Stay updated with the latest research and technology news
arXiv:2601.23229v1 Announce Type: new Abstract: Markov decision processes (MDPs) are a fundamental model in sequential decision making. Robust MDPs (RMDPs) extend this framework by allowing...
arXiv:2601.23233v1 Announce Type: new Abstract: Temporal link prediction in dynamic graphs is a fundamental problem in many real-world systems. Existing temporal graph neural networks mainly...
arXiv:2601.23236v1 Announce Type: new Abstract: We propose a variational framework that interprets transformer layers as iterations of an optimization algorithm acting on token embeddings. In...
arXiv:2601.23237v1 Announce Type: new Abstract: Several applications of the QR-AAA algorithm, a greedy scheme for vector-valued rational approximation, are presented. The focus is on demonstrating...
arXiv:2601.23238v1 Announce Type: new Abstract: Generative learning generates high dimensional data based on low dimensional conditions, also called prompts. Therefore, generative learning algorithms are eligible...
arXiv:2601.23240v1 Announce Type: new Abstract: We introduce a compressed representation of sets of sets that exploits how much they differ from each other. Our representation...
arXiv:2601.23244v1 Announce Type: new Abstract: The numerical computation of shortest paths or geodesics on surfaces, along with the associated geodesic distance, has a wide range...
arXiv:2601.23246v1 Announce Type: new Abstract: Transitivity is a central, generative principle in social and other complex networks, capturing the tendency for two nodes with a...
arXiv:2601.23248v1 Announce Type: new Abstract: Follow the regularized leader FTRL is the premier algorithm for online optimization. However, despite decades of research on its convergence...
arXiv:2601.23251v1 Announce Type: new Abstract: Vision-language models (VLMs) demonstrate impressive performance on standard video understanding benchmarks yet fail systematically on simple reasoning tasks that preschool...
arXiv:2601.23253v1 Announce Type: new Abstract: Vision-language models suffer performance degradation under domain shift, limiting real-world applicability. Existing test-time adaptation methods are computationally intensive, rely on...
arXiv:2601.23254v1 Announce Type: new Abstract: Repository-level code completion remains challenging for large language models (LLMs) due to cross-file dependencies and limited context windows. Prior work...
arXiv:2601.23255v1 Announce Type: new Abstract: Large audio-language models increasingly operate on raw speech inputs, enabling more seamless integration across domains such as voice assistants, education,...
arXiv:2601.23257v1 Announce Type: new Abstract: Software issue resolution in large repositories is a long-range decision process: choices made during localization shape the space of viable...
arXiv:2601.23258v1 Announce Type: new Abstract: Recent works on language identification and generation have established tight statistical rates at which these tasks can be achieved. These...
arXiv:2601.23261v1 Announce Type: new Abstract: The Muon optimizer has demonstrated strong empirical performance in pre-training large language models by performing matrix-level gradient (or momentum) orthogonalization...
arXiv:2601.23262v1 Announce Type: new Abstract: We introduce a guided stochastic sampling method that augments sampling from diffusion models with physics-based guidance derived from partial differential...
arXiv:2601.23265v1 Announce Type: new Abstract: Despite rapid advances in autonomous AI scientists powered by language models, generating publication-ready illustrations remains a labor-intensive bottleneck in the...
arXiv:2601.23266v1 Announce Type: new Abstract: This paper proposes a novel inverse reinforcement learning framework using a diffusion-based adaptive lookahead planner (IRL-DAL) for autonomous vehicles. Training...
arXiv:2601.23268v1 Announce Type: new Abstract: TCBench is a benchmark for evaluating global, short to medium-range (1-5 days) forecasts of tropical cyclone (TC) track and intensity....
arXiv:2601.23269v1 Announce Type: new Abstract: This work presents a data-driven framework for fast forward and inverse analysis in topology optimization (TO) by combining Rank Reduction...
arXiv:2601.23273v1 Announce Type: new Abstract: Prompt agents have recently emerged as a promising paradigm for automated prompt optimization, framing refinement as a sequential decision-making problem...
arXiv:2601.23278v1 Announce Type: new Abstract: Diffusion Large Language Models (DLLMs) offer a compelling alternative to Auto-Regressive models, but their deployment is constrained by high decoding...
arXiv:2601.23280v1 Announce Type: new Abstract: We propose a data-efficient, physics-aware generative framework in function space for inverse PDE problems. Existing plug-and-play diffusion posterior samplers represent...