Author(s): Gowtham Boyina Originally published on Towards AI. And the Forced Alignment Model Is the Interesting Part I’ve tested dozens of speech recognition models over the time. Most claim multilingual support but quietly fall apart when you give them actual Chinese dialects, accented English, or anything beyond standard broadcast audio. The ones that do work well are usually proprietary APIs with pricing that scales uncomfortably. from Qwen-ASR githubAlibaba’s Qwen team has introduced Qwen3-ASR, an open-source speech recognition system […]

Ver mais

Federated learning on connected electric vehicles (BEVs) faces severe instability due to intermittent connectivity, time-varying client participation, and pronounced client-to-client variation induced by diverse operating conditions. Conventional FedAvg and many advanced methods can suffer from excessive drift and degraded convergence under these realistic constraints. This work introduces Fractional-Order Roughness-Informed Federated Averaging (FO-RI-FedAvg), a lightweight and modular extension of FedAvg that improves stability through two complementary client-side mechanisms: (i) adaptive roughness-informed proximal regularization, which dynamically tunes the pull toward […]

Ver mais

arXiv:2601.00002v1 Announce Type: new Abstract: Knowledge Graphs (KGs) bear great potential for ecology and biodiversity researchers in their ability to support synthesis and integration efforts, meta-analyses, reasoning tasks, and overall machine interoperability of research data. However, this potential is yet to be realized as KGs are notoriously difficult to interact with via their query language SPARQL for many user groups alike. Additionally, a further hindrance for user-KG interaction is the fundamental disconnect between user requirements and requirements KGs […]

Ver mais

arXiv:2601.00227v1 Announce Type: new Abstract: Recent advances show that large language models (LLMs) can act as autonomous agents capable of generating GPU kernels, but integrating these AI-generated kernels into real-world inference systems remains challenging. FlashInfer-Bench addresses this gap by establishing a standardized, closed-loop framework that connects kernel generation, benchmarking, and deployment. At its core, FlashInfer Trace provides a unified schema describing kernel definitions, workloads, implementations, and evaluations, enabling consistent communication between agents and systems. Built on real serving […]

Ver mais

arXiv:2602.11311v1 Announce Type: new Abstract: When learners receive feedback, what they believe about its source may shape how they engage with it. As AI is used alongside human instructors, understanding these attribution effects is essential for designing effective hybrid AI-human educational systems. We designed a creative coding interface that isolates source attribution while controlling for content: all participants receive identical LLM-generated feedback, but half see it attributed to AI and half to a human teaching assistant (TA). We […]

Ver mais

arXiv:2602.07153v1 Announce Type: new Abstract: End-to-end GUI agents for real desktop environments require large amounts of high-quality interaction data, yet collecting human demonstrations is expensive and existing synthetic pipelines often suffer from limited task diversity or noisy, goal-drifting trajectories. We present a trajectory expansion framework Anchor that bootstraps scalable desktop supervision from a small set of verified seed demonstrations. Starting from each seed, we identify branch points that correspond to meaningful state changes and propose new, state-grounded task […]

Ver mais

arXiv:2602.07211v1 Announce Type: new Abstract: Recent studies have demonstrated that prompting large language models (LLM) with audio encodings enables effective speech understanding capabilities. However, most speech LLMs are trained on single-channel, single-talker data, which makes it challenging to directly apply them to multi-talker and multi-channel speech understanding task. In this work, we present a comprehensive investigation on how to enable directional multi-talker speech understanding capabilities for LLMs, specifically in smart glasses usecase. We propose two novel approaches to […]

Ver mais

The allocation of scarce donor organs constitutes one of the most consequential algorithmic challenges in healthcare. While the field is rapidly transitioning from rigid, rule-based systems to machine learning and data-driven optimization, we argue that current approaches often overlook a fundamental barrier: incentives. In this position paper, we highlight that organ allocation is not merely an optimization problem, but rather a complex game involving organ procurement organizations, transplant centers, clinicians, patients, and regulators. Focusing on US adult heart […]

Ver mais