corpus.blog
41554 blogs · [ { "id": "01a08784-8f7a-7330-9c15-d510496dc9f8", "title": "Inverse reinforcement learning", "url": "https://hugocisneros.com/notes/inverse_reinforcement_learning/", "published_at": "2026-04-26T15:23:00+00:00" }, { "id": "01a08784-8f7a-7330-9c15-d510496f5b74", "title": "Notes on: Self-Distillation Enables Continual Learning by Idan Shenfeld, Mehul Damani, Jonas Hübotter, Pulkit Agrawal (2026)", "url": "https://hugocisneros.com/notes/shenfeldselfdistillationcontinual2026/", "published_at": "2026-04-26T15:23:00+00:00" }, { "id": "01a08784-8f7a-7330-9c15-d5104a43342d", "title": "Off-policy distillation", "url": "https://hugocisneros.com/notes/off_policy_distillation/", "published_at": "2026-04-26T15:21:00+00:00" }, { "id": "01a08784-8f7a-7330-9c15-d5104a804864", "title": "On-policy distillation", "url": "https://hugocisneros.com/notes/on_policy_distillation/", "published_at": "2026-04-26T15:18:00+00:00" }, { "id": "01a08784-8f7a-7330-9c15-d5104aac7e4b", "title": "Notes on: Reinforcement Learning via Self-Distillation by Hübotter, J., Lübeck, F., Behric, L., Baumann, A., Bagatella, M., Marta, D., Hakimi, I., Shenfeld, I., Kleine Buening, T., Guestrin, C. & Krause, A. (2026)", "url": "https://hugocisneros.com/notes/hubotterreinforcementlearningselfdistillation2026/", "published_at": "2026-04-26T15:14:00+00:00" }, { "id": "01a08784-8f7a-7330-9c15-d5104b85b26e", "title": "Notes on: Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding by Christopher Clark, Jieyu Zhang, Zixian Ma, Jae Sung Park, Mohammadreza Salehi, Rohun Tripathi, Sangho Lee, Zhongzheng Ren, Chris Dongjoo Kim, Yinuo Yang, Vincent Shao, Yue Yang, Weikai Huang, Ziqi Gao, Taira Anderson, Jianrui Zhang, Jitesh Jain, George Stoica, Winson Han, Ali Farhadi, Ranjay Krishna (2026)", "url": "https://hugocisneros.com/notes/clarkmolmo2video2026/", "published_at": "2026-04-26T11:55:00+00:00" }, { "id": "01a08784-8f7a-7330-9c15-d5104bf91c26", "title": "Vision Language Models", "url": "https://hugocisneros.com/notes/vision_language_models/", "published_at": "2026-04-26T11:55:00+00:00" }, { "id": "01a08784-8f7a-7330-9c15-d5104cbb085c", "title": "Notes on: DeepEyes: Incentivizing \"Thinking with Images\" via Reinforcement Learning by Ziwei Zheng, Michael Yang, Jack Hong, Chenxiao Zhao, Guohai Xu, Le Yang, Chao Shen, Xing Yu (2025)", "url": "https://hugocisneros.com/notes/zhengdeepeyesincentivizing2025/", "published_at": "2026-04-26T11:54:00+00:00" }, { "id": "01a08784-8f7a-7330-9c15-d5104d3a9835", "title": "Notes on: GeoEyes: On-Demand Visual Focusing for Evidence-Grounded Understanding of Ultra-High-Resolution Remote Sensing Imagery by Fengxiang Wang, Mingshuo Chen, Yueying Li, Yajie Yang, Yifan Zhang, Long Lan, Xue Yang, Hongda Sun, Yulin Wang, Di Wang, Jun Song, Jing Zhang, Bo Du (2026)", "url": "https://hugocisneros.com/notes/wanggeoeyesondemand2026/", "published_at": "2026-04-26T11:53:00+00:00" }, { "id": "01a08784-8f7a-7330-9c15-d5104db11ddb", "title": "Notes on: LoRA Learns Less and Forgets Less by Dan Biderman, Jacob Portes, Jose Javier Gonzalez Ortiz, Mansheej Paul, Philip Greengard, Connor Jennings, Daniel King, Sam Havens, Vitaliy Chiley, Jonathan Frankle, Cody Blakeney, John P. Cunningham (2024)", "url": "https://hugocisneros.com/notes/bidermanloralearns2024/", "published_at": "2026-04-26T11:53:00+00:00" }, { "id": "01a08784-8f7a-7330-9c15-d5104e45cdcd", "title": "Supervised Fine Tuning", "url": "https://hugocisneros.com/notes/supervised_fine_tuning/", "published_at": "2026-04-26T11:53:00+00:00" }, { "id": "01a08784-8f7a-7330-9c15-d5104ebd92c5", "title": "Notes on: Residual Matrix Transformers: Scaling the Size of the Residual Stream by Brian Mak, Jeffrey Flanigan (2025)", "url": "https://hugocisneros.com/notes/makresidualmatrixtransformers2025/", "published_at": "2026-04-26T11:45:00+00:00" }, { "id": "01a08784-8f7a-7330-9c15-d5104f7f61c7", "title": "Knowledge Base