All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Stark Units Quantum Dilogarithm AlgebraicityUse for Stark unit algebraicity via quantum dilogarithm.Votes: 0GitHub stars: 3
- Ultra High Rate Quantum CodesUse when designing ultra-high-rate QEC codes.Votes: 0GitHub stars: 3
- W1 Robust Quantum SteinStein exponent robust to W1 Wasserstein almost-iid sources (arXiv 2609.17309).Votes: 0GitHub stars: 3
- Arxiv 2609 29268v1 Bridgemem Causal Dyadic Transition Residuals For T**arXiv ID:** 2609.29268v1 **Authors:** Zeyan Li, Libing Chen, Shengda Zhuo, Yin Tang, Jianfeng Xu **URL:** http://arxiv.org/abs/2609.29268v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29383v1 Lightweight Probabilistic Downscaling From A Deter**arXiv ID:** 2609.29383v1 **Authors:** Joseph McLean, Tiffany Vlaar, Sigrid Passano Hellan, Linus Ericsson **URL:** http://arxiv.org/abs/2609.29383v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29875v1 When Can Agents Forget Their Reasoning Iclr For Lo**arXiv ID:** 2609.29875v1 **Authors:** Mingxuan Wang, Fei Luo, Bo Wang, Guorun Yao, Yinglong Guo, Chao Ning, Hongyue Chen, Yanbiao Ma, Jungong Han **URL:** http://arxiv.org/abs/2609.29875v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29940v1 Mind What Matters For Reasoning Aligning Cross Mod**arXiv ID:** 2609.29940v1 **Authors:** Jiaqi Deng, Zonghan Wu, Zhan Heng, Xiaoshui Huang, Huan Huo, Guandong Xu **URL:** http://arxiv.org/abs/2609.29940v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30078v1 Nuclear Norm Regularized Bayesian Matrix Completio**arXiv ID:** 2609.30078v1 **Authors:** Calvin Tolbert **URL:** http://arxiv.org/abs/2609.30078v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30192v1 Sage Mitigating Long Horizon Reasoning Biases Via**arXiv ID:** 2609.30192v1 **Authors:** Xinyue Zeng, Jiawei Zhang, Yujun Yan, Dawei Zhou **URL:** http://arxiv.org/abs/2609.30192v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Channel Stein Theorem Causal OrderUse when testing quantum channels or proving channel discrimination exponents. Stein rate.Votes: 0GitHub stars: 3
- Arxiv 2609 29730v1 The Gold In Bias Maturing The Ai Design Process Th**arXiv ID:** 2609.29730v1 **Authors:** Samira Maghool, Paolo Ceravolo **URL:** http://arxiv.org/abs/2609.29730v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29744v1 Between The Commits Process Error And Claim Reliab**arXiv ID:** 2609.29744v1 **Authors:** Douglas Leith **URL:** http://arxiv.org/abs/2609.29744v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29775v1 Prefilling The Reasoning Channel Output Prefix Att**arXiv ID:** 2609.29775v1 **Authors:** Lukáš Brůna, Robert Bridges, Adam Ek **URL:** http://arxiv.org/abs/2609.29775v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29847v1 Elucidating The Conformal Structure Of The Brinkma**arXiv ID:** 2609.29847v1 **Authors:** Teo Deveney, Baige Xu, Takaharu Yaguchi **URL:** http://arxiv.org/abs/2609.29847v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29921v1 Who Holds The Pen Let Specifications Not Agents Si**arXiv ID:** 2609.29921v1 **Authors:** Haiqing Li, Xin Ma, Yinhao Wu, Wenliang Zhong, Feng Jiang, Thao M. Dang, Xiao Hu, Hehuan Ma, Yuzhi Guo, Junzhou Huang **URL:** http://arxiv.org/abs/2609.29921v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30058v1 Can Labor Markets Function In The Age Of Ai The Ev**arXiv ID:** 2609.30058v1 **Authors:** Itai Ashlagi, Ramesh Johari, Jon Kleinberg, Anushka Murthy **URL:** http://arxiv.org/abs/2609.30058v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30105v1 On The Sos Certifiability Of Log Concave Distribut**arXiv ID:** 2609.30105v1 **Authors:** Aleksandr Storozhenko **URL:** http://arxiv.org/abs/2609.30105v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30144v1 Enigmaforge The Question Is Hidden In The Story**arXiv ID:** 2609.30144v1 **Authors:** Daniel Eisner **URL:** http://arxiv.org/abs/2609.30144v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29194v1 Continuous Online Fault Detection For Mobile Robot**arXiv ID:** 2609.29194v1 **Authors:** Jordan Levy, Nicolas Verstaevel, Vincent