{"total":415,"papers":[{"id":"arxiv:2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","date":"2022-03-21","section":"Reasoning and the \"physics\" of language models","quality":0.242635,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/02a15b098d96a94d463bb470f59a34723abc34e59196f35c539f9796d8f3c3df/","source_url":"https://arxiv.org/abs/2203.11171","text_available":true},{"id":"arxiv:2402.13669","title":"Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning","date":"2024-02-21","section":"Post-training","quality":0.219878,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/1a8d11d48a58f35055e7f88f699cf42688a3698c63bd7026d5789f72a80581bf/","source_url":"https://arxiv.org/abs/2402.13669","text_available":true},{"id":"arxiv:2601.19897","title":"Self-Distillation Enables Continual Learning","date":"2026-01-27","section":"Post-training","quality":-0.07961,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/cc146df3e9ca40c6d111a5264e08710100c1b34bd0eabd9052e8d55d13589efe/","source_url":"https://arxiv.org/abs/2601.19897","text_available":true},{"id":"arxiv:2601.18734","title":"Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models","date":"2026-01-26","section":"Post-training","quality":0.122413,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/8a352e37fa79840a4f35f86ebc39661cfc34fbfc4391cd020a69af158c63485a/","source_url":"https://arxiv.org/abs/2601.18734","text_available":true},{"id":"arxiv:2607.13104","title":"Self-Improvements in Modern Agentic Systems: A Survey","date":"2026-07-14","section":"Agents, open-endedness, AGI","quality":0.274964,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/1452caf7b16ffdb8c2efd5093f46dc4df0f89c3d45a5566cd5fdafd69385b2a7/","source_url":"https://arxiv.org/abs/2607.13104","text_available":true},{"id":"arxiv:2601.21343","title":"Self-Improving Pretraining: using post-trained models to pretrain better models","date":"2026-01-29","section":"Data, training, optimization","quality":-0.306255,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/43ce1b189d6b21d445c0ce6d4d04b4352d268beb4346da43be19982402befde8/","source_url":"https://arxiv.org/abs/2601.21343","text_available":true},{"id":"arxiv:2602.06130","title":"Self-Improving World Modelling with Latent Actions","date":"2026-02-05","section":"Reinforcement learning","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/ac56340e6b81e232b48b92dcf79fe37efc1c00e676413e55c9d119a809eb644b/","source_url":"https://arxiv.org/abs/2602.06130","text_available":true},{"id":"doi:10.21203/rs.3.rs-6688473/v1","title":"Self-Programming AI: Code-Learning Agents for Autonomous Refactoring and Architectural Evolution","date":"2025-05-20","section":"Agents, open-endedness, AGI","quality":-0.709432,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/b0f0fe553367d786c06a0f6bf0a3f26a9e1a514a2e79342a3f899b89b4c59b4f/","source_url":"https://doi.org/10.21203/rs.3.rs-6688473/v1","text_available":true},{"id":"url:selfrag.github.io","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","date":"2023-10-17","section":"Retrieval, embeddings, benchmarks","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/f2a6b92a158b280a6699d4fda0ed474777be788abf9ed561ab7d61da1da57ad1/","source_url":"https://selfrag.github.io/","text_available":false},{"id":"arxiv:2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","date":"2023-03-30","section":"Post-training","quality":0.100328,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/accef2157d87cf33be93cb3a9af246528b0a3742a9e2e700a194956fac8f5cf4/","source_url":"https://arxiv.org/abs/2303.17651","text_available":true},{"id":"arxiv:2301.08243","title":"Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture","date":"2023-01-19","section":"Self-supervised learning and vision","quality":0.189344,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/475bac0a3b29edd42642bbe10d1a41bfb18a3022ac95b9b1a3db9e5d5d0b95fe/","source_url":"https://arxiv.org/abs/2301.08243","text_available":true},{"id":"arxiv:2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","date":"2020-10-03","section":"Data, training, optimization","quality":0.564643,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/e8386ef0dc42519cd17f8346b28a923ab9ad12f8bae3942e216a31c995d97f61/","source_url":"https://arxiv.org/abs/2010.01412","text_available":true},{"id":"url:sakana.ai/shinka-evolve","title":"ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution","date":"2025-09-17","section":"Agents, open-endedness, AGI","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a13eace17f3407cb1634b579b2738f15f1e035897a8f1842305198c6d2bf35e1/","source_url":"https://sakana.ai/shinka-evolve/","text_available":false},{"id":"arxiv:2509.20317","title":"SIM-CoT: