Knowledge catalogue
arXiv:2610.15223v1 Announce Type: cross Abstract: Recent observations that deep learning models train at the edge of stability have renewed interest in understanding stability properties of classical
arXiv:2601.07535v2 Announce Type: replace-cross Abstract: Clustering with bandit feedback refers to the problem of partitioning the arms of an N-armed stochastic bandit according to their underlying d
arXiv:2610.16417v1 Announce Type: new Abstract: Remote identity verification assumes that a camera stream shows a live person, yet public real-time face-swap tools can replace that person before the s
arXiv:2610.18412v1 Announce Type: new Abstract: Prompt-based adaptation offers several ways to specialize a frozen language model, ranging from natural-language prompt optimization to learned continuo
arXiv:2603.19233v2 Announce Type: replace Abstract: A fine-tuned Vision-Language-Action (VLA) policy can easily place the alphabet soup in the basket on command, just as it saw during fine-tuning. How
arXiv:2610.16452v1 Announce Type: new Abstract: Explainable face forgery detection requires not only correct judgments but also forensic evidence supported by the input image. However, training cues a
arXiv:2610.15690v1 Announce Type: cross Abstract: We establish uniform score bounds and Lipschitz continuity for truncated Gaussian, Cauchy, Boltzmann, and softmax policies under explicitly stated par
arXiv:2508.10688v3 Announce Type: replace Abstract: Single-image novel view synthesis requires viewpoint-dependent structural changes while retaining source-scene information and inferring unobserved
This model is a 74B parameter, 9B-active-parameter mixture-of-experts (MoE) model, packed into 24GB using 2-bit quantization with advanced quantization-aware training techniques to retain quality. It
arXiv:2610.14379v1 Announce Type: new Abstract: Retargeting human demonstrations into dynamically feasible dexterous hand trajectories requires resolving complex contact physics, yet current methods e
arXiv:2610.18564v1 Announce Type: new Abstract: Aerial map matching provides position observations for navigation, but a position error alone does not determine how an observation should be weighted.
arXiv:2610.14191v1 Announce Type: new Abstract: Forecasting tissue deformation from future instrument motion could support predictive planning and increasingly autonomous surgical systems. We study th
arXiv:2610.16895v1 Announce Type: cross Abstract: LLMs are used as high-level controllers for embodied agents, but it remains unclear whether they support collaborative reasoning, such as anticipating
arXiv:2610.15246v1 Announce Type: new Abstract: Tool-using agents alternate between model generation and tool execution, waiting for each tool call to complete before starting the next generation. Thi
arXiv:2610.17688v1 Announce Type: new Abstract: Occupancy world models provide a structured, metric representation of future driving scenes, making them a promising basis for end-to-end autonomous dri
arXiv:2610.15518v1 Announce Type: new Abstract: Probabilistic ocean modeling is essential for risk-aware marine operations, climate analysis, and scientific decision-making, where downstream decisions
arXiv:2610.16586v1 Announce Type: new Abstract: Generating accurate 3D molecules requires jointly determining a variable number of atoms, their identities, and geometry across spatial scales: global s
London-based offensive security startup CodeWall Ltd. officially launched today with 4 million in new funding to give enterprises such as banks autonomous artificial intelligence agents that attack th
arXiv:2610.14033v1 Announce Type: new Abstract: Recent progress in learned whole-body controllers for humanoid robots has enabled robust free-space motion by tracking kinematic targets such as joint o
arXiv:2610.16135v1 Announce Type: cross Abstract: Omni-modal large language models (Omni-LLMs) extend LLMs to process heterogeneous modalities (e.g., vision, audio, and IMU signals) alongside language
arXiv:2610.18323v1 Announce Type: new Abstract: Practical remote sensing applications often require both understanding and generation capabilities for the same geographic scene. However, most existing
arXiv:2610.18829v1 Announce Type: new Abstract: With the rapid development of multimodal large language models (MLLMs), evaluating their video understanding capabilities has become increasingly import
arXiv:2510.17719v3 Announce Type: replace Abstract: Adherent raindrops on camera lenses are a pervasive source of real-world image degradation, undermining outdoor visual perception for downstream app
arXiv:2610.15414v1 Announce Type: new Abstract: Multimodal remote sensing image generation emerges as a promising paradigm for recovering complete and complementary observations from heterogeneous and
arXiv:2610.18714v1 Announce Type: cross Abstract: Non-clashing teaching minimizes teaching complexity among models satisfying the Goldman--Mathias collusion-avoidance criterion. While the Vapnik--Cher
arXiv:2607.11432v2 Announce Type: replace Abstract: We study reinforcement learning (RL) from pairwise human-generated trajectory comparisons. We generalize preference-based RL by formalizing a novel
arXiv:2610.17424v1 Announce Type: new Abstract: Respecting a-priori known symmetries of underlying data is a key principle in designing efficient neural architectures. Convolutional neural networks ar
arXiv:2610.14131v1 Announce Type: cross Abstract: In the machine learning community, the reinforcement-learning-driven reasoning process has been intensively studied since around 2025. In this article
arXiv:2610.17451v1 Announce Type: new Abstract: Self-supervised polysomnography foundation models (PSG FMs) aim to capture clinically useful information beyond sleep staging, yet are rarely compared w
arXiv:2610.16815v1 Announce Type: cross Abstract: Calibration has been extensively studied for classifiers, but remains largely unexplored for crowdsourcing aggregation methods, which are increasingly
