All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Arxiv 2609 10135v1 Agent Based Ml Llm Fusion With Self Optimizing Pro**arXiv ID:** 2609.10135v1 **Authors:** Shuai Yan, Yang Xu, Shan He **URL:** http://arxiv.org/abs/2609.10135v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 10239v1 Literag Cost Efficient Graph Based Retrieval Augme**arXiv ID:** 2609.10239v1 **Authors:** Daniel Alejandro Coll Tejeda, Pedro García López, Daniel Barcelona-Pons **URL:** http://arxiv.org/abs/2609.10239v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 10264v1 Maverick Private And Verifiable Llm Inference Made**arXiv ID:** 2609.10264v1 **Authors:** Ben Merbaum, Mohammad Amin Raeisi, Wenhao Wang, Charalampos Papamanthou, Katerina Sotiraki, Fan Zhang **URL:** http://arxiv.org/abs/2609.10264v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 10305v1 Rilm Parameter Efficient Language Modeling Via Geo**arXiv ID:** 2609.10305v1 **Authors:** Fang Li **URL:** http://arxiv.org/abs/2609.10305v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Attending To Graph Transformers**arXiv ID:** 2302.04181 **Authors:** Luis Müller, Mikhail Galkin, Christopher Morris, Ladislav Rampášek **Published:** 2023-02-08T16:40:11Z **Abstract:** Recently, transformer architectures for graphs emerged as an alternative to established techniques for machine learning with graphs, such as (message-passing) graph neural networks. So far, they have shown promising empirical results, e.g., on molecular prediction datasets, often attributed to their ability to circumvent graph neural networ...Votes: 0GitHub stars: 3
- Automated Problem Identification Regression Vs Classification Via Evolutionary Deep Networks**arXiv ID:** 1707.00703 **Authors:** Emmanuel Dufourq, Bruce A. Bassett **Published:** 2017-07-03T18:00:08Z **Abstract:** Regression or classification? This is perhaps the most basic question faced when tackling a new supervised learning problem. We present an Evolutionary Deep Learning (EDL) algorithm that automatically solves this by identifying the question type with high accuracy, along with a proposed deep architecture. Typically, a significant amount of human insight and preparation is...Votes: 0GitHub stars: 3
- Autoregressive Flow Matching NeuralAutoregressive Flow Matching (AFM) framework for probabilistic prediction of neural dynamics from multimodal sensory input, enabling conditional distribution learning of future neural activity with closed-loop neurotechnology applications.Votes: 0GitHub stars: 3
- Better Language Models And Their ImplicationsSkill for AI agent capabilitiesVotes: 0GitHub stars: 3
- Bisco Llm Binary Spherical Coding Extreme CompressionCodebook-free binary spherical coding for extreme low-bit LLM weight compression. Maps weight chunks onto unit hypersphere and binarizes into sign streams. Residual BSQ stage for reconstruction error. Category-wise recovery distillation. Activation: binary spherical coding, LLM compression, low-bit quantization, lookup-free coding, model deployment.Votes: 0GitHub stars: 3
- Bleg Llm Functions As Powerful... Activation: fMRI, functional MRI, brain imaging, brain network, graph, connectivityVotes: 0GitHub stars: 3
- Brain Llm Alignment Tracks Training Data Not TypolDerived from arXiv:2605.23032 - Brain-LLM Alignment Tracks Training Data, Not TypologyVotes: 0GitHub stars: 3
- Building An Early Warning System For Llm Aided BioSkill for AI agent capabilitiesVotes: 0GitHub stars: 3
- Can Llms Deobfuscate BinaryDeobfuscating binary code remains a fundamental challenge in reverse engineering, as obfuscation is widely used to hinder analysis and conceal program logic. Although large languag... Activation: optimizationVotes: 0GitHub stars: 3
- Can We Break Llms Out Of Self Loops Fine Grained RDerived from arXiv:2607.18100 - Can We Break LLMs Out of Self-Loops? Fine-Grained Reasoning Control with Activation SteeringVotes: 0GitHub stars: 3
