{"total":415,"papers":[{"id":"url:openai.com/index/deep-double-descent","title":"Deep Double Descent (OpenAI)","date":"2020-01-23","section":"Data, training, optimization","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/dbfa3f03c433f18313852b6668892ef9cbe993f6949854e9270622c7cd29b701/","source_url":"https://openai.com/index/deep-double-descent/","text_available":false},{"id":"arxiv:2201.00650","title":"Deep Learning Interviews: Hundreds of fully solved job interview questions from a wide range of key topics in AI","date":"2021-12-30","section":"Books","quality":-0.830344,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/57ebb4ef207ddb9157af986f0e41e1b11146ae2c4f731fed2215b5a9b878d858/","source_url":"https://arxiv.org/abs/2201.00650","text_available":true},{"id":"url:link.springer.com/book/10.1007/978-3-031-45468-4","title":"Deep Learning: Foundations and Concepts (Bishop & Bishop)","date":"2023-11-01","section":"Books","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/17be02ab2f9c237ede36913bc7ed047ccbca2ace21de75ef1e3f99c3f20a5d43/","source_url":"https://link.springer.com/book/10.1007/978-3-031-45468-4","text_available":false},{"id":"arxiv:1712.06567","title":"Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning","date":"2017-12-18","section":"Reinforcement learning","quality":0.395745,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/7191dc11e224beb3dc9abb8cd4efc58c70b79939b61fd56e4416b4b5e1404312/","source_url":"https://arxiv.org/abs/1712.06567","text_available":true},{"id":"arxiv:1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","date":"2015-09-22","section":"Reinforcement learning","quality":0.079916,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a2f115ac879cd2efb9548baf3ecdcb925d2492f03b4b0940720f6e5b0840715b/","source_url":"https://arxiv.org/abs/1509.06461","text_available":true},{"id":"url:github.com/deepseek-ai/deepseek-harness","title":"DeepSeek Harness","date":"2026-08-13","section":"Harness","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/cccbf88a125b812263afd81c837238d85aaaa257f47b6ceed3e8ad0c1e8d5f34/","source_url":"https://github.com/deepseek-ai/deepseek-harness","text_available":false},{"id":"arxiv:2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","date":"2024-02-05","section":"Post-training","quality":0.322538,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/636fb871904bc06f742cfdea069796f9e9665f95bd58dc63260eaff5154ef985/","source_url":"https://arxiv.org/abs/2402.03300","text_available":true},{"id":"arxiv:2212.14024","title":"Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP","date":"2022-12-28","section":"Retrieval, embeddings, benchmarks","quality":0.294453,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/09c4c9bae4e016c9ce276cf84a46742b5b21168f4181202b35c207baf887f71e/","source_url":"https://arxiv.org/abs/2212.14024","text_available":true},{"id":"arxiv:2502.03407","title":"Detecting Strategic Deception Using Linear Probes","date":"2025-02-05","section":"AI safety and consciousness","quality":-0.38798,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/8297cbfb305547d6946bba3998d8921b9578398ed371961d3f0eeadd871e4a49/","source_url":"https://arxiv.org/abs/2502.03407","text_available":true},{"id":"arxiv:2101.02235","title":"Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies","date":"2021-01-06","section":"Retrieval, embeddings, benchmarks","quality":0.058238,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/5b44455f95aaaeefc838faceeaf20aaf1008889ca2e479d95291e245d5365a36/","source_url":"https://arxiv.org/abs/2101.02235","text_available":true},{"id":"url:diamond-wm.github.io","title":"Diffusion for World Modeling: Visual Details Matter in Atari","date":"2024-05-20","section":"Reinforcement learning","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/c30654641002c1bf51b73571279dc615b5e9c5eeb1270df69b46cc0f5b0536ae/","source_url":"https://diamond-wm.github.io/","text_available":false},{"id":"arxiv:2608.00146","title":"DiffusionGemma Technical Report","date":"2026-07-31","section":"LLMs: architectures, context, training","quality":0.286144,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/90a7b084496cd65968627c115230fc3a5e78005a66b5ebb34547e874754bc82e/","source_url":"https://arxiv.org/abs/2608.00146","text_available":true},{"id":"arxiv:2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","date":"2023-04-14","section":"Self-supervised