Knowledge catalogue
arXiv:2510.09592v2 Announce Type: replace Abstract: Real-time Spoken Language Models (SLMs) struggle to leverage Chain-of-Thought (CoT) reasoning due to the prohibitive latency of generating the entir
arXiv:2603.18256v2 Announce Type: replace-cross Abstract: Recent reasoning-based large language models have shown strong performance on tasks with verifiable outcomes, but their use in de novo molecul
arXiv:2605.10936v1 Announce Type: new Abstract: As wearable devices like smart glasses integrate Large Multimodal Models (LMMs) into the continuous first-person visual streams of individual users, the
arXiv:2605.10629v1 Announce Type: new Abstract: Recently, diffusion models have attracted considerable attention for magnetic resonance image reconstruction due to their high sample quality. However,
arXiv:2501.03544v5 Announce Type: replace-cross Abstract: Recent text-to-image (T2I) models have exhibited remarkable performance in generating high-quality images from text descriptions. However, the
arXiv:2605.08142v1 Announce Type: cross Abstract: Reasoning in large language models is predominantly evaluated through labeled benchmarks, conflating task performance with the quality of internal inf
arXiv:2605.10759v1 Announce Type: cross Abstract: Diffusion and flow-matching models scale because pretraining is supervised regression: a clean sample is noised analytically, and a model regresses ag
arXiv:2506.04289v3 Announce Type: replace Abstract: Transformer-based models have demonstrated remarkable reasoning abilities, but the mechanisms underlying relational reasoning remain poorly understo
arXiv:2605.09008v1 Announce Type: cross Abstract: Chain-of-Thought (CoT) prompting symbolized a huge improvement of reasoning capabilities of Large Language Models (LLMs). However, scaling up test-tim
arXiv:2502.00816v4 Announce Type: replace Abstract: We introduce Sundial, a family of native, flexible, and scalable time series foundation models. To predict the next-patch's distribution, we propose
arXiv:2605.06047v2 Announce Type: replace-cross Abstract: Tabular foundation models (TFMs), such as TabPFN-2.6, TabICLv2, ConTextTab, Mitra, LimiX, and TabDPT, achieve strong zero-shot performance thr
arXiv:2605.08116v1 Announce Type: cross Abstract: Recent work on text diffusion models offers a promising alternative to autoregressive generation, but controlling their safety remains underexplored.
arXiv:2605.10019v1 Announce Type: cross Abstract: Generative models trained on finite data face a fundamental tension: their score-matching or next-token objective converges to the empirical training
arXiv:2605.08133v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have emerged as a promising paradigm for end-to-end autonomous driving, yet their reliance on implicit parametric
arXiv:2605.06222v2 Announce Type: replace-cross Abstract: World Action Models (WAMs) have recently emerged as a promising paradigm for robotic manipulation by jointly predicting future visual observat
arXiv:2605.06797v1 Announce Type: new Abstract: We propose the Monge Inception Distance (MIND), a metric for evaluating generative models that addresses key limitations of the widely adopted Frechet I
arXiv:2605.07860v1 Announce Type: cross Abstract: Federated Learning (FL) has emerged as a promising paradigm for preserving client data ownership and control over distributed Internet of Things (IoT)
One of the most important properties of LLMs that we take for granted is that newer, bigger models are just better at everything. The AI Labs are pouring effort into economically valuable fields like
Alexey Shabanov / TestingCatalog AI News: OpenAI launches Daybreak, a cybersecurity initiative integrating AI models and Codex Security to help organizations patch vulnerabilities — OpenAI launches Da
arXiv:2605.07278v1 Announce Type: cross Abstract: A latent world model may achieve accurate short-horizon prediction while still inducing a latent space that is poorly aligned with planning. A key iss
arXiv:2605.07076v1 Announce Type: new Abstract: Large language models (LLMs) increasingly receive information as streams of passages, conversations, and long-context workflows. While longer context wi
arXiv:2605.07282v1 Announce Type: new Abstract: Final outputs hide when a checkpoint commits to its next-token prediction. We introduce the convergence gap, a model-diffing diagnostic that decodes eac
arXiv:2601.18744v2 Announce Type: replace Abstract: Time series are ubiquitous in real-world scenarios and crucial for applications ranging from energy management to traffic control. Consequently, the
arXiv:2605.07984v1 Announce Type: cross Abstract: We study planning site formation in language models -- where internal representations of structurally-constrained future tokens form during the forwar
This post provides a detailed review and practical guide for setting up and testing Ollama with DeepSeek models specifically on Ryzen APU systems. It likely covers performance benchmarks, configuratio
Anthropic: Anthropic details how it improved Claude's safety training after finding agentic misalignment in older models, such as Opus 4 blackmailing engineers — Last year, we released a case study on
CyberSecQwen-4B is a specialized 4-billion parameter language model designed for cybersecurity defense tasks that can run locally on standard hardware. The model addresses the need for small, efficien
OpenAI announced new voice intelligence models available through its API, expanding capabilities for developers to integrate advanced voice processing and understanding features into their application
arXiv:2605.05082v1 Announce Type: cross Abstract: We externally validated three deep learning models (DenseNet121, ViT-B/32, and ResNet50) for predicting mammographic breast density from breast ultras
arXiv:2602.22291v3 Announce Type: replace Abstract: While prior work has focused on projecting adversarial examples back onto the manifold of natural data to restore safety, we argue that a comprehens
