Artificial Intelligence news — Friday 23 October 2026

AI Business 17:26 UTC

The partners are using digital twins and AI agents as part of a roadmap to create world-first AI-powered manufacturing facilities.

OpenAI Blog 17:00 UTC

Learn how OpenAI scaled Habitat with reliable multi-tenancy, global caching, and Azure Cosmos DB to deliver 12× faster reads for ChatGPT.

Towards Data Science 15:30 UTC

Robust Estimation Series: Building Accurate Curves with Polynomials and Splines With Spurious Data The post Don’t Let Messy Data Bend Your Curves appeared first on Towards Data Science .

Amazon Science Blog 15:20 UTC

Text-to-speech systems — which convert written text into synthetic speech — display impressive naturalness in applications such as chatbots and virtual assistants, where interactions last seconds. But they tend not to fare as well with…

AI Business 14:40 UTC

Physical AI is pushing artificial intelligence into robots, factories and other real-world environments, where understanding language is only part of the challenge.

Towards Data Science 14:00 UTC

The mathematics, intuition, interpretation, and practical use of higher-order moments. The post Skewness and Kurtosis: From Moments to Machine Learning appeared first on Towards Data Science .

Towards Data Science 12:30 UTC

What does effective dimension reveal about redundancy, generalization, and trainability that parameter count, loss, and accuracy do not? The post Why Parameter Count Is Not Model Complexity: An Introduction to Effective Dimension appeared…

MIT Technology Review Biotech 12:10 UTC

This is today’s edition of The Download , our weekday newsletter that provides a daily dose of what’s going on in the world of technology. Are we there yet? A reality check on six big tech promises Some seemingly impossible feats are too…

Towards Data Science 11:00 UTC

Ask several models the same question, take a vote, and you get fewer independent opinions than you paid for. One formula says how many, and I checked it on six open models and 1,500 exam questions. The post Your Six AI Models Are Really…

OpenAI Blog 10:00 UTC

OpenAI explains how we strengthened containment for frontier model training and evaluation, including offline environments and high-compute red-teaming.

MIT Technology Review Biotech 09:00 UTC

Earlier this week, I attended a screening of You Can See Everything , the buzzy new documentary about the disgraced former biotech CEO Elizabeth Holmes. I went in not really knowing what to expect. I’d avoided spoilers (and won’t be giving…

Asian Scientist 07:19 UTC

As tiny mammals shrink to conserve energy during winter, their skulls undergo a surprising transformation. While the braincase gets smaller, the snout grows, revealing a more complex pattern of seasonal remodelling than scientists expected.

arXiv cs.CV 04:00 UTC

arXiv:2610.30724v1 Announce Type: new Abstract: Video provides a natural source of supervision: what happens next serves as a learning signal for visual world modeling. Yet masked video pretraining focuses on recovering missing content…

arXiv cs.CV 04:00 UTC

arXiv:2610.30652v1 Announce Type: new Abstract: Deep neural networks often struggle to provide reliable confidence estimates, making post-hoc calibration essential for reliable decision-making. Existing post-hoc methods largely rely on…

arXiv cs.AI 04:00 UTC

arXiv:2610.20731v2 Announce Type: replace-cross Abstract: Humans interpret multimodal observations of the world and forecast how it will evolve. Recent multimodal generative systems have demonstrated similar capabilities: they can…

arXiv cs.CV 04:00 UTC

arXiv:2610.06594v2 Announce Type: replace Abstract: Feed-forward visual geometry transformers such as VGGT reconstruct dense 3D structure from images in a single forward pass, simplifying multi-view 3D reconstruction. However, their…

arXiv cs.AI 04:00 UTC

arXiv:2610.30979v1 Announce Type: cross Abstract: Vehicle-to-everything (V2X) communication enables connected vehicles to make safety-critical decisions, but delayed, missing, or incorrect information can compromise driving safety…

arXiv cs.AI 04:00 UTC

arXiv:2607.26621v4 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated strong reasoning capabilities, motivating their adoption as backbones for foundation recommendation models (FRMs). Existing approaches…

arXiv cs.AI 04:00 UTC

arXiv:2610.30867v1 Announce Type: cross Abstract: Agents that call tools from a shared catalog can pool what they learn about which tool serves which request. We measure what pooled usage examples do to tool retrieval, reporting separately…

