All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Meta Learning In Context Brain DecodingMeta-learning In-Context approach for training-free cross-subject brain decoding. Enables zero-calibration BCI through context-based meta-learning. Triggers: meta-learning, brain decoding, cross-subject, training-free, in-context learning, zero-calibration BCI.Votes: 0GitHub stars: 3
- Meta Learning In Context Enables Training Free Cross SubjectVisual decoding from brain signals is a key challenge at the intersection of computer vision and neuroscience, requiring methods that bridge neural re... Activation: cs.LG, q-bio.NC, neuroscience, researchVotes: 0GitHub stars: 3
- Meta Learning In Context Enables Training Free Cross... Activation: meta-learning, in-context learning, cross-subjectVotes: 0GitHub stars: 3
- Meta Learning In Context Enables Training FreeMeta-learning In-Context Enables Training-Free Cross Subject Brain Decoding - Research insights and implementation patterns from arXiv:2604.08537v1Votes: 0GitHub stars: 3
- Metalearning And Universality Deep Representations And Gradient Descent Can Approximate Any Learning Algorithm**arXiv ID:** 1710.11622 **Authors:** Chelsea Finn, Sergey Levine **Published:** 2017-10-31T17:55:42Z **Abstract:** Learning to learn is a powerful paradigm for enabling models to learn from data more effectively and efficiently. A popular approach to meta-learning is to train a recurrent model to read in a training dataset as input and output the parameters of a learned model, or output predictions for new test inputs. Alternatively, a more recent approach to meta-learning aims to acquire de...Votes: 0GitHub stars: 3
- Metalearning Loss Functions For Deep Neural Networks**arXiv ID:** 2406.09713 **Authors:** Christian Raymond **Published:** 2024-06-14T04:46:14Z **Abstract:** Humans can often quickly and efficiently solve complex new learning tasks given only a small set of examples. In contrast, modern artificially intelligent systems often require thousands or millions of observations in order to solve even the most basic tasks. Meta-learning aims to resolve this issue by leveraging past experiences from similar learning tasks to embed the appropriate induct...Votes: 0GitHub stars: 3
- Metatrained Agents Implement Bayesoptimal Agents**arXiv ID:** 2010.11223 **Authors:** Vladimir Mikulik, Grégoire Delétang, Tom McGrath, Tim Genewein, Miljan Martic, Shane Legg, Pedro A. Ortega **Published:** 2020-10-21T18:05:21Z **Abstract:** Memory-based meta-learning is a powerful technique to build agents that adapt fast to any task within a target distribution. A previous theoretical study has argued that this remarkable performance is because the meta-training protocol incentivises agents to behave Bayes-optimally. We empirically inve...Votes: 0GitHub stars: 3
- Mice To Machines Neural Representations From Visual Cortex For Domain Generalization**arXiv ID:** 2505.06886 **Authors:** Ahmed Qazi, Hamd Jalil, Asim Iqbal **Published:** 2025-05-11T07:37:37Z **Abstract:** The mouse is one of the most studied animal models in the field of systems neuroscience. Understanding the generalized patterns and decoding the neural representations that are evoked by the diverse range of natural scene stimuli in the mouse visual cortex is one of the key quests in computational vision. In recent years, significant parallels have been drawn between the ...Votes: 0GitHub stars: 3
- Minmaxplus Neural Networks**arXiv ID:** 2102.06358 **Authors:** Ye Luo, Shiqing Fan **Published:** 2021-02-12T06:09:20Z **Abstract:** We present a new model of neural networks called Min-Max-Plus Neural Networks (MMP-NNs) based on operations in tropical arithmetic. In general, an MMP-NN is composed of three types of alternately stacked layers, namely linear layers, min-plus layers and max-plus layers. Specifically, the latter two types of layers constitute the nonlinear part of the network which is trainable and more ...Votes: 0GitHub stars: 3
- Ml Complexity ManagementComputational complexity lens for understanding how ML manages complex systems. Based on arxiv:2604.07233 'How Does Machine Learning Manage Complexity?' by Lance Fortnow. Use when analyzing ML's ability to model complex systems, understanding complexity bounds, P/poly-computable distributions, or when asked 'how does ML handle complexity?', 'ML complexity theory', 'computable distributions in ML'.Votes: 0GitHub stars: 3
