All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Arxiv 2609 29964v1 World Action Agent Harnessing Vlms For Robot Manip**arXiv ID:** 2609.29964v1 **Authors:** Yehang Zhang, Haojian Huang, Yifan Chang, Jianchong Su, Bohan Zhou, Yingjie Xu, Wosong Chen, Tianhao Zhou, Chenxu Wang, Tianyi Zhang, Yangkai Wei, Wenqian Li, Shiyuan Deng, Yinchuan Li, Ying-Cong Chen, Zexi Li **URL:** http://arxiv.org/abs/2609.29964v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30059v1 Kernelopt Dispatch Aware Agentic Search For Gpu Ke**arXiv ID:** 2609.30059v1 **Authors:** Aheli Poddar, Sanskar Prasad, Arindam Samanta, Subha Chakraborty, Vishal Goyal, Rohit Singh Rathaur **URL:** http://arxiv.org/abs/2609.30059v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30104v1 Mqss Selector Rl Guided Pass Selection For An Mlir**arXiv ID:** 2609.30104v1 **Authors:** Andre Youssefi, Ercüment Kaya, Minh Chung, Jorge Echavarria, Laura B. Schulz, Martin Schulz **URL:** http://arxiv.org/abs/2609.30104v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30177v1 Search Aware Reinforcement Learning For Multi Comp**arXiv ID:** 2609.30177v1 **Authors:** Nayoung Choi, Shengjian Chen, Xiaokai Wei, Wenzheng Zhang, Daiyao Yi, Rachit Pareek, Vincent Su, Michelle Gong, Jinho D. Choi **URL:** http://arxiv.org/abs/2609.30177v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30226v1 Poem Predicting Rl Outcomes From Existing Policies**arXiv ID:** 2609.30226v1 **Authors:** Kimia Hamidieh, Giannis Daras, Antonio Torralba **URL:** http://arxiv.org/abs/2609.30226v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30249v1 Rapid Robot Agentic Programming From Demonstration**arXiv ID:** 2609.30249v1 **Authors:** Yuyao Liu, Jiayuan Mao, David Hsu, Leslie Pack Kaelbling, Tomás Lozano-Pérez **URL:** http://arxiv.org/abs/2609.30249v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30250v1 Agentic Detection Of Online Conspiracies**arXiv ID:** 2609.30250v1 **Authors:** Lior Biton, Oren Tsur **URL:** http://arxiv.org/abs/2609.30250v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Harness Zero Agent As HarnessUse when building agent training pipelines or wanting to remove harness dependencies. Distills specialized agent-harness behaviors into model weights so gains survive with a single fixed harness at deployment.Votes: 0GitHub stars: 3
- Opd Pre Rl DistillationUse when training LLMs with RL on reasoning. Shows on-policy distillation as a preparation stage before RL beats SFT+RL, with divergence/trajectory-source selection rules.Votes: 0GitHub stars: 3
- Arxiv 2609 29233v1 Post Training Leaves Behavioral Shadows On Unrelat**arXiv ID:** 2609.29233v1 **Authors:** Ziyang Zhang, Yubin Jing, Yuanhao Zeng, Yuyao Li, Haofan Wang, Yichen Gong **URL:** http://arxiv.org/abs/2609.29233v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29947v1 Neuro Symbolic Ai For Industrial Configuration**arXiv ID:** 2609.29947v1 **Authors:** Danilo Valerio, Philipp Kogler, Stefan Bischof, Thomas Hubauer, Huzefa Rangwala **URL:** http://arxiv.org/abs/2609.29947v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Auditory Pathway Eeg Foundation ModelAudio-to-EEG foundation model for auditory neuroscience.Votes: 0GitHub stars: 3
- Matched Input Eeg Fm AuditUse when auditing EEG foundation models on BCI transfer.Votes: 0GitHub stars: 3