arXiv cs.LG 04:00 UTC

arXiv:2610.30228v1 Announce Type: new Abstract: To enable Industry 5.0, where autonomous systems are widely adopted and integrated with people to promote sustainable development in industries, it is imperative to adapt complex deep…

arXiv cs.AI 04:00 UTC

arXiv:2610.30461v1 Announce Type: cross Abstract: Learning useful representations from continually changing value targets remains a challenge in deep reinforcement learning. We study the temporal horizon of this supervision: smaller…

arXiv cs.LG 04:00 UTC

arXiv:2610.30844v1 Announce Type: new Abstract: Reverse Kullback-Leibler (KL) distillation has shown empirical promise for training language models, but its statistical guarantees and limits remain poorly understood. In particular, the…

arXiv cs.LG 04:00 UTC

arXiv:2610.31315v1 Announce Type: new Abstract: Many clinical decisions are a choice among a few fixed options, taken quickly and in large numbers. Such decisions also need an uncertainty estimate to know when to defer to a clinician…

arXiv cs.CL 04:00 UTC

arXiv:2610.30663v1 Announce Type: cross Abstract: Autoregressive encoder-decoder speech recognition models trained with teacher forcing can suffer from exposure bias, limiting their ability to recover from their own prediction errors at…

arXiv cs.CL 04:00 UTC

arXiv:2610.31422v1 Announce Type: new Abstract: Recent advances in specialized decision models have expanded the possibilities for zero-shot classification, yet their effectiveness on Vietnamese remains underexplored. This study evaluates…

arXiv cs.AI 04:00 UTC

arXiv:2607.28896v2 Announce Type: replace-cross Abstract: Unified audio models capable of audio understanding, audio generation and, increasingly, audio editing are proliferating rapidly. However, each capability is evaluated in isolation…

arXiv cs.AI 04:00 UTC

arXiv:2608.03496v2 Announce Type: replace-cross Abstract: Autonomous robots are moving rapidly from research labs into everyday life - on roads, in the air, in warehouses, and in space. Robot autonomy is no longer solely an academic…

arXiv cs.AI 04:00 UTC

arXiv:2609.17210v2 Announce Type: replace-cross Abstract: Vision-language-action (VLA) models, world-action models (WAMs), and offline reinforcement learning methods are rapidly expanding the design space of embodied policies, yet turning…

arXiv cs.AI 04:00 UTC

arXiv:2610.29606v2 Announce Type: replace-cross Abstract: Automatic phenotype information extraction plays an important role in rare disease diagnosis, genotype-phenotype analysis, and precision medicine. However, accurately identifying…

arXiv cs.AI 04:00 UTC

arXiv:2610.30162v1 Announce Type: cross Abstract: Model fusion aims to integrate the capabilities of multi-expert models into a single model. Existing evaluations offer limited coverage of reasoning with long chains of thought and tool…

arXiv cs.LG 04:00 UTC

arXiv:2610.20252v2 Announce Type: replace Abstract: Deep reinforcement learning (DRL) policies for planetary landing and other aerospace guidance, navigation, and control tasks are commonly trained under randomized disturbances to improve…

arXiv cs.LG 04:00 UTC

arXiv:2610.30890v1 Announce Type: cross Abstract: Deep Gaussian processes (DGPs) are appealing Bayesian regression models, but their standard discrete-depth parameterization often becomes harder to optimize as depth grows. We argue that…

arXiv cs.AI 04:00 UTC

arXiv:2610.31000v1 Announce Type: cross Abstract: Large language models (LLMs) have shown strong potential for cybersecurity, leading to growing interest in LLM-based automated cybersecurity log analysis. However, current datasets (1) are…

arXiv cs.AI 04:00 UTC

arXiv:2610.31260v1 Announce Type: cross Abstract: Projected quantum kernels (PQKs) have emerged as a notable approach to circumvent the hardness of machine learning tasks arising from the exponential dimensionality of the quantum Hilbert…

arXiv cs.AI 04:00 UTC

arXiv:2610.31130v1 Announce Type: new Abstract: Offline tests can fail to reveal whether an agent update will remain safe after deployment. We operationalize this post-audit mirage using matched safe and harmful lifecycles that expose…