- Ml Qem Variational AlgorithmsMachine Learning-based Quantum Error Mitigation (ML-QEM) for variational quantum algorithms. Uses near-Clifford circuit simulation for training data, transfers across Hamiltonians, outperforms ZNE in high-noise regimes. Applicable to NISQ processors. arXiv:2606.02697.Votes: 0GitHub stars: 3
- Mle Bench Evaluating Machine Learning Agents On MaSkill for AI agent capabilitiesVotes: 0GitHub stars: 3
- Model Agnostic Meta Learning Differentiable MpcModel-Agnostic Meta Learning (MAML) framework for Differentiable Model Predictive Control (MPC) to enable adaptive control strategies across varying scenarios. Combines meta-learning with differentiable MPC for real-time adaptability without extensive retraining. Use when needing adaptive MPC controllers that can quickly adjust to new system dynamics or environmental conditions.Votes: 0GitHub stars: 3
- Mpcs Neuroplastic Continual LearningMulti-Plasticity Continual System (MPCS) integrating 11 neuroplastic mechanisms for continual learning. Key finding: EWC regularization degrades performance at high task similarity. Pareto frontier analysis for model compression. Activates: continual learning, neuroplastic architecture, EWC regularization, plasticity-stability tradeoff, MEP-BENCH, multi-component learning, task-driven neurogenesis, topology-aware EWC.Votes: 0GitHub stars: 3
- Multi Source Multi View Graph Domain Adaptation HyperbolicMulti-Source Multi-View Graph Domain Adaptation with Hyperbolic Residual Encoding framework for cross-site Major Depressive Disorder (MDD) identification from resting-state fMRI. Use when working with multi-site neuroimaging data, cross-domain brain network analysis, heterogeneous functional connectivity views, or hyperbolic representation learning for clinical applications.Votes: 0GitHub stars: 3
- Munet Evolving Pretrained Deep Neural Networks Into Scalable Autotuning Multitask Systems**arXiv ID:** 2205.10937 **Authors:** Andrea Gesmundo, Jeff Dean **Published:** 2022-05-22T21:54:33Z **Abstract:** Most uses of machine learning today involve training a model from scratch for a particular task, or sometimes starting with a model pretrained on a related task and then fine-tuning on a downstream task. Both approaches offer limited knowledge transfer between different tasks, time-consuming human-driven customization to individual tasks and high computational costs especially wh...Votes: 0GitHub stars: 3
- Naive Fewshot Learning Uncovering The Fluid Intelligence Of Machines**arXiv ID:** 2205.12013 **Authors:** Tomer Barak, Yonatan Loewenstein **Published:** 2022-05-24T12:00:39Z **Abstract:** In this paper, we aimed to help bridge the gap between human fluid intelligence - the ability to solve novel tasks without prior training - and the performance of deep neural networks, which typically require extensive prior training. An essential cognitive component for solving intelligence tests, which in humans are used to measure fluid intelligence, is the ability to id...Votes: 0GitHub stars: 3
- Naturality Violation ScoreCategory-theory-based brain-DNN alignment methodology using Naturality Violation Score (NVS). Shifts alignment assessment from per-stimulus correspondence to preservation of candidate transformations. Activation: brain-DNN alignment, naturality violation, RSA critique, representational alignment, transformation alignment, brain model comparison, fMRI alignmentVotes: 0GitHub stars: 3
- Neugen Amplifying The Neural In Neural Radiance Fields For Domain Generalization**arXiv ID:** 2505.06894 **Authors:** Ahmed Qazi, Abdul Basit, Asim Iqbal **Published:** 2025-05-11T08:17:33Z **Abstract:** Neural Radiance Fields (NeRF) have significantly advanced the field of novel view synthesis, yet their generalization across diverse scenes and conditions remains challenging. Addressing this, we propose the integration of a novel brain-inspired normalization technique Neural Generalization (NeuGen) into leading NeRF architectures which include MVSNeRF and GeoNeRF. NeuGe...Votes: 0GitHub stars: 3
- Neural Associative Memory For Dualsequence Modeling**arXiv ID:** 1606.03864 **Authors:** Dirk Weissenborn **Published:** 2016-06-13T09:08:04Z **Abstract:** Many important NLP problems can be posed as dual-sequence or sequence-to-sequence modeling tasks. Recent advances in building end-to-end neural architectures have been highly successful in solving such tasks. In this work we propose a new architecture for dual-sequence modeling that is based on associative memory. We derive AM-RNNs, a recurrent associative memory (AM) which augments generi...Votes: 0GitHub stars: 3
