6 papers
DeepVision-103K: A Visually Diverse, Broad-Coverage, and Verifiable Mathematical Dataset for Multimodal Reasoning
Haoxiang Sun, Lizhen Xu, Bing Zhao +5
Reinforcement Learning with Verifiable Rewards (RLVR) has been shown effective in enhancing the visual reflection and reasoning capabilities of Large Multimodal Models (LMMs). Howe…
SA-VLA: Spatially-Aware Flow-Matching for Vision-Language-Action Reinforcement Learning
Xu Pan, Zhenglin Wan, Xingrui Yu +6
Vision-Language-Action (VLA) models exhibit strong generalization in robotic manipulation, yet reinforcement learning (RL) fine-tuning often degrades robustness under spatial distr…
Scaling Laws of Motion Forecasting and Planning -- Technical Report
Mustafa Baniodeh, Kratarth Goel, Scott Ettinger +14
We study the empirical scaling laws of a family of encoder-decoder autoregressive transformer models on the task of joint motion forecasting and planning in the autonomous driving…
Beyond flattening: a geometrically principled positional encoding for vision transformers with Weierstrass elliptic functions
Zhihang Xin, Xitong Hu, Rui Wang
Vision Transformers have demonstrated remarkable success in computer vision tasks, yet their reliance on learnable one-dimensional positional embeddings fundamentally disrupts the…
Discovering Symmetry Breaking in Physical Systems with Relaxed Group Convolution
Rui Wang, Elyssa Hofgard, Han Gao +2
Modeling symmetry breaking is essential for understanding the fundamental changes in the behaviors and properties of physical systems, from microscopic particle interactions to mac…
Relaxed Equivariant Graph Neural Networks
Elyssa Hofgard, Rui Wang, Robin Walters +1
3D Euclidean symmetry equivariant neural networks have demonstrated notable success in modeling complex physical systems. We introduce a framework for relaxed graph equivari…