Artificial Intelligence news — Thursday 08 October 2026

AI Business 21:12 UTC

Under the program, the vendor provides enterprises with models that can defend against bad actors.

OpenAI Blog 16:00 UTC

Across recruiting, engineering, and operations, Oracle turns specialist knowledge into fast, repeatable workflows with ChatGPT Work and Codex.

Towards Data Science 15:30 UTC

Three moves to decode the hype The post Everyone Is Selling AI at You — Here’s How to Keep Your Judgement appeared first on Towards Data Science .

Towards Data Science 14:00 UTC

AI agents can now write CUDA kernels that outperform PyTorch—but proving those speedups are real is the harder problem. I put them to the test on an NVIDIA DGX Spark and found that benchmark design matters just as much as the code. The…

Towards Data Science 12:30 UTC

A diffusion head for probabilistic time series forecasting: why a forecast can get the mean and the variance right and still describe a future that never happens, and how to fix it. The post Your Model's MSE Is Lying to You III: Time…

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. AI breakthroughs in robotics won’t change your life any time soon The hype around humanoid robots is…

OpenAI Blog 12:00 UTC

LegalOn cut estimated daily Codex costs by 65% while maintaining development speed. It matched Astra, Sol, and Luna to tasks and managed budgets strategically.

OpenAI Blog 12:00 UTC

With GPT-5.6, GPT-6 Astra, and GPT‑Image‑2.5, Pollo AI helps creators turn bold ideas into detailed images and cinematic video ads.

Towards Data Science 11:00 UTC

An exploration of the new data science roles emerging after the Large Language Model explosion. The post AI Engineers, Applied Scientists, Forward Deployed Engineers: Let's Unpack. appeared first on Towards Data Science .

MIT Technology Review Biotech 10:00 UTC

This week, we released our 2026 version of our Climate Tech Companies to Watch list. It’s an annual project that the MIT Technology Review team puts together. Our goal is to highlight some of the promising, interesting advances and firms…

MIT Technology Review Biotech 09:00 UTC

The story is a collaboration between MIT Technology Review and Aventine , a non-profit research foundation that creates and supports content about how technology and science are changing the way we live. A robot shaped like a human—white…

MIT Technology Review Biotech 08:17 UTC

Industrial AI is entering a new phase. After decades of predictive analytics and other specialized applications, advances in foundation models, physical AI, and agentic AI are making it possible to automate more complex tasks across…

arXiv cs.AI 04:00 UTC

arXiv:2610.08871v1 Announce Type: cross Abstract: Language model agents are increasingly deployed to automate everyday digital chores from managing emails and social media to handling banking and bills allowing users to step away from…

arXiv cs.AI 04:00 UTC

arXiv:2610.10304v1 Announce Type: cross Abstract: We study whether latent sequence compression of prompt prefixes preserves the capabilities that large language models rely on during inference. We introduce SemanticFold, a compression…

arXiv cs.CL 04:00 UTC

arXiv:2604.24197v3 Announce Type: replace Abstract: Image generation systems can produce plausible photographs, readable documents, and consistent depictions of people and places. When these artifacts are presented as records of real…

arXiv cs.LG 04:00 UTC

arXiv:2610.09763v1 Announce Type: new Abstract: Offline reinforcement learning enables reward-driven policy improvement from fixed datasets without requiring online exploration, making it particularly attractive in safety-critical domains…

arXiv cs.CV 04:00 UTC

arXiv:2603.13357v2 Announce Type: replace Abstract: Bi-CamoDiffusion is introduced, an evolution of the CamoDiffusion framework for camouflaged object detection. It integrates edge priors into early-stage embeddings via a parameter-free…

arXiv cs.CL 04:00 UTC

arXiv:2610.09529v1 Announce Type: new Abstract: There are more than 2,000 listed companies on the UK's London Stock Exchange, divided into 11 sectors who are required to communicate their financial results at least twice in a single…

