Rectified Robust Policy Optimization for Model-Uncertain Constrained Reinforcement Learning without Strong Duality

Kavli Affiliate: Yi Zhou | First 5 Authors: Shaocong Ma, Shaocong Ma, , , | Summary: The goal of robust constrained reinforcement learning (RL) is to optimize an agent’s performance under the worst-case model uncertainty while satisfying safety or resource constraints. In this paper, we demonstrate that strong duality does not generally hold in robust […]


Continue.. Rectified Robust Policy Optimization for Model-Uncertain Constrained Reinforcement Learning without Strong Duality

Rectified Robust Policy Optimization for Model-Uncertain Constrained Reinforcement Learning without Strong Duality

Kavli Affiliate: Yi Zhou | First 5 Authors: Shaocong Ma, Shaocong Ma, , , | Summary: The goal of robust constrained reinforcement learning (RL) is to optimize an agent’s performance under the worst-case model uncertainty while satisfying safety or resource constraints. In this paper, we demonstrate that strong duality does not generally hold in robust […]


Continue.. Rectified Robust Policy Optimization for Model-Uncertain Constrained Reinforcement Learning without Strong Duality

Bridging the Gap in Ophthalmic AI: MM-Retinal-Reason Dataset and OphthaReason Model toward Dynamic Multimodal Reasoning

Kavli Affiliate: Yi Zhou | First 5 Authors: Ruiqi Wu, Ruiqi Wu, , , | Summary: Multimodal large language models (MLLMs) have recently demonstrated remarkable reasoning abilities with reinforcement learning paradigm. Although several multimodal reasoning models have been explored in the medical domain, most of them focus exclusively on basic reasoning, which refers to shallow […]


Continue.. Bridging the Gap in Ophthalmic AI: MM-Retinal-Reason Dataset and OphthaReason Model toward Dynamic Multimodal Reasoning

Bridging the Gap in Ophthalmic AI: MM-Retinal-Reason Dataset and OphthaReason Model toward Dynamic Multimodal Reasoning

Kavli Affiliate: Yi Zhou | First 5 Authors: Ruiqi Wu, Ruiqi Wu, , , | Summary: Multimodal large language models (MLLMs) have recently demonstrated remarkable reasoning abilities with reinforcement learning paradigm. Although several multimodal reasoning models have been explored in the medical domain, most of them focus exclusively on basic reasoning, which refers to shallow […]


Continue.. Bridging the Gap in Ophthalmic AI: MM-Retinal-Reason Dataset and OphthaReason Model toward Dynamic Multimodal Reasoning

Integrated magneto-optic based magnetometer: classical and quantum limits

Kavli Affiliate: John E. Bowers | First 5 Authors: Paolo Pintus, Paolo Pintus, , , | Summary: Magnetic field sensors with high sensitivity and spatial resolution have profoundly impacted diverse applications ranging from geo-positioning and navigation to medical imaging, materials science, and space exploration. However, the use of high-precision magnetometers is often limited due to […]


Continue.. Integrated magneto-optic based magnetometer: classical and quantum limits

CSTEapp: An interactive R-Shiny application of the covariate-specific treatment effect curve for visualizing individualized treatment rule

Kavli Affiliate: Yi Zhou | First 5 Authors: , , , , | Summary: In precision medicine, deriving the individualized treatment rule (ITR) is crucial for recommending the optimal treatment based on patients’ baseline covariates. The covariate-specific treatment effect (CSTE) curve presents a graphical method to visualize an ITR within a causal inference framework. Recent […]


Continue.. CSTEapp: An interactive R-Shiny application of the covariate-specific treatment effect curve for visualizing individualized treatment rule

Schrödingerization for quantum linear systems problems

Kavli Affiliate: Long Zhang | First 5 Authors: Yin Yang, Yin Yang, , , | Summary: We develop a quantum algorithm for linear algebraic equations Ax=b from the perspective of Schr"odingerization-form problems, which are characterized by a system of linear convection equations in one higher dimension. When A is positive definite, the solution x can […]


Continue.. Schrödingerization for quantum linear systems problems

Autoregressive Typical Thermal States

Kavli Affiliate: Leon Balents | First 5 Authors: Tarun Advaith Kumar, Tarun Advaith Kumar, , , | Summary: A variety of generative neural networks recently adopted from machine learning have provided promising strategies for studying quantum matter. In particular, the success of autoregressive models in natural language processing has motivated their use as variational ans"atze, […]


Continue.. Autoregressive Typical Thermal States

GeoGPT-RAG Technical Report

Kavli Affiliate: Long Zhang | First 5 Authors: Fei Huang, Fei Huang, , , | Summary: GeoGPT is an open large language model system built to advance research in the geosciences. To enhance its domain-specific capabilities, we integrated Retrieval Augmented Generation(RAG), which augments model outputs with relevant information retrieved from an external knowledge source. GeoGPT […]


Continue.. GeoGPT-RAG Technical Report

Mass Loss and Subsequent Thermal Evolution of Surviving Helium White Dwarfs Shocked by Thermonuclear Supernovae

Kavli Affiliate: Lars Bildsten | First 5 Authors: Tin Long Sunny Wong, Tin Long Sunny Wong, , , | Summary: Following a type Ia supernova (SN Ia) in a double white dwarf (WD) binary, a surviving WD companion leaves at its orbital velocity $approx 1$,000 – 3,000 km/s. The Gaia mission has discovered seven such […]


Continue.. Mass Loss and Subsequent Thermal Evolution of Surviving Helium White Dwarfs Shocked by Thermonuclear Supernovae