9 papers
DriveVLA-M0: Failure-Aware Memory Augmentation for Autonomous Driving
Zebin Xing, Yupeng Zheng, Qiang Chen +10
Vision-Language-Action (VLA) models have recently emerged as a promising paradigm for end-to-end autonomous driving by enabling unified reasoning across perception, language, and p…
U-STS-LLM: A Unified Spatio-Temporal Steered Large Language Model for Traffic Prediction and Imputation
Yichen Zhang, Jun Li, Yiyang Ni +2
Accurate spatio-temporal cellular traffic analysis is fundamental to the reliable operation of modern mobile networks, as it underpins load forecasting for congestion avoidance and…
PI-TTA: Physics-Informed Source-Free Test-Time Adaptation for Robust Human Activity Recognition on Mobile Devices
Changyu Li, Lu Wang, Ming Lei +4
Source-free test-time adaptation (TTA) is appealing for mobile and wearable sensing because it enables on-device personalization from unlabeled test streams without centralizing pr…
DreamerAD: Efficient Reinforcement Learning via Latent World Model for Autonomous Driving
Pengxuan Yang, Yupeng Zheng, Deheng Qian +11
We introduce DreamerAD, the first latent world model framework that enables efficient reinforcement learning for autonomous driving by compressing diffusion sampling from 100 steps…
Latent-WAM: Latent World Action Modeling for End-to-End Autonomous Driving
Linbo Wang, Yupeng Zheng, Qiang Chen +14
We introduce Latent-WAM, an efficient end-to-end autonomous driving framework that achieves strong trajectory planning through spatially-aware and dynamics-informed latent world re…
LLaVA-UHD v3: Progressive Visual Compression for Efficient Native-Resolution Encoding in MLLMs
Shichu Sun, Yichen Zhang, Haolin Song +6
Visual encoding followed by token condensing has become the standard architectural paradigm in multi-modal large language models (MLLMs). Many recent MLLMs increasingly favor globa…
ContentV: Efficient Training of Video Generation Models with Limited Compute
Wenfeng Lin, Renjie Chen, Boyuan Liu +10
Recent advances in video generation demand increasingly efficient training recipes to mitigate escalating computational costs. In this report, we present ContentV, an 8B-parameter…
Towards Self-Improvement of Diffusion Models via Group Preference Optimization
Renjie Chen, Wenfeng Lin, Yichen Zhang +5
Aligning text-to-image (T2I) diffusion models with Direct Preference Optimization (DPO) has shown notable improvements in generation quality. However, applying DPO to T2I faces two…
CascadeV: An Implementation of Wurstchen Architecture for Video Generation
Wenfeng Lin, Jiangchuan Wei, Boyuan Liu +3
Recently, with the tremendous success of diffusion models in the field of text-to-image (T2I) generation, increasing attention has been directed toward their potential in text-to-v…