- Cascaded Transformer For Robust And Scalable Sla Decomposition Via Amortized Optimization**arXiv ID:** 2601.11859 **Authors:** Cyril Shih-Huan Hsu **Published:** 2026-01-17T01:01:53Z **Abstract:** The evolution toward 6G networks increasingly relies on network slicing to provide tailored, End-to-End (E2E) logical networks over shared physical infrastructures. A critical challenge is effectively decomposing E2E Service Level Agreements (SLAs) into domain-specific SLAs, which current solutions handle through computationally intensive, iterative optimization processes that incur sub...Votes: 0GitHub stars: 3
- Cheesebench Evaluating Large Language ModelsWe introduce CheeseBench, a benchmark that evaluates large language models (LLMs) on nine classical behavioral neuroscience paradigms (Morris water maze, Barnes maze, T-maze, radial arm maze, star maz. Activation: rodent behavior paradigms, LLM evaluation, ODE complexityVotes: 0GitHub stars: 3
- Classic Continual And Contrastive Learning Of Aspect Sentiment Classification Tasks**arXiv ID:** 2112.02714 **Authors:** Zixuan Ke, Bing Liu, Hu Xu, Lei Shu **Published:** 2021-12-05T23:55:53Z **Abstract:** This paper studies continual learning (CL) of a sequence of aspect sentiment classification(ASC) tasks in a particular CL setting called domain incremental learning (DIL). Each task is from a different domain or product. The DIL setting is particularly suited to ASC because in testing the system needs not know the task/domain to which the test data belongs. To our knowle...Votes: 0GitHub stars: 3
- Co Lmlm Continuous Query Limited Memory Language ModelsLimited memory language models (LMLMs) externalize factual knowledge during pretraining to a knowledge base (KB), rather than memorizing it in their weights. During generation, the model then fetches. Based on arXiv:2607.07707.Votes: 0GitHub stars: 3
- Compound Llm Agent DesignControlled study of compound LLM agent design in adversarial POMDPs. Identifies deliberation cascade pattern where distributing deliberation tools across a hierarchy degrades performance. Finds programmatic state abstraction delivers highest RPTS.Votes: 0GitHub stars: 3
- Computational Lesions Multilingual Language Models SeparateHow the brain supports language across different languages is a basic question in neuroscience and a useful test for multilingual artificial intelligence. Neuroimaging has identifi... Activation: brain, fmri, multilingual, lesionVotes: 0GitHub stars: 3
- Cooperation Is All You Need**arXiv ID:** 2305.10449 **Authors:** Ahsan Adeel, Junaid Muzaffar, Fahad Zia, Khubaib Ahmed, Mohsin Raza, Eamin Chaudary, Talha Bin Riaz, Ahmed Saeed **Published:** 2023-05-16T16:48:12Z **Abstract:** Going beyond 'dendritic democracy', we introduce a 'democracy of local processors', termed Cooperator. Here we compare their capabilities when used in permutation invariant neural networks for reinforcement learning (RL), with machine learning algorithms based on Transformers, such as ChatGPT. T...Votes: 0GitHub stars: 3
- Cross Seed Explainability Procrustes Sparse AutoencodersProcrustes-conditioned Joint End-to-end Top-K SAE for extracting cross-seed universal features from independently trained BERT models. Combines Top-K sparsity, end-to-end optimization, and dead-feature revival. Pearson r ≥ 0.70 across seeds. Activation: sparse autoencoder, cross-seed universality, Procrustes alignment, mechanistic interpretability, feature universality.Votes: 0GitHub stars: 3
- Cross Tokenizer On Policy DistillationCross-Tokenizer On-Policy Distillation framework using byte-prefix marginalization to enable knowledge transfer between models with different tokenizers while preserving policy quality.Votes: 0GitHub stars: 3
- Debate Graph Reliable Adaptive Reasoning Large Language Model Uncertain Knowledge GrapSkill derived from arXiv:2607.17266 - Debate-on-Graph: Reliable and Adaptive Reasoning of Large Language Model on Uncertain Knowledge GrapVotes: 0GitHub stars: 3
- Defining And Evaluating Political Bias In LlmsSkill for AI agent capabilitiesVotes: 0GitHub stars: 3
- Dels Spec Decoupled Long Short Contexts For Parallel Speculative DraftingSpeculative decoding accelerates LLM inference by drafting multiple tokens and verifying them in parallel. Block-parallel drafters such as DFlash further improve drafting efficiency by predicting an e. Based on arXiv:2607.07409.Votes: 0GitHub stars: 3
