All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Arxiv 2609 29803 Seek Skill Routed Evaluation With Evolvable Knowledge For Industrial SearchSEEK: Skill-Routed Evaluation with Evolvable Knowledge for Industrial Search (arXiv: 2609.29803)Votes: 0GitHub stars: 3
- Arxiv 2609 29983v1 From Interests To Semantic Ids Retrieval Grounded**arXiv ID:** 2609.29983v1 **Authors:** Mengdan Zhu, Yufan Zhao, Yao Zhao, Sophie Di, Tao Di, Yulan Yan, Sridhar Iyer, Liang Zhao **URL:** http://arxiv.org/abs/2609.29983v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30055v1 Era By Eon Benchmarking Enterprise Agents On Hidde**arXiv ID:** 2609.30055v1 **Authors:** Benjamin Gruenbaum, Doron Porat, Assaf Natanzon, Roy Zavida, Chen Dinachi, Or Itzahary **URL:** http://arxiv.org/abs/2609.30055v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30205v1 A Living Benchmark For Information Retrieval From**arXiv ID:** 2609.30205v1 **Authors:** Jordan L. Cahoon, Chloe O. Stanwyck, Sulaiman Somani, Philip Chung, Kevin R Keet, Kameron C. Black, Andrea T. Fisher, Sarita Khemani, Jerry Liu, Stephen Ma, Saloni K. Maharaj, Rita M. Pandya, Eduardo Perez-Guerrero, Priyanka Pillai, Lisa Shieh, David J. H. Wu, James Xie, James C. McAvoy, Teresa Nguyen, Jessica Tran, Lucy Yin, Bridget Lin, Alison Callahan, Jason A. Fries, Nigam H. Shah, Emily Alsentzer **URL:** http://arxiv.org/abs/2609.30205v1 **Utility...Votes: 0GitHub stars: 3
- Arxiv 2609 30210v1 The Alignment Illusion In Multimodal Large Languag**arXiv ID:** 2609.30210v1 **Authors:** Hong-Han Wang, Yuntao Wang, Hu Ding **URL:** http://arxiv.org/abs/2609.30210v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Brain Wide Benchmark Pretraining TransferBrainWideBench three-suite protocol for across-animal transfer on multi-region neural recordings. Use when benchmarking neural foundation models.Votes: 0GitHub stars: 3
- Swe Flux Runtime Reasoning BenchmarkUse when evaluating LLM code-execution reasoning or building execution-grounded benchmarks. Repository-level dynamic benchmark with gold answers auto-harvested from instrumented test executions, covering control flow, loops, state, dataflow, exceptions, invariants.Votes: 0GitHub stars: 3
- Arxiv 2609 29444v1 Itersynth Rethinking Deep Search Agents Via Role D**arXiv ID:** 2609.29444v1 **Authors:** Xingyu Wu, Yuchen Yan, Zhengxi Lu, Siqi Chen, Xin ZHANG, Aiting Liu, Chao Deng, Jie Liu, Jin Ma, Jian Shao, Jun Xiao, Yongliang Shen **URL:** http://arxiv.org/abs/2609.29444v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30001v1 Advancing Model Research In Agentx Long Horizon Au**arXiv ID:** 2609.30001v1 **Authors:** Shuang Yang, Zijie Zhuang, Changxin Lao, Pengbo Xu, Hanwen Xu, Yusheng Huang, Han Gao, Guanchen Wang, Tianbao Ma, Linxun Chen, Peilin Song, Xuming Wang, Chen Li, Fan Wu, Tao Wang, Zibo Zhao, Xiangyu Wu, An Liu, Fei Pan, Peng Jiang, Chen Yang, Zhaojie Liu, Wenwu Ou **URL:** http://arxiv.org/abs/2609.30001v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Ahgq Affine Pricing Group QuantizationAHGQ: unify affine pricing operator and Riccati transform via group quantization + thin-path holonomy. Use for geometric finance, Heston/CIR structure.Votes: 0GitHub stars: 3
- Arxiv 2609 29163v1 Edge Ai On Constrained Devices For Binary Sleep Wa**arXiv ID:** 2609.29163v1 **Authors:** Stefan Reitmann, Lena Oden **URL:** http://arxiv.org/abs/2609.29163v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Ai Exposure Stock ReturnsAI consumption factor and firm AI-beta long-short premium.Votes: 0GitHub stars: 3