- Neural Operator Enabled Topology Informed Evolutionary Strategy For PdeThe inverse design of physical systems governed by partial differential equations is computationally demanding due to the high dimensionality and non-convexity of design spaces. Generative models for. Based on arXiv:2607.07682.Votes: 0GitHub stars: 3
- Neural Pruning Via Growing Regularization**arXiv ID:** 2012.09243 **Authors:** Huan Wang, Can Qin, Yulun Zhang, Yun Fu **Published:** 2020-12-16T20:16:28Z **Abstract:** Regularization has long been utilized to learn sparsity in deep neural network pruning. However, its role is mainly explored in the small penalty strength regime. In this work, we extend its application to a new scenario where the regularization grows large gradually to tackle two central problems of pruning: pruning schedule and weight importance scoring. (1) The fo...Votes: 0GitHub stars: 3
- Neurips22 Crossdomain Metadl Competition Design And Baseline Results**arXiv ID:** 2208.14686 **Authors:** Dustin Carrión-Ojeda, Hong Chen, Adrian El Baz, Sergio Escalera, Chaoyu Guan, Isabelle Guyon, Ihsan Ullah, Xin Wang, Wenwu Zhu **Published:** 2022-08-31T08:31:02Z **Abstract:** We present the design and baseline results for a new challenge in the ChaLearn meta-learning series, accepted at NeurIPS'22, focusing on "cross-domain" meta-learning. Meta-learning aims to leverage experience gained from previous tasks to solve new tasks efficiently (i.e., with bet...Votes: 0GitHub stars: 3
- Nf Cot Latent Reasoning Normalizing FlowsLatent reasoning framework using normalizing flows for continuous thoughts that preserves CoT advantages (left-to-right generation, KV-cache, likelihood estimation)Votes: 0GitHub stars: 3
- Non Equilibrium Continual LearningNon-equilibrium stochastic dynamics framework for continual learning using Kramers escape theory. Unifies insight and repetitive learning through thermodynamic perspective. Activation: non-equilibrium continual learning, Kramers escape learning, stability-plasticity dilemma, 非平衡持续学习, Kramers逃逸学习.Votes: 0GitHub stars: 3
- Nonlinear Separation Principle Neural NetworksNonlinear separation principle for recurrent neural networks (RNNs) using contraction theory. Guarantees global exponential stability for contracting state-feedback controllers and observers. Applies to firing-rate and Hopfield RNN architectures. Based on paper by Gokhale et al. (arXiv 2604.15238, April 2026).Votes: 0GitHub stars: 3
- Nonstructured Dnn Weight Pruning Is It Beneficial In Any Platform**arXiv ID:** 1907.02124 **Authors:** Xiaolong Ma, Sheng Lin, Shaokai Ye, Zhezhi He, Linfeng Zhang, Geng Yuan, Sia Huat Tan, Zhengang Li, Deliang Fan, Xuehai Qian, Xue Lin, Kaisheng Ma, Yanzhi Wang **Published:** 2019-07-03T20:27:51Z **Abstract:** Large deep neural network (DNN) models pose the key challenge to energy efficiency due to the significantly higher energy consumption of off-chip DRAM accesses than arithmetic or SRAM operations. It motivates the intensive research on model compress...Votes: 0GitHub stars: 3
- Nothing Makes Sense In Deep Learning Except In The Light Of Evolution**arXiv ID:** 2205.10320 **Authors:** Artem Kaznatcheev, Konrad Paul Kording **Published:** 2022-05-20T17:34:20Z **Abstract:** Deep Learning (DL) is a surprisingly successful branch of machine learning. The success of DL is usually explained by focusing analysis on a particular recent algorithm and its traits. Instead, we propose that an explanation of the success of DL must look at the population of all algorithms in the field and how they have evolved over time. We argue that cultural evolu...Votes: 0GitHub stars: 3
- Object Based Attention Through Internal Gating**arXiv ID:** 2106.04540 **Authors:** Jordan Lei, Ari S. Benjamin, Konrad P. Kording **Published:** 2021-06-08T17:20:50Z **Abstract:** Object-based attention is a key component of the visual system, relevant for perception, learning, and memory. Neurons tuned to features of attended objects tend to be more active than those associated with non-attended objects. There is a rich set of models of this phenomenon in computational neuroscience. However, there is currently a divide between models t...Votes: 0GitHub stars: 3
