4 papers
Rethinking Depth Pruning for Vision Transformers: A Heterogeneity-Aware Perspective
Zhenfeng Su, Kang Zhao, Han Bao +4
While prior studies have successfully compressed vision Transformers (ViTs) through various pruning techniques, most have concentrated on width pruning to achieve significant reduc…
Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL
Sudong Wang, Weiquan Huang, Xiaomin Yu +9
The standard post-training recipe for large multimodal models (LMMs) applies supervised fine-tuning (SFT) on curated demonstrations followed by reinforcement learning with verifiab…
SECURE: Stable Early Collision Understanding via Robust Embeddings in Autonomous Driving
Wenjing Wang, Wenxuan Wang, Songning Lai
While deep learning has significantly advanced accident anticipation, the robustness of these safety-critical systems against real-world perturbations remains a major challenge. We…
ST-VLA: Enabling 4D-Aware Spatiotemporal Understanding for General Robot Manipulation
You Wu, Zixuan Chen, Cunxu Ou +9
Robotic manipulation in open-world environments requires reasoning across semantics, geometry, and long-horizon action dynamics. Existing hierarchical Vision-Language-Action (VLA)…