arXiv cs.LG 04:00 UTC

arXiv:2603.11228v2 Announce Type: replace-cross Abstract: The widespread use of large language models (LLMs) raises an important question: how do texts evolve when they are repeatedly processed by LLMs? In this paper, we define this…

arXiv cs.LG 04:00 UTC

arXiv:2609.25373v2 Announce Type: replace Abstract: On-device assistants require function-calling models that map natural language to local system actions, but existing resources emphasize web APIs or narrow mobile-action catalogs. We…

arXiv cs.AI 04:00 UTC

arXiv:2610.31586v1 Announce Type: cross Abstract: Accuracy on medical examinations is common evidence offered for the clinical use of language models, yet a health system that intends to run an open model on its own hardware needs to know…

arXiv cs.LG 04:00 UTC

arXiv:2609.03046v2 Announce Type: replace-cross Abstract: The last five-plus years have seen many protein engineering disciplines transformed by advances in machine learning (ML), but the same cannot be said for directed evolution…

arXiv cs.LG 04:00 UTC

arXiv:2512.17340v3 Announce Type: replace-cross Abstract: Fair regression methods have the potential to mitigate societal bias concerns in health care, but there has been little work on penalized fair regression when multiple groups…

arXiv cs.CL 04:00 UTC

arXiv:2610.30664v1 Announce Type: new Abstract: Large language models increasingly act as controllers in structured decision pipelines, yet their decisions are still executed by autoregressive text decoding. Hierarchical RAG is one such…

arXiv cs.CL 04:00 UTC

arXiv:2605.22880v2 Announce Type: replace Abstract: As large language model (LLM)-based agents increasingly participate in online discourse, red-teaming their capacity to support political influence campaigns is critical for information…

arXiv cs.LG 04:00 UTC

arXiv:2512.01775v2 Announce Type: replace Abstract: While reinforcement learning (RL) successfully enhances reasoning in large language models, its role in fostering compositional generalization (the ability to synthesize novel skills from…

arXiv cs.LG 04:00 UTC

arXiv:2610.23453v2 Announce Type: replace Abstract: Evaluating candidate changes (hypotheses) to recommendation models requires full-scale training runs consuming thousands of GPU-hours, severely limiting the hypothesis space engineers can…

arXiv cs.LG 04:00 UTC

arXiv:2610.30345v1 Announce Type: cross Abstract: Neural receivers for 5G New Radio (NR) match classical model-based receivers in link-level performance, but their robustness to adversarial perturbations at the receiver input remains…

arXiv cs.LG 04:00 UTC

arXiv:2610.31180v1 Announce Type: cross Abstract: Modern high energy nuclear and particle physics experiments produce large amounts of sparse data that must be reduced significantly in size before performing physics analysis. Recently…

arXiv cs.LG 04:00 UTC

arXiv:2610.31133v1 Announce Type: new Abstract: Real-world deployment of personalized federated learning (PFL) requires adapting to heterogeneous clients while preserving recognition performance beyond local distributions. However, high…

arXiv cs.LG 04:00 UTC

arXiv:2610.30411v1 Announce Type: new Abstract: Recent work in additive manufacturing and neural inverse design enables the creation of complex three-dimensional structures to manipulate physical fields, yet these designs must also adhere…

arXiv cs.CL 04:00 UTC

arXiv:2610.30778v1 Announce Type: new Abstract: Do people who speak different languages organize concepts in similar ways? This question lies at the heart of the Sapir--Whorf hypothesis and debates about linguistic relativity. Shared basic…

arXiv cs.LG 04:00 UTC

arXiv:2610.30394v1 Announce Type: new Abstract: Protein classifiers are highly sensitive to evaluation protocol: random train/test splits induce phylogenetic leakage, allowing models to exploit taxon-specific correlations and substantially…

arXiv cs.CL 04:00 UTC

arXiv:2610.30067v2 Announce Type: replace Abstract: Vietnamese pre-trained encoders have improved rapidly, but the strongest ones are large, multilingual-vocabulary models or depend on external word segmentation, which makes them costly to…

