10 papers
DataClaw0: Agentic Tailoring Multimodal Data from Raw Streams
Cong Wan, Zeyu Guo, Zijian Cai +6
Raw multimodal streams are abundant but noisy, redundant, and unaligned with any particular training objective. Turning them into supervision today means either brittle heuristics…
ReMoT: Reinforcement Learning with Motion Contrast Triplets
Cong Wan, Zeyu Guo, Jiangyang Li +5
We present ReMoT, a unified training paradigm to systematically address the fundamental shortcomings of VLMs in spatio-temporal consistency -- a critical failure point in navigatio…
ProSR: Process-Shaped Spatial Reasoning for Reliable Chain-of-Thought in VLMs
Jiangyang Li, Cong Wan, Changjie Wu +8
Reliable spatial reasoning remains a core bottleneck for vision-language models (VLMs). Existing mainstream training paradigms for spatial reasoning largely rely on outcome alignme…
DeepSight: Long-Horizon World Modeling via Latent States Prediction for End-to-End Autonomous Driving
Lingjun Zhang, Changjie Wu, Linzhe Shi +6
End-to-end autonomous driving systems are increasingly integrating Vision-Language Model (VLM) architectures, incorporating text reasoning or visual reasoning to enhance the robust…
Trajectory-Diversity-Driven Robust Vision-and-Language Navigation
Jiangyang Li, Cong Wan, SongLin Dong +4
Vision-and-Language Navigation (VLN) requires agents to navigate photo-realistic environments following natural language instructions. Current methods predominantly rely on imitati…
Is Parameter Isolation Better for Prompt-Based Continual Learning?
Jiangyang Li, Chenhao Ding, Songlin Dong +4
Prompt-based continual learning methods effectively mitigate catastrophic forgetting. However, most existing methods assign a fixed set of prompts to each task, completely isolatin…