Knowledge catalogue
arXiv:2610.20223v1 Announce Type: new Abstract: Vision-language-action (VLA) models have emerged as a powerful paradigm for robotic manipulation, enabling robots to generate actions from visual observ
arXiv:2610.18298v1 Announce Type: new Abstract: What binds large language models on auditable, hypothesis-driven decision tasks, where every candidate can be checked against the evidence? On the publi
arXiv:2411.06403v4 Announce Type: replace Abstract: Why can neural networks struggle to learn optimal play in a game with a simple, efficient solution algorithm? Motivated by empirical difficulties wi
arXiv:2610.15208v1 Announce Type: cross Abstract: Deep research requires connecting multiple steps of search, reasoning, and computation, with intermediate findings guiding what to investigate next. A
arXiv:2610.19314v1 Announce Type: new Abstract: Large language model (LLM) evaluators are increasingly used to assess personalized assistants, yet whether they can reliably judge personalization has r
arXiv:2610.19439v1 Announce Type: new Abstract: While LLM-based agent systems have demonstrated remarkable proficiency in reasoning and solving complex real-world tasks, they also come with substantia
arXiv:2505.13546v2 Announce Type: replace-cross Abstract: Automatic prompt generation plays a crucial role in enabling general-purpose multi-agent systems to perform diverse tasks autonomously. Existi
arXiv:2610.17584v1 Announce Type: new Abstract: Operational mobile networks are rich in observations but poor in interventions: they continuously generate large volumes of passive telemetry, while con
arXiv:2610.14659v1 Announce Type: new Abstract: Streaming speech assistants can launch tools before users finish speaking, overlapping execution with incoming speech to reduce user waiting time. Howev
arXiv:2610.18204v1 Announce Type: cross Abstract: Connection-tableau provers typically construct closed tableaux by backtracking search. This gives lightweight proof procedures, but their low-memory s
arXiv:2610.19494v1 Announce Type: new Abstract: Real-time monocular human pose estimation is an important sensing component for human-centered intelligent systems. While recent camera-based methods ha
arXiv:2610.17665v2 Announce Type: new Abstract: Can vision-language models turn 2D observations into 3D understanding that supports precise action? This requires inferring object geometry, anticipatin
arXiv:2610.18308v1 Announce Type: cross Abstract: Conversational Recommender Systems (CRSs) require reliable user simulators for cost-effective evaluation. LLM-based simulators have made realistic sim
arXiv:2610.17131v2 Announce Type: cross Abstract: Dynamic spatial audio reasoning requires a model to associate changing acoustic observations with the correct source and recover its spatial state at
arXiv:2610.19795v1 Announce Type: new Abstract: Video world models aim to simulate complex environments with realistic appearance and dynamics. Maintaining consistency over long interactions requires
arXiv:2610.15938v1 Announce Type: new Abstract: Evaluation of text generated by large language models (LLMs) is increasingly delegated to LLMs acting as judges, yet what such a judge must be shown rem
arXiv:2610.14736v1 Announce Type: new Abstract: Optimization by PROmpting (OPRO) directly leverages Large Language Models (LLMs) to generate candidate solutions through natural-language prompting. How
arXiv:2610.14776v1 Announce Type: cross Abstract: Text-to-speech (TTS) systems are conventionally optimized for intelligibility and speaker similarity. However, neither objective captures the prosodic
arXiv:2610.16333v1 Announce Type: new Abstract: As AI agents increasingly act through external tools, tool results are no longer simple outputs but execution artifacts that must remain correctly assoc
arXiv:2610.16155v1 Announce Type: new Abstract: Interactive-agent evaluations commonly rely on standardized LLM-based user simulators that exhibit broadly cooperative behavior, potentially overlooking
arXiv:2610.17609v1 Announce Type: new Abstract: Training-free self-improvement lets an agent use feedback to revise the response it is about to return and to update the harness state that shapes how i
arXiv:2610.20450v1 Announce Type: cross Abstract: Pairwise comparison data are a standard supervision signal in preference learning, but disagreement in such data can reflect stable latent heterogenei
arXiv:2610.19476v1 Announce Type: cross Abstract: Post-training often improves the performance of large audio-language models on audio understanding and reasoning benchmarks. However, these improvemen
arXiv:2610.16039v1 Announce Type: cross Abstract: Multi-agent LLM systems (MALS) introduce a privacy-leakage problem that conventional sensitivity-based defenses miss, since information disclosed to o
arXiv:2610.19814v1 Announce Type: new Abstract: Transformer-based tabular foundation models (TFMs) achieve state-of-the-art performance on small to medium-sized tabular prediction tasks while processi
arXiv:2610.19769v1 Announce Type: cross Abstract: Architectural technical debt arises when a system's implementation drifts from its inten ded modular decomposition, while the mapping between source f
arXiv:2610.20089v1 Announce Type: new Abstract: Pairwise preference feedback has become a widely adopted supervision signal for reinforcement learning in video generation models, as pairwise compariso
arXiv:2610.19993v1 Announce Type: new Abstract: Reconstruction of 3D structures using under-ice AUV video footage has been inaccurate, although it is not certain whether this is due to shortcomings in
arXiv:2610.10226v2 Announce Type: replace-cross Abstract: Can AI make Software Engineering (SE) -- the discipline -- obsolete? And can it make software engineers -- the professionals -- redundant? Thi
arXiv:2610.14493v1 Announce Type: new Abstract: Recent advances in machine learning have improved rainfall-runoff prediction, yet most data-driven models remain difficult to interpret and do not expli
