10 papers · 1 filter
Watch, Remember, Reason: Human-View Video Understanding with MLLMs
Jiahao Meng, Yue Tan, Qi Xu +12
Video understanding is being rapidly transformed by multimodal large language models (MLLMs), as research moves from short clips to long, multimodal, and knowledge-intensive video…
Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systems
Song Wang, Lingdong Kong, Xiaolu Liu +4
The rapid advancement of autonomous systems, including self-driving vehicles and drones, has intensified the need to forge true Spatial Intelligence from multi-modal onboard sensor…
AD-R1: Closed-Loop Reinforcement Learning for End-to-End Autonomous Driving with Impartial World Models
Tianyi Yan, Tao Tang, Xingtai Gui +11
End-to-end models for autonomous driving hold the promise of learning complex behaviors directly from sensor data, but face critical challenges in safety and handling long-tail eve…
Open-o3-Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence
Jiahao Meng, Xiangtai Li, Haochen Wang +8
Most video reasoning models only generate textual reasoning traces without indicating when and where key evidence appears. Recent models such as OpenAI-o3 have sparked wide interes…
RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning
Sicheng Feng, Kaiwen Tuo, Song Wang +3
Fine-grained visual reasoning remains a core challenge for multimodal large language models (MLLMs). The recently introduced ReasonMap highlights this gap by showing that even adva…
Beyond One Shot, Beyond One Perspective: Cross-View and Long-Horizon Distillation for Better LiDAR Representations
Xiang Xu, Lingdong Kong, Song Wang +2
LiDAR representation learning aims to extract rich structural and semantic information from large-scale, readily available datasets, reducing reliance on costly human annotations.…
MERIT: Multilingual Semantic Retrieval with Interleaved Multi-Condition Query
Wei Chow, Yuan Gao, Linfeng Li +15
Semantic retrieval is crucial for modern applications yet remains underexplored in current research. Existing datasets are limited to single languages, single images, or singular r…
PixelThink: Towards Efficient Chain-of-Pixel Reasoning
Song Wang, Gongfan Fang, Lingdong Kong +6
Existing reasoning segmentation approaches typically fine-tune multimodal large language models (MLLMs) using image-text pairs and corresponding mask labels. However, they exhibit…
PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learning
Song Wang, Xiaolu Liu, Lingdong Kong +6
Self-supervised representation learning for point cloud has demonstrated effectiveness in improving pre-trained model performance across diverse tasks. However, as pre-trained mode…
ReasonMap: Towards Fine-Grained Visual Reasoning from Transit Maps
Sicheng Feng, Song Wang, Shuyi Ouyang +5
Multimodal large language models (MLLMs) have demonstrated significant progress in semantic scene understanding and text-image alignment, with reasoning variants enhancing performa…