arXiv cs.CL 04:00 UTC

arXiv:2601.03369v3 Announce Type: replace-cross Abstract: With the rapid growth of video centered social media, the ability to anticipate risky events from visual data is a promising direction for ensuring public safety and preventing real…

arXiv cs.CL 04:00 UTC

arXiv:2607.09957v3 Announce Type: replace Abstract: We study English-to-Traditional-Chinese (Taiwan) subtitle translation for a free browser extension, where the model must run on the viewer's CPU in about 500 ms per subtitle. We train two…

arXiv cs.AI 04:00 UTC

arXiv:2610.31147v1 Announce Type: cross Abstract: Automated manufacturing requires data-driven decisions under uncertainty and sparse observational records, and unplanned downtime is a dominant cost of getting them wrong. Prescriptive…

arXiv cs.LG 04:00 UTC

arXiv:2610.31194v1 Announce Type: new Abstract: Joint-embedding predictive architectures (JEPAs) learn world models in latent space, enabling efficient planning but leaving their states opaque. We introduce Inside-JEPA, which places…

arXiv cs.LG 04:00 UTC

arXiv:2610.31433v1 Announce Type: new Abstract: KV cache compression for multimodal LLMs usually selects the visual tokens to keep once, at prefill, and reuses that selection for the whole generation. We show that this one-shot selection…

arXiv cs.LG 04:00 UTC

arXiv:2610.31524v1 Announce Type: cross Abstract: Nonparametric estimation of joint probability distributions is a core problem in statistics, which is notoriously challenging with high-dimensional data. Such challenges also arise with…

arXiv cs.LG 04:00 UTC

arXiv:2503.22244v3 Announce Type: replace Abstract: Policy gradient methods are among the most successful approaches for solving challenging reinforcement learning problems. Despite their empirical success, many state-of-the-art policy…

arXiv cs.LG 04:00 UTC

arXiv:2605.06166v2 Announce Type: replace Abstract: In Large Language Model (LLM) fine-tuning, parameter and data selection are common strategies for reducing fine-tuning cost, yet they are typically driven by separate scoring mechanisms…

arXiv cs.LG 04:00 UTC

arXiv:2608.16407v2 Announce Type: replace-cross Abstract: Point-of-interest (POI) recommendation models based on graph neural networks achieve strong performance by propagating collaborative signals over user-item interactions, yet they…

arXiv cs.AI 04:00 UTC

arXiv:2610.30528v1 Announce Type: cross Abstract: Predicting surrounding vehicles' lane-change intentions enables autonomous vehicles to anticipate potential hazards and respond proactively rather than relying solely on reactive maneuvers…

arXiv cs.LG 04:00 UTC

arXiv:2610.30963v1 Announce Type: cross Abstract: Detecting online social engineering (SE) scams often requires examining website workflows, verifying claims against external sources, and connecting evidence across multiple pages. Existing…

arXiv cs.AI 04:00 UTC

arXiv:2604.07487v3 Announce Type: replace Abstract: Large language model agents rely on effective model context to obtain task-relevant information for decision-making. Many existing context engineering approaches primarily rely on the…

arXiv cs.AI 04:00 UTC

arXiv:2605.06145v2 Announce Type: replace-cross Abstract: Unsupervised pretraining has driven empirical advances in goal-conditioned reinforcement learning (GCRL), but its theoretical foundations remain poorly understood. In particular, an…

arXiv cs.AI 04:00 UTC

arXiv:2606.08417v3 Announce Type: replace-cross Abstract: Diffusion language models (DLMs) have emerged as the leading non-autoregressive alternative to language modeling. Because their likelihoods are intractable, generative perplexity…

arXiv cs.LG 04:00 UTC

arXiv:2507.00034v3 Announce Type: replace Abstract: Critical heat flux (CHF) marks the onset of boiling crisis in light-water reactors, defining safe thermal-hydraulic operating limits. To support Phase II of the OECD/NEA AI/ML CHF…

arXiv cs.LG 04:00 UTC

arXiv:2505.05492v2 Announce Type: replace-cross Abstract: While machine learning fairness has made significant progress in recent years, most existing solutions focus on tabular data and are poorly suited for vision-based classification…

arXiv cs.CL 04:00 UTC

arXiv:2610.29351v2 Announce Type: replace-cross Abstract: Zero-shot cross-lingual voice cloning often carries the reference speaker's accent into the target language. We propose closed-loop dual-reference guidance, which pairs the original…

