All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Persistent Negatives Adversarial OpdPersistent-negative adversarial distillation for black-box on-policy distillation - anchor the discriminator with historical teacher-student comparisons to stop the moving-target reward problem. Use when distilling from API-only teachers (no token probabilities), training discriminator-based rewards, or stabilizing adversarial RLHF pipelines.Votes: 0GitHub stars: 3
- Purin Synaptic Efficacy AnnUse when adding short-term synaptic plasticity to CNNs.Votes: 0GitHub stars: 3
- Qbx Chiplet Hamiltonian CompilerUse when compiling 2-local Hamiltonians for chiplet QPUs.Votes: 0GitHub stars: 3
- Reciprocity Mechanical Network Learning FloorSymmetry sets untrainable error floors in physical nets.Votes: 0GitHub stars: 3
- Reward Shaped Nonlinguistic Rule CodesReward vs gradient channels shape emergent rule codes differently.Votes: 0GitHub stars: 3
- Spectral Window Transfer PretrainingSpectral-window transfer analysis for cross-domain foundation models - pretraining transfer quality is governed by the overlap between the pretrained model's spectral window and the target domain's spectra (infrared-pretrained model falls below untrained control on optical/UV tasks). Use for deciding pretrained-vs-in-domain pretraining for spectroscopy, sensor, or any wavelength/frequency-structured scientific data.Votes: 0GitHub stars: 3
- Anchored Hypergraph Credit AssignmentHySTAR - fix the value-decomposition basis (overlapping sparse hypergraph scaffold) while learning adaptive spatiotemporal representations, eliminating structural target drift in cooperative multi-agent RL. Use for credit assignment under partial observability, stable high-order coalition value decomposition, or when dynamic grouping keeps reshuffling your learning targets.Votes: 0GitHub stars: 3
- Efficient Ml Degradation Forecasting AemData-driven machine learning approach for medium-term degradation forecasting in Anion Exchange Membrane water electrolyzers using LSTMs and CNNsVotes: 0GitHub stars: 3
- Coupling Aware Subqubo SelectionUse when splitting a large QUBO into sub-problems for hybrid solvers.Votes: 0GitHub stars: 3
- Gkp Qldpc Circuit BenchmarksBenchmark GKP-concatenated qLDPC codes (BB vs tricycle) under circuit-level noise.Votes: 0GitHub stars: 3
- Hqnn Peptide Hla BindingUse when improving sample efficiency of biological sequence prediction (peptide-HLA/neoantigen binding) with hybrid quantum-classical neural networks in low-data regimes.Votes: 0GitHub stars: 3
- Ogp Separating Quantum Inspired OptimizationUse when OGP separates classical heuristics from QAOA depth barriers.Votes: 0GitHub stars: 3
- Qcnn Small Data GeneralizationUse when evaluating quantum CNN generalization in small-data regimes — encoding bottleneck analysis (amplitude vs angle), parameter-matched comparisons, mid-circuit measurement QCNN design.Votes: 0GitHub stars: 3
- Qdsm Quantum Attention Molecular ProfilingUse when replacing softmax attention with quantum-derived doubly stochastic matrices (QDSM) for data-limited molecular/gene-expression prediction from histopathology.Votes: 0GitHub stars: 3
- Quantum Auction Summation ReductionsReductions between quantum auctions and secure summation.Votes: 0GitHub stars: 3
- Quantum Mcts Fixed ConfidenceQuantum speedup for Monte Carlo tree search. Use when combining quantum oracles with game tree search.Votes: 0GitHub stars: 3
- Quantum U Statistics EfficiencyUnique Cramér-Rao-efficient quantum U-statistic estimators.Votes: 0GitHub stars: 3
- Rlq Grad Rl Qnn OptimizerRL agent emits QNN gradients to bypass barren plateau variance decay.Votes: 0GitHub stars: 3
- Snn Streaming Qubit ReadoutUse for real-time superconducting qubit readout with spiking neural networks on FPGA. Streaming SNN discriminators.Votes: 0GitHub stars: 3
- Structured Bayesian Dynamic Receptive FieldsGMRF-space + AR(1)-time Bayesian receptive fields via INLA. Use for spike-count RF estimation.Votes: 0GitHub stars: 3