Index", "url": "https://hugocisneros.com/notes/notes/", "published_at": "2026-04-25T22:00:00+00:00" }, { "id": "01a08784-8f7a-7330-9c15-d5104fbbb9a6", "title": "Open-vocabulary detection", "url": "https://hugocisneros.com/notes/open_vocabulary_detection/", "published_at": "2026-04-19T12:06:00+00:00" }, { "id": "01a08784-8f7a-7330-9c15-d5104fe844d8", "title": "Image segmentation", "url": "https://hugocisneros.com/notes/image_segmentation/", "published_at": "2026-04-19T12:05:00+00:00" }, { "id": "01a08784-8f7a-7330-9c15-d5105079eaa8", "title": "Reward hacking", "url": "https://hugocisneros.com/notes/reward_hacking/", "published_at": "2026-04-19T12:04:00+00:00" }, { "id": "01a08784-8f7a-7330-9c15-d51051638b00", "title": "Reward shaping", "url": "https://hugocisneros.com/notes/reward_shaping/", "published_at": "2026-04-19T12:04:00+00:00" }, { "id": "01a08784-8f7a-7330-9c15-d51051ac0738", "title": "Chain-of-Thought reasoning", "url": "https://hugocisneros.com/notes/chain_of_thought_reasoning/", "published_at": "2026-04-19T12:03:00+00:00" }, { "id": "01a08784-8f7a-7330-9c15-d510524a539e", "title": "Geospatial AI", "url": "https://hugocisneros.com/notes/geospatial_ai/", "published_at": "2026-04-19T12:00:00+00:00" }, { "id": "01a08784-8f7a-7330-9c15-d51052873ea8", "title": "Visual question answering", "url": "https://hugocisneros.com/notes/visual_question_answering/", "published_at": "2026-04-19T11:55:00+00:00" }, { "id": "01a08784-8f7a-7330-9c15-d51052fd366f", "title": "Coding agent", "url": "https://hugocisneros.com/notes/coding_agent/", "published_at": "2026-04-19T11:54:00+00:00" }, { "id": "01a08784-8f7a-7330-9c15-d510534653cf", "title": "Notes on: Meta-Harness: End-to-End Optimization of Model Harnesses by Lee, Y., Nair, R., Zhang, Q., Lee, K., Khattab, O., & Finn, C. (2026)", "url": "https://hugocisneros.com/notes/leemetaharnessendtoend2026/", "published_at": "2026-04-19T11:53:00+00:00" }, { "id": "01a08784-8f7a-7330-9c15-d5105400febc", "title": "Agentic reinforcement learning", "url": "https://hugocisneros.com/notes/agentic_reinforcement_learning/", "published_at": "2026-04-19T11:46:00+00:00" }, { "id": "01a08784-8f7a-7330-9c15-d510544650e7", "title": "Multimodal reasoning", "url": "https://hugocisneros.com/notes/multimodal_reasoning/", "published_at": "2026-04-19T11:42:00+00:00" }, { "id": "01a08784-8f7a-7330-9c15-d510546baf9b", "title": "Foundation models", "url": "https://hugocisneros.com/notes/foundation_models/", "published_at": "2026-04-19T11:40:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9aad31418", "title": "Switch transformer", "url": "https://hugocisneros.com/notes/switch_transformer/", "published_at": "2026-04-19T11:39:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9aaeab792", "title": "Notes on: Perception Encoder: The best visual embeddings are not at the output of the network by Daniel Bolya, Po-Yao Huang, Peize Sun, Jang Hyun Cho, Andrea Madotto, Chen Wei, Tengyu Ma, Jiale Zhi, Jathushan Rajasegaran, Hanoona Rasheed, Junke Wang, Marco Monteiro, Hu Xu, Shiyu Dong, Nikhila Ravi, Daniel Li, Piotr Dollár, Christoph Feichtenhofer (2025)", "url": "https://hugocisneros.com/notes/bolyaperceptionencoder2025/", "published_at": "2026-04-19T09:50:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9ab14a061", "title": "Notes on: V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning by Lorenzo Mur-Labadia, Matthew Muckley, Amir Bar, Mido Assran, Koustuv Sinha, Mike Rabbat, Yann LeCun, Nicolas Ballas, Adrien Bardes (2026)", "url": "https://hugocisneros.com/notes/murlabadiavjepa2026/", "published_at": "2026-04-19T09:49:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9ab999b8e", "title": "Notes on: End-to-End Object Detection with Transformers by Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, Sergey Zagoruyko (2020)", "url": "https://hugocisneros.com/notes/carionendtoendobject2020/", "published_at": "2026-04-19T09:28:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9ac374236", "title": "Notes