arXiv cs.CL 04:00 UTC

arXiv:2609.38923v3 Announce Type: replace Abstract: Working agents need to read diverse files, coordinate tools, and produce deliverables. Training such agents requires tasks built on many real files with verifiable results, but few…

arXiv cs.LG 04:00 UTC

arXiv:2610.31538v1 Announce Type: cross Abstract: Local anomaly detection is the task of identifying spatially confined anomalous or out-of-distribution (OOD) regions within an otherwise in-distribution (ID) image. Most existing methods…

arXiv cs.LG 04:00 UTC

arXiv:2603.21782v2 Announce Type: replace Abstract: The performance of machine learning models depends on discovering features in the data that are relevant to solving the given task while ignoring irrelevant variation. To check and…

arXiv cs.LG 04:00 UTC

arXiv:1502.05056v2 Announce Type: replace Abstract: We consider a recent innovative theory by Chastain et al. on the role of sex in evolution [PNAS'14]. In short, the theory suggests that the evolutionary process of gene recombination…

arXiv cs.LG 04:00 UTC

arXiv:2610.30280v1 Announce Type: new Abstract: Muon updates matrix-valued parameters along approximately orthogonalized directions and often trains large language models faster than AdamW, yet it remains unclear when and why…

arXiv cs.CL 04:00 UTC

arXiv:2610.30946v1 Announce Type: cross Abstract: Large Language Models (LLMs) can generate UML class diagrams from natural language requirements, but hallucinations may compromise the correctness and completeness of the resulting…

arXiv cs.LG 04:00 UTC

arXiv:2605.06145v2 Announce Type: replace Abstract: Unsupervised pretraining has driven empirical advances in goal-conditioned reinforcement learning (GCRL), but its theoretical foundations remain poorly understood. In particular, an…

arXiv cs.AI 04:00 UTC

arXiv:2610.30861v1 Announce Type: cross Abstract: Few-step autoregressive video generation enables low-latency streaming, yet prevailing training pipelines separate causal adaptation from distribution matching. Recent representation-based…

arXiv cs.CL 04:00 UTC

arXiv:2610.29896v2 Announce Type: replace Abstract: Existing social bias benchmarks evaluate large language models mostly on fluent, well-formed English, reflecting native speaker usage and leaving non-native writers unrepresented. To…

arXiv cs.AI 04:00 UTC

arXiv:2605.22880v2 Announce Type: replace-cross Abstract: As large language model (LLM)-based agents increasingly participate in online discourse, red-teaming their capacity to support political influence campaigns is critical for…

arXiv cs.CV 04:00 UTC

arXiv:2610.30347v1 Announce Type: new Abstract: We propose FiLM-CAM; a conditional-access image watermarking approach that enforces authorized encoding, decoding, and removal through keyed feature modulation. A secret key conditions a…

arXiv cs.CV 04:00 UTC

arXiv:2608.29925v2 Announce Type: replace Abstract: Controllable image relighting is an important problem in image editing, and hand-drawn scribbles provide an intuitive interface for specifying the desired illumination. However, existing…

arXiv cs.CL 04:00 UTC

arXiv:2610.31017v1 Announce Type: new Abstract: Single-document LoRA adapters have been proposed as units of knowledge to be merged and retrieved; yet open-book scoring, with the document in the prompt, can credit a document's own adapter…

arXiv cs.CL 04:00 UTC

arXiv:2605.30526v3 Announce Type: replace-cross Abstract: Post-trained language models often exhibit a recognizable AI-like writing style, yet its connection to post-training and internal representations remains poorly understood. In this…

arXiv cs.CL 04:00 UTC

arXiv:2405.00273v4 Announce Type: replace Abstract: Non-cognitive skills are crucial for personal and social life well-being, and such skill development can be supported by narrative-based (e.g., storytelling) technologies. While…

arXiv cs.CL 04:00 UTC

arXiv:2602.03358v2 Announce Type: replace-cross Abstract: Finding effective prompts for language models (LMs) is critical yet notoriously difficult: the prompt space is combinatorially large, rewards are sparse due to expensive target-LM…