- On First Order Meta Learning AlgorithmsSkill for AI agent capabilitiesVotes: 0GitHub stars: 3
- On Policy Distillation Dlm TransformationOn-Policy Distillation (OPD) methodology for transforming autoregressive models into diffusion language models efficiently, eliminating train-inference mismatch.Votes: 0GitHub stars: 3
- On Policy Distillation Test Time ScalingOPD: efficiency vs capability via test-time scaling.Votes: 0GitHub stars: 3
- On The Improvement Of Generalization And Stability Of Forwardonly Learning Via Neural Polarization**arXiv ID:** 2408.09210 **Authors:** Erik B. Terres-Escudero, Javier Del Ser, Pablo Garcia-Bringas **Published:** 2024-08-17T14:32:18Z **Abstract:** Forward-only learning algorithms have recently gained attention as alternatives to gradient backpropagation, replacing the backward step of this latter solver with an additional contrastive forward pass. Among these approaches, the so-called Forward-Forward Algorithm (FFA) has been shown to achieve competitive levels of performance in terms of g...Votes: 0GitHub stars: 3
- On The Inductive Bias Of Dropout**arXiv ID:** 1412.4736 **Authors:** David P. Helmbold, Philip M. Long **Published:** 2014-12-15T19:40:46Z **Abstract:** Dropout is a simple but effective technique for learning in neural networks and other settings. A sound theoretical understanding of dropout is needed to determine when dropout should be applied and how to use it most effectively. In this paper we continue the exploration of dropout as a regularizer pioneered by Wager, et.al. We focus on linear classification where a convex...Votes: 0GitHub stars: 3
- On Training Deep Boltzmann Machines**arXiv ID:** 1203.4416 **Authors:** Guillaume Desjardins, Aaron Courville, Yoshua Bengio **Published:** 2012-03-20T12:59:15Z **Abstract:** The deep Boltzmann machine (DBM) has been an important development in the quest for powerful "deep" probabilistic models. To date, simultaneous or joint training of all layers of the DBM has been largely unsuccessful with existing training methods. We introduce a simple regularization scheme that encourages the weight vectors associated with each hidden u...Votes: 0GitHub stars: 3
- Oneshot Imitation Learning**arXiv ID:** 1703.07326 **Authors:** Yan Duan, Marcin Andrychowicz, Bradly C. Stadie, Jonathan Ho, Jonas Schneider, Ilya Sutskever, Pieter Abbeel, Wojciech Zaremba **Published:** 2017-03-21T17:22:29Z **Abstract:** Imitation learning has been commonly applied to solve different tasks in isolation. This usually requires either careful feature engineering, or a significant number of samples. This is far from what we desire: ideally, robots should be able to learn from very few demonstrations of...Votes: 0GitHub stars: 3
- Opd Evolver On Policy Distillation AgentOPD-Evolver - On-policy distillation framework for cultivating holistic agent evolvers. Slow-fast co-evolution with four-level memory hierarchy: read, use, write, maintain experience. Outcome-calibrated memory attribution + privileged hindsight distillation. Use when: (1) building self-evolving agents, (2) memory management beyond storage, (3) agent experience learning. Activation: agent evolver, on-policy distillation, memory hierarchy, self-evolution, experience management.Votes: 0GitHub stars: 3
- Opd2 On Policy Delta DistillationOPD² for on-policy delta distillation.Votes: 0GitHub stars: 3
- Open Mopd Multi Teacher On Policy DistillationOpen-MOPD framework for diagnosing and fixing capability imbalance in multi-teacher on-policy distillation. Use when consolidating domain-specialized RL experts into a single generalist student with balanced cross-domain performance.Votes: 0GitHub stars: 3
- Optical Neural Networks Waveguide QedOptical neural networks using coherent transient dynamics in waveguide QED for all-optical neuromorphic computingVotes: 0GitHub stars: 3
- Overcoming Catastrophic Forgetting With Hard Attention To The Task**arXiv ID:** 1801.01423 **Authors:** Joan Serrà, Dídac Surís, Marius Miron, Alexandros Karatzoglou **Published:** 2018-01-04T16:22:22Z **Abstract:** Catastrophic forgetting occurs when a neural network loses the information learned in a previous task after training on subsequent tasks. This problem remains a hurdle for artificial intelligence systems with sequential learning capabilities. In this paper, we propose a task-based hard attention mechanism that preserves previous tasks' informati...Votes: 0GitHub stars: 3
