All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Parallel Training Of Deep Networks With Local Updates**arXiv ID:** 2012.03837 **Authors:** Michael Laskin, Luke Metz, Seth Nabarro, Mark Saroufim, Badreddine Noune, Carlo Luschi, Jascha Sohl-Dickstein, Pieter Abbeel **Published:** 2020-12-07T16:38:45Z **Abstract:** Deep learning models trained on large data sets have been widely successful in both vision and language domains. As state-of-the-art deep learning architectures have continued to grow in parameter count so have the compute budgets and times required to train them, increasing the need...Votes: 0GitHub stars: 3
- Popnasv3 A Paretooptimal Neural Architecture Search Solution For Image And Time Series Classification**arXiv ID:** 2212.06735 **Authors:** Andrea Falanti, Eugenio Lomurno, Danilo Ardagna, Matteo Matteucci **Published:** 2022-12-13T17:14:14Z **Abstract:** The automated machine learning (AutoML) field has become increasingly relevant in recent years. These algorithms can develop models without the need for expert knowledge, facilitating the application of machine learning techniques in the industry. Neural Architecture Search (NAS) exploits deep learning techniques to autonomously produce neur...Votes: 0GitHub stars: 3
- Post Training At The Edge Of Detectability A GamePost-Training at the Edge of Detectability: A Game-Theoretic Approach to Fine-TuningVotes: 0GitHub stars: 3
- Predicting The Future With Transformational States**arXiv ID:** 1803.09760 **Authors:** Andrew Jaegle, Oleh Rybkin, Konstantinos G. Derpanis, Kostas Daniilidis **Published:** 2018-03-26T18:00:07Z **Abstract:** An intelligent observer looks at the world and sees not only what is, but what is moving and what can be moved. In other words, the observer sees how the present state of the world can transform in the future. We propose a model that predicts future images by learning to represent the present state and its transformation given only a s...Votes: 0GitHub stars: 3
- Qualitydiversity Optimization As Multiobjective Optimization**arXiv ID:** 2602.00478 **Authors:** Xi Lin, Ping Guo, Yilu Liu, Qingfu Zhang, Jianyong Sun **Published:** 2026-01-31T03:01:13Z **Abstract:** The Quality-Diversity (QD) optimization aims to discover a collection of high-performing solutions that simultaneously exhibit diverse behaviors within a user-defined behavior space. This paradigm has stimulated significant research interest and demonstrated practical utility in domains including robot control, creative design, and adversarial sample g...Votes: 0GitHub stars: 3
- Recurrent Neural Networks With External Memory For Language Understanding**arXiv ID:** 1506.00195 **Authors:** Baolin Peng, Kaisheng Yao **Published:** 2015-05-31T05:10:03Z **Abstract:** Recurrent Neural Networks (RNNs) have become increasingly popular for the task of language understanding. In this task, a semantic tagger is deployed to associate a semantic label to each word in an input sequence. The success of RNN may be attributed to its ability to memorize long-term dependence that relates the current-time semantic label prediction to the observations many ti...Votes: 0GitHub stars: 3
- Robust Unsupervised Multiobject Tracking In Noisy Environments**arXiv ID:** 2105.10005 **Authors:** C. -H. Huck Yang, Mohit Chhabra, Y. -C. Liu, Quan Kong, Tomoaki Yoshinaga, Tomokazu Murakami **Published:** 2021-05-20T19:38:03Z **Abstract:** Physical processes, camera movement, and unpredictable environmental conditions like the presence of dust can induce noise and artifacts in video feeds. We observe that popular unsupervised MOT methods are dependent on noise-free inputs. We show that the addition of a small amount of artificial random noise causes ...Votes: 0GitHub stars: 3
- Scalable Recollections For Continual Lifelong Learning**arXiv ID:** 1711.06761 **Authors:** Matthew Riemer, Tim Klinger, Djallel Bouneffouf, Michele Franceschini **Published:** 2017-11-17T23:00:11Z **Abstract:** Given the recent success of Deep Learning applied to a variety of single tasks, it is natural to consider more human-realistic settings. Perhaps the most difficult of these settings is that of continual lifelong learning, where the model must learn online over a continuous stream of non-stationary data. A successful continual lifelong le...Votes: 0GitHub stars: 3