arXiv cs.LG 04:00 UTC

arXiv:2610.30668v1 Announce Type: new Abstract: Designing RNA molecules that bind to target protein structures requires generating both an RNA conformation and its bound complex geometry, without assuming a predefined binding site…

arXiv cs.LG 04:00 UTC

arXiv:2610.30954v1 Announce Type: new Abstract: Benchmarking in reinforcement learning is usually relative: algorithms are ranked by returns on environments with unknown optima. Distance to optimality remains unobservable, while…

arXiv cs.LG 04:00 UTC

arXiv:2610.30957v1 Announce Type: new Abstract: Offline contextual pricing often relies on logged observational data, but faces challenges from distributional shifts between training and deployment environments. Distributionally robust…

arXiv cs.LG 04:00 UTC

arXiv:2610.30965v1 Announce Type: new Abstract: AI models, and time-series models in particular are typically ranked by accuracy and deployed under constraints absent from that ranking. In this paper, we study a real setting where these…

arXiv cs.LG 04:00 UTC

arXiv:2610.30995v1 Announce Type: new Abstract: Electroencephalography (EEG)-to-language models offer a promising approach for translating complex neural signals into human-readable descriptions. However, generating plausible language does…

arXiv cs.CL 04:00 UTC

arXiv:2610.30612v1 Announce Type: cross Abstract: Hybrid retrieval, which fuses a sparse lexical retriever with a dense neural one, is widely recommended in the software documentation surveyed in September 2026, usually with reciprocal…

arXiv cs.LG 04:00 UTC

arXiv:2610.31616v1 Announce Type: new Abstract: On-policy distillation has been widely adopted for alleviating the distribution mismatch of off-policy distillation. Self-distillation further removes the need for an external teacher by…

arXiv cs.LG 04:00 UTC

arXiv:2610.30182v1 Announce Type: cross Abstract: AI governance agreements require methods to detect large model training runs on a monitored computing cluster, without trusting the operator. We develop a method to detect synchronous model…

arXiv cs.LG 04:00 UTC

arXiv:2610.30188v1 Announce Type: cross Abstract: Program optimization aims to improve performance while preserving behavior. Coding agents can already make programs faster by changing algorithms, data structures, and execution strategies…

arXiv cs.AI 04:00 UTC

arXiv:2606.07581v2 Announce Type: replace-cross Abstract: A trained model is usually described by its weights, as if the weights fixed its behavior. In practice the same weights are run by different programs. Training uses high-precision…

arXiv cs.CL 04:00 UTC

arXiv:2610.30882v1 Announce Type: cross Abstract: Reinforcement learning (RL) is credited with teaching reasoning models to write {wait} before reconsidering a step, yet large RL accuracy gains do not require the word. This view can…

arXiv cs.CL 04:00 UTC

arXiv:2606.12117v2 Announce Type: replace Abstract: Benchmark scores often misrepresent a large language model's (LLM's) knowledge, because they rely, e.g., on the model's ability to follow specific formatting requirements. This especially…

arXiv cs.CL 04:00 UTC

arXiv:2610.30912v1 Announce Type: cross Abstract: Fine-grained image-text retrieval requires a model not only to assess global semantic consistency between an image and a text, but also to model visual evidence for local textual semantics…

arXiv cs.CL 04:00 UTC

arXiv:2610.28673v2 Announce Type: replace Abstract: We study the 305M-parameter audio encoder shared by Gemma 4 and EmbeddingGemma 2 (bit-identical to that of Gemma 4 E2B except for the final audio-embedding projection) for Saudi and Gulf…

arXiv cs.CL 04:00 UTC

arXiv:2610.30676v1 Announce Type: new Abstract: Singular-value spectra encode important structure in transformer feed-forward projections, yet their causal role in downstream behavior remains underexplored. We study post-hoc spectral…

arXiv cs.CV 04:00 UTC

arXiv:2610.29322v2 Announce Type: replace Abstract: Accurate localization of neonatal hypoxic--ischemic encephalopathy (HIE) lesions on apparent diffusion coefficient (ADC) images is clinically important but is limited by scarce expert…