on: SAM 3: Segment Anything with Concepts by Nicolas Carion, Laura Gustafson, Yuan-Ting Hu, Shoubhik Debnath, Ronghang Hu, Didac Suris, Chaitanya Ryali, Kalyan Vasudev Alwala, Haitham Khedr, Andrew Huang, Jie Lei, Tengyu Ma, Baishan Guo, Arpit Kalla, Markus Marks, Joseph Greer, Meng Wang, Peize Sun, Roman Rädle, Triantafyllos Afouras, Effrosyni Mavroudi, Katherine Xu, Tsung-Han Wu, Yu Zhou, Liliane Momeni, Rishi Hazra, Shuangrui Ding, Sagar Vaze, Francois Porcher, Feng Li, Siyuan Li, Aishw", "url": "https://hugocisneros.com/notes/carionsamsegmentanything2025/", "published_at": "2026-04-19T09:28:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9acb519be", "title": "Attention", "url": "https://hugocisneros.com/notes/attention/", "published_at": "2026-04-12T08:44:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9accd9313", "title": "Diffusion language models", "url": "https://hugocisneros.com/notes/diffusion_language_models/", "published_at": "2026-04-12T08:33:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9ad2c559b", "title": "Notes on: DFlash: Block Diffusion for Flash Speculative Decoding by Jian Chen, Yesheng Liang, Zhijian Liu (2026)", "url": "https://hugocisneros.com/notes/chendflashblockdiffusion2026/", "published_at": "2026-04-12T08:33:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9ad7508a4", "title": "Generative modelling", "url": "https://hugocisneros.com/notes/generative_modelling/", "published_at": "2026-04-12T08:31:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9ae383fb6", "title": "Speculative Decoding", "url": "https://hugocisneros.com/notes/speculative_decoding/", "published_at": "2026-04-12T08:31:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9ae7a45e4", "title": "Grounding", "url": "https://hugocisneros.com/notes/grounding/", "published_at": "2026-04-09T15:40:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9af3d9e5f", "title": "Model Context Protocol", "url": "https://hugocisneros.com/notes/model_context_protocol/", "published_at": "2026-04-09T15:28:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9b031dc0b", "title": "3-SAT", "url": "https://hugocisneros.com/notes/3_sat/", "published_at": "2026-04-09T12:48:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9b0fec625", "title": "Token-level credit assignment in reasoning traces", "url": "https://hugocisneros.com/notes/token_credit_assignment/", "published_at": "2026-04-09T12:48:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9b1f5b0a2", "title": "GRPO", "url": "https://hugocisneros.com/notes/grpo/", "published_at": "2026-04-09T12:37:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9b24200b0", "title": "PPO", "url": "https://hugocisneros.com/notes/ppo/", "published_at": "2026-04-09T12:37:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9b26d81d9", "title": "Notes on: MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention by MiniMax (2025)", "url": "https://hugocisneros.com/notes/minimaxscalingtesttimecompute2025/", "published_at": "2026-04-09T12:21:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9b2806236", "title": "Notes on: Attention Residuals by Kimi Team, Guangyu Chen, Yu Zhang, Jianlin Su et al. (2026)", "url": "https://hugocisneros.com/notes/chenattentionresiduals2026/", "published_at": "2026-04-08T16:16:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9b29ba49f", "title": "Linear Attention", "url": "https://hugocisneros.com/notes/linear_attention/", "published_at": "2026-04-08T16:14:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9b3455ab2", "title": "Notes on: Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention by Katharopoulos, A., Vyas, A., Pappas, N., & Fleuret, F. (2020)", "url": "https://hugocisneros.com/notes/katharopoulostransformersarernns2020/", "published_at": "2026-04-08T16:14:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9b3b5a03f", "title": "Mixture