Stay updated with the latest research and technology news
arXiv:2601.17584v1 Announce Type: new Abstract: Large language models are increasingly used in software development, yet their ability to generate and maintain large, multi module systems...
arXiv:2601.17585v1 Announce Type: new Abstract: Modern language models (LMs) are trained in an autoregressive manner, conditioned only on the prefix. In contrast, sequence labeling (SL)...
arXiv:2601.17586v1 Announce Type: new Abstract: Deep learning models in medical image analysis often struggle with generalizability across domains and demographic groups due to data heterogeneity...
arXiv:2601.17587v1 Announce Type: new Abstract: Configuring the parameters of additive manufacturing processes for metal alloys is a challenging problem due to complex relationships between input...
arXiv:2601.17588v1 Announce Type: new Abstract: Recent advances in LLMs have reignited scientific debate over whether embodiment is necessary for intelligence. We present the argument that...
arXiv:2601.17589v1 Announce Type: new Abstract: While thousands of satellites photograph Earth every day, most of that data never makes it to the ground because downlink...
arXiv:2601.17593v1 Announce Type: new Abstract: Recent progress in large language models has renewed interest in mechanistically characterizing how multi-step reasoning is represented and computed. While...
arXiv:2601.17596v1 Announce Type: new Abstract: Existing machine learning engineering (MLE) agents struggle to iteratively optimize their implemented algorithms for effectiveness. To address this, we introduce...
arXiv:2601.17598v1 Announce Type: new Abstract: Deep reinforcement learning (DRL) has driven major advances in autonomous control. Still, standard Deep Q-Network (DQN) agents tend to rely...
arXiv:2601.17601v1 Announce Type: new Abstract: URLs serve as bridges between social media platforms and the broader web, linking user-generated content to external information resources. On...
arXiv:2601.17602v1 Announce Type: new Abstract: We study Transformer overparameterization through the lens of angular similarity in high-dimensional encoder-decoder embeddings. We apply Bernoulli dropout between the...
arXiv:2601.17604v1 Announce Type: new Abstract: Large Language Models (LLMs) are widely used to support software developers in tasks such as code generation, optimization, and documentation....
arXiv:2601.17606v1 Announce Type: new Abstract: Performant all-to-all collective operations in MPI are critical to fast Fourier transforms, transposition, and machine learning applications. There are many...
arXiv:2601.17607v1 Announce Type: new Abstract: Learning systems acquire structured internal representations from data, yet classical information-theoretic results state that deterministic transformations do not increase information....
arXiv:2601.17608v1 Announce Type: new Abstract: To support aging-in-place, adult children often provide care to their aging parents from a distance. These informal caregivers desire plug-and-play...
arXiv:2601.17609v1 Announce Type: new Abstract: In domains like medicine and finance, large-scale labeled data is costly and often unavailable, leading to models trained on small...
arXiv:2601.17614v1 Announce Type: new Abstract: Designing user interfaces that align with user preferences is a time-consuming process, which requires iterative cycles of prototyping, user testing,...
arXiv:2601.17615v1 Announce Type: new Abstract: Prefetching and off-chip prediction are two techniques proposed to hide long memory access latencies in high-performance processors. In this work,...
arXiv:2601.17616v1 Announce Type: new Abstract: Continual learning in Large Language Models (LLMs) is hindered by the plasticity-stability dilemma, where acquiring new capabilities often leads to...
arXiv:2601.17617v1 Announce Type: new Abstract: LLM-powered search agents are increasingly being used for multi-step information seeking tasks, yet the IR community lacks empirical understanding of...
arXiv:2601.17620v1 Announce Type: new Abstract: Biometric data is considered to be very private and highly sensitive. As such, many methods for biometric template protection were...
arXiv:2601.17622v2 Announce Type: new Abstract: We introduce Memento, a conversational AR assistant that permanently captures and memorizes user's verbal queries alongside their spatiotemporal and activity...
arXiv:2601.17625v1 Announce Type: new Abstract: Transformer-based neural decoders with large parameter counts, pre-trained on large-scale datasets, have recently outperformed classical machine learning models and small...
arXiv:2601.17627v1 Announce Type: new Abstract: AI coding agents can autonomously generate pull requests (PRs), yet little is known about how their contributions compare to those...