- Scaling Mapelites To Deep Neuroevolution**arXiv ID:** 2003.01825 **Authors:** Cédric Colas, Joost Huizinga, Vashisht Madhavan, Jeff Clune **Published:** 2020-03-03T23:02:37Z **Abstract:** Quality-Diversity (QD) algorithms, and MAP-Elites (ME) in particular, have proven very useful for a broad range of applications including enabling real robots to recover quickly from joint damage, solving strongly deceptive maze tasks or evolving robot morphologies to discover new gaits. However, present implementations of MAP-Elites and other QD ...Votes: 0GitHub stars: 3
- Secure Decentralized Federated Learning Gossip Virtual VotinggspDAG-FL: secure decentralized federated learning via gossip and virtual voting. Derives consensus from gossip history, uses Hashgraph-style virtual voting on compact DAG. Byzantine resilience with payload validation and semantic audit. Activation: decentralized federated learning, gossip protocol, virtual voting, Byzantine resilience, ledger-assisted FL.Votes: 0GitHub stars: 3
- Semantic Bottleneck For Computer Vision Tasks**arXiv ID:** 1811.02234 **Authors:** Maxime Bucher, Stéphane Herbin, Frédéric Jurie **Published:** 2018-11-06T09:01:02Z **Abstract:** This paper introduces a novel method for the representation of images that is semantic by nature, addressing the question of computation intelligibility in computer vision tasks. More specifically, our proposition is to introduce what we call a semantic bottleneck in the processing pipeline, which is a crossing point in which the representation of the image is...Votes: 0GitHub stars: 3
- Semantically Decomposing The Latent Spaces Of Generative Adversarial Networks**arXiv ID:** 1705.07904 **Authors:** Chris Donahue, Zachary C. Lipton, Akshay Balsubramani, Julian McAuley **Published:** 2017-05-22T18:00:02Z **Abstract:** We propose a new algorithm for training generative adversarial networks that jointly learns latent codes for both identities (e.g. individual humans) and observations (e.g. specific photographs). By fixing the identity portion of the latent codes, we can generate diverse images of the same subject, and by fixing the observation portion, ...Votes: 0GitHub stars: 3
- Specifying The Delegated Autonomy Boundary RequireDerived from arXiv:2607.17225 - Specifying the Delegated-Autonomy Boundary: Requirements Engineering for Agentic AIVotes: 0GitHub stars: 3
- Temporally Coherent Video Anonymization Through Gan Inpainting**arXiv ID:** 2106.02328 **Authors:** Thangapavithraa Balaji, Patrick Blies, Georg Göri, Raphael Mitsch, Marcel Wasserer, Torsten Schön **Published:** 2021-06-04T08:19:44Z **Abstract:** This work tackles the problem of temporally coherent face anonymization in natural video streams.We propose JaGAN, a two-stage system starting with detecting and masking out faces with black image patches in all individual frames of the video. The second stage leverages a privacy-preserving Video Generative Ad...Votes: 0GitHub stars: 3
- The Dark Room In The Reward Channel DenseThe Dark Room in the Reward Channel: Dense Prediction Rewards Collapse GRPO-Trained LLM Agents -- and What Actually WorksVotes: 0GitHub stars: 3
- The Red Queen GöDel Machine Co Evolving Agents AndDerived from arXiv:2606.26294 - The Red Queen Gödel Machine: Co-Evolving Agents and Their EvaluatorsVotes: 0GitHub stars: 3
- Toward A Neuroinspired Creative Decoder**arXiv ID:** 1902.02399 **Authors:** Payel Das, Brian Quanz, Pin-Yu Chen, Jae-wook Ahn, Dhruv Shah **Published:** 2019-02-06T21:06:58Z **Abstract:** Creativity, a process that generates novel and meaningful ideas, involves increased association between task-positive (control) and task-negative (default) networks in the human brain. Inspired by this seminal finding, in this study we propose a creative decoder within a deep generative framework, which involves direct modulation of the neuronal...Votes: 0GitHub stars: 3
- Toward Continuous Assurance For The Democratization Of AiToward Continuous Assurance for the Democratization of AI Agent Creation in IndustryVotes: 0GitHub stars: 3
- Toward Cryptographically Verifiable Authorization For Autonomous Ai AgentsToward cryptographically verifiable authorization for autonomous AI agents: A security hypothesis, preliminary formal model, and proof-of-concept implementationVotes: 0GitHub stars: 3
- Towards Graph Neural Networks For Provably Solving Convex Optimization Problems**arXiv ID:** 2502.02446 **Authors:** Chendi Qian, Christopher Morris **Published:** 2025-02-04T16:11:41Z **Abstract:** Recently, message-passing graph neural networks (MPNNs) have shown potential for solving combinatorial and continuous optimization problems due to their ability to capture variable-constraint interactions. While existing approaches leverage MPNNs to approximate solutions or warm-start traditional solvers, they often lack guarantees for feasibility, particularly in convex opt...Votes: 0GitHub stars: 3