arXiv cs.CV 04:00 UTC

arXiv:2610.09408v1 Announce Type: new Abstract: Audio-visual multi-segment grounding (AV-MSG) in untrimmed videos, reasoning over audio-visual evidence and predicting multiple segments for a query, is a fundamental problem but remains…

arXiv cs.CV 04:00 UTC

arXiv:2610.09304v1 Announce Type: cross Abstract: Facial movements convey subtle and important information that is critical for human social communication. Optical methods for face capture are difficult or impossible to use when the face…

arXiv cs.CV 04:00 UTC

arXiv:2610.09853v1 Announce Type: new Abstract: Pose-free feed-forward 3D Gaussian Splatting (3DGS) reconstructs a scene from sparse, unposed images in a single network pass, removing the need for camera calibration and per-scene…

arXiv cs.CV 04:00 UTC

arXiv:2603.20714v4 Announce Type: replace Abstract: 3D Gaussian Splatting (3DGS) has become the method of choice for photo-realistic novel view synthesis (NVS), due to its efficiency and compelling visual quality. 3DGS represents the scene…

arXiv cs.CL 04:00 UTC

arXiv:2606.09843v4 Announce Type: replace-cross Abstract: Do large language models' (LLMs') answers to self-report questionnaires predict how they behave? Prior work finds they do not, but it uses human personality inventories, so the gap…

arXiv cs.LG 04:00 UTC

arXiv:2610.10447v1 Announce Type: new Abstract: Reinforcement Learning (RL) from outcome rewards suffers from sparse supervision, particularly on difficult, long-horizon tasks where successful trajectories are rare and costly to generate…

arXiv cs.CL 04:00 UTC

arXiv:2605.10971v2 Announce Type: replace-cross Abstract: Discrete diffusion language models (DLMs) generate text by iteratively denoising all positions in parallel, offering an alternative to autoregressive models. Controlled generation…

arXiv cs.CL 04:00 UTC

arXiv:2610.01118v2 Announce Type: replace Abstract: A long-term conversational assistant must recall the right memory at the right moment, yet the memory that matters most is often not similar to what the user says now. Current systems…

arXiv cs.CL 04:00 UTC

arXiv:2608.21381v2 Announce Type: replace-cross Abstract: Personal intelligence is becoming a central frontier for user-facing AI agents. To be helpful in everyday life, agents must understand users across the digital contexts where their…

arXiv cs.CL 04:00 UTC

arXiv:2609.11917v2 Announce Type: replace-cross Abstract: As the supply of human-written text is exhausted, it has become standard practice to repeat language model training data. Prior work has studied data repetition for densely…

arXiv cs.CL 04:00 UTC

arXiv:2609.14767v2 Announce Type: replace-cross Abstract: Does authority in AI teams improve the outcome? Organizational theory asserts that authority facilitates decision making, improving quality. Meanwhile, some nascent AI research…

arXiv cs.LG 04:00 UTC

arXiv:2610.10105v1 Announce Type: new Abstract: The Fourier Neural Operator (FNO) learns solution operators of partial differential equations (PDEs) through Fourier-space kernel parameterization, but frequency truncation can limit the…

arXiv cs.LG 04:00 UTC

arXiv:2602.15472v5 Announce Type: replace-cross Abstract: We present a novel property-preserving kernel-based operator learning method for incompressible flows governed by the incompressible Navier--Stokes equations. Traditional numerical…

arXiv cs.AI 04:00 UTC

arXiv:2610.10407v1 Announce Type: new Abstract: As option markets grow and AI advances, agentic systems for option trading are gaining increasing attention. Language-model-based agents can reason over contextual information such as news…

arXiv cs.AI 04:00 UTC

arXiv:2610.06966v2 Announce Type: replace-cross Abstract: Indirect prompt injection (IPI) hides adversarial instructions in content that large language model (LLM) agents read at runtime. As agents compose heterogeneous capability units…

