Knowledge catalogue
arXiv:2607.05735v1 Announce Type: cross Abstract: Infinite-width limits are a standard way to reason about neural networks, but it is not automatic that the limiting learner has the same complexity-th
arXiv:2607.06461v1 Announce Type: cross Abstract: While recent Large Language Model (LLM)-based Text-to-Speech (TTS) systems have achieved remarkable naturalness, they predominantly rely on implicit e
arXiv:2607.06163v1 Announce Type: cross Abstract: Foundation Models for Electronic Health Records (FEMRs) are pretrained on large-scale structured patient data, enabling them to convert longitudinal p
arXiv:2607.03190v1 Announce Type: cross Abstract: Scenario-based transportation analysis specifies future assumptions through aggregate population targets, whereas generative population synthesis mode
arXiv:2607.04574v1 Announce Type: cross Abstract: For LLM agents, supervised fine-tuning is not only about teacher labels' quality, but also about which interaction contexts those labels condition on.
arXiv:2504.11907v3 Announce Type: replace Abstract: Autonomous exploration of cluttered environments requires efficient exploration strategies that guarantee safety against potential collisions with u
arXiv:2607.03385v1 Announce Type: cross Abstract: Policy learning has received substantial attention with the goal of learning policies from observational data for decision-making. A majority of work
arXiv:2606.12502v2 Announce Type: replace-cross Abstract: We propose that value -- the quantity goal-directed agents create, destroy, and exchange -- is a lawful structural quantity in the same catego
arXiv:2607.04367v1 Announce Type: new Abstract: In the development of cooking robots, mastering the task of cutting is crucial. A significant challenge lies in the diverse properties of food, which ne
arXiv:2607.04056v1 Announce Type: cross Abstract: Modern supply chains span diverse operational environments, ranging from e-commerce distribution networks to customized production-to-order manufactur
arXiv:2607.02944v1 Announce Type: cross Abstract: We propose PRECEDE, a precedent-guided co-scientist for side-effect-aware drug redesign that revises a parent compound to mitigate a specified side ef
arXiv:2606.16933v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) systems often degrade when operating conditions differ from those previously encountered, reflecting distributiona
arXiv:2602.19107v3 Announce Type: replace Abstract: Robotaxis are emerging as a promising form of urban mobility, but removing human drivers fundamentally reshapes passenger-vehicle interaction and ra
arXiv:2607.04162v1 Announce Type: cross Abstract: Open-ended tabletop manipulation requires agents to not only understand natural language but also adapt to dynamic environments and execution failures
arXiv:2607.03126v1 Announce Type: cross Abstract: Reinforcement Learning (RL) has substantially improved the reasoning ability of large language models (LLMs), but sparse outcome rewards still make to
arXiv:2603.08457v2 Announce Type: replace-cross Abstract: Robust single-vessel tracking from fixed coastal platforms is hindered by modality-specific degradations: cameras suffer from illumination and
arXiv:2607.05272v1 Announce Type: cross Abstract: Inference serving systems must balance throughput and latency under bursty, heterogeneous workloads, yet the industry standard remains static batching
arXiv:2509.22851v4 Announce Type: replace-cross Abstract: Margin-based optimization is fundamental to improving generalization and robustness in classification tasks. In the context of reward model le
arXiv:2512.14991v2 Announce Type: replace Abstract: We study reinforcement learning for controlled diffusion processes with unbounded continuous state spaces, bounded continuous actions, and polynomia
arXiv:2607.02572v1 Announce Type: cross Abstract: In multi-source image fusion scenarios, heterogeneous inputs are typically driven by distinct generative mechanisms and can be viewed as a composition
arXiv:2607.03454v1 Announce Type: cross Abstract: In this paper, we propose Adversarial Dynamics Priors (ADP) for perturbation-resilient humanoid locomotion control. Existing motion prior-based method
arXiv:2509.17255v2 Announce Type: replace-cross Abstract: We present the first language-model-driven agentic artificial intelligence (AI) system to autonomously execute multi-stage physics experiments
arXiv:2607.03516v1 Announce Type: cross Abstract: Enterprise artificial intelligence is moving from isolated experimentation toward operational dependency across copilots, retrieval-augmented generati
arXiv:2607.03528v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as critical decision-making components in high-stakes real-world AI systems, rendering LLM reli
arXiv:2607.03049v1 Announce Type: new Abstract: Fast estimation of the size of the largest overlap between tables enables blocking and query-by-table retrieval in large table repositories. The first a
arXiv:2512.11797v2 Announce Type: replace-cross Abstract: The collection of large-scale and diverse robot demonstrations remains a major bottleneck for imitation learning, as real-world data acquisiti
arXiv:2607.03132v1 Announce Type: new Abstract: Deep reinforcement learning (DRL) in industrial control often suffers from lag and overshoot due to purely reactive control based on the current trackin
arXiv:2607.04303v1 Announce Type: new Abstract: Learning-based stereo matching models struggle in underwater environments due to scarce in-domain data and the difficulty of extracting discriminative c
arXiv:2602.21534v3 Announce Type: replace Abstract: Agentic reinforcement learning (ARL) has rapidly gained attention as a promising paradigm for training agents to solve complex, multi-step interacti
As the @UN’s Global Dialogue on AI Governance wraps up today, I’ve been encouraged by the discussions surrounding AI and its implications for global collaboration and policymaking. I’m hopeful that we