Supervised Implicit Chain-of-Thought","date":"2025-09-24","section":"Reasoning and the \"physics\" of language models","quality":0.22707,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/72b64dd6a30c71d99920cafabbb2c909d03febab8991eeaf3c091b16cb7ed348/","source_url":"https://arxiv.org/abs/2509.20317","text_available":true},{"id":"arxiv:2509.13232","title":"Single-stream Policy Optimization","date":"2025-09-16","section":"Post-training","quality":-0.068041,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/d699d0e034b21f3b85c3f70ce4fb95064fbf59685ce752935e6d173dac2b71f3/","source_url":"https://arxiv.org/abs/2509.13232","text_available":true},{"id":"url:situational-awareness.ai","title":"Situational Awareness (Aschenbrenner)","date":"2024-05-29","section":"AI safety and consciousness","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/b8e91c39d818c455f92112f6b1e49e78cc51f470d5af221143e7425ac3e74539/","source_url":"https://situational-awareness.ai","text_available":false},{"id":"arxiv:2606.06574","title":"Skip a Layer or Loop It? Learning Program-of-Layers in LLMs","date":"2026-06-04","section":"LLMs: architectures, context, training","quality":0.192674,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/5abe08b6c82ce9a4010a09d82dbee40f8b4b0f88539bf8911ae36048a97bb917/","source_url":"https://arxiv.org/abs/2606.06574","text_available":true},{"id":"arxiv:2604.08690","title":"Skip-Connected Policy Optimization for Implicit Advantage","date":"2026-04-09","section":"Post-training","quality":0.295907,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/b5ec1244fd1b770994920ee69c200ecc134262e6011043284200eb18eb0d6c87/","source_url":"https://arxiv.org/abs/2604.08690","text_available":true},{"id":"doi:10.1371/journal.pcbi.1010628","title":"Sleep prevents catastrophic forgetting in spiking neural networks by forming joint synaptic weight representations","date":"2020-01-01","section":"NeuroAI","quality":0.107723,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/7e34ad47e15cfd27cb9f93eef1399cfa51820e1382157b2c698c13548efc960a/","source_url":"https://doi.org/10.1371/journal.pcbi.1010628","text_available":true},{"id":"arxiv:2412.13663","title":"Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference","date":"2024-12-18","section":"LLMs: architectures, context, training","quality":0.288117,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/ae6c000a40b751c4486e08fd61f5f7788d8bb57f0838e234e27a5a67f894e923/","source_url":"https://arxiv.org/abs/2412.13663","text_available":true},{"id":"arxiv:1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","date":"2018-01-04","section":"Reinforcement learning","quality":0.455513,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/21e70876ae9603903b2b20dd667a413bdd8b0abf37b9c11e284ea8b5e4124c74/","source_url":"https://arxiv.org/abs/1801.01290","text_available":true},{"id":"arxiv:2511.20347","title":"Soft Adaptive Policy Optimization","date":"2025-11-25","section":"Post-training","quality":0.121839,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/1e74c1ffcb5ea955bca4e6d610e9ba590965617f13bd8868f7f31e7b42fbfbfd/","source_url":"https://arxiv.org/abs/2511.20347","text_available":true},{"id":"arxiv:2605.12466","title":"Solve the Loop: Attractor Models for Language and Reasoning","date":"2026-05-12","section":"Reasoning and the \"physics\" of language models","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/eb46f81cd5718eb6b9256c583cf9dd2e97b793b4d14337e487c16285f96e2b9a/","source_url":"https://arxiv.org/abs/2605.12466","text_available":true},{"id":"arxiv:2305.14342","title":"Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training","date":"2023-05-23","section":"Data, training, optimization","quality":0.046984,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/afd7fbad6232c6801145c611952e4b6b6aacd1ecb692f56874317ace8a328858/","source_url":"https://arxiv.org/abs/2305.14342","text_available":true}],"next":"https://vinnik-dmitry07.github.io/favorite-papers/agents/catalog-0-15.html"}