February 2026

arXiv:2602.16873v1 Announce Type: new Abstract: As large language models from diverse providers converge toward comparable benchmark performance, the traditional paradigm of selecting a single best model per task yields diminishing returns. We argue that orchestration topology — the structural composition of how multiple agents are coordinated, parallelized, and synthesized — now dominates system-level performance over individual model capability. We present AdaptOrch, a formal framework for task-adaptive multi-agent orchestration that dynamically selects among four canonical topologies (parallel, sequential, hierarchical, […]

Ver mais

arXiv:2602.16872v1 Announce Type: new Abstract: Optical Character Recognition (OCR) is a fundamental task for digitizing information, serving as a critical bridge between visual data and textual understanding. While modern Vision-Language Models (VLM) have achieved high accuracy in this domain, they predominantly rely on autoregressive decoding, which becomes computationally expensive and slow for long documents as it requires a sequential forward pass for every generated token. We identify a key opportunity to overcome this bottleneck: unlike open-ended generation, OCR […]

Ver mais

arXiv:2602.16870v1 Announce Type: new Abstract: The Boreas Road Trip (Boreas-RT) dataset extends the multi-season Boreas dataset to new and diverse locations that pose challenges for modern autonomous driving algorithms. Boreas-RT comprises 60 sequences collected over 9 real-world routes, totalling 643 km of driving. Each route is traversed multiple times, enabling evaluation in identical environments under varying traffic and, in some cases, weather conditions. The data collection platform includes a 5MP FLIR Blackfly S camera, a 360 degree Navtech […]

Ver mais

arXiv:2602.16867v1 Announce Type: new Abstract: In this paper, we study the {em green bin packing} (GBP) problem where $beta ge 0$ and $G in [0, 1]$ are two given values as part of the input. The energy consumed by a bin is $max {0, beta (x-G) }$ where $x$ is the total size of the items packed into the bin. The GBP aims to pack all items into a set of unit-capacity bins so that the number of […]

Ver mais

arXiv:2602.16866v1 Announce Type: new Abstract: This letter investigates properties of the second-order cone relaxation of the optimal power flow (OPF) problem, with emphasis on relaxation tightness, nodal voltage angles recovery, and alternating-current-OPF feasibility in meshed networks. The theoretical discussion is supported by numerical experiments on standard IEEE test cases. Implications for power system planning are briefly outlined.

Ver mais

arXiv:2602.16864v1 Announce Type: new Abstract: Time series (TS) modeling has come a long way from early statistical, mainly linear, approaches to the current trend in TS foundation models. With a lot of hype and industrial demand in this field, it is not always clear how much progress there really is. To advance TS forecasting and analysis to the next level, here we argue that the field needs a dynamical systems (DS) perspective. TS of observations from natural or […]

Ver mais

arXiv:2602.16863v1 Announce Type: new Abstract: The ability to manipulate tools significantly expands the set of tasks a robot can perform. Yet, tool manipulation represents a challenging class of dexterity, requiring grasping thin objects, in-hand object rotations, and forceful interactions. Since collecting teleoperation data for these behaviors is challenging, sim-to-real reinforcement learning (RL) is a promising alternative. However, prior approaches typically require substantial engineering effort to model objects and tune reward functions for each task. In this work, we […]

Ver mais

arXiv:2602.16861v1 Announce Type: new Abstract: As the presence of autonomous robots in public spaces increases-whether navigating campus walkways or neighborhood sidewalks-understanding how to carefully study these robots becomes critical. While HRI research has conducted field studies in public spaces, these are often limited to controlled experiments with prototype robots or structured observational methods, such as the Wizard of Oz technique. However, the autonomous mobile robots we encounter today, particularly delivery robots, operate beyond the control of researchers, navigating […]

Ver mais

arXiv:2602.16858v1 Announce Type: new Abstract: The deployment of deep learning inference in production environments continues to grow, where throughput, latency, and hardware efficiency are critical. Although specialized accelerators are increasingly adopted, many inference workloads still run on CPU-only systems, particularly in legacy data centers and cost-sensitive environments. This study investigates the scalability limits of CPU-based inference for convolutional neural networks by benchmarking ResNet models across varying batch sizes on two hardware tiers: a legacy Intel Xeon E5-2403 v2 […]

Ver mais

arXiv:2602.16856v1 Announce Type: new Abstract: Video Quality Assessment (VQA) is evolving beyond single-number mean opinion score toward richer, multi-faceted evaluations of video content. In this paper, we present a large-scale multi-dimensional VQA dataset UltraVQA that encompasses diverse User-Generated Content~(UGC) annotated across five key quality dimensions: Motion Quality, Motion Amplitude, Aesthetic Quality, Content Quality, and Clarity Quality. Each video in our dataset is scored by over 3 human raters on these dimensions, with fine-grained sub-attribute labels, and accompanied by […]

Ver mais