15 papers · 1 filter
NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation
NVIDIA, :, Aarti Basant +32
As autonomous vehicle capabilities advance, the safe evaluation of driving policies in long-tail scenarios remains a critical bottleneck. In closed-loop simulation, the driving pol…
One-Shot Crowd Counting With Density Guidance For Scene Adaptation
Jiwei Chen, Qi Wang, Junyu Gao +3
Crowd scenes captured by cameras at different locations vary greatly, and existing crowd models have limited generalization for unseen surveillance scenes. To improve the generaliz…
Efficient Reasoning via Thought Compression for Language Segmentation
Qing Zhou, Shiyu Zhang, Yuyu Jia +4
Chain-of-thought (CoT) reasoning has significantly improved the performance of large multimodal models in language-guided segmentation, yet its prohibitive computational cost, stem…
Beyond Prompt Degradation: Prototype-guided Dual-pool Prompting for Incremental Object Detection
Yaoteng Zhang, Zhou Qing, Junyu Gao +1
Incremental Object Detection (IOD) aims to continuously learn new object categories without forgetting previously learned ones. Recently, prompt-based methods have gained popularit…
UNICBench: UNIfied Counting Benchmark for MLLM
Chenggang Rong, Tao Han, Zhiyuan Zhao +5
Counting is a core capability for multimodal large language models (MLLMs), yet there is no unified counting dataset to rigorously evaluate this ability across image, text, and aud…
Scale Efficient Training for Large Datasets
Qing Zhou, Junyu Gao, Qi Wang
The rapid growth of dataset scales has been a key driver in advancing deep learning research. However, as dataset scale increases, the training process becomes increasingly ineffic…