- Discovering Heuristics With Large Language Models Llms For Mixedinteger Programs Singlemachine Scheduling**arXiv ID:** 2510.24013 **Authors:** İbrahim Oğuz Çetinkaya, İ. Esra Büyüktahtakın, Parshin Shojaee, Chandan K. Reddy **Published:** 2025-10-28T02:43:04Z **Abstract:** Our study contributes to the scheduling and combinatorial optimization literature with new heuristics discovered by leveraging the power of Large Language Models (LLMs). We focus on the single-machine total tardiness (SMTT) problem, which aims to minimize total tardiness by sequencing n jobs on a single processor without preem...Votes: 0GitHub stars: 3
- Distilled Reinforcement Learning For Llm Post TraiDerived from arXiv:2607.17247 - Distilled Reinforcement Learning for LLM Post-trainingVotes: 0GitHub stars: 3
- Distilled Reinforcement Learning Llm Post TrainingSkill derived from arXiv:2607.17247 - Distilled Reinforcement Learning for LLM Post-trainingVotes: 0GitHub stars: 3
- Do Ai Agents Know When A Task Is Simple Toward ComDo AI Agents Know When a Task Is Simple? Toward Complexity-Aware Reasoning and Execution - Large language model (LLM) agents increasingly automate multi-step engineering and informatics workflows, yet they rarely ask how much effort a task a...Votes: 0GitHub stars: 3
- Do Large Gpt Models Discover Moral Dimensions In Language Representations A Topological Study Of Sentence Embeddings**arXiv ID:** 2309.09397 **Authors:** Stephen Fitz **Published:** 2023-09-17T23:38:39Z **Abstract:** As Large Language Models are deployed within Artificial Intelligence systems, that are increasingly integrated with human society, it becomes more important than ever to study their internal structures. Higher level abilities of LLMs such as GPT-3.5 emerge in large part due to informative language representations they induce from raw text data during pre-training on trillions of words. These e...Votes: 0GitHub stars: 3
- Do You Remember Toward Memorycentric Multimodal Ai**arXiv ID:** 2607.11919 **Authors:** Xuguang Yu, Weigang Zheng, Minyue Yu **Published:** 2026-07-07T19:07:27Z **Abstract:** Human memory is reconstructive, not a faithful recording. Current multimodal LLMs (MLLMs) lack this capability: they process images through a frozen visual encoder, produce a one-shot text output, and discard internal representations. We present DoYouRemember, a three-stage architecture introducing reconstructive memory into MLLMs: (1) a VQ-VAE compresses images into di...Votes: 0GitHub stars: 3
- Docmaster Hierarchical Structure Aware Document AnalysisHierarchical structure-aware document analysis system using LLMs. Parses documents into hierarchical trees preserving layouts, builds structure-aware semantic indices for filtering and question answering. Handles academic papers, technical manuals, financial reports. Activation: document analysis, hierarchical structure, LLM system, information extraction, document understanding.Votes: 0GitHub stars: 3
- Dominotree Conditional Tree Structured Drafting Speculative DecodingTraining-free best-first draft tree for speculative decoding using Domino's conditional non-factorized correction. Achieves up to 6.6x speedup on Qwen3-4B and highest mean accept length (10.7 tokens/round). GPU-native CUDA-graph builder for efficient tree construction. Activation: speculative decoding, tree-structured drafting, Domino conditioning, LLM inference, block-diffusion.Votes: 0GitHub stars: 3
- Dual Hypothesis Reasoning Framework Llm GuardrailsSkill derived from arXiv:2607.17575 - A Dual-Hypothesis Reasoning Framework for LLM GuardrailsVotes: 0GitHub stars: 3
- E Spl Evolutionary System Prompt LearningE-SPL (Evolutionary System Prompt Learning): Evolutionary system prompt learning for self-evolving LLMs. Uses reinforcement learning to optimize system prompts, enabling LLMs to improve themselves through interaction without external supervision. Activation: self-evolution, system-prompt, RL.Votes: 0GitHub stars: 3
- Edge Llm Rag Mission OrchestrationPolicy-aware edge LLM-RAG framework for mission-critical Internet of Battlefield Things orchestration. Intent-driven control with safety guarantees.Votes: 0GitHub stars: 3
- Efficient Llm Inference SurveySkill for AI agent capabilitiesVotes: 0GitHub stars: 3
