Stay updated with the latest research and technology news
arXiv:2601.20408v1 Announce Type: new Abstract: Enterprise LLM deployment faces a critical scalability challenge: organizations must optimize models systematically to scale AI initiatives within constrained compute...
arXiv:2601.20409v1 Announce Type: new Abstract: Time series forecasting requires capturing patterns across multiple temporal scales while maintaining computational efficiency. This paper introduces AWGformer, a novel...
arXiv:2601.20411v1 Announce Type: new Abstract: In this work, we explore an energy-efficient implementation of the polyphase network for a filter bank multicarrier (FBMC) system. The...
arXiv:2601.20412v1 Announce Type: new Abstract: The ability of Large Language Models (LLMs) to use external tools unlocks powerful real-world interactions, making rigorous evaluation essential. However,...
arXiv:2601.20413v1 Announce Type: new Abstract: Schadenfreude, or the pleasure derived from others' misfortunes, has become a visible and performative feature of online news engagement, yet...
arXiv:2601.20415v1 Announce Type: new Abstract: Given the increasing adoption of AI solutions in professional environments, it is necessary for developers to be able to make...
arXiv:2601.20417v1 Announce Type: new Abstract: Current speech LLMs bridge speech foundation models to LLMs using projection layers, training all of these components on speech instruction...
arXiv:2601.20419v1 Announce Type: new Abstract: Recent research has shown that aligning fine-grained text descriptions with localized image patches can significantly improve the zero-shot performance of...
arXiv:2601.20420v1 Announce Type: new Abstract: Developing human understandable interpretation of large language models (LLMs) becomes increasingly critical for their deployment in essential domains. Mechanistic interpretability...
arXiv:2601.20422v1 Announce Type: new Abstract: Modern content platforms offer paid promotion to mitigate cold start by allocating exposure via auctions. Our empirical analysis reveals a...
arXiv:2601.20424v1 Announce Type: new Abstract: Existing research often treats parliamentary discourse as a homogeneous whole, overlooking topic-specific patterns. Parliamentary speeches address a wide range of...
arXiv:2601.20425v1 Announce Type: new Abstract: We introduce the Quartet of Diffusions, a structure-aware point cloud generation framework that explicitly models part composition and symmetry. Unlike...
arXiv:2601.20426v1 Announce Type: new Abstract: We introduce Mix2Morph, a text-to-audio diffusion model fine-tuned to perform sound morphing without a dedicated dataset of morphs. By finetuning...
arXiv:2601.20427v1 Announce Type: new Abstract: Cause-effect chains, as a widely used modeling method in real-time embedded systems, are extensively applied in various safety-critical domains. End-to-end...
arXiv:2601.20428v1 Announce Type: new Abstract: Diffusion Map is a spectral dimensionality reduction technique which is able to uncover nonlinear submanifolds in high-dimensional data. And, it...
arXiv:2601.20429v1 Announce Type: new Abstract: 3D Gaussian Splatting has gained widespread adoption across diverse applications due to its exceptional rendering performance and visual quality. While...
arXiv:2601.20430v1 Announce Type: new Abstract: This paper presents Youtu-Parsing, an efficient and versatile document parsing model designed for high-performance content extraction. The architecture employs a...
arXiv:2601.20432v1 Announce Type: new Abstract: Audio watermarking embeds auxiliary information into speech while maintaining speaker identity, linguistic content, and perceptual quality. Although recent advances in...
arXiv:2601.20433v1 Announce Type: new Abstract: Deepfake detection is a widely researched topic that is crucial for combating the spread of malicious content, with existing methods...
arXiv:2601.20435v1 Announce Type: new Abstract: The convergence of high-performance computing (HPC) and artificial intelligence (AI) is driving the emergence of increasingly complex parallel applications and...
arXiv:2601.20437v1 Announce Type: new Abstract: This paper presents "Remember Me, Not Save Me," an AR & AI system enabling virtual citizens to develop personality through...
arXiv:2601.20439v1 Announce Type: new Abstract: Large Language Models show great potential with external tools, but face significant challenges in complex, multi-turn tool invocation. They often...
arXiv:2601.20445v1 Announce Type: new Abstract: Heterogeneous systems commonly adopt dynamic scheduling algorithms to improve resource utilization and enhance scheduling flexibility. However, such flexibility may introduce...
arXiv:2601.20448v1 Announce Type: new Abstract: Recent lightweight MLP-based models have achieved strong performance in time series forecasting by capturing stable trends and seasonal patterns. However,...