All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Arxiv 2609 29958v1 Multi Dimensional Matching**arXiv ID:** 2609.29958v1 **Authors:** Irene Aldridge **URL:** http://arxiv.org/abs/2609.29958v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29959v1 Not All Confusion Is Equal A Source Aware Uncertai**arXiv ID:** 2609.29959v1 **Authors:** Hai Huang, Helmut Mayer **URL:** http://arxiv.org/abs/2609.29959v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29961v1 A Contraction Framework For Stochastic Operators W**arXiv ID:** 2609.29961v1 **Authors:** Ids van der Werf, Sergio Rozada, Antonio G. Marques **URL:** http://arxiv.org/abs/2609.29961v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29963v1 Adatex4d Adaptive Texture Capacity Allocation For**arXiv ID:** 2609.29963v1 **Authors:** De Jiang, Peiqiang Wang, Kehong Yuan, Shaohua Ma **URL:** http://arxiv.org/abs/2609.29963v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29974v1 Diverse Geometries Frozen Weights Robust Heterogen**arXiv ID:** 2609.29974v1 **Authors:** Ali Haghpanah Jahromi, Mohammad Taheri **URL:** http://arxiv.org/abs/2609.29974v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29988v1 Let Training Guide Selection Online Synthetic Data**arXiv ID:** 2609.29988v1 **Authors:** Yanran Wu, Sana Lakdawala, Renzo Tassara Miller, Chongyang Bai, Sharath Ciddu, Shivendra Pratap Singh, Kungang Li, Sandeep Pandey, Chunwei Liu **URL:** http://arxiv.org/abs/2609.29988v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29995v1 Guardrails Or Roadblocks Effects Of Pedagogical St**arXiv ID:** 2609.29995v1 **Authors:** Madeleine Eastwood, Harshith Narne, Joseph Hilby, Paul Denny, Ashish Aggarwal, Amanpreet Kapoor **URL:** http://arxiv.org/abs/2609.29995v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29999v1 Ghost Q Towards Studying Grounding Hallucinations**arXiv ID:** 2609.29999v1 **Authors:** Saim Rehman, Muhammad Shafique **URL:** http://arxiv.org/abs/2609.29999v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30012v1 Low Cost Assays For Measuring Model Behavior Acros**arXiv ID:** 2609.30012v1 **Authors:** Tapan Parikh **URL:** http://arxiv.org/abs/2609.30012v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30017v1 Canopy Exploiting Piecewise Smooth Tree Priors For**arXiv ID:** 2609.30017v1 **Authors:** Michael Jerge, Suman Jana **URL:** http://arxiv.org/abs/2609.30017v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30028v1 How Does Adversarial Influence Scale In Multi Agen**arXiv ID:** 2609.30028v1 **Authors:** Addison J. Wu, Jasin Cekinmez, Michel Liao, Karthik Narasimhan, Thomas L. Griffiths **URL:** http://arxiv.org/abs/2609.30028v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30036v1 Aim Short To Reach Far Your Frozen World Model Can**arXiv ID:** 2609.30036v1 **Authors:** Xvyuan Liu, Jianjie Fang, Chen Gao, Yong Li **URL:** http://arxiv.org/abs/2609.30036v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30047v1 From Processing To Functionality Engineering Acces**arXiv ID:** 2609.30047v1 **Authors:** Tobias Gergs, Rouven Lamprecht, Sahitya Yarragolla, Ole Gronenberg, Luca Vialetto, Hermann Kohlstedt, Thomas Mussenbrock, Jan Trieschmann **URL:** http://arxiv.org/abs/2609.30047v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30054v1 Sciwalker Synthesizing Scientific Coding Problems**arXiv ID:** 2609.30054v1 **Authors:** Chenxi Li, Wenxuan Zeng, Yun Luo, Fangchen Yu, Peng Ye, Yu Cheng, Jun Zhang **URL:** http://arxiv.org/abs/2609.30054v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30063v1 Self Play Pretraining With Zero Data**arXiv ID:** 2609.30063v1 **Authors:** Aditya Cowsik, Kfir Dolev, Michael Y. Li, G. Bruno De Luca, Nourya Cohen, Noah D. Goodman, Yoav Levine **URL:** http://arxiv.org/abs/2609.30063v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30074v1 How Reproducible Are Evaluation Conclusions A Self**arXiv ID:** 2609.30074v1 **Authors:** Dipankar Sarkar **URL:** http://arxiv.org/abs/2609.30074v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30085v1 Residual Correlation As A Diagnostic For Joint Unc**arXiv ID:** 2609.30085v1 **Authors:** Fangqin Zhou, Joaquin Vanschoren **URL:** http://arxiv.org/abs/2609.30085v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30088v1 