of Experts", "url": "https://hugocisneros.com/notes/mixture_of_experts/", "published_at": "2026-04-08T16:11:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9b3e2541c", "title": "Notes on: Embarrassingly Simple Self-Distillation Improves Code Generation by Zhang, R., Bai, R. H., Zheng, H., Jaitly, N., Collobert, R., & Zhang, Y. (2026)", "url": "https://hugocisneros.com/notes/zhangembarrassinglysimpleselfdistillation2026/", "published_at": "2026-04-08T12:10:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9b47112bd", "title": "Test-time compute", "url": "https://hugocisneros.com/notes/test_time_compute/", "published_at": "2026-04-08T11:55:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9b4a4e431", "title": "Reinforcement learning with verifiable rewards", "url": "https://hugocisneros.com/notes/reinforcement_learning_with_verifiable_rewards/", "published_at": "2026-04-08T11:53:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9b50538d1", "title": "Self-training", "url": "https://hugocisneros.com/notes/self_training/", "published_at": "2026-04-08T11:47:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9b5b0507a", "title": "Synthetic training data", "url": "https://hugocisneros.com/notes/synthetic_training_data/", "published_at": "2026-04-07T17:26:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9b62900e0", "title": "Text embeddings", "url": "https://hugocisneros.com/notes/text_embeddings/", "published_at": "2026-04-07T17:23:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9b6d88976", "title": "In-context learning", "url": "https://hugocisneros.com/notes/in_context_learning/", "published_at": "2026-04-07T17:21:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9b72b16b1", "title": "Scaling laws", "url": "https://hugocisneros.com/notes/scaling_laws/", "published_at": "2026-04-07T17:20:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9b77e0871", "title": "Contrastive learning", "url": "https://hugocisneros.com/notes/contrastive_learning/", "published_at": "2026-04-07T17:17:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9b8724468", "title": "Tool calling", "url": "https://hugocisneros.com/notes/tool_calling/", "published_at": "2026-04-07T17:12:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9b95fb034", "title": "Semantic similarity", "url": "https://hugocisneros.com/notes/semantic_similarity/", "published_at": "2026-04-07T14:02:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9b97b0eb4", "title": "Self-supervised learning", "url": "https://hugocisneros.com/notes/self_supervised_learning/", "published_at": "2026-04-07T14:00:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9b9cc00a4", "title": "Spatial Reasoning", "url": "https://hugocisneros.com/notes/spatial_reasoning/", "published_at": "2026-04-07T13:58:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9ba75c0b3", "title": "Notes on: CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery by Ao Qu, Han Zheng, Zijian Zhou, Yihao Yan, Yihong Tang, Shao Yong Ong, Fenglu Hong, Kaichen Zhou, Chonghe Jiang, Minwei Kong, Jiacheng Zhu, Xuan Jiang, Sirui Li, Cathy Wu, Bryan Kian Hsiang Low, Jinhua Zhao, Paul Pu Liang (2026)", "url": "https://hugocisneros.com/notes/qucoralautonomousmultiagent2026/", "published_at": "2026-04-07T09:15:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9baae39fb", "title": "Multi-agent collaboration", "url": "https://hugocisneros.com/notes/multi_agent_collaboration/", "published_at": "2026-04-07T09:13:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9bb2c7c9b", "title": "Agent", "url": "https://hugocisneros.com/notes/agent/", "published_at": "2026-04-07T09:12:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9bbab9864", "title": "Notes on: Training Language Models via Neural Cellular Automata by Dan Lee, Seungwook Han, Akarsh Kumar, Pulkit Agrawal (2026)", "url": "https://hugocisneros.com/notes/leetraininglanguagemodels2026/", "published_at": "2026-04-07T09:11:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9bc7298e9", "title": "Notes on: Gecko: Versatile Text Embeddings Distilled from Large Language Models by Jinhyuk Lee, et al. (2024)", "url": "https://hugocisneros.com/notes/leegeckoversatiletext2024/", "published_at": "2026-04-07T08:20:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9bc8720ac", "title": "Knowledge distillation", "url": "https://hugocisneros.com/notes/knowledge_distillation/", "published_at": "2026-04-07T08:18:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9bd856f56", "title": "Complexity metrics", "url": "https://hugocisneros.com/notes/complexity_metrics/", "published_at": "2026-04-05T15:07:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9bdae1c86", "title": "LLM", "url": "https://hugocisneros.com/notes/llm/", "published_at": "2026-04-05T15:07:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9be4adc84", "title": "Retrieval augmented generation", "url": "https://hugocisneros.com/notes/retrieval_augmented_generation/", "published_at": "2026-04-05T12:42:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9bea40428", "title": "Notes on: Large Language Models as Optimizers by Yang, C., Wang, X., Lu, Y., Liu, H., Le, Q. V., Zhou, D., & Chen, X. (2023)", "url": "https://hugocisneros.com/notes/yanglargelanguagemodels2023/", "published_at": "2026-04-05T10:00:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9bf794a40", "title": "LLM Harness", "url": "https://hugocisneros.com/notes/llm_harness/", "published_at": "2026-04-04T21:40:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9c055ea2b", "title": "Q: What do the notes say about geospatial analysis?", "url": "https://hugocisneros.com/notes/2026-04-04-geospatial-analysis/", "published_at": "2026-04-03T22:00:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9c0d86873", "title": "Take your Adblocker to go", "url": "https://hugocisneros.com/blog/take-your-adblocker-to-go/", "published_at": "2026-01-02T08:40:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9c180603e", "title": "Parliament", "url": "https://hugocisneros.com/projects/parliament/", "published_at": "2025-09-30T22:00:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9c2213c83", "title": "Bring Your Laptop", "url": "https://hugocisneros.com/projects/bring_your_laptop/", "published_at": "2025-07-31T22:00:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9c2f75f04", "title": "EasyRoute", "url": "https://hugocisneros.com/projects/easyroute/", "published_at": "2025-05-31T22:00:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9c3aa04dd", "title": "HatchForge", "url": "https://hugocisneros.com/projects/svg_sdf_renderer/", "published_at": "2025-03-31T22:00:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9c3deabe3", "title": "Optimizing Geospatial Workflows: Practical PostGIS Tricks", "url": "https://hugocisneros.com/blog/optimizing-geospatial-workflows-practical-postgis-tricks/", "published_at": "2025-03-25T08:00:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9c4a00297", "title": "Giffen goods", "url": "https://hugocisneros.com/notes/giffen_goods/", "published_at": "2024-10-29T07:26:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9c573dd29", "title": "Anatomy of a MapServer: How to Leverage and Visualize Your Geographical Data", "url": "https://hugocisneros.com/blog/anatomy-of-a-mapserver-how-to-leverage-and-visualize-your-geographical-data/", "published_at": "2024-10-14T08:00:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9c607540a", "title": "Automation", "url": "https://hugocisneros.com/notes/automation/", "published_at": "2023-05-10T18:45:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9c629ca23", "title": "Quantization", "url": "https://hugocisneros.com/notes/quantization/", "published_at": "2023-05-01T06:18:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9c649a910", "title": "Universal