arXiv:2607.02686v1 Announce Type: new Abstract: Reinforcement learning agents operating under partial observability must act on incomplete information, making them natural candidates for guidance from
At UMA, we build and own the full stack, from hardware to software. This allows us to bake safety in at all levels, rather than bolt it on as an afterthought. Because trust is everything when robots s
arXiv:2607.04837v1 Announce Type: new Abstract: Large-scale humanoid motion-tracking controllers are commonly improved by reallocating training effort: difficult motions are sampled more often, isolat
arXiv:2607.04590v1 Announce Type: new Abstract: Pairwise human comparisons are a primary interface through which modern AI systems learn human preferences. RLHF and related alignment pipelines typical
arXiv:2605.11404v2 Announce Type: replace Abstract: Large language models (LLMs) can simulate human-like reasoning and decision-making in individual agents. LLM-powered multi-agent systems (MAS) combi
arXiv:2607.04311v1 Announce Type: new Abstract: Subject-driven and multi-element video generation are central to controllable video synthesis, but existing methods still struggle to preserve identity
arXiv:2607.04433v1 Announce Type: cross Abstract: The rapid integration of large language model-based agents into recommender systems has driven a shift from static, ranking-based pipelines toward aut
arXiv:2604.03329v2 Announce Type: replace-cross Abstract: Automatic violence detection from video is challenging because violent interactions may be distant, occluded, or only partially visible. Audio
arXiv:2607.02671v1 Announce Type: cross Abstract: Benign overfitting and double descent have come to shape our understanding of generalization in deep learning, establishing that overfitting is not on
arXiv:2607.03453v1 Announce Type: cross Abstract: Inference-time alignment methods, such as Best-of-N, offer a flexible alternative to training-based alignment by using reward models to select high-qu
arXiv:2603.06576v2 Announce Type: replace-cross Abstract: The integration of Large Language Models (LLMs) into autonomous driving has attracted growing interest for their strong reasoning and semantic
arXiv:2607.03017v1 Announce Type: new Abstract: The aging global population drives demand for assistive robots, yet the safety risks and costs of physical testing make Human-in-the-Loop (HITL) simulat
arXiv:2607.05052v1 Announce Type: cross Abstract: Human value detection is commonly formulated as sentence-level multi-label classification over the 19 refined Schwartz values, typically predicted as
arXiv:2607.03163v1 Announce Type: new Abstract: Generalizable robot manipulation requires stable 3D understanding of functional object parts, such as handles, tool heads, openings, and graspable regio
arXiv:2607.04249v1 Announce Type: new Abstract: Precise medical image segmentation is crucial for clinical diagnosis and treatment planning, yet relies heavily on expensive expert annotations. Semi-su
When we first made BGP route policies for Cloud Router generally available over a year ago, our goal was to give network administrators deep, programmable control over how network paths are evaluated
arXiv:2607.02643v1 Announce Type: new Abstract: Diffusion-based generative models have transformed visual content synthesis, yet they remain vulnerable to unauthorized usage and lack reliable attribut
arXiv:2607.02915v1 Announce Type: cross Abstract: In many scientific and engineering domains, maximizing discovery within a limited sampling budget demands strategic, observation-guided exploration. W
arXiv:2601.18253v2 Announce Type: replace-cross Abstract: Accurate evaluation of user satisfaction is critical for iterative development of conversational AI. However, for open-ended assistants, tradi
arXiv:2607.03748v1 Announce Type: new Abstract: Unified multi-modal models (UMMs) have shown promising interleaved text-image reasoning capabilities, yet effectively optimizing such multi-turn generat
arXiv:2607.03510v1 Announce Type: cross Abstract: Enterprise artificial intelligence is moving from experimentation into operational workflows. Early programs focused on model access and retrieval-aug
arXiv:2607.04560v1 Announce Type: new Abstract: Web domain credibility evaluation is vital for combating misinformation. It is conducted by examining factors such as domain type, transparency, and ove
arXiv:2607.05242v1 Announce Type: cross Abstract: Personalized incentive allocation is vital for e-commerce, where uplift modeling is the standard for estimating Individual Treatment Effects (ITE). Ho
arXiv:2602.24266v2 Announce Type: replace-cross Abstract: Which internal mechanisms of a neural network can be replaced while preserving the computation it performs? Structured pruning asks for smalle
arXiv:2607.04451v1 Announce Type: new Abstract: Evaluation of autonomous vehicle (AV) planners in safety-critical closed-loop simulation is essential for real-world deployment. However, generating con
arXiv:2607.03903v1 Announce Type: new Abstract: Multi-task offline safe reinforcement learning (RL) promises to learn a shared optimal safe policy from offline data across multiple tasks. This paradig
arXiv:2607.04218v1 Announce Type: new Abstract: The growing demand for privacy-preserving, data-intensive applications such as IoT, augmented reality, and autonomous systems positions Federated Learni
arXiv:2607.05150v1 Announce Type: new Abstract: In this paper, we introduce Claim-Level Rubric Rewards (CuRe), a structured reward framework designed to address the reward-design bottleneck in reinfor
arXiv:2607.02841v1 Announce Type: cross Abstract: End-to-end autonomous driving (E2E-AD) aims to directly map raw sensor information to driving actions. Recently, with the rapid advancement of multi-m
arXiv:2607.03338v1 Announce Type: new Abstract: Closed-loop (or feedback) error-state Kalman filters with their relatives and offspring are the state-of-the-art in modern aided inertial navigation res