arXiv cs.CL 04:00 UTC

arXiv:2610.09371v1 Announce Type: cross Abstract: Calibrated uncertainty quantification is essential to ensuring AI agents are trustworthy and reliable. However, when agents seek to maximize user engagement or revenue, confidence reports…

arXiv cs.CL 04:00 UTC

arXiv:2505.19912v3 Announce Type: replace Abstract: We present Adjacent Possible Exploration (APE), a selective fine-tuning method for adapting large language models that systematically explores parameter modifications while maintaining…

arXiv cs.CV 04:00 UTC

arXiv:2605.27813v2 Announce Type: replace Abstract: Text-to-image diffusion models generate images by iterative denoising, so their internal layers produce trajectories of activations rather than single static representations. Sparse…

arXiv cs.CV 04:00 UTC

arXiv:2609.31765v2 Announce Type: replace Abstract: Accurate and rapid prediction of the aerodynamic drag coefficient ($C_D$) is essential for vehicle design, particularly during early-stage design, where many candidate geometries must be…

arXiv cs.LG 04:00 UTC

arXiv:2412.09119v4 Announce Type: replace Abstract: Machine unlearning, the process of selectively removing data from trained models, is increasingly crucial for addressing privacy concerns and knowledge gaps post-deployment. Despite this…

arXiv cs.CL 04:00 UTC

arXiv:2609.00940v2 Announce Type: replace Abstract: Solving problems through repeated attempts is a sequential modeling task: at each step, the solver receives feedback and decides how to revise their solutions. Predicting whether…

arXiv cs.LG 04:00 UTC

arXiv:2610.10310v1 Announce Type: new Abstract: Recursive self-improvement requires carrying accepted changes into later improvement cycles, while studying agent-proposed changes also requires substantial research infrastructure. Existing…

arXiv cs.CV 04:00 UTC

arXiv:2610.09079v1 Announce Type: cross Abstract: Large language models equipped with development environments have moved code generation toward repository-scale construction, yet building complete repositories remains difficult because…

arXiv cs.LG 04:00 UTC

arXiv:2609.36252v2 Announce Type: replace Abstract: Closed-form recourse moves a rejected user along the unit gradient $\hat g$ of the classifier score $f$ by the promised distance $d_p=|f(x)|/\|\nabla f(x)\|$, at which the linearized…

arXiv cs.CL 04:00 UTC

arXiv:2610.08835v1 Announce Type: new Abstract: The spread of fake news may cause severe social consequences. Existing fake news detection methods mainly focus on stylistic variations or incorporate external information such as…

arXiv cs.CL 04:00 UTC

arXiv:2606.22272v2 Announce Type: replace Abstract: Applying pre-trained language models to new domains through full fine-tuning is computationally expensive and prone to catastrophic forgetting. To address this limitation, we introduce a…

arXiv cs.CL 04:00 UTC

arXiv:2610.09063v1 Announce Type: cross Abstract: Multi-label topic assignment for user-generated content (UGC) -- including product reviews and buyer-seller conversations -- poses unique scalability challenges in large-scale e-commerce…

arXiv cs.LG 04:00 UTC

arXiv:2610.08977v1 Announce Type: new Abstract: Accurate and low latency channel estimation is critical for modern MIMO systems, particularly under mobility, where channels exhibit structured sparsity and strong temporal correlation. This…

arXiv cs.CL 04:00 UTC

arXiv:2610.08814v1 Announce Type: cross Abstract: Compositional generalization remains challenging when language models must combine familiar reasoning operations in unfamiliar ways. The Scenario-Based Commonsense Reasoning Evaluation…

arXiv cs.CL 04:00 UTC

arXiv:2610.10318v1 Announce Type: new Abstract: Social media is a rich source of real-time public sentiment, but widely used sentiment analysis tools are often applied without understanding their limitations. In this study, we evaluate the…

arXiv cs.CL 04:00 UTC

arXiv:2602.11133v3 Announce Type: replace-cross Abstract: Diffusion language models generate text through iterative refinement, a process that is often computationally inefficient because many tokens reach stability long before the final…