basic income", "url": "https://hugocisneros.com/notes/universal_basic_income/", "published_at": "2023-04-10T20:31:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9c6a4bea6", "title": "Dividing a Square into 7 Similar Rectangles", "url": "https://hugocisneros.com/bookmarks/dividingasquareinto7similarrectangles/", "published_at": "2023-03-11T12:48:07+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9c79d30be", "title": "Circular random() for rarest traits", "url": "https://hugocisneros.com/bookmarks/circularrandomforraresttraits/", "published_at": "2023-03-11T12:23:27+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9c85e48e0", "title": "Getting Past “Ampersand-Driven Development” in Rust - Blog", "url": "https://hugocisneros.com/bookmarks/gettingpastampersanddrivendevelopmentinrustblog/", "published_at": "2023-03-09T15:57:52+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9c8f100d0", "title": "Snap.js", "url": "https://hugocisneros.com/bookmarks/snapjs/", "published_at": "2023-03-08T11:05:45+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9c9eda1d7", "title": "Online gradient descent written in SQL", "url": "https://hugocisneros.com/bookmarks/onlinegradientdescentwritteninsql/", "published_at": "2023-03-07T17:24:27+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9ca4ece55", "title": "Why SAT Is Hard", "url": "https://hugocisneros.com/bookmarks/whysatishard/", "published_at": "2023-02-26T16:44:05+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9cb082075", "title": "Should GPT exist?", "url": "https://hugocisneros.com/bookmarks/shouldgptexist/", "published_at": "2023-02-23T15:16:27+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9cbf3fd82", "title": "Gopher", "url": "https://hugocisneros.com/notes/gopher/", "published_at": "2023-02-22T12:28:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9ccd0be86", "title": "Online privacy", "url": "https://hugocisneros.com/notes/online_privacy/", "published_at": "2023-02-22T12:28:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9cd99ab2b", "title": "Sparrow", "url": "https://hugocisneros.com/notes/sparrow/", "published_at": "2023-02-22T12:28:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9ce8aeb65", "title": "Surveillance", "url": "https://hugocisneros.com/notes/surveillance/", "published_at": "2023-02-22T12:28:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9cf8961bb", "title": "what is the randomart image for?", "url": "https://hugocisneros.com/bookmarks/whatistherandomartimagefor/", "published_at": "2023-02-21T16:53:13+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9cfc8a198", "title": "The dangers behind image resizing", "url": "https://hugocisneros.com/bookmarks/thedangersbehindimageresizing/", "published_at": "2023-02-21T15:56:13+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9d0178bd5", "title": "Ssh", "url": "https://hugocisneros.com/notes/ssh/", "published_at": "2023-02-21T15:52:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9d029282e", "title": "Privacy", "url": "https://hugocisneros.com/notes/privacy/", "published_at": "2023-02-21T14:48:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9d0af76c6", "title": "LayerNorm", "url": "https://hugocisneros.com/notes/layernorm/", "published_at": "2023-02-21T14:44:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9d1ae4db1", "title": "Batch normalization", "url": "https://hugocisneros.com/notes/batch_normalization/", "published_at": "2023-02-21T13:47:00+00:00" }, { "id": "01a08784-8f7b-710f-99a1-03d9d21cc80b", "title": "ChatGPT", "url": "https://hugocisneros.com/notes/chatgpt/", "published_at": "2023-02-13T12:26:00+00:00" } ] posts Claim your blog
Back to hugocisneros.com
Blog · corpus.blog/blogs/hugocisneros.com/posts

hugocisneros.com

hugocisneros.com

2026

Inverse reinforcement learningoriginal ↗
26 Apr 2026
Notes on: Self-Distillation Enables Continual Learning by Idan Shenfeld, Mehul Damani, Jonas Hübotter, Pulkit Agrawal (2026)original ↗