- Neural Field Bumps Interneuron SubtypesThree-population (E/PV/SST) stochastic neural field model of working-memory bump attractors with interneuron subtypes. Use when analyzing bump stability in neural fields, modeling PV/SST inhibitory subtypes, studying working-memory diffusion/wandering, or applying interface-based Heaviside neural field analysis.Votes: 0GitHub stars: 3
- Neural Surrogate Affective Neuromodulation DesignAI-driven neural surrogate framework for in silico design of cognitive-affective neuromodulation targets. Combines fMRI decoding, deep generative modeling (VDVAE), and constrained latent-space steering with closed-form first-order perturbation solutions. Activation: neuromodulation target design, fMRI latent steering, representational perturbation, affective valence modulation, Good Regulator Theorem, inverse design.Votes: 0GitHub stars: 3
- Nvc Mdd Eeg FnirsUse for resting-state EEG-fNIRS neurovascular coupling metrics in depression. GFP peak-locked HbT correlation analysis.Votes: 0GitHub stars: 3
- Arxiv 2609 29016v1 Evotreenad Genealogy Guided Evolution For Llm Driv**arXiv ID:** 2609.29016v1 **Authors:** Lishan Yu, Derek Jiu, Qizhen Lan, Xiaoqian Jiang **URL:** http://arxiv.org/abs/2609.29016v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29421 Rufus Air An Open Llm Post Training RecipeRufus-Air: An Open LLM Post-Training Recipe (arXiv: 2609.29421)Votes: 0GitHub stars: 3
- Arxiv 2609 29421v1 Rufus Air An Open Llm Post Training Recipe**arXiv ID:** 2609.29421v1 **Authors:** Chia-Yuan Chang, Renyuan Cheng, Rui Feng, Xiaotian Han, Yuan He, Hongye Jin, Linwei Li, Shiyang Li, Fenglin Liu, Xin Liu, Priyanka Nigam, Haoyang Wen, Zhenghao Xu, Zhuocheng Xu, Bing Yin, Qingyu Yin, Chao Zhang, Rongzhi Zhang, Zhihan Zhang, Zixuan Zhang, Zixuan Zhang, Tuo Zhao **URL:** http://arxiv.org/abs/2609.29421v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29460v1 Agricountdino Parameter Efficient Exemplar Guided**arXiv ID:** 2609.29460v1 **Authors:** Shengjie Guo, Xin Li, Borjana Arsova, Hanno Scharr, Silvio Salvi **URL:** http://arxiv.org/abs/2609.29460v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29773v1 Breaking The Environment Wall Evolving Llm Agent E**arXiv ID:** 2609.29773v1 **Authors:** Yukai Wu, Yuanjing Yang, Le Zhou, Shaokun Han, Haoyu Wang, Zirui Tang, Weihuang Zheng, Maxm Pan, Xuanhe Zhou, Fan Wu **URL:** http://arxiv.org/abs/2609.29773v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29775 Prefilling The Reasoning Channel Output Prefix Attacks On Reasoning LlmsPrefilling the Reasoning Channel: Output-Prefix Attacks on Reasoning LLMs (arXiv: 2609.29775)Votes: 0GitHub stars: 3
- Arxiv 2609 29807v1 Cordial Calibrating Ordinal Llm Outputs From Few L**arXiv ID:** 2609.29807v1 **Authors:** Xiangwei Wang, Peng Wang, Saman Halgamuge **URL:** http://arxiv.org/abs/2609.29807v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29845v1 Your Transformer Can Hold Two Thoughts At Once Evi**arXiv ID:** 2609.29845v1 **Authors:** Pavel Tikhonov, Anton Korznikov, Matvey Mikhalchuk, Nikita Dragunov, Temurbek Rahmatullaev, Polina Druzhinina, Anton Razzhigaev, Ivan Oseledets, Elena Tutubalina **URL:** http://arxiv.org/abs/2609.29845v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29935v1 Robust Detection Of Llm Generated Text Under Conta**arXiv ID:** 2609.29935v1 **Authors:** Jiaxun Li, Saptarshi Chakraborty, Ambuj Tewari **URL:** http://arxiv.org/abs/2609.29935v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29948v1 Endoprompt Victim Side Pseudo References For Utili**arXiv ID:** 2609.29948v1 **Authors:** Qingyu Wu, Zeyu Feng, Yongda Yu, Yuzhe Luo, Hua Cheng **URL:** http://arxiv.org/abs/2609.29948v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29960v1 Beyond Average Safety Chance Constrained Llm Fine**arXiv ID:** 2609.29960v1 **Authors:** Taha Entesari, Mahyar Fazlyab **URL:** http://arxiv.org/abs/2609.29960v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30009v1 Automated Regulatory Compliance Question Answering**arXiv ID:** 2609.30009v1 **Authors:** Tobias Deußer, Abhishek Pillai, Aurelio F. Bariviera, Dhananjay Bhardwaj, Lorenz Sparrenberg, David Berghaus, Christian Bauckhage, Rafet Sifa **URL:** http://arxiv.org/abs/2609.30009v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30167v1 Do Audio Language Models Hear And Read Distinctive**arXiv ID:** 2609.30167v1 **Authors:** Yuanhao Chen, Peter Chin **URL:** http://arxiv.org/abs/2609.30167v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30218v1 Minimally Invasive Steering Of Language Models**arXiv ID:** 2609.30218v1 **Authors:** Taha Entesari, Jingyu Zhang, Daniel Khashabi, Mahyar Fazlyab **URL:** http://arxiv.org/abs/2609.30218v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30227v1 To Trust Or Not To Trust Retrieval Augmented Fact**arXiv ID:** 2609.30227v1 **Authors:** Debajyoti Mazumder, Mamta, Abhirama Subramanyam Penamakuri **URL:** http://arxiv.org/abs/2609.30227v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 30266v1 Llm Agents Can Easily Tamper With Their Own Traces**arXiv ID:** 2609.30266v1 **Authors:** Jeremy Qin, David Schmotz, Derck Prinzhorn, Luca Beurer-Kellner, Ameya Prabhu, Maksym Andriushchenko **URL:** http://arxiv.org/abs/2609.30266v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Adaptive Delay Frequency BurstingUse when modeling adaptive delay-coupled oscillators. Quantized detuning frequency bursts.Votes: 0GitHub stars: 3
- Arxiv 2609 29117v1 A Concentration Bound For Two Timescale Actor Crit**arXiv ID:** 2609.29117v1 **Authors:** Prashansa Panda, Shalabh Bhatnagar **URL:** http://arxiv.org/abs/2609.29117v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29142v1 Not Every Token Is Worth Distilling Selective Supe**arXiv ID:** 2609.29142v1 **Authors:** Yibo Zhao, Zixuan Yang, Yunshi Lan, Xiang Li **URL:** http://arxiv.org/abs/2609.29142v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29159v1 Functional Dynamic Mode Decomposition Learning Inf**arXiv ID:** 2609.29159v1 **Authors:** Stefan Klus, Eirini Ioannou **URL:** http://arxiv.org/abs/2609.29159v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29179v1 Towards Deployable Underwater Vessel Classificatio**arXiv ID:** 2609.29179v1 **Authors:** Abishek Soti, Thura Pyae Sone, Naqib Ibnul, Htoo Htet Aung, Henry Zhong, Gregory Cohen, Ying Xu **URL:** http://arxiv.org/abs/2609.29179v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29242v1 Aft Neural Function Approximators For 1d Nonlinear**arXiv ID:** 2609.29242v1 **Authors:** Miriam Goldack, Johann Groß, Malte Krack, Merten Stender **URL:** http://arxiv.org/abs/2609.29242v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29270v1 Learnable Time Frequency Masks For Explaining Time**arXiv ID:** 2609.29270v1 **Authors:** Theresa