arXiv:2610.14344v1 Announce Type: new Abstract: Scaling deep learning models efficiently requires predictable performance transfer across compute regimes. Establishing reliable hyperparameter transfer
arXiv:2602.08302v2 Announce Type: replace Abstract: Delayed generalization, where training accuracy becomes nearly perfect substantially before test accuracy, has often been studied in the context of
arXiv:2610.18727v1 Announce Type: new Abstract: Natural Language Autoencoders (NLAs) are proposed as oversight tools for language models: an Activation Verbaliser (AV) writes an English explanation of
arXiv:2610.18333v1 Announce Type: cross Abstract: Random features provide a standard approach to scaling kernel methods to large datasets by approximating the kernel with a finite-dimensional feature
arXiv:2610.17347v1 Announce Type: new Abstract: We revisit the statistical mechanics of Transformer attention via modern Hopfield models. We present a free-energy formalism to characterize parameter r
arXiv:2610.15078v1 Announce Type: new Abstract: Machine-learned interatomic potentials (MLIPs) accelerate molecular dynamics (MD) simulations by learning the energies and forces that govern atomic mot
arXiv:2506.15660v2 Announce Type: replace-cross Abstract: We consider the problem of estimating the spectral norm of a matrix using only matrix-vector products. We propose a new Counterbalance estimat
arXiv:2610.16798v1 Announce Type: new Abstract: Chain-of-Thought (CoT) enables transformers to solve complex reasoning tasks by generating intermediate reasoning steps. Despite strong empirical succes
arXiv:2610.14074v1 Announce Type: new Abstract: Large language models typically support different inference budgets through separate model sizes or fixed compute configurations. In multi-turn interact
arXiv:2610.16179v1 Announce Type: new Abstract: Latte art is a complex task requiring dexterity and precision, making it a challenging and commercially relevant task. A one-shot learning system is emp
arXiv:2508.06163v2 Announce Type: replace-cross Abstract: Merging multiple task-specific fine-tuned checkpoints into a single multi-task model provides an attractive alternative to joint multi-task tr
arXiv:2610.14687v1 Announce Type: new Abstract: Many physical systems exhibit one-way coupling: exogenous fields such as medium density or obstacle geometry influence the dynamics without being affect
arXiv:2610.18188v1 Announce Type: new Abstract: Learning robot policies from demonstrations is often limited by the cost of collecting diverse, high-quality expert data. While an appealing alternative
arXiv:2610.16219v1 Announce Type: cross Abstract: Time series (TS) anomaly detection (AD) lacks a universal detector, with the best choice determined by the series rather than by the algorithm. Existi
arXiv:2610.16464v1 Announce Type: cross Abstract: We study online individualized treatment selection when only the outcome under the assigned treatment is observed. Our objective is to preferentially
arXiv:2607.17614v2 Announce Type: replace-cross Abstract: Recent advances in deep-learning-based nonlinear system identification have led to encoder-based estimation of neural state-space (ANN-SS) mod
arXiv:2610.17203v1 Announce Type: new Abstract: Large language models can answer the same question in different styles, but users' preferred styles are hidden and vary across users and questions. We s
arXiv:2610.15177v1 Announce Type: new Abstract: As agentic AI systems take on increasingly complex and consequential tasks, securing them against prompt injection becomes critical. Existing defenses o
arXiv:2502.04356v2 Announce Type: replace-cross Abstract: In response to the success of proprietary Large Language Models (LLMs), there is a growing interest in developing open, non-proprietary LLMs a
arXiv:2610.17656v1 Announce Type: new Abstract: Reliable video reasoning requires models to produce correct answers and expose supporting visual evidence. Open-o3-Video enables verifiable reasoning by
OpenAI is in the news again. This time, it’s due to a recent incident involving corporate espionage. According to a statement the AI lab released on 13th October, the company discovered a “sophisticat
OpenAI Group PBC called in the Federal Bureau of Investigation to come and arrest one of its employees after a “sophisticated recording device” was discovered hidden within the artificial intelligence
arXiv:2610.17143v1 Announce Type: new Abstract: Large language model (LLM)-based multi-agent systems are increasingly applied across diverse domains, yet different applications require different forms
arXiv:2610.14157v1 Announce Type: cross Abstract: We introduce OpenMobile-2, a near-frontier mobile agent with fully open training environments and recipes. We make three key advances: (1) Diverse env
arXiv:2610.18210v1 Announce Type: new Abstract: This chapter provides a mathematical introduction to operator surrogates, which are finite-parametric maps approximating complex (typically nonlinear) o
arXiv:2610.14022v1 Announce Type: new Abstract: On-policy distillation (OPD) improves language-model by supervising a student on prefixes sampled from its own policy, but its supervision remains confi
arXiv:2508.12943v3 Announce Type: replace-cross Abstract: Public service systems in many African regions suffer from delayed emergency response and spatial inequity, causing avoidable suffering. This
arXiv:2610.18258v1 Announce Type: new Abstract: We study stochastic contextual bandits with an unknown context-lumpable structure. The S contexts are partitioned into r blocks, and every arm has the s
arXiv:2312.09877v3 Announce Type: replace Abstract: This paper considers the setting in which local Mixture-of-experts (MoE) models are fitted independently on distributed datasets and must be combine
arXiv:2610.16560v1 Announce Type: new Abstract: PAC-Bayesian generalization bounds are among the strongest distribution-dependent guarantees in statistical learning and are typically expressed in term