今日从 arXiv 订阅中筛选 10 篇论文。

Arxiv ID2608.24855幻觉翻译2608.24855

⚡ LeFlow: Generative Latent Flow Planning for World Models

LeFlow: Generative Latent Flow Planning for World Models
Arxiv ID2608.23927幻觉翻译2608.23927

⚡ GlanceWAM: Sparse Test-Time Imagination for World-Action Models

GlanceWAM: Sparse Test-Time Imagination for World-Action Models
Arxiv ID2608.24763幻觉翻译2608.24763

⚡ MoTE: Mixture of Task Experts for Multi-Task Video Understanding

MoTE: Mixture of Task Experts for Multi-Task Video Understanding
Arxiv ID2608.24044幻觉翻译2608.24044

⚡ JEPA-x: Cross-Predictive Physics Grounding for Forecastable Latent Dynamics

JEPA-x: Cross-Predictive Physics Grounding for Forecastable Latent Dynamics
Arxiv ID2608.24302幻觉翻译2608.24302

⚡ VideoHarness-RSI: Recursive Harness Self-Improvement for Long-Video Understanding

VideoHarness-RSI: Recursive Harness Self-Improvement for Long-Video Understanding
Arxiv ID2608.24136幻觉翻译2608.24136

⚡ Steering Recurrent Reasoners at Inference Time with Readout Feedback

Steering Recurrent Reasoners at Inference Time with Readout Feedback
Arxiv ID2608.24680幻觉翻译2608.24680

⚡ Game2World Engine: Unlocking In-the-Wild Gameplay Videos for World Model Training

Game2World Engine: Unlocking In-the-Wild Gameplay Videos for World Model Training
Arxiv ID2608.24293幻觉翻译2608.24293

⚡ Keep-or-Drop? Adaptive Tokenizer for Compact Video Representation

Keep-or-Drop? Adaptive Tokenizer for Compact Video Representation
Arxiv ID2608.23720幻觉翻译2608.23720

⚡ Platonic Representation Hypothesis on World Models

Platonic Representation Hypothesis on World Models
Arxiv ID2608.24366幻觉翻译2608.24366

⚡ Variance-Guided Spatial Attention Fusion for Robust End-to-End Driving

Variance-Guided Spatial Attention Fusion for Robust End-to-End Driving

自动生成于 2026-08-27 · 基于 arXiv Daily Digest