Dahl Frehr, Francisco Pelayo, Lukas Raad, Alicia García Sanz, Thea Brüsch, Tommy Sonne Alstrøm **URL:** http://arxiv.org/abs/2609.29270v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29281v1 Online Task Adaptation Via Self Organisation**arXiv ID:** 2609.29281v1 **Authors:** Krsto Proroković **URL:** http://arxiv.org/abs/2609.29281v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29283v1 From Text Decisions To Pixels An Study Of Jev Styl**arXiv ID:** 2609.29283v1 **Authors:** Xunlan Zhou, Xianliang Yang, Li Zhao **URL:** http://arxiv.org/abs/2609.29283v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29291v1 Sufficiently Reduced Distributional Regression**arXiv ID:** 2609.29291v1 **Authors:** Alexander Henzi, Tiange Liu, Xinwei Shen **URL:** http://arxiv.org/abs/2609.29291v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29307v1 Beyond Feature Reliability Repeat Informed Multifr**arXiv ID:** 2609.29307v1 **Authors:** Yu Chang, Anzhe Cheng, Jiahao Chen, Heng Ping, Peiyu Zhang, Puquan Pan, Tamoghna Chattopadhyay, Sophia Thomopoulos, Shahin Nazarian, Paul Thompson, Paul Bogdan **URL:** http://arxiv.org/abs/2609.29307v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29317v1 Neuralized Multi Wavelet Decomposition For Time Se**arXiv ID:** 2609.29317v1 **Authors:** Xiaohan Jiang, Jingyuan Wang, Jiahao Ji, Yongyao Wang, Chen Yang, Junjie Wu **URL:** http://arxiv.org/abs/2609.29317v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29327v1 Gcul Ambiguity Identification In Text Emotion Clas**arXiv ID:** 2609.29327v1 **Authors:** Zhongqi Fan, Tianyou Zhang, Fei Chen **URL:** http://arxiv.org/abs/2609.29327v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29330v1 Flowatom Atom Based Evidence Aggregation For Multi**arXiv ID:** 2609.29330v1 **Authors:** Chongru Fan, Wentao Huang, Wei Wang, Zhenquan Ding, Jinqiao Shi, Wei Cai, Zhiyu Hao **URL:** http://arxiv.org/abs/2609.29330v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29381v1 An Auditable Conditional Strategy Framework For Op**arXiv ID:** 2609.29381v1 **Authors:** Daoyun Wang, Zhicheng Huang, Huaiyuan Sun, Jiaqi Xu, Xiaowei Xu, Zhibo Zheng, Zhongxing Bing, Yuxiao Lin, Yicheng Liang, Chao Gao, Bowen Xue, Kai Zhang, Song Xu, Wanpu Yan, Hui Xia, Lin Li, Xiang Yan, Mu Hu, Qianli Ma, Zhiqiang Xue, Xiaofang Liu, Zhihai Han, Nan Zhang, Chuanhao Tang, Tongmei Zhang, Lan Song, Zhaohui Zhu, Xuan Zeng, Shafei Wu, Hui Guan, Lei Deng, Huaxia Yang, Zeliang Lian, Wubin Sun, Yongxin Wang, Xiaohui Shen, Binlin Wang, Tiantian Gu, ...Votes: 0GitHub stars: 3
- Arxiv 2609 29382v1 Decoupled Early Exits For Task Dependent Compute A**arXiv ID:** 2609.29382v1 **Authors:** Riccardo Andrea Izzo, Rimvydas Rubavicius, Gianluca Bardaro, Subramanian Ramamoorthy, Matteo Matteucci, Alessandro Suglia **URL:** http://arxiv.org/abs/2609.29382v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29384v1 Segment Level Risk Discovery In Online Handwriting**arXiv ID:** 2609.29384v1 **Authors:** Changqing Gong, Huafeng Qin, Mounîm A. El-Yacoubi **URL:** http://arxiv.org/abs/2609.29384v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 29386v1 More Plr Multi Output Regression Employed For Part**arXiv ID:** 2609.29386v1 **Authors:** Santo M. A. R. Thies, Juan C. Alfaro, Viktor Bengs **URL:** http://arxiv.org/abs/2609.29386v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3