arXiv

CMuon: Accelerating and Stabilizing Diffusion Transformer Training via Chunked Momentum Orthogonalization

Diffusion Transformers (DiTs) have achieved state-of-the-art (SOTA) performance in visual generative modeling, yet th...

AI 聚合
2026-08-04
arXiv

Abduction Without a Body? Representational Grounding and the Abduction Loop for Scientific Hypothesis Generation

Can scientific abduction occur without continuous sensorimotor embodiment? Recent arguments in AI and philosophy of s...

AI 聚合
2026-08-04
arXiv

Optimizing Minimax Regret in Uncertain MDPs with Small Sets of Policies

Sequential decision-making in real-world applications often involves uncertainty about the environment's model. Uncer...

AI 聚合
2026-08-04
arXiv

Magnet: Detecting Cross-Session AI Misuse Through Capability Accumulation

The most capable AI deployments are not single models but ensembles of specialized agents that delegate and act in co...

AI 聚合
2026-08-04
arXiv

Analytic Planning under Uncertainty with Moment Closure

Effective model-based reinforcement learning in stochastic environments requires planning that accounts for predictiv...

AI 聚合
2026-08-04
arXiv

Who Should Be Generated? Justifying Demographic Targets in Open-Ended Generation

Fairness evaluation concerns not only what a model produces, but also what its outputs ought to be compared against. ...

AI 聚合
2026-08-04
arXiv

A Taxonomy of Cognitive Capability Gaps in Generative and Agentic AI

Cognitive AI seeks to move beyond language generation and autonomous task execution toward systems capable of sustain...

AI 聚合
2026-08-04
arXiv

Structured Memory for Edge Language Models: Persistent Context and Corpus Retrieval via O(1) SSM State Injection

Retrieval-augmented generation (RAG) imposes a prefill cost proportional to retrieved context length, and -- with Tra...

AI 聚合
2026-08-04
arXiv

AtumAI: A Principled Framework for Agentic Generation of Datacenter Control-Plane Policies

The efficiency of a datacenter rests on its control plane policies. Designing these policies is increasingly hard: th...

AI 聚合
2026-08-04
arXiv

CoWAM: Coordination Contracts for Selective Policy Intervention with WAMs

World Action Models (WAMs) augment robot policies with action-conditioned predicted futures, but a plausible future a...

AI 聚合
2026-08-04
arXiv

UEmbed: Unified Sparse and Dense Multimodal Embeddings

Sparse retrieval underpins modern search systems, from web search to retrieval-augmented generation. Existing work ha...

AI 聚合
2026-08-04
arXiv

Bridging Artificial Intelligence and Power Systems Education Using a Hands-On Executable Framework

Artificial intelligence (AI) is increasingly central to power and energy systems, supporting modeling, forecasting, o...

AI 聚合
2026-08-04
首页 上一页 第 86 / 215 页 下一页 末页