9 papers
Euler: Towards Human-Centered Multi-Agent Mathematical Discovery
Qiuyu Chen, Qi Wang, Liang Xu +3
Mathematical research drives scientific discovery, and recent advances in AI for mathematics have shown that language-model agents can solve challenging problems and develop substa…
Efficient On-policy Visual-RL via Stochastic Decoupled Policy Gradient
Haoxiang You, Yilang Liu, Davis Zong +5
We present the stochastic decoupled policy gradient (SDPG), a lightweight visual reinforcement learning (RL) method that trains diverse visuomotor control policies end-to-end withi…
EgoIntrospect: An Egocentric Dataset and Benchmark for User-Centric Internal State Reasoning
Zeyu Wang, Chang Liu, Eduardus Tjitrahardja +22
Despite extensive efforts on egocentric video datasets and benchmarks, understanding users' internal states, which is crucial for enabling seamless AI assistant experiences, remain…
OrbiSim: World Models as Differentiable Physics Engines for Embodied Intelligence
Jiajian Li, Jingyuan Huang, Junru Gong +3
We present OrbiSim, a novel robotic simulation paradigm that redefines world models as a fully differentiable physics engine for embodied intelligence. Unlike prior world models th…
Goal-Driven Reward by Video Diffusion Models for Reinforcement Learning
Qi Wang, Mian Wu, Yuyang Zhang +7
Reinforcement Learning (RL) has achieved remarkable success in various domains, yet it often relies on carefully designed programmatic reward functions to guide agent behavior. Des…
Interpretable Single-View 3D Gaussian Splatting using Unsupervised Hierarchical Disentangled Representation Learning
Yuyang Zhang, Baao Xie, Hu Zhu +4
Gaussian Splatting (GS) has recently marked a significant advancement in 3D reconstruction, delivering both rapid rendering and high-quality results. However, existing 3DGS methods…
Plasticine: Accelerating Research in Plasticity-Motivated Deep Reinforcement Learning
Mingqi Yuan, Qi Wang, Guozheng Ma +8
Developing lifelong learning agents is crucial for artificial general intelligence (AGI). However, deep reinforcement learning (RL) systems often suffer from plasticity loss, where…
Disentangled World Models: Learning to Transfer Semantic Knowledge from Distracting Videos for Reinforcement Learning
Qi Wang, Zhipeng Zhang, Baao Xie +6
Training visual reinforcement learning (RL) in practical scenarios presents a significant challenge, RL agents suffer from low sample efficiency in environments wi…
Open-World Reinforcement Learning over Long Short-Term Imagination
Jiajian Li, Qi Wang, Yunbo Wang +4
Training visual reinforcement learning agents in a high-dimensional open world presents significant challenges. While various model-based methods have improved sample efficiency by…