arXiv cs.AI 04:00 UTC

arXiv:2608.09930v2 Announce Type: replace-cross Abstract: Automated Text-to-Speech (TTS) evaluation methods (Mean Opinion Score (MOS) predictors and Audio Large Language Model (Audio-LLM) judges) are expected to reflect human perception…

arXiv cs.AI 04:00 UTC

arXiv:2605.12122v2 Announce Type: replace-cross Abstract: Unlearning specific concepts in text-to-image diffusion models has become increasingly important for preventing undesirable content generation. Among prior approaches, sparse…

arXiv cs.CV 04:00 UTC

arXiv:2610.31152v1 Announce Type: new Abstract: As AI generated images are getting popular these days, discussions on such generations are widely existed in current public forums, software repositories, and photography tutorials. Moreover…

arXiv cs.CV 04:00 UTC

arXiv:2610.30634v1 Announce Type: new Abstract: Unsupervised federated learning with Vision-Language Models (e.g., CLIP) offers a promising solution for label-free classification, yet its performance often degrades under severe non-IID…

arXiv cs.LG 04:00 UTC

arXiv:2602.11957v2 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly used for content creation in regulated domains such as pharmaceuticals, where content must be medical accurate and legally compliant…

arXiv cs.CV 04:00 UTC

arXiv:2610.30293v1 Announce Type: new Abstract: We introduce EgoHand, a monocular 3D hand reconstruction model that achieves state-of-the-art performance on egocentric video. Central to our approach is the curation of a high-quality…

arXiv cs.CV 04:00 UTC

arXiv:2610.31565v1 Announce Type: new Abstract: Generating 360-degree panoramas requires both local perspective fidelity and global spherical continuity. Existing representations face a trade-off: equirectangular projection (ERP) enables…

arXiv cs.LG 04:00 UTC

arXiv:2610.31323v1 Announce Type: new Abstract: Many deployments require a model to move rapidly from a data-rich source to a related target observed only sparsely. This is especially consequential where target data are difficult to…

arXiv cs.AI 04:00 UTC

arXiv:2610.30705v1 Announce Type: cross Abstract: Text embedding and text generation are two of the most useful capabilities of modern large language models, yet they are typically provided by separate specialized models (an embedder and a…

arXiv cs.CL 04:00 UTC

arXiv:2610.30533v1 Announce Type: new Abstract: Industry Foundation Classes (IFC), the standard for building information exchange in architecture, engineering, and construction (AEC), is increasingly queried through large language models…

arXiv cs.LG 04:00 UTC

arXiv:2610.30744v1 Announce Type: new Abstract: Masked diffusion models (MDMs) generate sequences by progressively unmasking tokens, but errors introduced during decoding are typically irreversible. Recent work has shown that iterative…

arXiv cs.CL 04:00 UTC

arXiv:2610.31172v1 Announce Type: new Abstract: LLM-as-a-Judge evaluation is increasingly applied to multilingual tasks, yet prompting strategies such as Chain-of-Thought and Role Conditioning are recommended based solely on English…

arXiv cs.CL 04:00 UTC

arXiv:2610.31259v1 Announce Type: new Abstract: Search is a central component of Automatic Speech Recognition (ASR) systems and has been deeply investigated for classical ASR modeling based on Hidden Markov Models (HMMs). However, in work…

arXiv cs.CL 04:00 UTC

arXiv:2610.26976v2 Announce Type: replace Abstract: We establish sharp degree bounds for Putinar sum-of-squares (SOS) certificates in terms of the positivity margin $\delta$. For any fixed Archimedean quadratic module with prescribed…

arXiv cs.AI 04:00 UTC

arXiv:2610.30537v1 Announce Type: new Abstract: Frontier language models now score above 90% on popular knowledge benchmarks and are increasingly deployed as agents that carry out multi-hour professional work. Yet no existing benchmark…

arXiv cs.LG 04:00 UTC

arXiv:2610.30688v1 Announce Type: new Abstract: Wrist photoplethysmography (PPG) heart rate estimates are vulnerable to motion artifacts, and corrections that reduce mean error can worsen individual windows. We propose an agent…

arXiv cs.AI 04:00 UTC

arXiv:2603.13285v4 Announce Type: replace-cross Abstract: Existing evaluation methods largely rely on clean, static benchmarks, which can overestimate true model performance by failing to capture the noise and variability inherent in…