Knowledge catalogue
arXiv:2610.17320v1 Announce Type: new Abstract: Stochastic optimization models sequential decision-making under uncertainty, typically assuming known input distributions. When these distributions are
arXiv:2610.16226v1 Announce Type: cross Abstract: Network decision-making tasks, including adaptive bitrate streaming, load balancing, and congestion control, require policies to process heterogeneous
arXiv:2511.19548v2 Announce Type: replace Abstract: Neuroeconomics appears to offer welfare economics an evidential supplement, since neural data may help distinguish choices that express genuine pref
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:2610.15690v1 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: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:2610.15246v1 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:2610.14033v1 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:2610.15414v1 Announce Type: new Abstract: Multimodal remote sensing image generation emerges as a promising paradigm for recovering complete and complementary observations from heterogeneous and
arXiv:2610.17424v1 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: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:2610.18188v1 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:2610.15177v1 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: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: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:2407.04224v2 Announce Type: replace Abstract: Numerous locomotion controllers have been designed based on Reinforcement Learning (RL) to facilitate blind quadrupedal locomotion traversing challe
arXiv:2610.17900v1 Announce Type: cross Abstract: Extended chain-of-thought reasoning improves problem-solving performance but increases inference cost and latency, motivating more accurate answers wi
arXiv:2610.18443v1 Announce Type: new Abstract: The fidelity of teleoperated demonstrations used for imitation learning is determined by how faithfully a robot hand can replicate the operator's postur
arXiv:2610.16103v1 Announce Type: new Abstract: Generalist visual-navigation policies tell a robot which direction to go but not how far. A separate lifting step is needed at deployment to convert the
arXiv:2610.17281v1 Announce Type: new Abstract: SE(3)-equivariance provides a useful geometric inductive bias for visuomotor policies, encoding that actions covary with rigid transformations of the ob
arXiv:2610.15491v1 Announce Type: new Abstract: Active debris removal requires a servicer spacecraft to approach a non-cooperative tumbling object, capture it, and arrest its rotation. This sequence i
arXiv:2610.15173v1 Announce Type: cross Abstract: We investigate whether a physics foundation model (PFM) pretrained for PDE forecasting can be repurposed for closed-loop fluid-flow control. We constr
arXiv:2610.14713v1 Announce Type: new Abstract: While diffusion models achieve impressive image generation capabilities, they suffer from high computational costs, implausible artifacts, and limited a
arXiv:2610.15548v1 Announce Type: new Abstract: Quadruped robots deployed for inspection and field missions must cross heterogeneous terrain, from stairs, slopes, and gaps to high platforms, stepping
arXiv:2610.15537v1 Announce Type: cross Abstract: Typed decision interfaces restrict models to predefined actions, yet schema-valid choices can still trigger policy-violating state changes. Evaluating
arXiv:2610.17788v1 Announce Type: new Abstract: Distributional critics model the full return distribution, providing richer signals for exploration and risk-sensitive control. Recent work has shown th
arXiv:2610.14864v1 Announce Type: new Abstract: Action chunking improves temporal coherence in visuomotor imitation learning by jointly predicting sequences of future actions. However, many existing p
arXiv:2610.14001v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) uses a self-teacher conditioned on privileged information to turn the sparse outcome signal of reinforcement learning
arXiv:2610.14704v1 Announce Type: new Abstract: Coupling a pretrained vision-language model (VLM) with a diffusion or flow-matching action expert has become the mainstream vision-language-action (VLA)
arXiv:2610.18331v1 Announce Type: cross Abstract: Do multilingual language models learn a universal internal geometry for color, and is it perceptually grounded or primarily linguistic? We decompose c
arXiv:2604.02341v2 Announce Type: replace Abstract: Mathematical reasoning in large language models has improved substantially with reinforcement learning using verifiable rewards, where final answers
arXiv:2602.21189v3 Announce Type: replace Abstract: Pass@k is a widely used performance metric for verifiable large language model tasks, including mathematical reasoning, code generation, and short-a
arXiv:2610.17667v1 Announce Type: new Abstract: Diffusion models and Flow Matching can represent flexible distributions over robot actions, but many reinforcement learning algorithms also require the
