Stay updated with the latest research and technology news
arXiv:2601.20742v1 Announce Type: new Abstract: "Compression Tells Intelligence", is supported by research in artificial intelligence, particularly concerning (multimodal) large language models (LLMs/MLLMs), where compression efficiency...
arXiv:2601.20745v1 Announce Type: new Abstract: As large language models (LLMs) continue to scale, deployment is increasingly bottlenecked by the memory wall, motivating a shift toward...
arXiv:2601.20747v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for emotional support and mental health-related interactions outside clinical settings, yet little is...
arXiv:2601.20749v1 Announce Type: new Abstract: How do students develop AI literacy through everyday practice rather than formal instruction? While normative AI literacy frameworks proliferate, empirical...
arXiv:2601.20750v1 Announce Type: new Abstract: We deal with the numerical solution of the time-dependent partial differential equations using the adaptive space-time discontinuous Galerkin (DG) method....
arXiv:2601.20753v1 Announce Type: new Abstract: Preference-Conditioned Policy Learning (PCPL) in Multi-Objective Reinforcement Learning (MORL) aims to approximate diverse Pareto-optimal solutions by conditioning policies on user-specified...
arXiv:2601.20755v1 Announce Type: new Abstract: As large language models (LLMs) move from research to production, understanding how inference engines behave in real time has become...
arXiv:2601.20756v1 Announce Type: new Abstract: Score-based diffusion models have recently been extended to infinite-dimensional function spaces, with uses such as inverse problems arising from partial...
arXiv:2601.20757v1 Announce Type: new Abstract: For socially sensitive tasks like hate speech detection, the quality of explanations from Large Language Models (LLMs) is crucial for...
arXiv:2601.20758v1 Announce Type: new Abstract: We present ScaleFree, a GPU-accelerated adaptive Kernel Density Estimation (KDE) algorithm for scalable, interactive multiscale point cloud exploration. With this...
arXiv:2601.20759v1 Announce Type: new Abstract: Building on the collaborative Equational Theories project initiated by Terence Tao fifteen months ago, and combining it with ideas coming...
arXiv:2601.20760v1 Announce Type: new Abstract: Re-inforcement learning from human feedback (RLHF) has been effective in the task of AI alignment. However, one of the key...
arXiv:2601.20761v1 Announce Type: new Abstract: In this letter, we address the problem of developing quantum state tomography (QST) methods that remain valid at any time...
arXiv:2601.20764v1 Announce Type: new Abstract: Fog and edge computing require adaptive control schemes that can handle partial observability, severe latency requirements, and dynamically changing workloads....
arXiv:2601.20765v1 Announce Type: new Abstract: A fundamental challenge in offline reinforcement learning is distributional shift. Scarce data or datasets dominated by out-of-distribution (OOD) areas exacerbate...
arXiv:2601.20772v1 Announce Type: new Abstract: COMET-SG1 is a lightweight, stability-oriented autoregressive regression model designed for time-series prediction on edge and embedded AI systems. Unlike recurrent...
arXiv:2601.20773v1 Announce Type: new Abstract: Deployed machine learning systems must continuously evolve as data, architectures, and regulations change, often without access to original training data...
arXiv:2601.20774v1 Announce Type: new Abstract: Multitask learning and related frameworks have achieved tremendous success in modern applications. In multitask learning problem, we are given a...
arXiv:2601.20775v1 Announce Type: new Abstract: This paper advances the theoretical understanding of active learning label complexity for decision trees as binary classifiers. We make two...
arXiv:2601.20776v1 Announce Type: new Abstract: This paper rethinks steady-hand robotic manipulation by using a weakly supervised framework that fuses calibration-aware perception with admittance control. Unlike...
arXiv:2601.20779v1 Announce Type: new Abstract: In an ordinal election, two candidates are said to be perfect clones if every voter ranks them adjacently. The independence...
arXiv:2601.20781v1 Announce Type: new Abstract: Gaussian process regression uses data measured at sensor locations to reconstruct a spatially dependent function with quantified uncertainty. However, if...
arXiv:2601.20783v1 Announce Type: new Abstract: Modern blockchain applications benefit from the ability to specify sequencing constraints on the transactions that interact with them. This paper...
arXiv:2601.20784v1 Announce Type: new Abstract: Neuro-symbolic AI systems integrate neural perception with symbolic reasoning to enable data-efficient, interpretable, and robust intelligence beyond purely neural models....