20 citations · 59 across the 35 of their papers we have counts for
35 papers
PG-3DGS: Optimizing 3D Gaussian Splatting to Satisfy Physics Objectives
Zachary Lee, Maxwell Jacobson, Yexiang Xue
Recent advances in Gaussian Splatting have enabled fast, high-fidelity 3D scene generation, yet these methods remain purely visual and lack an understanding of how shapes behave in…
Enforcing Constraints in Generative Sampling via Adaptive Correction Scheduling
Noah Trupin, Yexiang Xue
Hard constraints in generative sampling are typically enforced by projection, applied either once at the end of sampling or after every update. This binary framing overlooks a fund…
Zero-shot Imitation Learning by Latent Topology Mapping
Maxwell J. Jacobson, Yexiang Xue
Imitation learning is effective for training agents when expert demonstrations are available, but collecting demonstrations for every complex task in an environment is costly. We s…
Reducing Hallucinations in LLM-based Scientific Literature Analysis Using Peer Context Outlier Detection
Daniel Xie, Maxwell J. Jacobson, Adil Wazeer +3
Reducing hallucinations in Large Language Models (LLMs) is essential for accurate data extraction from large text corpora. Current methods, like prompt engineering and chain-of-tho…
A Multi-Agent Human-LLM Collaborative Framework for Closed-Loop Scientific Literature Summarization
Maxwell J. Jacobson, Daniel Xie, Jackson Shen +6
Scientific discovery is slowed by fragmented literature that requires excessive human effort to gather, analyze, and understand. AI tools, including autonomous summarization and qu…
Vertical Symbolic Regression via Deep Policy Gradient
Nan Jiang, Md Nasim, Yexiang Xue
Vertical Symbolic Regression (VSR) recently has been proposed to expedite the discovery of symbolic equations with many independent variables from experimental data. VSR reduces th…
Vertical Symbolic Regression
Nan Jiang, Md Nasim, Yexiang Xue
Automating scientific discovery has been a grand goal of Artificial Intelligence (AI) and will bring tremendous societal impact. Learning symbolic expressions from experimental dat…
End-to-end Phase Field Model Discovery Combining Experimentation, Crowdsourcing, Simulation and Learning
Md Nasim, Anter El-Azab, Xinghang Zhang +1
The availability of tera-byte scale experiment data calls for AI driven approaches which automatically discover scientific models from data. Nonetheless, significant challenges pre…
Hypothesis Network Planned Exploration for Rapid Meta-Reinforcement Learning Adaptation
Maxwell Joseph Jacobson, Rohan Menon, John Zeng +1
Meta-Reinforcement Learning (Meta-RL) learns optimal policies across a series of related tasks. A central challenge in Meta-RL is rapidly identifying which previously learned task…
Integrating Symbolic Reasoning into Neural Generative Models for Design Generation
Maxwell Joseph Jacobson, Yexiang Xue
Design generation requires tight integration of neural and symbolic reasoning, as good design must meet explicit user needs and honor implicit rules for aesthetics, utility, and co…
Racing Control Variable Genetic Programming for Symbolic Regression
Nan Jiang, Yexiang Xue
Symbolic regression, as one of the most crucial tasks in AI for science, discovers governing equations from experimental data. Popular approaches based on genetic programming, Mont…
Efficient Learning of PDEs via Taylor Expansion and Sparse Decomposition into Value and Fourier Domains
Md Nasim, Yexiang Xue
Accelerating the learning of Partial Differential Equations (PDEs) from experimental data will speed up the pace of scientific discovery. Previous randomized algorithms exploit spa…
Solving Satisfiability Modulo Counting for Symbolic and Statistical AI Integration With Provable Guarantees
Jinzhao Li, Nan Jiang, Yexiang Xue
Satisfiability Modulo Counting (SMC) encompasses problems that require both symbolic decision-making and statistical reasoning. Its general formulation captures many real-world pro…
Adversarial Style Transfer for Robust Policy Optimization in Deep Reinforcement Learning
Md Masudur Rahman, Yexiang Xue
This paper proposes an algorithm that aims to improve generalization for reinforcement learning agents by removing overfitting to confounding features. Our approach consists of a m…
Symbolic Regression via Control Variable Genetic Programming
Nan Jiang, Yexiang Xue
Learning symbolic expressions directly from experiment data is a vital step in AI-driven scientific discovery. Nevertheless, state-of-the-art approaches are limited to learning sim…
Adversarial Policy Optimization in Deep Reinforcement Learning
Md Masudur Rahman, Yexiang Xue
The policy represented by the deep neural network can overfit the spurious features in observations, which hamper a reinforcement learning agent from learning effective policy. Thi…
Robust Policy Optimization in Deep Reinforcement Learning
Md Masudur Rahman, Yexiang Xue
The policy gradient method enjoys the simplicity of the objective where the agent optimizes the cumulative reward directly. Moreover, in the continuous action domain, parameterized…
Learning Markov Random Fields for Combinatorial Structures via Sampling through Lovász Local Lemma
Nan Jiang, Yi Gu, Yexiang Xue
Learning to generate complex combinatorial structures satisfying constraints will have transformative impacts in many application domains. However, it is beyond the capabilities of…
Human-centered XAI for Burn Depth Characterization
Maxwell J. Jacobson, Daniela Chanci Arrubla, Maria Romeo Tricas +4
Approximately 1.25 million people in the United States are treated each year for burn injuries. Precise burn injury classification is an important aspect of the medical AI field. I…
On the Value of Behavioral Representations for Dense Retrieval
Nan Jiang, Dhivya Eswaran, Choon Hui Teo +4
We consider text retrieval within dense representational space in real-world settings such as e-commerce search where (a) document popularity and (b) diversity of queries associate…
Bootstrap State Representation using Style Transfer for Better Generalization in Deep Reinforcement Learning
Md Masudur Rahman, Yexiang Xue
Deep Reinforcement Learning (RL) agents often overfit the training environment, leading to poor generalization performance. In this paper, we propose Thinker, a bootstrapping metho…
Provable Constrained Stochastic Convex Optimization with XOR-Projected Gradient Descent
Fan Ding, Yijie Wang, Jianzhu Ma +1
Provably solving stochastic convex optimization problems with constraints is essential for various problems in science, business, and statistics. Recently proposed XOR-Stochastic G…
A Fast Randomized Algorithm for Massive Text Normalization
Nan Jiang, Chen Luo, Vihan Lakshman +2
Many popular machine learning techniques in natural language processing and data mining rely heavily on high-quality text sources. However real-world text datasets contain a signif…
Language Generation via Combinatorial Constraint Satisfaction: A Tree Search Enhanced Monte-Carlo Approach
Maosen Zhang, Nan Jiang, Lei Li +1
Generating natural language under complex constraints is a principled formulation towards controllable text generation. We present a framework to allow specification of combinatori…