arXiv:2610.14737v1 Announce Type: new Abstract: Training language agents on long-horizon interactive tasks is challenging because sparse terminal rewards provide weak credit signals for intermediate a
arXiv:2610.14832v1 Announce Type: new Abstract: This paper presents a reproducibility study of ``Boosting the Visual Interpretability of CLIP via Adversarial Fine-Tuning'', published at ICLR 2025, whi
arXiv:2610.16309v1 Announce Type: new Abstract: Despite rapid progress, generalist robot policies remain brittle during execution. Reliable deployment therefore requires runtime monitoring that provid
arXiv:2610.15675v1 Announce Type: cross Abstract: Quantization lowers deployment costs of vision-language-action (VLA) policies but can compromise task completion. Across five VLA models and 4,050 rea
Recursive self-improvement is one of the most discussed ideas in AI right now. RSI-Anything measures it in code repair, GUI agents, lab planning, and chemistry. They find that the lab-planning score m
arXiv:2610.14415v1 Announce Type: new Abstract: A long-standing goal in robotics is to develop generalist robots that can perform tasks across a wide range of settings, flexibly specified with images
arXiv:2606.13169v2 Announce Type: replace Abstract: This paper proposes a novel regularization design to effectively smooth policy functions in reinforcement learning. While regularization that enhanc
arXiv:2610.16632v1 Announce Type: new Abstract: Memory-based long-video generation aims to combine user control with long-range visual consistency. We organize this process into three functional compo
arXiv:2610.15867v1 Announce Type: new Abstract: Collision-resilient airframes allow quadrotors to survive impacts, but do not ensure autonomous post-collision recovery. Innovation gating in stock onbo
arXiv:2610.18804v1 Announce Type: new Abstract: Raw image intensities are a poor surrogate for similarity across images in correspondence problems. Further, while auxiliary segmentation labels can pro
arXiv:2610.15237v1 Announce Type: new Abstract: Autonomous Surface Vehicles (ASVs) have been increasingly deployed to perform different kinds of maritime tasks in recent years, which motivates the nee
arXiv:2610.18186v1 Announce Type: new Abstract: Large-scale applications of lifelong multi-agent path finding (LMAPF) call for computationally inexpensive movement decisions under changing traffic con
arXiv:2610.14042v1 Announce Type: new Abstract: A longstanding goal for robot reinforcement learning (RL) is that robots learn from their own physical experience, as humans and animals do. A key obsta
arXiv:2610.16524v1 Announce Type: new Abstract: Market making under realistic order-flow dynamics is challenging due to the clustered, self-exciting nature of order arrivals, which are naturally model
arXiv:2610.18055v1 Announce Type: cross Abstract: We study stochastic bandits without knowledge of reward scales or tail parameters. Almost-sure regret guarantees describe eventual learning but do not
arXiv:2610.17722v1 Announce Type: cross Abstract: Quantum Machine Learning (QML) has a theoretical advantage over classical algorithms for specific synthetic data that is computationally hard. However
arXiv:2610.14102v1 Announce Type: cross Abstract: Sparse-view cone-beam computed tomography (CBCT) is severely under-constrained by limited X-ray projections. Learned reconstruction can provide comple
arXiv:2610.14035v1 Announce Type: new Abstract: Contact-rich manipulation requires a robot to be precise in free space to establish the intended contacts, and compliant once in contact to avoid excess
arXiv:2610.18163v1 Announce Type: new Abstract: Robot manipulation policies trained through imitation learning commonly rely on costly demonstrations recorded in one task direction and at one temporal
arXiv:2610.14500v1 Announce Type: new Abstract: Many widely used activation functions, including ReLU, GELU, Swish, and Sigmoid, produce predominantly positive outputs, resulting in a nonzero post-act
arXiv:2610.15681v1 Announce Type: new Abstract: Parametric Computer-Aided-Design (CAD) modeling from human intent remains challenging, particularly during the conceptual design stage, where design goa
arXiv:2610.18598v1 Announce Type: new Abstract: Multimodal LLMs are typically trained by first aligning a vision encoder with a language model via projector training on large image-caption datasets, f
arXiv:2610.16666v1 Announce Type: new Abstract: Vision-language models (VLMs) like CLIP have shown great success in image tasks, however, applying CLIP to open-vocabulary video recognition poses chall
arXiv:2610.14572v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards improves the reasoning capabilities of large language models, but remains computationally expensive and s
arXiv:2610.17579v1 Announce Type: cross Abstract: Inference-time alignment steers diffusion models toward downstream objectives without costly fine-tuning, but existing methods typically optimize expe
arXiv:2610.18699v1 Announce Type: new Abstract: Evaluating robot policies before deployment typically requires producing new trajectories through real-world execution, simulators, or learned world mod