arXiv:2610.18596v1 Announce Type: cross Abstract: Reinforcement learning (RL) post-training improves robot foundation models (RFMs) beyond their demonstrations, but real-world deployment demands more:
arXiv:2610.15343v1 Announce Type: new Abstract: World models and video understanding models are increasingly deployed in dynamic visual environments, yet their robustness to physical adversarial threa
Anthropic cautions that lightweight AI models—requiring far less compute than frontier models—could soon gain the ability to self‑replicate across Internet‑of‑Things devices, creating new autonomous w
arXiv:2610.15159v1 Announce Type: new Abstract: Existing depth-compression methods for large language models (LLMs) score layers individually or group only adjacent or contiguous layers, implicitly as
arXiv:2610.15543v1 Announce Type: cross Abstract: We study federated learning from continuously arriving data: each client samples from its own distribution, these distributions drift over time, and t
arXiv:2610.14034v1 Announce Type: new Abstract: Foundation models are expanding robot capabilities, enabling robots to handle more diverse objects, follow sophisticated instructions, and operate in co
arXiv:2610.17582v1 Announce Type: new Abstract: Entities in real-world systems often evolve over time: users shift between information consumption patterns, researchers migrate between fields, and fir
arXiv:2610.17926v1 Announce Type: new Abstract: Autoregressive video generation relies on memory retrieval to model long-range dependencies. This capability becomes particularly critical for multi-sho
arXiv:2506.17585v4 Announce Type: replace-cross Abstract: Large language models can answer questions correctly and still hallucinate their citations. Most citation systems address this by retrieving d
arXiv:2610.16093v1 Announce Type: cross Abstract: Predicting single-cell perturbation responses requires mapping between two unpaired populations of cells measured before and after the perturbation. O
arXiv:2610.16293v1 Announce Type: new Abstract: Garment manipulation requires inferring both garment identity and complete configuration from partial, self-occluded observations. This creates a chicke
arXiv:2610.18040v1 Announce Type: new Abstract: We introduce Contractor Filters (CFs), a set-membership architecture for nonlinear continuous-time state estimation with bounded uncertainties and spora
arXiv:2610.17680v1 Announce Type: cross Abstract: Building a co-registered SAR-optical corpus for self-supervised Earth Observation is above all an acquisition problem, yet the main multi-modal datase
arXiv:2610.16177v1 Announce Type: new Abstract: Open-vocabulary 3D Gaussian segmentation typically binds semantic features to the per-Gaussian state via per-scene gradient training (1-4 h) or the more
arXiv:2610.14258v1 Announce Type: new Abstract: Regularization-based continual learning protects each parameter in proportion to an estimate of its importance, yet these estimates come from finite sam
arXiv:2603.16157v2 Announce Type: replace Abstract: While Reinforcement Learning (RL) enhances Large Language Model reasoning, on-policy algorithms like GRPO are sample-inefficient as they discard pas
arXiv:2610.14120v1 Announce Type: cross Abstract: A defined-benefit pension is only as safe as its sponsor, yet sponsor distress is under-instrumented relative to plan-side modelling. We present a tra
arXiv:2610.16523v1 Announce Type: cross Abstract: Training LLM agents to interact with users over multiple turns is challenging because the learning signal depends not only on the agent, but also on t
arXiv:2610.18738v1 Announce Type: new Abstract: Off-policy data in reinforcement learning with verifiable rewards (RLVR) can arise from asynchronous generation, rollout-training mismatch, and response
arXiv:2610.18790v1 Announce Type: new Abstract: Long-term robot autonomy depends on more than effective action generation: a policy must recognize when its behavior is no longer sufficiently supported
arXiv:2610.16845v1 Announce Type: cross Abstract: Standardizing a rare feature can help stochastic gradient descent learn its effect within a finite budget, but it also changes the noise cost of learn
arXiv:2610.17503v1 Announce Type: new Abstract: Event logs are ubiquitous across real-world domains, including business processes, manufacturing workflows, healthcare, and many other operational syste
arXiv:2610.16558v1 Announce Type: cross Abstract: World models capture environment dynamics and support counterfactual reasoning for planning. In image-goal navigation, where the target often lies bey
This continues the small-model browser experiments from the previous posts. Two standard, off-the-shelf models ran locally on the same Samsung Galaxy S21: Gemma 4 E2B, Q3_K_M as the reasoner Qwen3.5-0
arXiv:2506.10946v3 Announce Type: replace Abstract: Unlearning large language models (LLMs) is important due to copyright and privacy concerns. A key challenge is unintended forgetting, where removing
arXiv:2610.15431v1 Announce Type: new Abstract: Monocular depth estimation (MDE) has emerged as a cost-effective alternative to hardware-dependent 3D sensing modalities, yet predicting precise metric
arXiv:2610.15715v1 Announce Type: cross Abstract: Linear attention promises the efficiency needed for long-context language modelling, yet its fixed-size recurrent state must simultaneously support on
arXiv:2610.14971v1 Announce Type: new Abstract: WavePhaseNet introduced frequency-resolved semantic representations, QuantumPhaseNet introduced gauge-covariant phase connections, and ModularPhaseNet m
arXiv:2610.15830v1 Announce Type: new Abstract: When several predictions use the same internal representation, information about some targets can remain easier to recover than information about others
arXiv:2610.14544v1 Announce Type: new Abstract: Roadside 4D occupancy forecasting predicts future semantic occupancy in a fixed infrastructure coordinate system. Roadside scenes are globally structure