- Towards Less Constrained Macroneural Architecture Search**arXiv ID:** 2203.05508 **Authors:** Vasco Lopes, Luís A. Alexandre **Published:** 2022-03-10T17:53:03Z **Abstract:** Networks found with Neural Architecture Search (NAS) achieve state-of-the-art performance in a variety of tasks, out-performing human-designed networks. However, most NAS methods heavily rely on human-defined assumptions that constrain the search: architecture's outer-skeletons, number of layers, parameter heuristics and search spaces. Additionally, common search spaces consi...Votes: 0GitHub stars: 3
- Utilizing A Digital Swarm Intelligence Platform To Improve Consensus Among Radiologists And Exploring Its Applications**arXiv ID:** 2107.07341 **Authors:** Rutwik Shah, Bruno Astuto, Tyler Gleason, Will Fletcher, Justin Banaga, Kevin Sweetwood, Allen Ye, Rina Patel, Kevin McGill, Thomas Link, Jason Crane, Valentina Pedoia, Sharmila Majumdar **Published:** 2021-06-26T06:52:06Z **Abstract:** Radiologists today play a key role in making diagnostic decisions and labeling images for training A.I. algorithms. Low inter-reader reliability (IRR) can be seen between experts when interpreting challenging cases. While ...Votes: 0GitHub stars: 3
- Variational Rejection Sampling**arXiv ID:** 1804.01712 **Authors:** Aditya Grover, Ramki Gummadi, Miguel Lazaro-Gredilla, Dale Schuurmans, Stefano Ermon **Published:** 2018-04-05T07:53:41Z **Abstract:** Learning latent variable models with stochastic variational inference is challenging when the approximate posterior is far from the true posterior, due to high variance in the gradient estimates. We propose a novel rejection sampling step that discards samples from the variational posterior which are assigned low likelihoo...Votes: 0GitHub stars: 3
- Where To Intervene Benchmarking Fairness Aware Learning On DifferentiallyMachine learning models are increasingly deployed in high-stakes domains, raising concerns about both privacy and fairness. Differential Privacy (DP) has become a gold standard for privacy-preserving. Based on arXiv:2607.07471.Votes: 0GitHub stars: 3
- Self Adaptive Cps Anomaly DetectionSelf-adaptive anomaly detection for autonomous cyber-physical systems. Integrates RL-based detector selection, ensemble drift detection, and human-in-the-loop retraining with catastrophic forgetting prevention.Votes: 0GitHub stars: 3
- Sg Jepa Spiking Graph EmbeddingScalable and Efficient Joint Spiking Embedding Predictive Architecture for Large-Scale Dynamic GraphsVotes: 0GitHub stars: 3
- 5g Industrial Cps SecuritySecurity implications and threat modeling for 5G communication in industrial cyber-physical systems. ICS security analysis and mitigation strategies.Votes: 0GitHub stars: 3
- A Physics Informed Framework For Pid Tuning Of CheA Physics-Informed Framework for PID Tuning of Chemical Processes Using Large Language Model AgentsVotes: 0GitHub stars: 3
- Allostatic Control Systems Goal GovernanceFramework for designing control systems that govern not only goal pursuit but also goal appropriateness in changing environments. Implements two-timescale control with fast regulation loop and slow goal governance loop.Votes: 0GitHub stars: 3
- Anomaly Detection Dynamical SystemsLog-likelihood ratio based real-time anomaly detection for dynamical systems with theoretical characterization of error rates. Identifies system anomalies from multiple possible plant models for linear Gaussian systems. Use for: anomaly detection, fault diagnosis, dynamical system monitoring, log-likelihood ratio testing, industrial control applications. Activation: anomaly detection, log-likelihood ratio, dynamical systems, industrial control, fault detection.Votes: 0GitHub stars: 3
- Anytime Lidar Resolution Scaling Object DetectionAnytime computing method for LiDAR-based 3D object detection in cyber-physical systems. Multi-resolution inference with single DNN model, deadline-aware scheduler predicts execution time for all resolutions. Deployed in simulated autonomous driving with collision-free navigation. Use when working with anytime-computing, lidar-detection, input-resolution-scaling.Votes: 0GitHub stars: 3
- Arxiv 0308025 Controlled Hierarchical Filtering Model Of NeocortControlled hierarchical filtering: Model of neocortical sensory processing (arXiv: 0308025)Votes: 0GitHub stars: 3
