arXiv:2602.15859v1 Announce Type: new Abstract: Building reliable conversational AI assistants for customer-facing industries remains challenging due to noisy conversational data, fragmented knowledge, and the requirement for accurate human hand-off – particularly in domains that depend heavily on real-time information. This paper presents an end-to-end framework for constructing and evaluating a conversational AI assistant directly from historical call transcripts. Incoming transcripts are first graded using a simplified adaptation of the PIPA framework, focusing on observation alignment and appropriate response […]

Ver mais

arXiv:2602.17808v1 Announce Type: new Abstract: IoT applications are increasingly relying on on-device AI accelerators to ensure high performance, especially in limited connectivity and safety-critical scenarios. However, the limited on-chip memory of these accelerators forces inference runtimes to swap model segments between host and accelerator memory, substantially inflating latency. While collaborative processing by partitioning the model processing between CPU and accelerator resources can reduce accelerator memory pressure and latency, naive partitioning may worsen end-to-end latency by either shifting excessive […]

Ver mais

arXiv:2603.11784v1 Announce Type: cross Abstract: As scaling laws push the training of frontier large language models (LLMs) toward ever-growing data requirements, training pipelines are approaching a regime where much of the publicly available online text may be consumed. At the same time, widespread LLM usage increases the volume of machine-generated content on the web; together, these trends raise the likelihood of generated text re-entering future training corpora, increasing the associated risk of performance degradation often called model collapse. […]

Ver mais

arXiv:2602.11318v1 Announce Type: new Abstract: In machine learning, “ground truth” refers to the assumed correct labels used to train and evaluate models. However, the foundational “ground truth” paradigm rests on a positivistic fallacy that treats human disagreement as technical noise rather than a vital sociotechnical signal. This systematic literature review analyzes research published between 2020 and 2025 across seven premier venues: ACL, AIES, CHI, CSCW, EAAMO, FAccT, and NeurIPS, investigating the mechanisms in data annotation practices that facilitate […]

Ver mais

How did AI like Microsoft’s Tay work? This was 2016, before LLMs. No powerful GPUs with HBM and Google’s first TPU is cutting edge. Transformers didn’t exist. It seems much better than other contemporary chatbots like SimSimi. It adapts to user engagement and user generated text very quickly, adjusting the text it generates which is grammatically coherent and apparently context appropriate and contains information unlike SimSimi. There is zero information on its inner workings. Could it just have […]

Ver mais

Adjoint-based shape optimization of ship hulls is a powerful tool for addressing high-dimensional design problems in naval architecture, particularly in minimizing the ship resistance. However, its application to vessels that employ complex propulsion systems introduces significant challenges. They arise from the need for transient simulations extending over long periods of time with small time steps and from the reverse temporal propagation of the primal and adjoint solutions. These challenges place considerable demands on the required storage and computing […]

Ver mais

With the increasing demand for high-quality imaging in consumer electronics, image aesthetic assessment (IAA) has been widely applied to electronic cameras and display devices. Although the deformable attention mechanism has been introduced into IAA due to its perceptual capabilities, enabling models to refine attention regions by learning interest points and their corresponding offsets, existing methods often lack guidance from aesthetic composition features during the offset generation process, which limits their performance in aesthetic evaluation tasks. To address this […]

Ver mais

Residual reinforcement learning (RL) enables stable online refinement of expressive pretrained policies by freezing the base and learning only bounded corrections. However, value learning in residual RL poses unique challenges that remain poorly understood. In this work, we identify two key bottlenecks: cold start pathology, where the critic lacks knowledge of the value landscape around the base policy, and structural scale mismatch, where the residual contribution is dwarfed by the base action. Through systematic investigation, we uncover the […]

Ver mais

arXiv:2602.22274v1 Announce Type: new Abstract: Traffic flow forecasting has emerged as an indispensable mission for daily life, which is required to utilize the spatiotemporal relationship between each location within a time period under a graph structure to predict future flow. However, the large travel demand for broader geographical areas and longer time spans requires models to distinguish each node clearly and possess a holistic view of the history, which has been paid less attention to in prior works. […]

Ver mais