26 Apr 2026
Off-policy distillationoriginal ↗
26 Apr 2026
On-policy distillationoriginal ↗
26 Apr 2026
Notes on: Reinforcement Learning via Self-Distillation by Hübotter, J., Lübeck, F., Behric, L., Baumann, A., Bagatella, M., Marta, D., Hakimi, I., Shenfeld, I., Kleine Buening, T., Guestrin, C. & Krause, A. (2026)original ↗
26 Apr 2026
Notes on: Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding by Christopher Clark, Jieyu Zhang, Zixian Ma, Jae Sung Park, Mohammadreza Salehi, Rohun Tripathi, Sangho Lee, Zhongzheng Ren, Chris Dongjoo Kim, Yinuo Yang, Vincent Shao, Yue Yang, Weikai Huang, Ziqi Gao, Taira Anderson, Jianrui Zhang, Jitesh Jain, George Stoica, Winson Han, Ali Farhadi, Ranjay Krishna (2026)original ↗
26 Apr 2026
Vision Language Modelsoriginal ↗
26 Apr 2026
Notes on: DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning by Ziwei Zheng, Michael Yang, Jack Hong, Chenxiao Zhao, Guohai Xu, Le Yang, Chao Shen, Xing Yu (2025)original ↗
26 Apr 2026
Notes on: GeoEyes: On-Demand Visual Focusing for Evidence-Grounded Understanding of Ultra-High-Resolution Remote Sensing Imagery by Fengxiang Wang, Mingshuo Chen, Yueying Li, Yajie Yang, Yifan Zhang, Long Lan, Xue Yang, Hongda Sun, Yulin Wang, Di Wang, Jun Song, Jing Zhang, Bo Du (2026)original ↗
26 Apr 2026
Notes on: LoRA Learns Less and Forgets Less by Dan Biderman, Jacob Portes, Jose Javier Gonzalez Ortiz, Mansheej Paul, Philip Greengard, Connor Jennings, Daniel King, Sam Havens, Vitaliy Chiley, Jonathan Frankle, Cody Blakeney, John P. Cunningham (2024)original ↗
26 Apr 2026
Supervised Fine Tuningoriginal ↗
26 Apr 2026
Notes on: Residual Matrix Transformers: Scaling the Size of the Residual Stream by Brian Mak, Jeffrey Flanigan (2025)original ↗
26 Apr 2026
Knowledge Base Indexoriginal ↗
25 Apr 2026
Open-vocabulary detectionoriginal ↗
19 Apr 2026
Image segmentationoriginal ↗
19 Apr 2026
Reward hackingoriginal ↗
19 Apr 2026
Reward shapingoriginal ↗
19 Apr 2026
Chain-of-Thought reasoningoriginal ↗
19 Apr 2026
Geospatial AIoriginal ↗
19 Apr 2026
Visual question answeringoriginal ↗
19 Apr 2026
Coding agentoriginal ↗
19 Apr 2026
Notes on: Meta-Harness: End-to-End Optimization of Model Harnesses by Lee, Y., Nair, R., Zhang, Q., Lee, K., Khattab, O., & Finn, C. (2026)original ↗
19 Apr 2026
Agentic reinforcement learningoriginal ↗
19 Apr 2026
Multimodal reasoningoriginal ↗
19 Apr 2026
Foundation modelsoriginal ↗
19 Apr 2026
Switch transformeroriginal ↗
19 Apr 2026
Notes on: Perception Encoder: The best visual embeddings are not at the output of the network by Daniel Bolya, Po-Yao Huang, Peize Sun, Jang Hyun Cho, Andrea Madotto, Chen Wei, Tengyu Ma, Jiale Zhi, Jathushan Rajasegaran, Hanoona Rasheed, Junke Wang, Marco Monteiro, Hu Xu, Shiyu Dong, Nikhila Ravi, Daniel Li, Piotr Dollár, Christoph Feichtenhofer (2025)original ↗
19 Apr 2026
Notes on: V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning by Lorenzo Mur-Labadia, Matthew Muckley, Amir Bar, Mido Assran, Koustuv Sinha, Mike Rabbat, Yann LeCun, Nicolas Ballas, Adrien Bardes (2026)original ↗
19 Apr 2026
Notes on: End-to-End Object Detection with Transformers by Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, Sergey Zagoruyko (2020)original ↗
19 Apr 2026
Notes on: SAM 3: Segment Anything with Concepts by Nicolas Carion, Laura Gustafson, Yuan-Ting Hu, Shoubhik Debnath, Ronghang Hu, Didac Suris, Chaitanya Ryali, Kalyan Vasudev Alwala, Haitham Khedr, Andrew Huang, Jie Lei, Tengyu Ma, Baishan Guo, Arpit Kalla, Markus Marks, Joseph Greer, Meng Wang, Peize Sun, Roman Rädle, Triantafyllos Afouras, Effrosyni Mavroudi, Katherine Xu, Tsung-Han Wu, Yu Zhou, Liliane Momeni, Rishi Hazra, Shuangrui Ding, Sagar Vaze, Francois Porcher, Feng Li, Siyuan Li, Aishworiginal ↗
19 Apr 2026
Attentionoriginal ↗
12 Apr 2026
Diffusion language modelsoriginal ↗
12 Apr 2026