- Efficient Training Of Language Models To Fill In TSkill for AI agent capabilitiesVotes: 0GitHub stars: 3
- Empirical Grounding Improves Realism Llm Agents Simulating Human Behavior During DisruptionsSkill derived from arXiv:2607.17437 - Empirical Grounding Improves the Realism of LLM Agents Simulating Human Behavior During DisruptionsVotes: 0GitHub stars: 3
- Empirical Grounding Improves The Realism Of Llm AgDerived from arXiv:2607.17437 - Empirical Grounding Improves the Realism of LLM Agents Simulating Human Behavior During DisruptionsVotes: 0GitHub stars: 3
- Espl Evolutionary System Prompt Learning---\nname: espl-evolutionary-system-prompt-learning\ndescription: 'Evolutionary System Prompt Learning (E-SPL) jointly improves model context (system prompt) and model weights through parallel sampling and LLM self-reflection driven evolution. Based on arXiv:2602.14697.'\n---\n\n# Evolutionary System Prompt Learning (E-SPL)\n\n**arXiv**: 2602.14697 | **Utility**: 0.9\n\n## Overview\nEvolutionary System Prompt Learning (E-SPL) jointly improves model context (system prompt) and model weights th...Votes: 0GitHub stars: 3
- Evaluating Chain Of Thought MonitorabilitySkill for AI agent capabilitiesVotes: 0GitHub stars: 3
- Evaluating Large Language Models Trained On CodeSkill for AI agent capabilitiesVotes: 0GitHub stars: 3
- Evo Generative Llm MergingEvolutionary Generative Merging (EvoGM) methodology for LLM model merging. Uses evolutionary algorithms to optimize model weight interpolation by generating candidate merge configurations, evaluating them with lightweight benchmarks, and evolving better solutions. Use when: (1) Merging multiple LLM checkpoints or fine-tuned variants, (2) Optimizing merge weights for multi-task performance, (3) Finding Pareto-optimal tradeoffs between capabilities, (4) Replacing grid search for model merging.Votes: 0GitHub stars: 3
- Evojail Evolutionary Diverse Jailbreak Prompt Generation For Large Language Models**arXiv ID:** 2605.02921 **Authors:** Rui Tang, Kaiyu Xu, Pengsen Cheng, Hao Ren, Haizhou Wang, Shuyu Jiang **Published:** 2026-04-22T02:59:49Z **Abstract:** As LLMs continue to shape real-world applications, automated jailbreak generation becomes essential to reveal safety weaknesses and guide model improvement. Existing automatic jailbreak generation methods have not yet fully considered two important aspects: adaptability to evolving safety-finetuned models, which affects their effectivene...Votes: 0GitHub stars: 3
- Evolutionary Multiobjective Optimization Of Large Language Model Prompts For Balancing Sentiments**arXiv ID:** 2401.09862 **Authors:** Jill Baumann, Oliver Kramer **Published:** 2024-01-18T10:21:15Z **Abstract:** The advent of large language models (LLMs) such as ChatGPT has attracted considerable attention in various domains due to their remarkable performance and versatility. As the use of these models continues to grow, the importance of effective prompt engineering has come to the fore. Prompt optimization emerges as a crucial challenge, as it has a direct impact on model performance...Votes: 0GitHub stars: 3
- Experimental Evaluation Of Machine Learning Models For Goaloriented Customer Service Chatbot With Pipeline Architecture**arXiv ID:** 2409.18568 **Authors:** Nurul Ain Nabilah Mohd Isa, Siti Nuraishah Agos Jawaddi, Azlan Ismail **Published:** 2024-09-27T09:11:52Z **Abstract:** Integrating machine learning (ML) into customer service chatbots enhances their ability to understand and respond to user queries, ultimately improving service performance. However, they may appear artificial to some users and affecting customer experience. Hence, meticulous evaluation of ML models for each pipeline component is crucial ...Votes: 0GitHub stars: 3
- Explicit Operator Ssm Neural OscillatorMathematical framework establishing explicit correspondence between state space models (S4/S4D) and exactly solvable nonlinear oscillator networks. Derives closed-form analytical operator for complete S4D forward propagation. Activation: state space model, S4, SSM, neural oscillator, sequence modeling, mathematical operator, computational neuroscience.Votes: 0GitHub stars: 3
- Extracting Concepts From Gpt 4Skill for AI agent capabilitiesVotes: 0GitHub stars: 3