今日从 arXiv 订阅中筛选 8 篇论文。

Arxiv ID2604.21479幻觉翻译2604.21479

⚡ Frozen LLMs as Map-Aware Spatio-Temporal Reasoners for Vehicle Trajectory Prediction

Frozen LLMs as Map-Aware Spatio-Temporal Reasoners for Vehicle Trajectory Prediction
Arxiv ID2604.21873幻觉翻译2604.21873

⚡ Grounding Video Reasoning in Physical Signals

Arxiv ID2604.21444幻觉翻译2604.21444

⚡ HiCrew Hierarchical Reasoning for Long-Form Video Understanding via Question-Aware Multi-Agent Collaboration

HiCrew Hierarchical Reasoning for Long-Form Video Understanding via Question-Aware Multi-Agent Collaboration
Arxiv ID2604.20983幻觉翻译2604.20983

⚡ Thinking Like a Botanist Challenging Multimodal Language Models with Intent-Driven Chain-of-Inquiry

Arxiv ID2604.20937幻觉翻译2604.20937

⚡ Sink-Token-Aware Pruning for Fine-Grained Video Understanding in Efficient Video LLMs

Sink-Token-Aware Pruning for Fine-Grained Video Understanding in Efficient Video LLMs
Arxiv ID2604.21160幻觉翻译2604.21160

⚡ Reinforcing 3D Understanding in Point-VLMs via Geometric Reward Credit Assignment

Reinforcing 3D Understanding in Point-VLMs via Geometric Reward Credit Assignment
Arxiv ID2604.21461幻觉翻译2604.21461

⚡ Do MLLMs Understand Pointing Benchmarking and Enhancing Referential Reasoning in Egocentric Vision

Do MLLMs Understand Pointing Benchmarking and Enhancing Referential Reasoning in Egocentric Vision
Arxiv ID2604.21668幻觉翻译2604.21668

⚡ Encoder-Free Human Motion Understanding via Structured Motion Descriptions

Encoder-Free Human Motion Understanding via Structured Motion Descriptions

自动生成于 2026-04-24 · 基于 arXiv Daily Digest