DyTopo: Dynamic Topology Routing for Multi-Agent Reasoning via Semantic Matching
arXiv:2602.06039v1 Announce Type: new Abstract: Multi-agent systems built from prompted large language models can improve multi-round reasoning, yet most existing…
Attention Is Not Retention: The Orthogonality Constraint in Infinite-Context Architectures
arXiv:2601.15313v2 Announce Type: replace-cross Abstract: Biological memory solves a problem that eludes current AI: storing specific episodic facts without corrupting…
Towards Universal Neural Likelihood Inference
arXiv:2508.09100v2 Announce Type: replace-cross Abstract: We introduce universal neural likelihood inference (UNLI): enabling a single model to provide data-grounded, conditional…
“I’m happy even though it’s not real”: GenAI Photo Editing as a Remembering Experience
arXiv:2602.03104v2 Announce Type: replace-cross Abstract: Generative Artificial Intelligence (GenAI) is increasingly integrated into photo applications on personal devices, making editing…
AI-Generated Code Is Not Reproducible (Yet): An Empirical Study of Dependency Gaps in LLM-Based Coding Agents
arXiv:2512.22387v2 Announce Type: replace-cross Abstract: The rise of Large Language Models (LLMs) as coding agents promises to accelerate software development,…
Toward Multiphysics-Informed Machine Learning for Sustainable Data Center Operations: Intelligence Evolution with Deployable Solutions for Computing Infrastructure
arXiv:2505.19414v2 Announce Type: replace Abstract: The revolution in artificial intelligence (AI) has brought sustainable challenges in data center management due…
Synergizing Kolmogorov-Arnold Networks with Dynamic Adaptive Weighting for High-Frequency and Multi-Scale PDE Solutions
arXiv:2512.22283v2 Announce Type: replace-cross Abstract: PINNs enhance scientific computing by incorporating physical laws into neural network structures, leading to significant…
DPO Unchained: Your Training Algorithm is Secretly Disentangled in Human Choice Theory
arXiv:2507.07855v3 Announce Type: replace-cross Abstract: Normative theories allow one to elicit key parts of a ML algorithm from first principles,…