Knowledge catalogue
arXiv:2609.15035v1 Announce Type: new Abstract: Short-term photovoltaic power forecasting requires models to represent regular solar cycles and weather-driven fluctuations whose importance changes wit
How often do AI agents cheat? We’re releasing CheatBench, a reward gaming evaluation spanning math, coding, knowledge work, visual tasks, and more. After Hugging Face, AI companies tried to address th
arXiv:2609.15320v1 Announce Type: new Abstract: Volume-based multimodal retrieval jointly scores a text query with a candidate's video, audio, and subtitle embeddings. While this approach captures hig
arXiv:2609.13768v1 Announce Type: new Abstract: Multi-hop question answering often fails when retrieval treats evidence as isolated matches to the original question, since the facts needed to answer a
arXiv:2609.15005v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) policies perform robot manipulation tasks using multimodal inputs such as visual observations, proprioceptive states, and
arXiv:2510.13311v2 Announce Type: replace Abstract: Unsupervised tabular anomaly detection is a critical task with applications spanning offensive language detection, network security, and quality con
New York Times: Jensen Huang took a surprise call from President Trump onstage at the All-In Summit on Monday in LA, where the two dismissed fears of an AI takeover — Mr. Trump called Jensen Huang, Nv
arXiv:2609.15770v1 Announce Type: new Abstract: Light detection and ranging (LiDAR) remains less explored than RGB-D sensing for perceptive legged locomotion, and existing LiDAR-based approaches often
arXiv:2505.08123v2 Announce Type: replace-cross Abstract: Multi-material decomposition (MMD) enables quantitative reconstruction of tissue compositions in the human body, supporting a wide range of cl
arXiv:2609.14083v1 Announce Type: cross Abstract: Variable importance scores from tree-based methods such as random forests favor continuous predictors over categorical ones. We present a theoretical
arXiv:2609.14636v1 Announce Type: cross Abstract: On-policy distillation (OPD) has become a standard approach for transferring capabilities from large teachers to compact students. Its cost, however,
arXiv:2609.14558v1 Announce Type: new Abstract: Autonomous Surface Vehicles (ASVs) are increasingly expected to operate in ports and harbour environments, where operators may specify navigation target
arXiv:2609.13235v1 Announce Type: cross Abstract: Networked manipulation endpoints couple perception to actuation across compute- and bandwidth-limited links, yet commonly exchange dense geometric sta
arXiv:2609.15883v1 Announce Type: cross Abstract: Offline reinforcement learning aims to learn a policy solely from fixed datasets, which often contain multimodal action distributions. Flow policies c
arXiv:2609.14299v1 Announce Type: new Abstract: Predicting under an acquisition budget requires choosing feature groups whose value can depend on later queries. O-MPAC transfers finite-horizon risk-co
arXiv:2512.04068v3 Announce Type: replace Abstract: To handle underspecified or ambiguous queries, AI assistants need a policy for managing their uncertainty to determine (a) when to guess the user in
arXiv:2609.15447v1 Announce Type: new Abstract: Combining aerial thrust with spring-loaded hopping makes monopedal quadcopters promising for locomotion over complex terrain, but heuristic proportional
arXiv:2609.14207v1 Announce Type: new Abstract: We propose to finetune vision-language models to generate more pragmatically optimal referring expressions by transforming observations of incremental l
arXiv:2609.14972v1 Announce Type: new Abstract: We study continuous-time and possibly high-dimensional stochastic control problems where drift coefficients and running reward functions are unknown. Du
arXiv:2609.15113v1 Announce Type: cross Abstract: As robotic systems grow more general, legal norms are needed to integrate them into society. This paper extends the isomorphism problem of aligning le
arXiv:2609.13845v1 Announce Type: cross Abstract: World models trained with joint-embedding predictive architectures learn compact, structured latent representations from physical interaction, yet pla
arXiv:2609.15162v1 Announce Type: new Abstract: Diffusion Policy (DP) is a powerful Learning from Demonstration (LfD) method for robotic manipulation, yet it suffers from discontinuous and non-smooth
arXiv:2609.14138v1 Announce Type: cross Abstract: As LLM agents become integrated into increasingly complex workflows, they must continually acquire new capabilities while retaining competence on prev
arXiv:2609.13195v1 Announce Type: cross Abstract: Large Audio-Language Models (LALMs) have recently shown strong capabilities in speech understanding and question answering (QA), but they also inherit
arXiv:2606.13989v2 Announce Type: replace-cross Abstract: Recent alignment-free non-autoregressive (NAR) text-to-speech (TTS) models formulate synthesis as a conditional infilling task, bypassing expl
arXiv:2603.02504v3 Announce Type: replace Abstract: Large Language Models (LLMs) achieve strong performance on natural language tasks but remain unreliable in mathematical reasoning, frequently genera
arXiv:2609.15707v1 Announce Type: new Abstract: Powerful technologies labeled ``AI''-without sufficient epistemic caution-are already reshaping political and private life, bringing both new dangers an
arXiv:2512.16565v2 Announce Type: replace-cross Abstract: Reinforcement learning has gained attention for modern Large Language Model post-training. The actor-only variants of Proximal Policy Optimiza
arXiv:2609.14327v1 Announce Type: new Abstract: Variance penalization is a principled approach to risk-sensitive reinforcement learning (RL) that explicitly trades expected return for policy stability
arXiv:2609.15051v1 Announce Type: cross Abstract: Training prompts in online reinforcement learning (RL) differ substantially in how informative they are for the current policy: some are already satur
