192 citations · 206 across the 19 of their papers we have counts for
22 papers
End-to-End Stability of Online Active Learning in Large-Scale Neural Systems
Shuiwen Shen, Jinhua Zhang, Chenlei Hou +6
Online Active Learning (OAL) aims to extend deep learning from static inference after offline training to continuous adaptation during real-time interaction with a changing physica…
SWIM: Vision-Language-Grounded Soft Whole-Body Interactive Manipulation
Tingcong Liu, Aye Phyu Phyu Aung, Junjie Xiong +4
Soft and continuum robots enable manipulation through distributed body deformation and contact, yet translating language and visual context into executable whole-body actuation rem…
RDEx-CASK: Cauchy Mutation, Archive, and Stagnation Kick for RDEx-CSOP
Dikshant, Dikshit Chauhan, Chen Hao +3
We extend RDEx-CSOP with 3 changes that target stagnation & late-stage variance, plus minor parameter tuning. The second scale factor in the standard branch is sampled independentl…
Aligning LLMs with Graph Neural Solvers for Combinatorial Optimization
Shaodi Feng, Zhuoyi Lin, Yaoxin Wu +4
Recent research has demonstrated the effectiveness of large language models (LLMs) in solving combinatorial optimization problems (COPs) by representing tasks and instances in natu…
DRAGON: LLM-Driven Decomposition and Reconstruction Agents for Large-Scale Combinatorial Optimization
Shengkai Chen, Zhiguang Cao, Jianan Zhou +5
Large Language Models (LLMs) have recently shown promise in addressing combinatorial optimization problems (COPs) through prompt-based strategies. However, their scalability and ge…
TS-HINT: Enhancing Semiconductor Time Series Regression Using Attention Hints From Large Language Model Reasoning
Jonathan Adam Rico, Nagarajan Raghavan, Senthilnath Jayavelu
Existing data-driven methods rely on the extraction of static features from time series to approximate the material removal rate (MRR) of semiconductor manufacturing processes such…
Bridging Synthetic and Real Routing Problems via LLM-Guided Instance Generation and Progressive Adaptation
Jianghan Zhu, Yaoxin Wu, Zhuoyi Lin +5
Recent advances in Neural Combinatorial Optimization (NCO) methods have significantly improved the capability of neural solvers to handle synthetic routing instances. Nonetheless,…
Incremental Multistep Forecasting of Battery Degradation Using Pseudo Targets
Jonathan Adam Rico, Nagarajan Raghavan, Senthilnath Jayavelu
Data-driven models accurately perform early battery prognosis to prevent equipment failure and further safety hazards. Most existing machine learning (ML) models work in offline mo…
Lifelong Learner: Discovering Versatile Neural Solvers for Vehicle Routing Problems
Shaodi Feng, Zhuoyi Lin, Jianan Zhou +5
Deep learning has been extensively explored to solve vehicle routing problems (VRPs), which yields a range of data-driven neural solvers with promising outcomes. However, most neur…
Compound Fault Diagnosis for Train Transmission Systems Using Deep Learning with Fourier-enhanced Representation
Jonathan Adam Rico, Nagarajan Raghavan, Senthilnath Jayavelu
Fault diagnosis prevents train disruptions by ensuring the stability and reliability of their transmission systems. Data-driven fault diagnosis models have several advantages over…
Stochastic Approximation and Brownian Repulsion based Evolutionary Search
Rajdeep Dutta, T Venkatesh Varma, Saikat Sarkar +4
Many global optimization algorithms of the memetic variety rely on some form of stochastic search, and yet they often lack a sound probabilistic basis. Without a recourse to the po…
XMOL: Explainable Multi-property Optimization of Molecules
Aye Phyu Phyu Aung, Jay Chaudhary, Ji Wei Yoon +1
Molecular optimization is a key challenge in drug discovery and material science domain, involving the design of molecules with desired properties. Existing methods focus predomina…
Caption, Create, Continue: Continual Learning with Pre-trained Generative Vision-Language Models
Indu Solomon, Aye Phyu Phyu Aung, Uttam Kumar +1
Continual learning (CL) enables models to adapt to evolving data streams without catastrophic forgetting, a fundamental requirement for real-world AI systems. However, the current…
U-TELL: Unsupervised Task Expert Lifelong Learning
Indu Solomon, Aye Phyu Phyu Aung, Uttam Kumar +1
Continual learning (CL) models are designed to learn new tasks arriving sequentially without re-training the network. However, real-world ML applications have very limited label in…
Cross-Problem Learning for Solving Vehicle Routing Problems
Zhuoyi Lin, Yaoxin Wu, Bangjian Zhou +4
Existing neural heuristics often train a deep architecture from scratch for each specific vehicle routing problem (VRP), ignoring the transferable knowledge across different VRP va…
S-REINFORCE: A Neuro-Symbolic Policy Gradient Approach for Interpretable Reinforcement Learning
Rajdeep Dutta, Qincheng Wang, Ankur Singh +3
This paper presents a novel RL algorithm, S-REINFORCE, which is designed to generate interpretable policies for dynamic decision-making tasks. The proposed algorithm leverages two…
Robust Representation Learning with Self-Distillation for Domain Generalization
Ankur Singh, Senthilnath Jayavelu
Despite the recent success of deep neural networks, there remains a need for effective methods to enhance domain generalization using vision transformers. In this paper, we propose…
Latent Preserving Generative Adversarial Network for Imbalance classification
Tanmoy Dam, Md Meftahul Ferdaus, Mahardhika Pratama +3
Many real-world classification problems have imbalanced frequency of class labels; a well-known issue known as the "class imbalance" problem. Classic classification algorithms tend…
Does Adversarial Oversampling Help us?
Tanmoy Dam, Md Meftahul Ferdaus, Sreenatha G. Anavatti +2
Traditional oversampling methods are generally employed to handle class imbalance in datasets. This oversampling approach is independent of the classifier; thus, it does not offer…
Predicting antimicrobial activity of conjugated oligoelectrolyte molecules via machine learning
Armi Tiihonen, Sarah J. Cox-Vazquez, Qiaohao Liang +12
New antibiotics are needed to battle growing antibiotic resistance, but the development process from hit, to lead, and ultimately to a useful drug, takes decades. Although progress…
DO-GAN: A Double Oracle Framework for Generative Adversarial Networks
Aye Phyu Phyu Aung, Xinrun Wang, Runsheng Yu +3
In this paper, we propose a new approach to train Generative Adversarial Networks (GANs) where we deploy a double-oracle framework using the generator and discriminator oracles. GA…
An invertible crystallographic representation for general inverse design of inorganic crystals with targeted properties
Zekun Ren, Siyu Isaac Parker Tian, Juhwan Noh +14
Realizing general inverse design could greatly accelerate the discovery of new materials with user-defined properties. However, state-of-the-art generative models tend to be limite…