今日从 arXiv 订阅中筛选 10 篇论文。

Arxiv ID2609.03379幻觉翻译2609.03379

⚡ RecurTrace: Adaptive Latent Reasoning with Loop-Time Memory

RecurTrace: Adaptive Latent Reasoning with Loop-Time Memory
Arxiv ID2609.03952幻觉翻译2609.03952

⚡ WorldReward: Reward Modeling for Camera-Conditioned World Models

WorldReward: Reward Modeling for Camera-Conditioned World Models
Arxiv ID2609.03602幻觉翻译2609.03602

⚡ SV-WAM: An Efficient Surround-View World-Action Model for End-to-End Autonomous Driving

SV-WAM: An Efficient Surround-View World-Action Model for End-to-End Autonomous Driving
Arxiv ID2609.03572幻觉翻译2609.03572

⚡ Drive-HWM: Hierarchical World Models for Dynamic-Latent Guided Autonomous Driving

Drive-HWM: Hierarchical World Models for Dynamic-Latent Guided Autonomous Driving
Arxiv ID2609.04070幻觉翻译2609.04070

⚡ Continuous Actions from Discrete Minds: Latent-Aligned Planning for End-to-End Autonomous Driving

Continuous Actions from Discrete Minds: Latent-Aligned Planning for End-to-End Autonomous Driving
Arxiv ID2609.04131幻觉翻译2609.04131

⚡ Beyond Retrieval: Progressive Latent Memory Evolution for Streaming Video Understanding

Beyond Retrieval: Progressive Latent Memory Evolution for Streaming Video Understanding
Arxiv ID2609.03729幻觉翻译2609.03729

⚡ Unfold The World: Factorize 4D Properties in Reinforcing Spatial Reasoning

Unfold The World: Factorize 4D Properties in Reinforcing Spatial Reasoning
Arxiv ID2609.03673幻觉翻译2609.03673

⚡ Do Video Generators Track the World Across Segments? A Benchmark and Method for World-State Reasoning in Video Continuation

Do Video Generators Track the World Across Segments? A Benchmark and Method for World-State Reasoning in Video Continuation
Arxiv ID2609.04110幻觉翻译2609.04110

⚡ The Shape of Time: Video-Token Contrast for Temporal Understanding in VideoLMs

The Shape of Time: Video-Token Contrast for Temporal Understanding in VideoLMs
Arxiv ID2609.04196幻觉翻译2609.04196

⚡ Puffin-World: Scaling a Unified Multimodal Model with Native 3D World States

Puffin-World: Scaling a Unified Multimodal Model with Native 3D World States

自动生成于 2026-09-05 · 基于 arXiv Daily Digest