evaluations ignore the models' ability to improve through inf
arXiv:2608.17248v1 Announce Type: cross Abstract: When computational models (either physics-based or data-driven) are used for the sensitivity analysis of engineering systems, the sensitivity estimate
arXiv:2608.17370v1 Announce Type: new Abstract: Generative models promise a route to explainable clinical AI: rather than probe a classifier, model the distributions of healthy and diseased patients a
arXiv:2511.19759v3 Announce Type: replace Abstract: Semi-supervised learning (SSL) has emerged as an efficient paradigm for medical image segmentation, reducing the reliance on extensive expert annota
arXiv:2507.04491v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are rapidly being integrated into psychological and behavioral research as research tools, evaluation targets, hu
arXiv:2608.15660v1 Announce Type: cross Abstract: Federated learning (FL) enables privacy-preserving distributed model training but faces challenges from heterogeneous model architectures and limited
arXiv:2608.15695v1 Announce Type: new Abstract: Conventional action recognition typically relies on successful pixel decoding of the bitstream. However, bitstream corruption during storage or transmis
arXiv:2608.15124v1 Announce Type: new Abstract: In contextual optimization, the decision-maker seeks optimal decisions to minimize a cost function, that varies based on observed features. This context
arXiv:2504.09209v3 Announce Type: replace-cross Abstract: Masked modeling has shown promise in co-speech gesture generation. However, it struggles to identify semantically significant frames for effec
arXiv:2506.16697v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are entering psychological research both as tools and as objects of inquiry. Yet many studies apply human instrum
arXiv:2608.15279v1 Announce Type: new Abstract: 4D occupancy forecasting models the spatio-temporal evolution of 3D scenes and is crucial for autonomous driving, especially for corner-case simulation.
arXiv:2411.10023v3 Announce Type: replace Abstract: Deep neural networks have enabled numerous studies and applications on both Euclidean data, such as images and text, and non-Euclidean data, such as
arXiv:2608.16094v1 Announce Type: new Abstract: Accurate protein structure prediction is fundamental to structural biology because protein structure underlies molecular function and provides a basis f
arXiv:2608.15429v1 Announce Type: new Abstract: Prior embedding models for sequential recommendation typically operate within a homogeneous action space, limiting their ability to capture cross-surfac
arXiv:2608.16843v1 Announce Type: new Abstract: Foundation models are increasingly used for perception, reasoning, planning, and action generation in embodied agents, creating security risks that can
arXiv:2608.14579v1 Announce Type: new Abstract: Logic synthesis optimization poses significant challenges due to exponentially growing search spaces, sparse reward signals, and diverse logic structure
arXiv:2608.15351v1 Announce Type: new Abstract: Nominal LoRA rank is a design parameter; calibrated spectral evidence is a separate inferential quantity. This article develops a finite-sample framewor
arXiv:2608.15211v1 Announce Type: new Abstract: Training high-resolution AI-based Earth forecasting models is memory-intensive. Window-based Swin Transformers reduce the quadratic cost of global atten
arXiv:2608.16643v1 Announce Type: cross Abstract: Automated detection of errors in clinical documentation is a promising application of large language models (LLMs), yet decisions to deploy such model
arXiv:2607.14345v4 Announce Type: replace-cross Abstract: People use language models for practical questions whose answers are difficult to verify. We show that models exhibit covert value leakage: th
arXiv:2608.15323v1 Announce Type: new Abstract: Understanding a model and its learning mechanisms in depth requires identifying when its internal structures become useful, rather than simply looking a
arXiv:2608.14352v1 Announce Type: cross Abstract: Large Language Model (LLM)-based agents are increasingly used for complex tasks such as software testing and cybersecurity assessment. While these age
arXiv:2608.13751v1 Announce Type: new Abstract: Large pre-trained models have become foundational components of modern machine learning systems. Yet adapting these models to novel categories typically
Original Article - https://x.com/p_nawrot/status/2089315591010079034 I've spent the last few years working on efficient attention and KV Cache Compression. I've read many papers, dug deep into referen
arXiv:2608.14071v1 Announce Type: new Abstract: As large language models scale, their training-token budgets must also increase to maintain an appropriate tokens-per-parameter ratio ((TPP)). However,
arXiv:2603.01959v2 Announce Type: replace Abstract: State-Space Models (SSMs) have recently been shown to achieve strong empirical performance on a variety of long-range sequence modeling tasks while
This model is insane at 3D website design. I asked GLM 5.3 (left) & Fable 5 (right) to make me a 3d biking website. GLM nailed it while Fable failed. GLM cost 0.14 while Fable cost 2.21. More than 15x
