Song Wang
6 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
SAFEDREAM introduces a lightweight, external world-model framework that proactively detects multi-turn jailbreak attacks by modeling cumulative safety erosion and predicting early failure points.
The paper proposes a novel framework combining behavior-invariant task representation learning and a Transformer-based world model to achieve robust generalization in offline meta-reinforcement learning, particularly in sparse-reward settings.
The paper proposes a novel framework combining behavior-invariant task representation learning and a Transformer-based world model to achieve robust generalization in offline meta-reinforcement learning, particularly in sparse-reward settings.
This paper proposes a new framework, Aligned Refinement Policy (ARP), to learn visuomotor policies for long-horizon manipulation tasks.
JoyNexus is a multi-tenant service for VLA model supervised fine-tuning, reinforcement learning, and evaluation, which decouples services, introduces group batching, and improves training efficiency.
ClearGS improves 3D Gaussian Splatting from handheld videos with uneven viewpoint coverage and mixed frame quality.
Papers
ClearGS: Reliability-Aware Gaussian Splatting from Handheld Videos
Xuanzhi Liu, Xinyi Wu, Hang Pan, Wensi Huang +3 more
ClearGS improves 3D Gaussian Splatting from handheld videos with uneven viewpoint coverage and mixed frame quality.