- Arxiv 2606 14299 What Drives Test Time Adaptation For Clip A ControWhat Drives Test-Time Adaptation for CLIP? A Controlled Empirical Study from an Update Perspective (arXiv: 2606.14299)Votes: 0GitHub stars: 3
- Arxiv 2608 05783v1 Grom Gradient Free Rapid One Shot Machine Unlearni**arXiv ID:** 2608.05783v1 **Authors:** Paweł Batorski, Przemysław Spurek, Paul Swoboda **URL:** http://arxiv.org/abs/2608.05783v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2608 06154v1 Visual Grounding In Zero Shot Vision Language ContVisual Grounding in Zero-Shot Vision-Language Control (arXiv: 2608.06154v1)Votes: 0GitHub stars: 3
- Arxiv 2608 06240v1 Prism Distribution Gated Flow Matching For ControlPRISM: Distribution-Gated Flow Matching for Controllable Unpaired Image Translation (arXiv: 2608.06240v1)Votes: 0GitHub stars: 3
- Arxiv 2608 12974v1 Comment On Modeling Rapid Language Learning By Dis**arXiv ID:** 2608.12974v1 **Authors:** Orr Well, Idan Tarshish, Nur Lan, Roni Katzir **URL:** http://arxiv.org/abs/2608.12974v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2608 19879 A Repeated Measurements Approach To Soh Battery MoA Repeated Measurements Approach to $SoH$ Battery Modelling of Cyclic Aged Data in a Laboratory Environment (arXiv: 2608.19879)Votes: 0GitHub stars: 3
- Arxiv 2608 20123 Discrete Diffusion Inference Time Control With NesDiscrete Diffusion Inference-Time Control with Nested Sequential Monte Carlo (arXiv: 2608.20123)Votes: 0GitHub stars: 3
- Arxiv 2608 20290 Phantom Gains Auditing Self Improvement Against APhantom Gains: Auditing Self-Improvement Against a Measured Null (arXiv: 2608.20290)Votes: 0GitHub stars: 3
- Arxiv 2608 20337 Information On Trajectories Martingales And RandomInformation on trajectories: martingales and random times (arXiv: 2608.20337)Votes: 0GitHub stars: 3
- Arxiv 2608 22765v1 Learning To Control Coupled Dynamics Environments**arXiv ID:** 2608.22765v1 **Authors:** Ege C. Kaya, Aliasghar Pourghani, Mahsa Ghasemi, Vijay Gupta, Abolfazl Hashemi **URL:** http://arxiv.org/abs/2608.22765v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2608 25777v1 Locallstc A Long Short Term Control Architecture F**arXiv ID:** 2608.25777v1 **Authors:** Weiming Li, Helen Paik, Yulei Sui **URL:** http://arxiv.org/abs/2608.25777v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2608 26788v1 Decoupling Planning And Control For Instructable A**arXiv ID:** 2608.26788v1 **Authors:** Zineng Tang, Kelsey R. Allen, Sjoerd van Steenkiste, Ishita Dasgupta, Alane Suhr **URL:** http://arxiv.org/abs/2608.26788v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2608 30889v1 Safety Screening For Voltage Control In Active Dis**arXiv ID:** 2608.30889v1 **Authors:** Sarra Bouchkati, Petros Ellinas, Adriana Geisler, Steffen Kortmann, Johanna Vorwerk, Spyros Chatzivasiliadis, Andreas Ulbig **URL:** http://arxiv.org/abs/2608.30889v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 02106v1 Git4data Database Native Version Control For Ai Ag**arXiv ID:** 2609.02106v1 **Authors:** Hongshen Gou, Zuyu Zhang, Yuze Sun, Peng Xu, Feng Tian, Long Wang, Jianguo Wang **URL:** http://arxiv.org/abs/2609.02106v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 08725v1 Baff Bid Aware Filter Family For Mitigating Traini**arXiv ID:** 2609.08725v1 **Authors:** Jeonglyul Oh, Ikkyu Choi, Inseop Youn, Youngjae Kim **URL:** http://arxiv.org/abs/2609.08725v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 09564v1 Robust Industrial Cyber Physical Classification Us**arXiv ID:** 2609.09564v1 **Authors:** Ammar Kamoona, Sajad Koushkbaghi, Mahdi Jalili, Peter McTaggart, Xinghuo Yu **URL:** http://arxiv.org/abs/2609.09564v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Automated Cps Testing ActAutomated CPS Testing Framework (ACT) for continuous testing of open-source cyber-physical systems with robotic platforms. End-to-end automated testing integrated with open-source infrastructure such as GitHub. Use for: continuous CPS testing, open-source robotic platforms testing, multi-module CPS validation, GitHub-integrated testing workflows. Activation: automated CPS testing, cyber-physical systems testing, robotic platforms testing, continuous CPS testing, ACT framework.Votes: 0GitHub stars: 3
- Automated Cps TestingAutomated CPS Testing Framework - Automated continuous testing framework combining SIL simulation, HIL simulation, and actual robotic platform testing... Activation: CPS testing, cyber-physical systems, robotic testing.Votes: 0GitHub stars: 3