今日从 arXiv 订阅中筛选 8 篇论文。

Arxiv ID2604.25276幻觉翻译2604.25276

⚡ OmniVTG A Large-Scale Dataset and Training Paradigm for Open-World Video Temporal Grounding

OmniVTG A Large-Scale Dataset and Training Paradigm for Open-World Video Temporal Grounding
Arxiv ID2604.25809幻觉翻译2604.25809

⚡ Instruction-Evidence Contrastive Dual-Stream Decoding for Grounded Vision-Language Reasoning

Arxiv ID2604.25405幻觉翻译2604.25405

⚡ Leveraging Previous-Traversal Point Cloud Map Priors for Camera-Based 3D Object Detection and Tracking

Leveraging Previous-Traversal Point Cloud Map Priors for Camera-Based 3D Object Detection and Tracking
Arxiv ID2604.25416幻觉翻译2604.25416

⚡ Biased Dreams Limitations to Epistemic Uncertainty Quantification in Latent Space Models

Arxiv ID2604.25642幻觉翻译2604.25642

⚡ Prefill-Time Intervention for Mitigating Hallucination in Large Vision-Language Models

Prefill-Time Intervention for Mitigating Hallucination in Large Vision-Language Models
Arxiv ID2604.25855幻觉翻译2604.25855

⚡ SIEVES Selective Prediction Generalizes through Visual Evidence Scoring

SIEVES Selective Prediction Generalizes through Visual Evidence Scoring
Arxiv ID2604.24893幻觉翻译2604.24893

⚡ Interactive Episodic Memory with User Feedback

Interactive Episodic Memory with User Feedback
Arxiv ID2604.25574幻觉翻译2604.25574

⚡ Control Your Queries Heterogeneous Query Interaction for Camera-Radar Fusion

Control Your Queries Heterogeneous Query Interaction for Camera-Radar Fusion

自动生成于 2026-04-30 · 基于 arXiv Daily Digest