- Arxiv 2609 29350v1 Learning A Flow To Self Supervised Representations**arXiv ID:** 2609.29350v1 **Authors:** Yuling Jiao, Wensen Ma, Houduo Qi, Defeng Sun **URL:** http://arxiv.org/abs/2609.29350v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29396v1 Wearable Ecg Quality Assessment A Deep Learning An**arXiv ID:** 2609.29396v1 **Authors:** Xiaopeng Mao, Marike Weisbjerg, Sadasivan Puthusserypady **URL:** http://arxiv.org/abs/2609.29396v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29409v1 Machine Unlearning For Gibbs Supervised Learning A**arXiv ID:** 2609.29409v1 **Authors:** Yaiza Bermudez, Samir M. Perlaza, Iñaki Esnaola **URL:** http://arxiv.org/abs/2609.29409v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29798v1 Benchmarking And Domain Adaptation Of Automatic Sp**arXiv ID:** 2609.29798v1 **Authors:** Stephen E. Moore, Akwasi Asare, Mich-Seth Owusu, Paul Azunre, Joel Budu, Lawrence A. Adu-Gyamfi **URL:** http://arxiv.org/abs/2609.29798v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30037v1 Aerial Adversarial Evaluation Of Robustness In Acc**arXiv ID:** 2609.30037v1 **Authors:** Saim Rehman, Muhammad Shafique **URL:** http://arxiv.org/abs/2609.30037v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30048v1 Style Not Self Surface Cues Explain Zero Shot Code**arXiv ID:** 2609.30048v1 **Authors:** Ehsan Barkhordar, Surendrabikram Thapa **URL:** http://arxiv.org/abs/2609.30048v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30050v1 Nnv3 Expanding Neural Network Verification To New**arXiv ID:** 2609.30050v1 **Authors:** Anne M. Tumlin, Samuel Sasaki, Ben Wooding, Diego Manzanas Lopez, Muhammad Usama Zubair, Navid Hashemi, Hongchao Zhang, Waseem Abbas, Ipek Oguz, Meiyi Ma, Taylor T. Johnson **URL:** http://arxiv.org/abs/2609.30050v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30258v1 Temporal Gradient Inversion For Private Trajectory**arXiv ID:** 2609.30258v1 **Authors:** Sudip Bhujel, Shanghao Shi, Ruiquan Huang, Ning Zhang, Yang Xiao **URL:** http://arxiv.org/abs/2609.30258v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Cfm Multitask Policy DistillationUse when training multi-task robot manipulation policies. Distills single-task conditional flow matching experts into one shared multi-task policy by transferring velocity fields, avoiding capacity blow-up or performance drops of naive concatenated training.Votes: 0GitHub stars: 3
- Gradient Tunneling Nmc Feedback LearningUse when training spiking microcircuits/reservoirs online. Causality-gradient feedback learning without surrogate gradients.Votes: 0GitHub stars: 3
- Lastopd Latent Onpolicy DistillationLastOPD methodology — fixing latent-alignment collapse in on-policy distillation by applying latent supervision only at the last-layer state with a short crossfade into token-level OPD. Use when: (1) student-teacher latent alignment in OPD degrades after early gains, (2) alignment metric improves but downstream performance collapses, (3) combining latent + token distillation signals. Keywords: on-policy distillation, latent collapse, reverse KL, LLM distillation, layer-mismatch.Votes: 0GitHub stars: 3
- Memory Attention Lookup ValuesUse when designing efficient attention variants or reducing GPU memory for LLM inference. Replaces the value projection with token-indexed memory tables plus contextual keys; value construction reduces to lookup+add.Votes: 0GitHub stars: 3
- Repulsive Self Attention NonequilibriumUse when analyzing attention dynamics or recurrent transformer collective behavior. Minimal repulsive self-attention model (V=-I) exhibiting chaos, attention condensation, and emergent locality across d=2 and d=N scaling regimes.Votes: 0GitHub stars: 3