arXiv:2605.03903v1 Announce Type: new Abstract: Large Multimodal Models (LMMs) have recently shown strong performance on Optical Character Recognition (OCR) tasks, demonstrating their promising capabi
arXiv:2605.02285v1 Announce Type: new Abstract: The deployment of Large Language Models (LLMs) for specialized engineering domains, such as circuit analysis, often faces a trade-off between reasoning
arXiv:2605.03547v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs), trained on web-scale data, risk memorizing and regenerating copyrighted visual content such as characters and logo
arXiv:2605.03855v1 Announce Type: new Abstract: Human-AI collaboration requires AI agents to understand human behavior for effective coordination. While advances in foundation models show promising ca
arXiv:2605.03460v1 Announce Type: cross Abstract: Time series (TS) reasoning models (TSRMs) have shown promising capabilities in general domains, yet they consistently fail on financial domain, which
Ryan Whitwam / Ars Technica: Google releases Multi-Token Prediction drafters for its Gemma 4 models, which use a form of speculative decoding to guess future tokens for faster inference — Google launc
arXiv:2605.03497v1 Announce Type: new Abstract: Score-based diffusion models in infinite-dimensional function spaces provide a mathematically principled framework for modelling function-valued data, o
arXiv:2511.08877v2 Announce Type: replace Abstract: Large language models (LLMs) generate fluent text across a wide range of tasks, but the fabrication of non-existent academic citations remains a cri
arXiv:2605.03438v1 Announce Type: new Abstract: Pre-trained 3D point cloud foundation models (PFMs) have demonstrated strong transferability across diverse downstream tasks. However, full fine-tuning
arXiv:2603.10083v2 Announce Type: replace-cross Abstract: Quantum machine learning models based on parameterized circuits can be viewed as Fourier series approximators. However, they often struggle to
arXiv:2605.04039v1 Announce Type: new Abstract: Clinical LLMs are often scaled by increasing model size, context length, retrieval complexity, or inference-time compute, with the implicit expectation
arXiv:2605.02269v1 Announce Type: new Abstract: Specification gaming is a critical failure mode of LLM agents. Despite this, there has been little systematic research into when it arises and what driv
arXiv:2605.03276v1 Announce Type: new Abstract: Real-world video editing demands not only expert knowledge of cinematic techniques but also multimodal reasoning to select, align, and combine footage i
arXiv:2605.01449v1 Announce Type: cross Abstract: Universal adversarial attacks on aligned multimodal large language models are increasingly reported with attack success rates in the 60-80% range, sug
We’ve developed our own inference engine Runtime-Optimized Serving Engine (ROSE) to serve models ranging from embeddings to trillion-parameter LLMs. With CuTeDSL integrated into our inference engine,
arXiv:2605.03475v1 Announce Type: new Abstract: Evaluating generative video models remains an open problem. Reference-based metrics such as Structural Similarity Index Measure (SSIM) and Peak Signal t
arXiv:2605.02270v1 Announce Type: new Abstract: This paper presents the first comprehensive comparative analysis of modern machine learning architectures for transliteration between Tajik (Cyrillic sc
arXiv:2605.01451v1 Announce Type: new Abstract: Large language models (LLMs) are rapidly being integrated into high-stakes public safety systems, including emergency call triage and dispatch decision
arXiv:2605.01896v1 Announce Type: new Abstract: Emerging multi-modal world models attempt to jointly generate videos across diverse modalities (e.g., RGB, depth, and mask), yet they fail to fully expl
arXiv:2605.02626v1 Announce Type: new Abstract: Preference optimization has become a central paradigm for aligning large language models with human feedback. Direct Preference Optimization (DPO) simpl
Large language models are becoming increasingly costly to develop and operate, creating a need for open-source alternatives that reduce dependency on expensive proprietary models and make AI more acce
arXiv:2605.01333v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have emerged as a promising paradigm for dental image analysis. However, their ability to capture the multi-lev
arXiv:2603.27259v2 Announce Type: replace Abstract: Long video understanding (LVU) remains a core challenge in multimodal learning. Although recent vision-language models (VLMs) have made notable prog
arXiv:2605.01653v1 Announce Type: new Abstract: We introduce SteeringDiffusion, a bottlenecked activation-level control interface for diffusion models that exposes a smooth, monotonic, and runtime-adj
arXiv:2605.00369v1 Announce Type: new Abstract: We study how large language models can be used to evolve inventory policies in online, non-stationary environments. Our work is motivated by recent adva
This post discusses Ollama's functionality for resuming work with Anthropic's Claude models, indicating that users can safely restore previous sessions or states using a command-line interface (`ollam
arXiv:2602.04212v2 Announce Type: replace Abstract: Though large language models (LLMs) have enabled great success across a wide variety of tasks, they still appear to fall short of one of the loftier
arXiv:2605.00018v1 Announce Type: new Abstract: Data-driven MoCap-to-radar models generate plausible micro-Doppler spectrograms, but do they actually learn the underlying physics? We introduce a physi
small milestone: uninstalled the chatgpt app. codex is strict superset now! found something cool - among frontier models, @xai @grok 4.30 is the most intelligence per dollar you can get, beating even
arXiv:2604.27415v1 Announce Type: new Abstract: With the rapid advancement of semiconductor technology, Electronic Design Automation (EDA) has become an increasingly knowledge-intensive and document-d