learning and vision","quality":0.201878,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/b15933596df35497024556ae88bfa696f3b0e8372b678194f04f1bfb9f3be553/","source_url":"https://arxiv.org/abs/2304.07193","text_available":true},{"id":"arxiv:2301.06627","title":"Dissociating language and thought in large language models","date":"2023-01-16","section":"Reasoning and the \"physics\" of language models","quality":0.052829,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/3791d7ed420be517ded1ee7ae5558cf6afa948ea5b841a76ec3da8a9134ec565/","source_url":"https://arxiv.org/abs/2301.06627","text_available":true},{"id":"arxiv:2604.08302","title":"DMax: Aggressive Parallel Decoding for dLLMs","date":"2026-04-09","section":"LLMs: architectures, context, training","quality":0.217022,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/22790263bd218aac28626fe3dab2fcd0ed73ceef94aa8a948bef2cb8bc007f7a/","source_url":"https://arxiv.org/abs/2604.08302","text_available":true},{"id":"arxiv:2504.13837","title":"Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?","date":"2025-04-18","section":"Post-training","quality":0.022969,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/b90f70269aeb02311d74ffaadf47e139683424a47118dc18619000ba72174d17/","source_url":"https://arxiv.org/abs/2504.13837","text_available":true},{"id":"arxiv:2601.07055","title":"Dr. Zero: Self-Evolving Search Agents without Training Data","date":"2026-01-11","section":"Agents, open-endedness, AGI","quality":0.057854,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/3baa3e7fc5768b75e4ef3e64c3cc5297fa42ef19b03bc918ef5352e437e1c168/","source_url":"https://arxiv.org/abs/2601.07055","text_available":true},{"id":"arxiv:2609.14858","title":"Dream-RSI: Recursive Self-Improvement through Evolving Worlds","date":"2026-09-14","section":"Agents, open-endedness, AGI","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/4c9ce361df4d9a5f89f3dc0a70a71e795eb66f2c4e3c262f73f04b2d117c8ea1/","source_url":"https://arxiv.org/abs/2609.14858","text_available":true},{"id":"url:tufalabs.ai/research/duck-harness","title":"Duck Harness: Winning Solution for ARC-AGI-3 Milestone 1 (Tufa Labs)","date":"2026-07-01","section":"Harness","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/b15badb28c192b3eaa7ff763e7207141406ee559e3b97db13c0226a4cfded614/","source_url":"https://tufalabs.ai/research/duck-harness/","text_available":false},{"id":"arxiv:1511.06581","title":"Dueling Network Architectures for Deep Reinforcement Learning","date":"2015-11-20","section":"Reinforcement learning","quality":0.086863,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/0a5f0593cf943c782ba38ae2fc386f953f859b9d3fc9722e8f17f67ca9cf50b5/","source_url":"https://arxiv.org/abs/1511.06581","text_available":true},{"id":"arxiv:2604.09168","title":"ELT: Elastic Looped Transformers for Visual Generation","date":"2026-04-10","section":"Self-supervised learning and vision","quality":0.057548,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/63d4e5f1a267b96ed4474fa233f7d3bb2171aae949c0139db37b58b4e45eca47/","source_url":"https://arxiv.org/abs/2604.09168","text_available":true},{"id":"doi:10.1101/2023.04.04.535512","title":"Emergence of belief-like representations through reinforcement learning","date":"2023-01-01","section":"NeuroAI","quality":0.020583,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/9d2435d24ab2dd723deaaf49fce26c2e3d6a9ff8cbcf4ca353c34957e8e7ab84/","source_url":"https://doi.org/10.1101/2023.04.04.535512","text_available":true},{"id":"arxiv:2212.09196","title":"Emergent Analogical Reasoning in Large Language Models","date":"2022-12-19","section":"Reasoning and the \"physics\" of language models","quality":0.120017,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/f74e529a278203e2c144ab7400a343836d9549cf1ae4843c584408448ad3f5a9/","source_url":"https://arxiv.org/abs/2212.09196","text_available":true},{"id":"arxiv:2606.25010","title":"Emergent Capabilities Arise Randomly from Learning Sparse Attention Patterns","date":"2026-06-23","section":"Reasoning and the \"physics\" of language models","quality":0.029627,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/f87db387bad54ae4fbc0589d2a702f78aeb0817b28f20844f6502bc552a89c2f/","source_url":"https://arxiv.org/abs/2606.25010","text_available":true}],"next":"https://vinnik-dmitry07.github.io/favorite-papers/agents/catalog-0-5.html"}