- Rt Opd Reward Tilted DistillationRT-OPD methodology — reward-tilted on-policy distillation using teacher with-vs-without-modality log-probability contrast to force acoustic grounding in audio-language models. Use when: (1) multimodal students exploit text shortcuts and ignore perceptual evidence, (2) distilling multimodal models on-policy, (3) counterfactual modality-ablation reward design. Keywords: on-policy distillation, reward tilting, counterfactual contrast, audio-language, modality grounding.Votes: 0GitHub stars: 3
- Token Span Collapse Sequential DistillationUse when compressing long-context inference or reducing autoregressive compute. Lightweight merge module collapses predictable token spans into single surrogate embeddings with KV-cache rollback, no retraining of the backbone.Votes: 0GitHub stars: 3
- Trace Temporal Gradient InversionTRACE methodology — temporal gradient-inversion attack on embodied RL that autoregressively reconstructs private observation-action trajectories from per-step policy gradients, exploiting cross-time gradient correlation and closed-form action recovery. Use when: (1) auditing privacy leakage of distributed/federated RL gradient streams, (2) designing sequence-aware privacy defenses, (3) threat-modeling gradient sharing in embodied agents. Keywords: gradient inversion, embodied RL, privacy atta...Votes: 0GitHub stars: 3
- Arxiv 2609 30027v1 Synthetic Hospital An Open Verifiable Physician Va**arXiv ID:** 2609.30027v1 **Authors:** Christine Park, Valerie Chen, Tim Dettmers **URL:** http://arxiv.org/abs/2609.30027v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Dt4x Plus Diagnosis Decision TreeUse when building hybrid model-based + data-driven fault diagnosis systems. Enhanced symbolic-regression decision tree whose node expressions separate target classes while preserving ARR coherence of non-target classes.Votes: 0GitHub stars: 3
- Arxiv 2609 29876v1 Ontology Mediated Neurosymbolic Constraint Acquisi**arXiv ID:** 2609.29876v1 **Authors:** Stefan Bischof, Juliana Kainz, Danilo Valerio **URL:** http://arxiv.org/abs/2609.29876v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29150v1 A Particle Swarm Assisted Gradient Meta Learning A**arXiv ID:** 2609.29150v1 **Authors:** Kang Zhou **URL:** http://arxiv.org/abs/2609.29150v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29191v1 Asirf An Agentic Framework For Context Dependent S**arXiv ID:** 2609.29191v1 **Authors:** Sudha Priyadarshini, Mohamed Chahine Ghanem **URL:** http://arxiv.org/abs/2609.29191v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29428 Agentic Ger Terminology Recovery In Long Form Speech Using Global Contextagentic-ger: terminology recovery in long-form speech using global context (arXiv: 2609.29428)Votes: 0GitHub stars: 3
- Arxiv 2609 29428v1 Agentic Ger Terminology Recovery In Long Form Spee**arXiv ID:** 2609.29428v1 **Authors:** Yanqiao Zhu, Wupeng Wang, Zhifu Gao, Xiangang Li, Xie Chen **URL:** http://arxiv.org/abs/2609.29428v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29429 Just Ask Jev Reinforcement Learning For Calibrated Decisions As A Zero Shot Detector Of Ai AlignmenJust Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignmen (arXiv: 2609.29429)Votes: 0GitHub stars: 3
- Arxiv 2609 29429v1 Just Ask Jev Reinforcement Learning For Calibrated**arXiv ID:** 2609.29429v1 **Authors:** Ruoqi Guo, Yi Liu, Gelei Deng, Yuekang Li, Lida Zhao, Yutao Wu, Simin Chen, Ying Zhang, Leo Yu Zhang **URL:** http://arxiv.org/abs/2609.29429v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29444 Itersynth Rethinking Deep Search Agents Via Role Decoupled Iterative SynthesisIterSynth: Rethinking Deep Search Agents via Role-Decoupled Iterative Synthesis (arXiv: 2609.29444)Votes: 0GitHub stars: 3