Bloomberg: Sources: Stripe has finalized a deal to acquire AI model marketplace OpenRouter for more than 7B; OpenRouter was valued at 1.3B in May — Stripe Inc. has finalized an agreement to acquire Op
OpenRouter Inc., which sells developers a single door into more than 400 artificial intelligence models, has agreed to terms to sell itself to Stripe Inc. for north of 7 billion, according to a report
Yutori's browser-use agents run in tight loops: screenshot, action, repeat, dozens of times per task. On Together AI, their Navigator model beats frontier performance at 2x faster inference and 4-5x l
arXiv:2608.12368v1 Announce Type: new Abstract: Agreement with human judgments is a common proxy for evaluating the alignment of large language models (LLMs). Yet agreement in final labels does not sh
arXiv:2608.13101v1 Announce Type: new Abstract: Research on automatic speaking assessment (ASA) has increasingly adopted multimodal speech large language models to assess learners' speaking performanc
CONFIRMED: @c_valenzuelab, cofounder and co-CEO of @runwayml, is speaking at Thesis, our inaugural conference on work and AI. Language models predict the next token, aka the next unit of text. Runway’
arXiv:2512.19804v2 Announce Type: replace Abstract: Reduced-order models (ROMs) can represent spatiotemporal processes in significantly fewer dimensions and can often be solved many orders of magnitud
arXiv:2608.11423v1 Announce Type: cross Abstract: Robust comparisons of federated aggregation methods require joint consideration of predictive performance, threat definitions, metric semantics, and e
arXiv:2608.11548v1 Announce Type: cross Abstract: We propose a hue-split model-tree method for boundary-continuous cross-camera RGB mapping. Cross-camera RGB mapping aims to produce consistent color r
arXiv:2608.11235v1 Announce Type: new Abstract: Diffusion language models (DLMs) update many tokens in parallel, yet practical decoders often use a fixed denoising horizon. Many predictions stabilize
arXiv:2608.11911v1 Announce Type: cross Abstract: A central promise of useful quantum advantage is the ability to compute ground states of Hamiltonian systems beyond the reach of classical simulation
arXiv:2608.12283v1 Announce Type: cross Abstract: Large language models can extract richer signals from financial news than fixed sentiment lexicons, and recent work has explored feeding such signals
arXiv:2608.11919v1 Announce Type: new Abstract: Training large language models on limited hardware is increasingly a scheduling problem across GPU compute, host memory, PCIe transfer, and storage band
arXiv:2606.17598v2 Announce Type: replace-cross Abstract: Humans naturally leverage diverse sensing modalities to interact with the physical world, while most Vision-Language-Action (VLA) models for r
arXiv:2608.12088v1 Announce Type: new Abstract: Generative models can produce images nearly indistinguishable from real data, yet rigorous and interpretable evaluation remains challenging. Conventiona
Wall Street Journal: Sources: Demis Hassabis pitched a new independent industry AI safety entity, modeled on the IAEA, to top Trump officials before stepping down as DeepMind's CEO — Demis Hassabis di
arXiv:2608.11788v1 Announce Type: cross Abstract: Continual pre-training (CPT) has been widely adopted as a method for domain adaptation in large language models. However, CPT has consistently been ac
arXiv:2608.11415v1 Announce Type: cross Abstract: Large language models are being proposed as agents in scientific workflows, in domains where no downstream verifier exists. Such deployment assumes th
arXiv:2512.01906v3 Announce Type: replace Abstract: Spiking neural networks (SNNs) are biologically inspired, event-driven models suited for temporal data processing and energy-efficient neuromorphic
arXiv:2512.22525v2 Announce Type: replace Abstract: Recently unified generation and editing models have achieved remarkable success with their impressive performance. These models rely mainly on text
Hey guys, Just finished benchmarking DeepSeek V4 Flash 284B + DSpark on a single RTX PRO 6000 96GB. Short version: DSpark: ~15–17% faster generation on my coding workload On this setup, the DSpark dra
arXiv:2608.10166v1 Announce Type: cross Abstract: Digital watermarking has emerged as a critical technique for provenance and copyright attribution in AI-generated imagery, yet its robustness against
arXiv:2608.10154v1 Announce Type: cross Abstract: We present results from reconstructing multiple-choice model (MCM) and three-parameter logistic (3PL) model curves using a fine-tuned multimodal large
arXiv:2603.19201v3 Announce Type: replace Abstract: Contact-rich manipulation tasks, such as wiping and assembly, require accurate perception of contact forces, friction changes, and state transitions
arXiv:2608.09900v1 Announce Type: new Abstract: Large language model evaluations typically focus on performance under nominal conditions, creating an illusion of capability where models comfortably wa
arXiv:2512.13003v2 Announce Type: replace-cross Abstract: Out-of-distribution (OOD) detection is essential for determining when a supervised model encounters inputs that differ meaningfully from its t
arXiv:2607.28503v3 Announce Type: replace Abstract: In this paper we present an active, constantly updated AI benchmark which measures the integrity of frontier language models against being co-opted