- Parallel Architecture And Hyperparameter Search Via Successive Halving And Classification**arXiv ID:** 1805.10255 **Authors:** Manoj Kumar, George E. Dahl, Vijay Vasudevan, Mohammad Norouzi **Published:** 2018-05-25T17:12:38Z **Abstract:** We present a simple and powerful algorithm for parallel black box optimization called Successive Halving and Classification (SHAC). The algorithm operates in $K$ stages of parallel function evaluations and trains a cascade of binary classifiers to iteratively cull the undesirable regions of the search space. SHAC is easy to implement, requires ...Votes: 0GitHub stars: 3
- Partial Fusion Neural NetworksPartial fusion of neural networks interpolating between ensembles and weight aggregation via neuron-level similarity matching and partial optimal transport. Frames partial fusion as generalized pruning where neurons are deleted or linearly combined.Votes: 0GitHub stars: 3
- Pateaae Incorporating Adversarial Autoencoder Into Private Aggregation Of Teacher Ensembles For Spoken Command Classification**arXiv ID:** 2104.01271 **Authors:** Chao-Han Huck Yang, Sabato Marco Siniscalchi, Chin-Hui Lee **Published:** 2021-04-02T23:10:57Z **Abstract:** We propose using an adversarial autoencoder (AAE) to replace generative adversarial network (GAN) in the private aggregation of teacher ensembles (PATE), a solution for ensuring differential privacy in speech applications. The AAE architecture allows us to obtain good synthetic speech leveraging upon a discriminative training of latent vectors. Suc...Votes: 0GitHub stars: 3
- Persona Pruner Lightweight RoleplayingPersona-Pruner methodology for sculpting lightweight language models for role-playing tasks. Enables efficient pruning of LMs while preserving persona-consistent stylized interactions. Use when: model pruning for role-playing, lightweight character chatbots, persona-preserving model compression, efficient LM distillation.Votes: 0GitHub stars: 3
- Phenomenological Renormalization Group Neuronal CriticalityPhenomenological Renormalization Group (PRG) validation methodology for detecting criticality in neuronal models. Validates PRG coarse-graining on excitable cellular automata and stochastic E/I LIF networks, introduces adaptive ISI-based time binning to eliminate spurious criticality signatures. Use for brain criticality analysis, avalanche dynamics, renormalization group neuroscience, scale-invariant neural activity. Activation: PRG, renormalization group, critical brain, neuronal criticalit...Votes: 0GitHub stars: 3
- Photonic Neural Network MemoryMemory mechanisms in integrated photonic neural networks from physical principles to system design. Use for understanding optical computing memory, photonic reservoir computing, and neuromorphic photonics. Keywords: photonic neural networks, optical computing, memory mechanisms, integrated photonics, neuromorphic photonics, reservoir computing.Votes: 0GitHub stars: 3
- Phys Mcp Physical Neural Networksphys-MCP: substrate-aware control plane architecture for heterogeneous Physical Neural Networks (PNNs) spanning molecular, chemical, biological, photonic, memristive, and mechanical substrates. Provides capability models, lifecycle semantics, telemetry interfaces, and digital-twin bindings. Includes wetware-facing API via Cortical Labs adapter. Use when: orchestrating physical neural networks, edge-cloud PNN integration, wetware computing, substrate-aware orchestration, neuromorphic hardware ...Votes: 0GitHub stars: 3
- Physics Guided Neural NetworkDesign neural networks that embed physical constraints (equations, symmetries, conservation laws) directly into the computational graph. Use when modeling physical systems, scientific computing, or when physics-informed AI is needed. Keywords: PGNN, physics-guided NN, physics-informed ML, physics-embedded NN, scientific ML, holographic QCD, AdS Dirac equation.Votes: 0GitHub stars: 3
- Physics Guided Neural NetworksPhysics-guided neural network design and training methods. Embed physical laws, constraints, and symmetries into neural network architecture for improved modeling of physical systems (quantum mechanics, statistical physics, fluid dynamics, materials science). Activation: physics guided neural network, 物理学指导神经网络, physics-informed neural network, PINN, physics-constrained learning, quantum neural network, physics-aware training.Votes: 0GitHub stars: 3