Publications (17)
Modified Kedem-Katchalsky equations for osmosis through nano-pore
Liangsuo Shu, Xiaokang Liu, Yingjie Li +4
This work presents a modified Kedem-Katchalsky equations for osmosis through nano-pore. osmotic reflection coefficient of a solute was found to be chiefly affected by the entrance…
Gemini Robotics: Bringing AI into the Physical World
Gemini Robotics Team, Saminda Abeyruwan, Joshua Ainslie +115
Recent advancements in large multimodal models have led to the emergence of remarkable generalist capabilities in digital domains, yet their translation to physical agents such as…
Penney's game for permutations
Sergi Elizalde, Yixin Lin
We consider the permutation analogue of Penney's game for words. Two players, in order, each choose a permutation of length ; then a sequence of independent random values fr…
Masked Trajectory Models for Prediction, Representation, and Control
Philipp Wu, Arjun Majumdar, Kevin Stone +4
We introduce Masked Trajectory Models (MTM) as a generic abstraction for sequential decision making. MTM takes a trajectory, such as a state-action sequence, and aims to reconstruc…
Curious iLQR: Resolving Uncertainty in Model-based RL
Sarah Bechtle, Yixin Lin, Akshara Rai +2
Curiosity as a means to explore during reinforcement learning problems has recently become very popular. However, very little progress has been made in utilizing curiosity for lear…
Proc4Gem: Foundation models for physical agency through procedural generation
Yixin Lin, Jan Humplik, Sandy H. Huang +18
In robot learning, it is common to either ignore the environment semantics, focusing on tasks like whole-body control which only require reasoning about robot-environment contacts,…
Learning State-Dependent Losses for Inverse Dynamics Learning
Kristen Morse, Neha Das, Yixin Lin +3
Being able to quickly adapt to changes in dynamics is paramount in model-based control for object manipulation tasks. In order to influence fast adaptation of the inverse dynamics…
Speech Emotion Recognition Via CNN-Transformer and Multidimensional Attention Mechanism
Xiaoyu Tang, Yixin Lin, Ting Dang +2
Speech Emotion Recognition (SER) is crucial in human-machine interactions. Mainstream approaches utilize Convolutional Neural Networks or Recurrent Neural Networks to learn local e…
Atomic Coherence Assisted Multipartite Entanglement Generation with DELC Four-Wave Mixing
Yuliang Liu, Jiajia Wei, Mengqi Niu +7
Multipartite entanglement plays an important role in quantum information processing and quantum metrology. Here, the dressing-energy-level-cascaded (DELC) four-wave mixing (FWM) pr…
Differentiable and Learnable Robot Models
Franziska Meier, Austin Wang, Giovanni Sutanto +2
Building differentiable simulations of physical processes has recently received an increasing amount of attention. Specifically, some efforts develop differentiable robotic physics…
Efficient and Interpretable Robot Manipulation with Graph Neural Networks
Yixin Lin, Austin S. Wang, Eric Undersander +1
Manipulation tasks, like loading a dishwasher, can be seen as a sequence of spatial constraints and relationships between different objects. We aim to discover these rules from dem…
Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?
Arjun Majumdar, Karmesh Yadav, Sergio Arnaud +12
We present the largest and most comprehensive empirical study of pre-trained visual representations (PVRs) or visual 'foundation models' for Embodied AI. First, we curate CortexBen…
Transformers are Adaptable Task Planners
Vidhi Jain, Yixin Lin, Eric Undersander +2
Every home is different, and every person likes things done in their particular way. Therefore, home robots of the future need to both reason about the sequential nature of day-to-…
RB2: Robotic Manipulation Benchmarking with a Twist
Sudeep Dasari, Jianren Wang, Joyce Hong +12
Benchmarks offer a scientific way to compare algorithms using objective performance metrics. Good benchmarks have two features: (a) they should be widely useful for many research g…
Encoding Physical Constraints in Differentiable Newton-Euler Algorithm
Giovanni Sutanto, Austin S. Wang, Yixin Lin +4
The recursive Newton-Euler Algorithm (RNEA) is a popular technique for computing the dynamics of robots. RNEA can be framed as a differentiable computational graph, enabling the dy…
A Hybrid Framework for Blood Vessel Morphology Classification: Discrete Geometry-based Tortuosity Feature Measurement, Information Gain-based Feature Selection, and Random Forest Classification
Yu Zhong, Jingzhi Guo, Luyao Li +5
The paper presents a framework that quantifies and classifies internal carotid artery tortuosity using discrete geometric features, information‑gain based feature selection, and a…
MoDem: Accelerating Visual Model-Based Reinforcement Learning with Demonstrations
Nicklas Hansen, Yixin Lin, Hao Su +3
Poor sample efficiency continues to be the primary challenge for deployment of deep Reinforcement Learning (RL) algorithms for real-world applications, and in particular for visuo-…