Stay updated with the latest research and technology news
arXiv:2509.14994v2 Announce Type: replace Abstract: Dynamic time warping (DTW) is widely used to align time series evolving on mismatched timescales, yet most applications reduce alignment...
arXiv:2509.15674v3 Announce Type: replace Abstract: We focus on a binary classification problem in an edge intelligence system where false negatives are more costly than false...
arXiv:2509.15922v2 Announce Type: replace Abstract: In speech enhancement, knowledge distillation (KD) compresses models by transferring a high-capacity teacher's knowledge to a compact student. However, conventional...
arXiv:2509.16495v2 Announce Type: replace Abstract: Efficient parallelism is necessary for achieving low-latency, high-throughput inference with large language models (LLMs). Tensor parallelism (TP) is the state-of-the-art...
arXiv:2509.16891v4 Announce Type: replace Abstract: While Large Language Models (LLMs) have demonstrated impressive reasoning and planning abilities in textual domains and can effectively follow instructions...
arXiv:2509.17052v3 Announce Type: replace Abstract: Large-scale text-to-speech (TTS) systems are limited by the scarcity of clean, multilingual recordings. We introduce Sidon, a fast, open-source speech...
arXiv:2509.17191v2 Announce Type: replace Abstract: Understanding cultural heritage artifacts such as ancient Greek pottery requires expert-level reasoning that remains challenging for current MLLMs due to...
arXiv:2509.17265v2 Announce Type: replace Abstract: Recommender systems have been shown to exhibit popularity bias by over-recommending popular items and under-recommending relevant niche items. We seek...
arXiv:2509.17429v4 Announce Type: replace Abstract: Accurate temporal prediction is the bridge between comprehensive scene understanding and embodied artificial intelligence. However, predicting multiple fine-grained states of...
arXiv:2509.17466v3 Announce Type: replace Abstract: Journaling can potentially serve as an effective method for autistic adolescents to improve narrative skills. However, its text-centric nature and...
arXiv:2509.17743v4 Announce Type: replace Abstract: Large language models (LLMs) have shown promise in generating program workflows for visual tasks. However, previous approaches often rely on...
arXiv:2509.18052v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed to simulate human collective behaviors, yet the methodological rigor of these "AI societies"...
arXiv:2509.18135v2 Announce Type: replace Abstract: Accurate multivariate time series forecasting hinges on inter-series correlations, which often evolve in complex ways across different temporal scales. Existing...
arXiv:2509.18403v3 Announce Type: replace Abstract: Wikipedia serves as a key infrastructure for public access to scientific knowledge, but it faces challenges in maintaining the credibility...
arXiv:2509.18413v2 Announce Type: replace Abstract: Voice anonymization aims to conceal speaker identity and attributes while preserving intelligibility, but current evaluations rely almost exclusively on Equal...
arXiv:2509.19163v2 Announce Type: replace Abstract: AI "slop" is an increasingly popular term used to describe low-quality AI-generated text, but there is currently no agreed upon...
arXiv:2509.19391v2 Announce Type: replace Abstract: Low-Rank Adaptation (LoRA) is widely used to efficiently adapt Transformers by adding trainable low-rank matrices to attention projections. While effective,...
arXiv:2509.20529v3 Announce Type: replace Abstract: Model discovery aims to uncover governing differential equations of dynamical systems directly from experimental data. Benchmarking such methods is essential...
arXiv:2509.20677v2 Announce Type: replace Abstract: In-context learning (ICL) is a pivotal capability for the practical deployment of large-scale language models, yet its stability heavily depends...
arXiv:2509.20787v4 Announce Type: replace Abstract: Driven by the simple and effective Dense O2O, DEIM demonstrates faster convergence and enhanced performance. In this work, we extend...
arXiv:2509.20808v2 Announce Type: replace Abstract: Hardware Fuzzing emerged as one of the crucial techniques for finding security flaws in modern hardware designs by testing a...
arXiv:2509.21155v3 Announce Type: replace Abstract: For an LLM to correctly respond to an instruction it must understand both the semantics and the domain (i.e., subject...
arXiv:2509.21981v2 Announce Type: replace Abstract: Effective real-world multi-agent collaboration requires not only accurate planning but also the ability to reason about collaborators' intents--a crucial capability...
arXiv:2509.22500v2 Announce Type: replace Abstract: Constrained optimization is a powerful framework for enforcing requirements on neural networks. These constrained deep learning problems are typically solved...