Song Wang

Rethinking Memory Mechanisms of Foundation Agents in the Second Half: A Survey

arXiv 2026

VisionTrim: Unified Vision Token Compression for Training-Free MLLM Acceleration

arXiv 2026

How Much Reasoning Do Retrieval-Augmented Models Add beyond LLMs? A Benchmarking Framework for Multi-Hop Inference over Hybrid Knowledge

arXiv 2026

Inst3D-LMM: Instance-Aware 3D Scene Understanding with Multi-modal Instruction Tuning

CVPR 2025 1

Can MLLMs Guide Me Home? A Benchmark Study on Fine-Grained Visual Reasoning from Transit Maps

arXiv 2025

Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future

arXiv 2025

RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning

arXiv 2025

Uncertainty-Instructed Structure Injection for Generalizable HD Map Construction

CVPR 2025 1

A Coarse-to-Fine Approach to Multi-Modality 3D Occupancy Grounding

arXiv 2025

Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systems

arXiv 2025

3D and 4D World Modeling: A Survey

arXiv 2025

SAM4D: Segment Anything in Camera and LiDAR Streams

ICCV 2025

PixelThink: Towards Efficient Chain-of-Pixel Reasoning

arXiv 2025

Complex Logical Instruction Generation

arXiv 2025

Reasoning of Large Language Models over Knowledge Graphs with Super-Relations

arXiv 2025

PianoMotion10M: Dataset and Benchmark for Hand Motion Generation in Piano Performance

arXiv 2024

TokenPacker: Efficient Visual Projector for Multimodal LLM

arXiv 2024

Large Language Models for Data Annotation and Synthesis: A Survey

arXiv 2024

Integrative Decoding: Improve Factuality via Implicit Self-consistency

arXiv 2024