arXiv cs.AI 04:00 UTC

arXiv:2605.01616v3 Announce Type: replace-cross Abstract: Human behavior is difficult to observe continuously at scale, yet it leaves measurable traces in everyday device use. We test whether encrypted smartphone network traffic---a…

arXiv cs.CL 04:00 UTC

arXiv:2610.10154v1 Announce Type: new Abstract: We introduce Hyperbolic Symplectic Positional Encoding (HySPE), grounding positional attention in non-compact symplectic transformations. While canonical Rotary Position Embedding (RoPE)…

arXiv cs.CL 04:00 UTC

arXiv:2610.10114v1 Announce Type: new Abstract: The architectural design of Large Language Models (LLMs) is shifting from traditional full-attention-only models to hybrid models, which combine different attention modules to improve…

arXiv cs.AI 04:00 UTC

arXiv:2410.11687v4 Announce Type: replace-cross Abstract: In-context learning lets a sequence model adapt to a new task from examples in its input. A prominent line of work shows how self-attention can be constructed to implement gradient…

arXiv cs.CV 04:00 UTC

arXiv:2607.28198v2 Announce Type: replace-cross Abstract: Many dexterous manipulation tasks require the object to remain securely held throughout the interaction. From the perspective of hand-object relational motion, such manipulation…

arXiv cs.CV 04:00 UTC

arXiv:2610.05870v2 Announce Type: replace Abstract: Generative models can synthesize high-quality inauthentic multimedia content that is already being misused at scale. We evaluate twenty deepfake detectors against ten generators released…

arXiv cs.CL 04:00 UTC

arXiv:2610.10049v1 Announce Type: new Abstract: Reasoning models allocate extra computation at inference time and present their answers as the product of deliberate thought. If this deliberation works the way dual-process accounts of human…

arXiv cs.CV 04:00 UTC

arXiv:2610.10448v1 Announce Type: cross Abstract: MemoCare is an interactive mobile system for automated multimodal cognitive screening. A React Native application combines spoken responses, temporal and spatial orientation, touchscreen…

arXiv cs.CV 04:00 UTC

arXiv:2610.10438v1 Announce Type: new Abstract: Embodied and assistive agents must do more than recognize objects: they must reason about where an object belongs given the layout of an environment and the habits of the people who live in…

arXiv cs.CL 04:00 UTC

arXiv:2609.35308v2 Announce Type: replace Abstract: Large language models treat conversation history as unverified context, so false premises injected into prior turns can be adopted as fact, a failure mode we term session-level…

arXiv cs.LG 04:00 UTC

arXiv:2610.08820v1 Announce Type: new Abstract: Large language model-based multi-agent systems improve complex problem solving through collaboration, while latent communication directly transmits model internal states to avoid the high…

arXiv cs.LG 04:00 UTC

arXiv:2610.09635v1 Announce Type: cross Abstract: Anomaly detection on small and unbalanced datasets remains very challenging in machine learning, although this scenario is common in several domains, including healthcare, cybersecurity…

arXiv cs.AI 04:00 UTC

arXiv:2610.05610v2 Announce Type: replace-cross Abstract: Embodied, ego-centric intelligence fundamentally requires the ability to comprehend spatial audio within complex environments. While large audio-language models excel at…

arXiv cs.AI 04:00 UTC

arXiv:2610.06083v2 Announce Type: replace-cross Abstract: Most adversarial attacks on deep reinforcement learning (DRL) assume white-box access to the victim policy, which rarely holds in practice. This paper studies transfer-based…

arXiv cs.AI 04:00 UTC

arXiv:2609.23665v2 Announce Type: replace-cross Abstract: Language models now generate symbolic music from text, and research has focused on musicality. However, many applications require a score that meets explicit constraints, which…

arXiv cs.CV 04:00 UTC

arXiv:2610.09376v1 Announce Type: new Abstract: Acquiring a complete set of magnetic resonance imaging (MRI) contrasts is time-intensive and uncomfortable for patients, despite the diagnostic value of multi-contrast imaging. This motivates…