Talon, Benoit Gaudou **URL:** http://arxiv.org/abs/2609.29194v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29379v1 On The Second Order Optimization For Spiking Neura**arXiv ID:** 2609.29379v1 **Authors:** Ngoc Phu Doan, Ihsen Alouani **URL:** http://arxiv.org/abs/2609.29379v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29984v1 A Spiking Neural Network Model Of Elementary Self**arXiv ID:** 2609.29984v1 **Authors:** R. Lahoz-Beltra **URL:** http://arxiv.org/abs/2609.29984v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30102v1 Activation Flexible Ann To Snn Conversion With Fin**arXiv ID:** 2609.30102v1 **Authors:** Ruiyu Jia, Zhuo-Cheng Xiao **URL:** http://arxiv.org/abs/2609.30102v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Ctmc Markov Neuron Ann Snn ConversionUse for ANN-SNN conversion via CTMC Markov neurons.Votes: 0GitHub stars: 3
- Fp Snn Activation Energy PruningUse to prune SNNs: spike-count activation energy criterion.Votes: 0GitHub stars: 3
- Gsap Gated Spike Axial PropagationUse when building spike-native token interactions in SNNs.Votes: 0GitHub stars: 3
- Latent Kinetic Ising Spike TrainsSpiKIsing latent-variable kinetic Ising framework for inferring directed effective connectivity from continuous-time spike trains. Use when analyzing neural spike train data, reconstructing functional/effective connectivity, applying kinetic Ising models to neural data, or separating network dynamics from single-neuron refractory effects.Votes: 0GitHub stars: 3
- Mea Array Spiking Rvq Motif TransformerUse when generatively modeling sparse binary spike volumes from MEA/HD-MEA recordings. Discrete generative model with RVQ motif vocabulary + factorized masked transformer for array-wide spiking activity.Votes: 0GitHub stars: 3
- Predictive Suppression Layers SnnPredictive coding layer variants for communication-efficient spiking neural networks — a per-layer predictor transmits only "surprising" spikes, via signed spiking residuals (error units) or an error-magnitude-driven gate that suppresses predictable activity (predictive suppression, including strictly event-driven hard-STE and respike binary variants). Achieves ~3× reduction in communicated inter-layer activity while increasing task accuracy, with metrics that decouple local processing cost (...Votes: 0GitHub stars: 3
- Snn Dmn Self ConsciousnessUse for DMN self-consciousness SNN modeling with IIT phi.Votes: 0GitHub stars: 3
- Snn World Model Prediction ChainFully-spiking world-model rollout for model-based RL.Votes: 0GitHub stars: 3
- Spikfax Second Order SnnSecond-order KFAC optimizer for SNN training (SpiKFAX).Votes: 0GitHub stars: 3
- Vanillasort Spike SortingUse when spike sorting with noisy auto-generated labels.Votes: 0GitHub stars: 3
- Arxiv 2609 29102v1 Elf Reg Scaling Continuous Diffusion Language Mode**arXiv ID:** 2609.29102v1 **Authors:** Zeyu Michael Li, William Xingxu Chen, Bingshuo Qian, Jiayin Liu, Xiang Cheng **URL:** http://arxiv.org/abs/2609.29102v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29216v1 Fb Gdm Fully Bayesian Guided Diffusion Models For**arXiv ID:** 2609.29216v1 **Authors:** Gatien Séguy, Thomas Rodet **URL:** http://arxiv.org/abs/2609.29216v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29740 Topu Lbvs A Realistic Multi Target Benchmark For Ligand Based Virtual ScreeningTopU-LBVS: A Realistic Multi Target Benchmark for Ligand Based Virtual Screening (arXiv: 2609.29740)Votes: 0GitHub stars: 3
- Arxiv 2609 29973v1 Learning Better Reasoning For Generative Recommend**arXiv ID:** 2609.29973v1 **Authors:** Mengdan Zhu, Yufan Zhao, Sophie Di, Yao Zhao, Tao Di, Yulan Yan, Sridhar Iyer, Liang Zhao **URL:** http://arxiv.org/abs/2609.29973v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30087v1 Return Or Revise Learning When Revision Helps Retr**arXiv ID:** 2609.30087v1 **Authors:** Nicholas Kashani Motlagh, Tim Anderson, Jeremy Gwinnup, Grant Erdmann **URL:** http://arxiv.org/abs/2609.30087v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30096v1 Accelerating Video Diffusion Via Training Free Tra**arXiv ID:** 2609.30096v1 **Authors:** Mustafa Munir, Huy Vu, Shreyas Misra, Rohit Jena, Sajad Norouzi, Ali Taghibakhshi, Anis Ahmad, Anjul Patney, Pavlo Molchanov, Nima Tajbakhsh **URL:** http://arxiv.org/abs/2609.30096v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Lpo Vqa Pce Credit PortfolioLoan portfolio optimization via QUBO + Pauli Correlation Encoding + VQA. Covers credit-risk QCBO modeling, qubit-efficient encoding, annealing, top-K feasibility.Votes: 0GitHub stars: 3