At Skm Net An Accelerated Trainable Sampling Kaczm**arXiv ID:** 2609.30088v1 **Authors:** Xiaochen Zhang, Haoyu Zhu, Yao Zhang, Qingchun Hou **URL:** http://arxiv.org/abs/2609.30088v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30094v1 Privdrift Auditing User Secret Leakage Under Topic**arXiv ID:** 2609.30094v1 **Authors:** Luciano Maldonado **URL:** http://arxiv.org/abs/2609.30094v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30100v1 R Deim Net An Efficient Rationale Augmented Dual E**arXiv ID:** 2609.30100v1 **Authors:** Pushp, Vaibhav Prajapati, Himangshu Sarma **URL:** http://arxiv.org/abs/2609.30100v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30115v1 Orbital Error Dynamics Self Organized Criticality**arXiv ID:** 2609.30115v1 **Authors:** Volkan Dağlı, Zerrin Dağlı, Dağhan Dağlı **URL:** http://arxiv.org/abs/2609.30115v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30123v1 Hexis Compiling Skills Into Extended Finite State**arXiv ID:** 2609.30123v1 **Authors:** Minghao LI **URL:** http://arxiv.org/abs/2609.30123v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30137v1 Screen Before You Serve Simulation For Production**arXiv ID:** 2609.30137v1 **Authors:** Edesio Alcoba, Kevin Rossell, Aman Gupta, Shao Tang, Jiwoo Hong, Pabel Carrillo-Mendoza, Wanderson Conceição Ferreira, Alvaro Tedeschi, Zayd Simjee, Shreya Rajpal, Bruno Finardi Hime, Christian Sousa, Luis Moneda, Herbert Fei, Daniel Silva, Rohan Ramanath **URL:** http://arxiv.org/abs/2609.30137v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30147v1 Grasp Generating Revising And Assessing For Strate**arXiv ID:** 2609.30147v1 **Authors:** Arunabh Srivastava, Mohammad A., Khojastepour, Srimat Chakradhar, Sennur Ulukus **URL:** http://arxiv.org/abs/2609.30147v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30151v1 Does A Model S Stated Reason For Rejecting A Candi**arXiv ID:** 2609.30151v1 **Authors:** Archit Rastogi **URL:** http://arxiv.org/abs/2609.30151v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30157v1 Learning And Interpreting Policies For Simultaneou**arXiv ID:** 2609.30157v1 **Authors:** Leon Rode, Sumeet Khatri, Supartha Podder **URL:** http://arxiv.org/abs/2609.30157v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30173v1 Gridsfm A Foundation Model For Solving Ac Optimal**arXiv ID:** 2609.30173v1 **Authors:** Luke Bhan, Weiwei Yang, Margaret Capetz, Baosen Zhang **URL:** http://arxiv.org/abs/2609.30173v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30185v1 Intrinsic Extrinsic Coupling In Learning Dynamics**arXiv ID:** 2609.30185v1 **Authors:** Qinyou Wang **URL:** http://arxiv.org/abs/2609.30185v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30186v1 Jev Mobile Jev As An Executor For Mobile Gui Agent**arXiv ID:** 2609.30186v1 **Authors:** Linghua Zhang **URL:** http://arxiv.org/abs/2609.30186v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30198v1 Beyond Compression Training Latent Representations**arXiv ID:** 2609.30198v1 **Authors:** Andreas E. Robertson, Ashley T. Lenau, John D. Shimanek, Benjamin A. Jasperson, Vivek Oommen, David L. Damm, Krishna Garikipati, Remi Dingreville **URL:** http://arxiv.org/abs/2609.30198v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30199v1 Explorationbench Measuring Ai Systems Exploration**arXiv ID:** 2609.30199v1 **Authors:** Ming Zhang, Zhenghao Xiang, Peizhong Gao, Yujiong Shen, Yuhui Wang, Zhonghan Yue, Shihan Dou, Zhangyue Yin, Junjie Ye, Shichun Liu, Weihuang Zheng, Jiahao Chen, Jiayi Chen, Hongzhang Liu, Jiaqi Shao, Tao Gui, Qi Zhang, Xuanjing Huang, Suncong Zheng, Maxm Pan **URL:** http://arxiv.org/abs/2609.30199v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30212v1 Anchored Extra Proximal Methods Optimal Higher Ord**arXiv ID:** 2609.30212v1 **Authors:** Ruichen Jiang, TaeHo Yoon **URL:** http://arxiv.org/abs/2609.30212v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30214v1 Underwater C3 Jepa An Object Centric Cross View Wo**arXiv ID:** 2609.30214v1 **Authors:** Yuncong Yang, Jinlong Li, Yulong Xue, Feng Wu, Chunwen Zhang, Lei Qiao, Xuyang Wang **URL:** http://arxiv.org/abs/2609.30214v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30215v1 