Notes on: DFlash: Block Diffusion for Flash Speculative Decoding by Jian Chen, Yesheng Liang, Zhijian Liu (2026)original ↗
12 Apr 2026
Generative modellingoriginal ↗
12 Apr 2026
Speculative Decodingoriginal ↗
12 Apr 2026
Groundingoriginal ↗
9 Apr 2026
Model Context Protocoloriginal ↗
9 Apr 2026
3-SAToriginal ↗
9 Apr 2026
Token-level credit assignment in reasoning tracesoriginal ↗
9 Apr 2026
GRPOoriginal ↗
9 Apr 2026
PPOoriginal ↗
9 Apr 2026
Notes on: MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention by MiniMax (2025)original ↗
9 Apr 2026
Notes on: Attention Residuals by Kimi Team, Guangyu Chen, Yu Zhang, Jianlin Su et al. (2026)original ↗
8 Apr 2026
Linear Attentionoriginal ↗
8 Apr 2026
Notes on: Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention by Katharopoulos, A., Vyas, A., Pappas, N., & Fleuret, F. (2020)original ↗
8 Apr 2026
Mixture of Expertsoriginal ↗
8 Apr 2026
Notes on: Embarrassingly Simple Self-Distillation Improves Code Generation by Zhang, R., Bai, R. H., Zheng, H., Jaitly, N., Collobert, R., & Zhang, Y. (2026)original ↗
8 Apr 2026
Test-time computeoriginal ↗
8 Apr 2026
Reinforcement learning with verifiable rewardsoriginal ↗
8 Apr 2026
Self-trainingoriginal ↗
8 Apr 2026
Synthetic training dataoriginal ↗
7 Apr 2026
Text embeddingsoriginal ↗
7 Apr 2026
In-context learningoriginal ↗
7 Apr 2026
Scaling lawsoriginal ↗
7 Apr 2026
Contrastive learningoriginal ↗
7 Apr 2026
Tool callingoriginal ↗
7 Apr 2026
Semantic similarityoriginal ↗
7 Apr 2026
Self-supervised learningoriginal ↗
7 Apr 2026
Spatial Reasoningoriginal ↗
7 Apr 2026
Notes on: CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery by Ao Qu, Han Zheng, Zijian Zhou, Yihao Yan, Yihong Tang, Shao Yong Ong, Fenglu Hong, Kaichen Zhou, Chonghe Jiang, Minwei Kong, Jiacheng Zhu, Xuan Jiang, Sirui Li, Cathy Wu, Bryan Kian Hsiang Low, Jinhua Zhao, Paul Pu Liang (2026)original ↗
7 Apr 2026
Multi-agent collaborationoriginal ↗
7 Apr 2026
Agentoriginal ↗
7 Apr 2026
Notes on: Training Language Models via Neural Cellular Automata by Dan Lee, Seungwook Han, Akarsh Kumar, Pulkit Agrawal (2026)original ↗
7 Apr 2026
Notes on: Gecko: Versatile Text Embeddings Distilled from Large Language Models by Jinhyuk Lee, et al. (2024)original ↗
7 Apr 2026
Knowledge distillationoriginal ↗
7 Apr 2026
Complexity metricsoriginal ↗
5 Apr 2026
LLMoriginal ↗
5 Apr 2026
Retrieval augmented generationoriginal ↗
5 Apr 2026
Notes on: Large Language Models as Optimizers by Yang, C., Wang, X., Lu, Y., Liu, H., Le, Q. V., Zhou, D., & Chen, X. (2023)original ↗
5 Apr 2026
LLM Harnessoriginal ↗
4 Apr 2026
Q: What do the notes say about geospatial analysis?original ↗
3 Apr 2026
Take your Adblocker to gooriginal ↗
2 Jan 2026

2025

Parliamentoriginal ↗
30 Sept 2025
Bring Your Laptoporiginal ↗
31 Jul 2025
EasyRouteoriginal ↗
31 May 2025
HatchForgeoriginal ↗
31 Mar 2025
Optimizing Geospatial Workflows: Practical PostGIS Tricksoriginal ↗
25 Mar 2025

2024

Giffen goodsoriginal ↗
29 Oct 2024
Anatomy of a MapServer: How to Leverage and Visualize Your Geographical Dataoriginal ↗
14 Oct 2024

2023

Automationoriginal ↗
10 May 2023
Quantizationoriginal ↗
1 May 2023
Universal basic incomeoriginal ↗
10 Apr 2023
Dividing a Square into 7 Similar Rectanglesoriginal ↗
11 Mar 2023
Circular random() for rarest traitsoriginal ↗
11 Mar 2023
Getting Past “Ampersand-Driven Development” in Rust - Blogoriginal ↗
9 Mar 2023
Snap.jsoriginal ↗
8 Mar 2023
Online gradient descent written in SQLoriginal ↗
7 Mar 2023
Why SAT Is Hardoriginal ↗
26 Feb 2023
Should GPT exist?original ↗
23 Feb 2023
Gopheroriginal ↗
22 Feb 2023
Online privacyoriginal ↗
22 Feb 2023
Sparroworiginal ↗
22 Feb 2023
Surveillanceoriginal ↗
22 Feb 2023
what is the randomart image for?original ↗
21 Feb 2023
The dangers behind image resizingoriginal ↗
21 Feb 2023
Sshoriginal ↗
21 Feb 2023
Privacyoriginal ↗
21 Feb 2023
LayerNormoriginal ↗
21 Feb 2023
Batch normalizationoriginal ↗
21 Feb 2023
ChatGPToriginal ↗
13 Feb 2023
Next