- Arxiv 2609 25956 Governed Ai Agent Coordination Dementia CareResearch paper: Governed AI-Agent Coordination for Dementia Care: Architecture, Safety Contracts, and Evidence-Derived Workflow Verification.Votes: 0GitHub stars: 3
- Arxiv 2609 30971 Scihorizon Elab Agentic Protocol Task CompilerResearch paper: SciHorizon-eLab: An Agentic Protocol-to-Task Compiler for Scalable Benchmarking.Votes: 0GitHub stars: 3
- Arxiv 2609 31060 Crowd In Machine Autonomous Agent IncidentsResearch paper: The Crowd in the Machine: A Crisis-Informatics Reading of the 2026 Autonomous Agent Incidents.Votes: 0GitHub stars: 3
- Arxiv 2609 39788 Safety Of Latent Communication In Multi Agent SystemsResearch paper: Safety of Latent Communication in Multi-Agent Systems. Demonstrates that benign link training in latent communication increases harmful compliance relative to text-based communication. Develops RL-based attack raising harmful-compliance from 27.9 to 76.9, and shows reward adaptation enables repair without updating agents.Votes: 0GitHub stars: 3
- Arxiv 2610 00972 Veriharness Scaling Agentic VerificationResearch paper: VeriHarness: Scaling Agentic Verification for Long-Horizon Tasks. Introduces agentic verification framework that transforms LLMs into verifiers with workspaces, evidence tools, and reusable verification skills. Achieves highest selection scores across five long-horizon benchmarks with $100K+ rollout dataset released.Votes: 0GitHub stars: 3
- Arxiv 2509 25045 Hyperdimensional Probe Decoding Llm Representations Via VectWe introduce the Hyperdimensional Probe, a hybrid supervised probe that combines symbolic representations with neural probing. Leveraging Vector Symbolic Architectures (VSAs) and hypervector algebra, it unifies prior methods: the top-down interpretability of supervised probes, SAE's sparsity-driven proxy space, and output-oriented logit investigation. Our approach enables deeper input-focused feature extraction while supporting output-oriented analysis across different LLMs, embedding sizes, andVotes: 0GitHub stars: 3
- Belief Self Distillation User ModelsBelief Self-Distillation (BSD) - extract, read, and causally write a frozen LLM's implicit user model from natural conversations, no external annotations. Use for user-model interpretability, hidden-state steering that actually works, refusal-behavior intervention, and testing whether probed states have causal roles.Votes: 0GitHub stars: 3
- Oracle Distillation Weak QueryOracle distillation - clean queries from noisy oracles.Votes: 0GitHub stars: 3
- Self Supervised Confidence EfficiencyConfidence-only fine-tuning makes reasoning models shorter - metacognitive supervision (predicting own answer confidence at intermediate trace points) reduces generated tokens up to 25% at matched accuracy with no length objective, no early stopping, only 600 training problems. Use when improving reasoning efficiency without explicit length penalties or inference-time stopping machinery.Votes: 0GitHub stars: 3
- Tabular Attention BenchmarkAttention backend benchmarking for tabular foundation models - row/column alternating attention has asymmetric shape profiles (long row sequences, short column sequences, strided memory layout) so optimal backend (FlashAttention-2/3/4, cuDNN, vLLM, SageAttention) differs per attention type and hardware. Use when optimizing TabPFN/Mitra/ConTextTab-style inference, choosing attention kernels for 2D tabular layouts, or benchmarking attention on A100/H100/B200.Votes: 0GitHub stars: 3
- Dtqw Diffusion Medical ImagingQuantum-walk forward diffusion + classical U-Net denoising for medical images.Votes: 0GitHub stars: 3