A Nearly Quadratic Lower Bound For Linear Optimiza**arXiv ID:** 2609.30215v1 **Authors:** Santosh S. Vempala **URL:** http://arxiv.org/abs/2609.30215v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30217v1 Instrumental Monitor Evasion Emerges Under Ordinar**arXiv ID:** 2609.30217v1 **Authors:** David Schmotz, Derck Prinzhorn, Luca Beurer-Kellner, Anselm Paulus, Ameya Prabhu, Maksym Andriushchenko **URL:** http://arxiv.org/abs/2609.30217v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30219v1 Requirement Bound Verified Commissioning A Frozen**arXiv ID:** 2609.30219v1 **Authors:** Mehmet Iscan **URL:** http://arxiv.org/abs/2609.30219v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30222v1 Trackeverything Long Horizon Dense Tracking Via De**arXiv ID:** 2609.30222v1 **Authors:** Ayush Jain, Sreeharsha Paruchuri, Ishita Gupta, Fan Zhang, Tanner Schmidt, Jakob Engel, Katerina Fragkiadaki, Adam W. Harley **URL:** http://arxiv.org/abs/2609.30222v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30233v1 Coding Agents For Generalized Task And Motion Plan**arXiv ID:** 2609.30233v1 **Authors:** Matteo Merler, Bowen Li, Josh Roy, Yichao Liang, Qianwei Wang, Yixuan Huang, Tom Silver **URL:** http://arxiv.org/abs/2609.30233v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30247v1 Rolling Wam World Action Models With Rolling Imagi**arXiv ID:** 2609.30247v1 **Authors:** Yinghua Zhou, Junjie Ye, Yiqi Zhao, Hao Dong, Celina Shiyu Wang, Ruohai Ge, Tingyi Yang, Basile Van Hoorick, Gaurav Sukhatme, Vitor Guizilini, Yue Wang **URL:** http://arxiv.org/abs/2609.30247v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30264v1 Ad Wm Action Discriminative World Models For Count**arXiv ID:** 2609.30264v1 **Authors:** Jiabin Qiu, Zixuan Chen, Hongye Cao, Jieqi Shi, Jing Huo, Yang Gao **URL:** http://arxiv.org/abs/2609.30264v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Boolean Threshold Neuron CapacityNeuron capacity from Boolean threshold function asymptotics.Votes: 0GitHub stars: 3
- Brain To Language Decoding SurveyBrain-to-language decoding tasks, signals, and evaluation.Votes: 0GitHub stars: 3
- Cerevla Consequence Aware Residual GovernanceUse when deploying frozen action-chunked VLA policies on robots. Lightweight residual refinement plus predictive consequence evaluation with selective suppression — cerebellum-inspired governor that corrects chunked execution errors without retraining.Votes: 0GitHub stars: 3
- Conformal E Process Changepoint DetectionUse when doing distribution-free online changepoint detection with e-processes.Votes: 0GitHub stars: 3
- Conpro Contrast Projection PretrainingConPro methodology — self-supervised pretraining whose target is a physics-derived temporal projection (normalized drop below temporal median), converting unlabeled modality dynamics into free supervision for label-efficient segmentation. Use when: (1) unlabeled sequences record a physical process that labels encode statically, (2) designing self-supervised targets that beat reconstruction pretexts, (3) stacking pretraining + semi-supervised training for label efficiency. Keywords: self-super...Votes: 0GitHub stars: 3
- Cot Prefix Scoring PitfallCoT-prefix scoring pitfall methodology — diagnosing how appended reasoning cues break logit-based answer readout in VLM multiple-choice evaluation, plus linear-probe/generation recovery diagnostics. Use when: (1) multiple-choice eval scores collapse after adding reasoning instructions, (2) designing logit-readout evaluation for reasoning models, (3) distinguishing model-knowledge failure from evaluation-interface mismatch. Keywords: CoT evaluation, answer decoding, logit readout, VLM evaluati...Votes: 0GitHub stars: 3
- Cross Substrate Access AssayUse when transferring brain tests to AI substrates.Votes: 0GitHub stars: 3
- Csows Cost Sensitive Window Expert AggregationUse for online window-size expert aggregation with regret bounds.Votes: 0GitHub stars: 3
- Disorder Promoted StabilityDisorder promotes network stability; non-Hermitian J theory.Votes: 0GitHub stars: 3
- Elise Scaffold Dendritic Sequence LearningScaffold+dendritic local plasticity learns long sequences.Votes: 0GitHub stars: 3