arXiv cs.LG 04:00 UTC

arXiv:2610.09877v1 Announce Type: new Abstract: Mixed-precision post-training quantization is a network compression method that assigns bits layer by layer, under a global memory budget using a small calibration set. The main difficulties…

arXiv cs.LG 04:00 UTC

arXiv:2610.09411v1 Announce Type: new Abstract: Multimodal representations enable zero-shot classification and retrieval, but aligning independently trained models usually requires large amounts of paired data. Yet, the Platonic…

arXiv cs.LG 04:00 UTC

arXiv:2610.09457v1 Announce Type: new Abstract: Methods that recover individual latent variables of the world, from nonlinear ICA to dictionary learning and causal representation learning, anchor the latents to observations through…

arXiv cs.LG 04:00 UTC

arXiv:2610.09792v1 Announce Type: new Abstract: Electroencephalography (EEG) is highly susceptible to electromyographic (EMG) artifacts, whose temporal heterogeneity and spatial-spectral overlap with neural activity can leave mixed sources…

arXiv cs.LG 04:00 UTC

arXiv:2610.09994v1 Announce Type: new Abstract: Models with near-identical predictive performance can yield substantially different predictions, a phenomenon known as predictive multiplicity. Prior work has mostly studied this at the level…

arXiv cs.LG 04:00 UTC

arXiv:2610.10304v1 Announce Type: new Abstract: We study whether latent sequence compression of prompt prefixes preserves the capabilities that large language models rely on during inference. We introduce SemanticFold, a compression scheme…

arXiv cs.LG 04:00 UTC

arXiv:2610.10367v1 Announce Type: new Abstract: Interpretability offers a solution to safe autonomy by providing transparency into an agent's underlying decision-making model. Within sequential-decision making tasks, differentiable…

arXiv cs.LG 04:00 UTC

arXiv:2610.10395v1 Announce Type: new Abstract: Transformers can execute algorithms on data given in their input. We ask whether they can do the same for causal discovery. We study a standard continuous method that repeatedly updates a…

arXiv cs.LG 04:00 UTC

arXiv:2610.10437v1 Announce Type: new Abstract: Flow policies capture rich and diverse action distributions, and fine-tuning them with off-policy RL to improve beyond the demonstrations has drawn growing interest. However, fine-tuning a…

arXiv cs.CL 04:00 UTC

arXiv:2610.09710v1 Announce Type: new Abstract: ANN-to-SNN conversion offers a practical route toward energy-efficient spiking Vision-Language-Action (VLA) models by bypassing the substantial cost of training large-scale SNNs from scratch…

arXiv cs.LG 04:00 UTC

arXiv:2610.08827v1 Announce Type: cross Abstract: Automatic Speech Recognition (ASR) systems often underperform for children and non-native speakers, while adapting adult ASR models to child speech can cause adult-speech forgetting. We…

arXiv cs.LG 04:00 UTC

arXiv:2610.09087v1 Announce Type: cross Abstract: Large language models are informing decisions with ever-higher stakes. As the consequences of their errors grow, a central question becomes harder to ignore: how much can we trust an…

arXiv cs.LG 04:00 UTC

arXiv:2610.09274v1 Announce Type: cross Abstract: The Visual Geometry Grounded Transformer (VGGT) marks a significant leap forward in 3D scene reconstruction, as it is the first model that directly infers all key 3D attributes (camera…

arXiv cs.LG 04:00 UTC

arXiv:2610.09276v1 Announce Type: cross Abstract: Modern DBMSs expose hundreds of configuration knobs, resulting in a high-dimensional and heterogeneous search space that makes automated tuning costly. Existing ML-based tuning systems…

arXiv cs.LG 04:00 UTC

arXiv:2610.09871v1 Announce Type: cross Abstract: Implicit modeling and Relative Geologic Time are geological modeling techniques that enable more efficient, faster, less biased and more reproducible modeling results. For optimal…

