今日从 arXiv 订阅中筛选 10 篇论文。

Arxiv ID2609.02531幻觉翻译2609.02531

⚡ Spatially Aware World Action Model via Geometric Latent Diffusion

Arxiv ID2609.02159幻觉翻译2609.02159

⚡ World-Coherent Decoding: Self-Verifying Test-Time Planning for World Action Models

World-Coherent Decoding: Self-Verifying Test-Time Planning for World Action Models
Arxiv ID2609.02886幻觉翻译2609.02886

⚡ SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models

SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models
Arxiv ID2609.02049幻觉翻译2609.02049

⚡ The Dynamics of Continuous Mixture Collapse in Language Models

The Dynamics of Continuous Mixture Collapse in Language Models
Arxiv ID2609.02341幻觉翻译2609.02341

⚡ Towards Zero-Shot Transfer Across Embodiments For Driving VLAs

Towards Zero-Shot Transfer Across Embodiments For Driving VLAs
Arxiv ID2609.01659幻觉翻译2609.01659

⚡ Beyond Textual Chain-of-Thought: A Survey on Action-Grounded Reasoning in Autonomous Driving

Beyond Textual Chain-of-Thought: A Survey on Action-Grounded Reasoning in Autonomous Driving
Arxiv ID2609.02780幻觉翻译2609.02780

⚡ ShallowStream: Index Shallow then Answer Deep for Streaming Video Understanding

ShallowStream: Index Shallow then Answer Deep for Streaming Video Understanding
Arxiv ID2609.02359幻觉翻译2609.02359

⚡ TempoGround: State-Aware Streaming Visual Grounding with Vision-Language Models

TempoGround: State-Aware Streaming Visual Grounding with Vision-Language Models
Arxiv ID2609.01609幻觉翻译2609.01609

⚡ DiDrive: A Risk-Aware Hierarchical Diffusion Framework for Safe Offline RL in Autonomous Driving

DiDrive: A Risk-Aware Hierarchical Diffusion Framework for Safe Offline RL in Autonomous Driving
Arxiv ID2609.01924幻觉翻译2609.01924

⚡ Looped Transformers under the Jacobian Lens: Does the Global Workspace Survive Recurrence?

Looped Transformers under the Jacobian Lens: Does the Global Workspace Survive Recurrence?

自动生成于 2026-09-04 · 基于 arXiv Daily Digest