20 papers
WAM-TTT: Steering World-Action Models by Watching Human Play at Test Time
Yusen Feng, Bingchen Han, Jiangran Lyu +13
Steering robot foundation models (RFMs) toward new task variants or user-preferred behaviors remains challenging, often requiring additional robot demonstrations, task-specific fin…
S-Agent: Spatial Tool-Use Elicits Reasoning for Spatial Intelligence
Yalun Dai, Hao Li, Shulin Tian +10
Real-world spatial intelligence requires reasoning over a continuous and evolving 3D world, yet existing VLMs and tool-augmented agents largely remain tied to static, stateless inf…
A Unified Latent Space Disentanglement VAE Framework with Robust Disentanglement Effectiveness Evaluation
Xiaoan Lang, Md Mostafizer Rahman, Fang Liu
Evaluating and interpreting latent representations, such as variational autoencoders (VAEs), remains a significant challenge for diverse data types, especially when ground-truth ge…
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players
Fangfu Liu, Kai He, Tianchang Shen +7
World models for interactive video generation have largely focused on single-agent settings, where future observations are generated from a single control signal. However, many gen…
GEM: Generative Supervision Helps Embodied Intelligence
Ruowen Zhao, Bangguo Li, Zuyan Liu +9
Embodied Vision-Language Models (VLMs) have demonstrated impressive performance and generalization in robotics, particularly within Vision-Language-Action frameworks. However, a si…
Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence
Diankun Wu, Fangfu Liu, Yi-Hsin Hung +1
Recent advancements in Multimodal Large Language Models (MLLMs) have significantly enhanced performance on 2D visual tasks. However, improving their spatial intelligence remains a…