arXiv cs.LG 04:00 UTC

arXiv:2610.09943v1 Announce Type: cross Abstract: Reinforcement learning (RL) fine-tuning improves vision-language-action (VLA) policies through closed-loop experience, yet generalization beyond the fine-tuning distribution remains…

arXiv cs.LG 04:00 UTC

arXiv:2605.10971v2 Announce Type: replace Abstract: Discrete diffusion language models (DLMs) generate text by iteratively denoising all positions in parallel, offering an alternative to autoregressive models. Controlled generation methods…

arXiv cs.LG 04:00 UTC

arXiv:2606.03904v2 Announce Type: replace Abstract: Multi-objective optimization (MOO) underlies many machine learning problems, yet MOO solvers across the loss-balancing, gradient-balancing, and Pareto-based families almost universally…

arXiv cs.LG 04:00 UTC

arXiv:2609.21926v2 Announce Type: replace Abstract: Many machine learning systems try to explain complex data - like images or financial time series - in terms of hidden, independent factors that generated them. Recovering the true…

arXiv cs.LG 04:00 UTC

arXiv:2610.02199v2 Announce Type: replace Abstract: Full-parameter fine-tuning of large language models (LLMs) incurs substantial optimizer state memory overhead, limiting the model sizes that fit on modern GPUs. Existing approaches either…

arXiv cs.LG 04:00 UTC

arXiv:2606.07399v3 Announce Type: replace-cross Abstract: Generative models are increasingly used to support decision-making in complex systems, where interventions may be joint and high-dimensional, and outcomes are high-dimensional…

arXiv cs.AI 04:00 UTC

arXiv:2610.09002v1 Announce Type: new Abstract: When agents share a reward for completed tasks, reporting unsafe work can reduce the reporter's reward by stopping a task. Audits can make reporting optimal without ensuring that further…

arXiv cs.CV 04:00 UTC

arXiv:2610.08826v1 Announce Type: new Abstract: Full-sphere panoramic cameras let fixed monitoring systems and mobile robots track people in every direction, but a planar bounding box does not fully describe where a person is on the…

arXiv cs.CV 04:00 UTC

arXiv:2610.09383v1 Announce Type: new Abstract: Sparse-view 3D coronary reconstruction commonly relies on cross-view correspondence and triangulation, which are vulnerable to vessel overlap and foreshortening, or on volumetric prediction…

arXiv cs.CL 04:00 UTC

arXiv:2604.20021v2 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) become increasingly popular, caching responses so that they can be reused by users with semantically similar queries has become a vital strategy for…

arXiv cs.LG 04:00 UTC

arXiv:2610.09782v1 Announce Type: new Abstract: Causal discovery becomes particularly challenging when the available sample size is small relative to the number of variables. This challenge also arises in the linear non-Gaussian acyclic…

arXiv cs.LG 04:00 UTC

arXiv:2610.09690v1 Announce Type: cross Abstract: Autonomous underwater vehicles (AUVs) commonly rely on inertial navigation systems (INS) aided by Doppler velocity logs (DVLs) for reliable underwater navigation. Accurate DVL velocity…

arXiv cs.AI 04:00 UTC

arXiv:2610.09108v1 Announce Type: cross Abstract: Policy learning drives many of the most consequential and heavily-invested applications of reinforcement learning today. Yet the core optimization problem it rests on (maximizing expected…

arXiv cs.AI 04:00 UTC

arXiv:2607.14097v3 Announce Type: replace Abstract: We introduce RegNetAgents, an AI-oriented multi-agent framework for structured, query-driven regulatory candidate identification across heterogeneous gene regulatory networks. It…

arXiv cs.AI 04:00 UTC

arXiv:2609.18278v2 Announce Type: replace Abstract: Artificial Intelligence (AI) is currently only applied to non-safety critical applications due to the strict standards and regulations for railway industries. We propose to review the…