- Arxiv 2609 29465 Swe Prometheus Measuring Engineering Governance Improvements In Real World RepositoriesSWE-Prometheus: Measuring Engineering Governance Improvements in Real-World Repositories (arXiv: 2609.29465)Votes: 0GitHub stars: 3
- Arxiv 2609 29773 Breaking The Environment Wall Evolving Llm Agent Environments For Recursive Self ImprovementBreaking the Environment Wall: Evolving LLM Agent Environments for Recursive Self-Improvement (arXiv: 2609.29773)Votes: 0GitHub stars: 3
- Arxiv 2609 29808 Hard Stop Kernel Level Preemption And Containment For Rogue Agentic ExecutionHard Stop: Kernel-Level Preemption and Containment for Rogue Agentic Execution (arXiv: 2609.29808)Votes: 0GitHub stars: 3
- Arxiv 2609 29837 Pubg Ally A Conversational Embodied Agent As An Ai TeammatePUBG Ally: A Conversational Embodied Agent as an AI Teammate (arXiv: 2609.29837)Votes: 0GitHub stars: 3
- Arxiv 2609 29837v1 Pubg Ally A Conversational Embodied Agent As An Ai**arXiv ID:** 2609.29837v1 **Authors:** Beomsoo Kim, Byeongju Kim, Dohyun Kim, Dongwon Kim, Eunchong Kim, Hongmin Kim, Hyeojung Im, Hyeonbin Hwang, Hyeonghwan Kim, Hyoseok Seol, Insub Im, Irene Chen, Jaeseung Jeon, Jimin Hong, Kiyoon Yoo, Minkyoung Park, Seohyeon Jung, Seungjun Chung, Sue Hyun Park, Sungwoo Kim, Youngin Cho, Yujeong Son, Kangwook Lee, Hyunseung Kim **URL:** http://arxiv.org/abs/2609.29837v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29875 When Can Agents Forget Their Reasoning Iclr For Long Horizon Agent Context CompressionWhen Can Agents Forget Their Reasoning? ICLR for Long-Horizon Agent Context Compression (arXiv: 2609.29875)Votes: 0GitHub stars: 3
- Arxiv 2609 29881v1 A New Gap Sequence For Shellsort Rl Driven Algorit**arXiv ID:** 2609.29881v1 **Authors:** Bo Liu **URL:** http://arxiv.org/abs/2609.29881v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29892 Qwen Planner Agent A Closed Loop Ai For Ai Framework For Real World Mobile Planner AgentsQwen-Planner-Agent: A Closed-Loop AI-for-AI Framework for Real-World Mobile Planner Agents (arXiv: 2609.29892)Votes: 0GitHub stars: 3
- Arxiv 2609 29892v1 Qwen Planner Agent A Closed Loop Ai For Ai Framewo**arXiv ID:** 2609.29892v1 **Authors:** Tingyu Qu, Weigao Sun, Yuecheng Liu, Yucheng Zhao, Yi Zhu, Yifeng Ding, Qiyi Wang, Sihan Cao, Pengkun Jiao, Hanlei Xie, Xiongwei Wu, Qichao Wang, Haodong Zhang, Jiajun Liu, Yuhao Wang, Yuqing Xie, Junpeng Zhao, Long Chen, Ming Ma, Sihan Yang, Ziwang Zhao, Yanhao Jia, Liangquan Gong, Feida Zhu, Yiran Zhong, Steven Hoi **URL:** http://arxiv.org/abs/2609.29892v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29901 Working With Agentic Teammates When A New Organizational Actor Collides With The Human EcosystemWorking with Agentic `Teammates': When a New Organizational Actor Collides with the Human Ecosystem (arXiv: 2609.29901)Votes: 0GitHub stars: 3
- Arxiv 2609 29901v1 Working With Agentic Teammates When A New Organiza**arXiv ID:** 2609.29901v1 **Authors:** Rida Qadri, Remi Denton, Michael Madaio, Mahima Pushkarna, Leslie Lai, Sherry Moore, Michelle Chen Huebscher, Andrew Butcher, Ritom Sen, Hsiao-Yu Tung, Shaan Mathur, Yimeng Liu, Shibl Mourad, Noah Fiedel, Edward Grefenstette, Michael Terry **URL:** http://arxiv.org/abs/2609.29901v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29921 Who Holds The Pen Let Specifications Not Agents Sign OffWho Holds the Pen? Let Specifications, Not Agents, Sign Off (arXiv: 2609.29921)Votes: 0GitHub stars: 3