arXiv:2609.13244v1 Announce Type: cross Abstract: We study dark manipulation: after a brief lit Write encodes z0 = Enc(rgb), a policy pi(z) and open-loop dynamics f(z,a) complete contact-rich skills w
arXiv:2609.15198v1 Announce Type: new Abstract: Contact-rich manipulation benefits from tactile feedback, yet physical tactile sensors introduce hardware, calibration, synchronization, and maintenance
arXiv:2404.06023v3 Announce Type: replace-cross Abstract: Motivated by Q-learning, we study nonsmooth contractive stochastic approximation (SA) with constant stepsize. We focus on two important classe
arXiv:2609.14469v1 Announce Type: new Abstract: Accurate 3D localization of unmanned aerial vehicles (UAVs) remains challenging for existing multimodal approaches due to sparse LiDAR geometry, modalit
arXiv:2609.14868v1 Announce Type: new Abstract: We present a primitive-informed sampling-based model predictive control (MPC) framework for multi-fingered dexterous manipulation. Sampling-based MPC av
arXiv:2609.15643v1 Announce Type: new Abstract: Flow-matching diffusion models have recently emerged as a strong paradigm for high-fidelity visual generation. However, their prohibitively high fine-tu
arXiv:2512.08463v2 Announce Type: replace Abstract: We study how privileged information about a physical system affects the discovery of high-performing policies when training a reinforcement learning
arXiv:2609.14878v1 Announce Type: new Abstract: Real-world reinforcement learning (RL) offers a promising route to dexterous manipulation policies that can adapt directly from physical interaction, bu
arXiv:2609.15296v1 Announce Type: new Abstract: Universal multimodal embedding (UME) learns unified representations across modalities, enabling a single model to support diverse retrieval tasks. Recen
arXiv:2609.13425v1 Announce Type: cross Abstract: Training diffusion models with multiple rewards requires distinguishing user preference from reward informativeness. User preference determines how mu
arXiv:2609.13672v1 Announce Type: new Abstract: AI agents can be interrupted while editing files, calling tools, or carrying out multi-step tasks. Restarting repeats completed work, but continuing fro
arXiv:2609.15313v1 Announce Type: cross Abstract: Autoregressive generation of interleaved text and acoustic tokens is a common approach to spoken-response generation in speech large language models.
arXiv:2609.15123v1 Announce Type: cross Abstract: Flow-based policies offer an expressive representation for online reinforcement learning, but conventional flow matching requires samples drawn from t
arXiv:2609.13791v1 Announce Type: new Abstract: Recognition pipelines typically adopt a restore-then-recognize workflow, yet decades of experience show that generating visually pleasing images seldom
arXiv:2609.14485v1 Announce Type: new Abstract: Retrieval-Guided Fine-Tuning (RAG-FT) incorporates retrieved data directly into the training objective, but the statistical consequences of noisy retrie
arXiv:2609.14633v1 Announce Type: new Abstract: Recent advances in data-driven robot manipulation policies have substantially improved task execution and generalization. However, real-world deployment
arXiv:2609.13851v1 Announce Type: cross Abstract: Post-training vision-language-action (VLA) models for specific robots and tasks requires in-domain demonstrations, yet collecting diverse robot data i
arXiv:2609.15488v1 Announce Type: new Abstract: Machine learning models process large amounts of data, and Principal Component Analysis (PCA) is a widely used technique to reduce the dimensionality of
arXiv:2609.13545v1 Announce Type: cross Abstract: Learning-based adaptive control of robotic manipulators with non-observable friction memory has been addressed by attention- based meta-controllers wh
arXiv:2609.15639v1 Announce Type: new Abstract: Part-level control is essential for modern 3D asset creation, where objects are frequently edited, reused, animated, or fabricated through their individ
arXiv:2609.13966v1 Announce Type: cross Abstract: Video highlight detection aims to identify temporally important segments that capture the most informative or engaging events in a video. Reliable pre
arXiv:2609.14902v1 Announce Type: cross Abstract: Shapley value (SV)-based methods are the prevailing framework for feature attribution in machine learning, yet existing population-level Shapley estim
arXiv:2609.15825v1 Announce Type: new Abstract: A self-supervised encoder is trained once, frozen, and reused through lightweight probes on tasks nobody named at training time; the practitioner's ques
arXiv:2609.14504v1 Announce Type: new Abstract: Geophysical data collected from active field sites are often contaminated by complex and heterogeneous noise, obscuring weak seismic events, and complic
arXiv:2609.14151v1 Announce Type: cross Abstract: Steering language models using a set of contrastive representations has been a canonical and computationally efficient method for controlling model be
arXiv:2609.14647v1 Announce Type: cross Abstract: Robots, and humanoid robots in particular, are increasingly competent at individual behaviors, each obtained by training a specialized controller. A s
arXiv:2609.14922v1 Announce Type: cross Abstract: For constant-stepsize stochastic approximation (SA), the iterates converge in distribution to a stationary law that depends on the stepsize alpha. Ste
arXiv:2609.15509v1 Announce Type: new Abstract: Recent advances in robot imitation learning have produced visuomotor policies that predict actions directly from visual observations. Yet visually simil
arXiv:2609.13309v1 Announce Type: cross Abstract: Protocol optimization in computed tomography (CT) aims to improve diagnostic image quality while reducing radiation dose, but the interdependence of a
arXiv:2609.15032v1 Announce Type: new Abstract: Live free-viewpoint visualization of real humans is critical for immersive communication and interactive digital experiences. Existing methods either re