arXiv cs.AI 04:00 UTC

arXiv:2604.24197v3 Announce Type: replace-cross Abstract: Image generation systems can produce plausible photographs, readable documents, and consistent depictions of people and places. When these artifacts are presented as records of real…

arXiv cs.AI 04:00 UTC

arXiv:2610.09146v1 Announce Type: new Abstract: Large language models (LLMs) and vision-language models (VLMs) are usually frozen after deployment, so they do not learn from the cases they solve. This is especially concerning in medicine…

arXiv cs.AI 04:00 UTC

arXiv:2610.09218v1 Announce Type: new Abstract: LLM-guided program evolution has enabled discoveries in mathematics and computational optimization, raising the prospect of reinforcement learning (RL) algorithms that self-evolve to improve…

arXiv cs.AI 04:00 UTC

arXiv:2610.08809v1 Announce Type: cross Abstract: Depression severity among patients with chronic or acute medical conditions is influenced by a complex interaction of baseline psychological state, demographic characteristics, clinical…

arXiv cs.AI 04:00 UTC

arXiv:2610.10311v1 Announce Type: cross Abstract: Emerging computer hardware often trades reliability for energy efficiency; here we show that large-language models (LLMs) can be trained to tolerate this unreliability, and that rather than…

arXiv cs.AI 04:00 UTC

arXiv:2605.00556v2 Announce Type: replace-cross Abstract: Partial driving automation creates a tension: drivers remain legally responsible while being less active in control. Meaningful human control (MHC), a normative framework that can…

arXiv cs.CV 04:00 UTC

arXiv:2610.10436v1 Announce Type: new Abstract: Adversarial perturbations can alter the predictions of frozen vision-language models (VLMs) while leaving their confidence and image--text similarity patterns seemingly plausible. We…

arXiv cs.AI 04:00 UTC

arXiv:2610.09152v1 Announce Type: cross Abstract: Multilingual LLM benchmarks omit Slovak, a morphologically rich West Slavic language of five million speakers, or cover it only by machine translation. We present sk-bench, a native-first…

arXiv cs.LG 04:00 UTC

arXiv:2610.10057v1 Announce Type: new Abstract: With the rise of univariate time series foundation models (e.g., Sundial, Timer), initial efforts have been made to extend them to multivariate settings. However, these models mainly focus on…

arXiv cs.AI 04:00 UTC

arXiv:2610.09305v1 Announce Type: cross Abstract: Benchmarks for measuring the quality of action-conditioned world models are still evolving and shifting away from visual similarity-based metrics to action-semantic and physically-grounded…

arXiv cs.AI 04:00 UTC

arXiv:2610.09296v1 Announce Type: new Abstract: AI evaluation shapes the decisions of model providers, users, funders, and regulators. We argue that designing valid benchmarks requires contextualizing design choices in the dynamics of this…

arXiv cs.LG 04:00 UTC

arXiv:2610.09717v1 Announce Type: cross Abstract: Quantum kernel methods are leading candidates for a practical quantum advantage in machine learning, but assessing that potential requires two quantities usually reported separately: how…

arXiv cs.AI 04:00 UTC

arXiv:2606.08849v2 Announce Type: replace Abstract: Urban public transport disruptions require rapid response strategies, yet existing studies rarely provide a decision support framework to compare alternative disruption response solutions…

arXiv cs.LG 04:00 UTC

arXiv:2610.09304v1 Announce Type: cross Abstract: Facial movements convey subtle and important information that is critical for human social communication. Optical methods for face capture are difficult or impossible to use when the face…

arXiv cs.LG 04:00 UTC

arXiv:2610.09563v1 Announce Type: new Abstract: Effective traffic signal control (TSC) requires policies that respond to changing traffic demand and network conditions while meeting different control objectives. However, adapting existing…

arXiv cs.CV 04:00 UTC

arXiv:2604.01989v4 Announce Type: replace Abstract: While multimodal large language models demonstrate strong entity-level perception, faithfully grounding relational interactions between objects remains a persistent challenge. Although…