- Arxiv 2509 25072 Optimizing Privacy Preserving Primitives To Support Llm ScalWe present an overview of efforts to bridge the gap between overhead and practicality for privacy-preserving learning systems using MPC, ZKPs, and FHE. Through hardware/software/algorithm co-design, we show progress towards enabling LLM-scale applications in privacy-preserving settings including DNN IP ownership, ethical LLM usage enforcement, and transformer inference.Votes: 0GitHub stars: 3
- Arxiv 2609 28693 Progressive Skill Discovery Access ControlResearch paper: Progressive Skill Discovery as Access Control for Tool-Using LLM Agents: Structural Governance through Role-Scoped Capability Delivery.Votes: 0GitHub stars: 3
- Arxiv 2609 28900 Codetta Multi Agent CollusionResearch paper: Codetta: High-Capacity, Keyless, and Undetectable Multi-Agent Collusion.Votes: 0GitHub stars: 3
- Arxiv 2609 30614 Subjects Not Authors Authorship HazardResearch paper: Subjects, Not Authors: The Authorship Hazard in Agentic Dataspaces.Votes: 0GitHub stars: 3
- Encryptability Coordinate Choice He FedavgQuaternion chart makes SU(2) updates degree-2 → depth-1 homomorphic FL.Votes: 0GitHub stars: 3
- Arxiv 2509 25411 Hybrid Layer Wise Ann Snn With Surrogate Spike Encoding DecoWe propose a novel hybrid ANN-SNN framework that integrates layer-wise encode-decode SNN blocks within conventional ANN pipelines. Central to our method is the use of surrogate gradients for a bit-plane-based spike encoding function, enabling end-to-end differentiable training across ANN and SNN layers. This design achieves competitive accuracy with energy-efficient computing.Votes: 0GitHub stars: 3
- Causal Pieces Snn ExpressivityUse when analysing SNN expressivity or choosing SNN weight init. Causal pieces theory.Votes: 0GitHub stars: 3
- Mdtf Temporal Fusion Local SnnUse when building deep SNNs trained with local STDP and temporal fusion.Votes: 0GitHub stars: 3
- Openarchevo Native Snn DiscoveryUse when evolving native SNN architectures with LLM searchVotes: 0GitHub stars: 3
- Urchin Spiking Language ModelURCHIN: A Horizontal Spiking Language Model for Data-Constrained Pretraining. Single-layer Dale's-law E/I LIF connectome with multi-transmission loop, dual parallel-SSM/serial-RSNN deployment from one weight set. Use when building biologically-plausible spiking LMs, BabyLM-scale training, or event-driven edge language models.Votes: 0GitHub stars: 3
- Arxiv 2509 25077 Bridge Rl Optimized Depth To Image Generation For MonocularWe propose BRIDGE, an RL-optimized depth-to-image generation framework that synthesizes over 20M realistic and geometrically accurate RGB images from diverse source depth maps. Then we train depth estimation models with hybrid supervision integrating teacher pseudo-labels with ground truth depth. BRIDGE achieves breakthroughs in scale and domain diversity, consistently outperforming state-of-the-art approaches.Votes: 0GitHub stars: 3
- Arxiv 2509 26625 Learning To See Before Seeing Demystifying Llm Visual PriorsLLMs develop rich visual priors despite text-only training. We reveal that visual priors are composed of separable perception and reasoning priors with unique scaling trends and origins. Visual reasoning ability is predominantly developed by pre-training on reasoning-centric data (code, math, academia). We propose a data-centric recipe for pre-training vision-aware LLMs verified in 1T token scale pre-training across 100+ controlled experiments consuming 500,000 GPU-hours.Votes: 0GitHub stars: 3
- Flatclip Surface Frozen Encoder FmriCortical flatmaps + frozen SigLIP2 for fMRI prediction.Votes: 0GitHub stars: 3
- Hierinrseg Implicit Neural SegmentationHierINRSeg - hierarchical multi-layer INR aggregation for parameter-efficient semantic segmentation; INR advantages concentrate in low-parameter and limited-augmentation regimes, so aggregate complementary semantic structure distributed across INR layers instead of scaling parameters. Use for segmentation under memory budgets, cross-site domain shift, or analyzing when INRs beat CNNs.Votes: 0GitHub stars: 3