arXiv cs.LG 04:00 UTC

arXiv:2610.10379v1 Announce Type: new Abstract: Continual learning requires models to adapt to new domains and new classes while retaining prior knowledge. Many existing methods rely on continued optimization, using regularization, replay…

arXiv cs.LG 04:00 UTC

arXiv:2610.09549v1 Announce Type: new Abstract: And-Inverter Graphs (AIGs) are fundamental representations for logic synthesis and verification in Electronic Design Automation (EDA). As structured representations of complex digital…

arXiv cs.AI 04:00 UTC

arXiv:2610.10405v1 Announce Type: new Abstract: Monitoring the chain-of-thought of reasoning artificial intelligence (AI) models remains a key approach to detecting deception and other forms of misbehavior in such models. However, semantic…

arXiv cs.AI 04:00 UTC

arXiv:2609.12890v3 Announce Type: replace-cross Abstract: In autoregressive forecasting, long prediction rollouts provide distant supervision, but backpropagation through time (BPTT) carries gradients from those losses through many…

arXiv cs.AI 04:00 UTC

arXiv:2610.10506v1 Announce Type: new Abstract: Many of the questions now put to large language models have no correct answer to score against: what a policy is worth, which option a user should choose, how to weigh competing values…

arXiv cs.LG 04:00 UTC

arXiv:2610.09111v1 Announce Type: cross Abstract: Deterministic inference is essential for reliable and trustworthy machine learning. Prior studies of text generation have shown that changing factors such as batch size, batch composition…

arXiv cs.AI 04:00 UTC

arXiv:2610.09034v1 Announce Type: new Abstract: Multi-agent path planning (MAPP) in continuous environments often relies on roadmaps to balance safety and search efficiency. However, traditional roadmap generation methods, such as lattice…

arXiv cs.AI 04:00 UTC

arXiv:2610.09590v1 Announce Type: new Abstract: Long-running autonomous agents must reuse accumulated reasoning experience without allowing explicit historical memory and LLM context to grow indefinitely. However, existing memory…

arXiv cs.CL 04:00 UTC

arXiv:2610.10536v1 Announce Type: cross Abstract: Modern language models undergo reinforcement learning with verifiable rewards (RLVR) on top of already-trained checkpoints. A key promise of RLVR is the discovery of new reasoning…

arXiv cs.LG 04:00 UTC

arXiv:2601.20250v2 Announce Type: replace Abstract: Recently, flow-based generative models have shown superior efficiency compared to diffusion models. In this paper, we study rectified flow models, which constrain transport trajectories…

arXiv cs.AI 04:00 UTC

arXiv:2602.03317v2 Announce Type: replace-cross Abstract: Quantitative imaging methods, such as magnetic resonance fingerprinting (MRF), aim to extract interpretable pathology biomarkers by estimating biophysical tissue parameters from…

arXiv cs.CV 04:00 UTC

arXiv:2610.10391v1 Announce Type: new Abstract: End-to-end multi-object trackers have narrowed the gap with classical tracking-by-detection on association-difficult benchmarks. Yet they still make spatially implausible errors no classical…

arXiv cs.CL 04:00 UTC

arXiv:2610.09237v1 Announce Type: cross Abstract: Scientific studies of language agents need behavioral variables that support hypotheses across tasks and models. We formulate this research problem as learning and testing a hierarchy of…

arXiv cs.LG 04:00 UTC

arXiv:2610.10273v1 Announce Type: new Abstract: Despite its widespread use, Proximal Policy Optimization with clipping (PPO-Clip) remains difficult to tune, and the interactions among critic learning, clipping, and rollout reuse remain…

arXiv cs.LG 04:00 UTC

arXiv:2610.09136v1 Announce Type: new Abstract: Learning a directed acyclic graph (DAG) from observational data is a challenging combinatorial problem due to the exponential growth in the number of candidate parent-set configurations…