{"total":415,"papers":[{"id":"url:people.idsia.ch/~juergen/most-cited-neural-nets.html","title":"The most cited neural nets of the 20th century (Schmidhuber)","date":"2021-12-01","section":"LLMs: architectures, context, training","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a07ae08185ac4ab008e5384d2dab1a6ce15cf327b9414fb3ccc3afa8e5ac914a/","source_url":"https://people.idsia.ch/~juergen/most-cited-neural-nets.html","text_available":false},{"id":"url:lilianweng.github.io/lil-log/2018/01/23/the-multi-armed-bandit-problem-and-its-solutions.html","title":"The Multi-Armed Bandit Problem and Its Solutions (Lilian Weng)","date":"2018-01-23","section":"Reinforcement learning","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/24db6186104ad4deb9b8cf44d92e009bc23dc6d50c9467ff1d5b3745e2babd0b/","source_url":"https://lilianweng.github.io/lil-log/2018/01/23/the-multi-armed-bandit-problem-and-its-solutions.html","text_available":false},{"id":"arxiv:2405.07987","title":"The Platonic Representation Hypothesis","date":"2024-05-13","section":"Representation alignment","quality":-0.102668,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/6c7695929f8bbcea43ee98da9cd8f2fe806f2ba292f0b4e3e7fea2b64254afb4/","source_url":"https://arxiv.org/abs/2405.07987","text_available":true},{"id":"arxiv:2205.07802","title":"The Primacy Bias in Deep Reinforcement Learning","date":"2022-05-16","section":"Reinforcement learning","quality":0.266696,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/4e2aca370b941bb16bb6fefc359c420f6d4bde5a956bedaf0a84e6e71febc5bc/","source_url":"https://arxiv.org/abs/2205.07802","text_available":true},{"id":"arxiv:2309.12288","title":"The Reversal Curse: LLMs trained on \"A is B\" fail to learn \"B is A\"","date":"2023-09-21","section":"Reasoning and the \"physics\" of language models","quality":0.172246,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/02782a7d9697d5df8f8ae84424becf682d10e8671ee5e18fd75499de0e0a6694/","source_url":"https://arxiv.org/abs/2309.12288","text_available":true},{"id":"arxiv:2405.15682","title":"The Road Less Scheduled","date":"2024-05-24","section":"Data, training, optimization","quality":0.34565,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/205e2d6291f9c17e2c0e0de4392fe953a5e711d00b6758c8752a76f69af587ff/","source_url":"https://arxiv.org/abs/2405.15682","text_available":true},{"id":"arxiv:2604.17121","title":"The Topological Trouble With Transformers","date":"2026-04-18","section":"LLMs: architectures, context, training","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/7f9d762bbe192e1208f6d7dc289b7e79c23d4bdde0b1b3999ff5fda55b0dcd1a/","source_url":"https://arxiv.org/abs/2604.17121","text_available":true},{"id":"arxiv:2312.13558","title":"The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction","date":"2023-12-21","section":"Reasoning and the \"physics\" of language models","quality":0.025953,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/e6ddb16378e3684d190823b8f271c8c3273b47f7bada2fc2c692b828d40e3384/","source_url":"https://arxiv.org/abs/2312.13558","text_available":true},{"id":"arxiv:2505.15134","title":"The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning","date":"2025-05-21","section":"Reasoning and the \"physics\" of language models","quality":0.233035,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/12b01b403e280a32d41fd991a27fa30f33315e09f0f42a4f43e9bece5ad9c53d/","source_url":"https://arxiv.org/abs/2505.15134","text_available":true},{"id":"arxiv:2606.17056","title":"The Value Axis: Language Models Encode Whether They're on the Right Track","date":"2026-06-15","section":"AI safety and consciousness","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/969b67b08341367524f91a84c873d4fedbe44a95fa24841e03b2f8e111caa9a6/","source_url":"https://arxiv.org/abs/2606.17056","text_available":true},{"id":"url:papers.ssrn.com/sol3/papers.cfm?abstract_id=5239006","title":"The Virtue of Complexity debate (Kelly, Malamud & Zhou versus Nagel)","date":"2025-05-07","section":"Finance","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/05fe455657d140fe8017011fb4555a6e90ec7f9ec5c5af9346b7cac616cb0664/","source_url":"https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5239006","text_available":false},{"id":"arxiv:2606.08720","title":"This is how the Neocortex Learns","date":"2026-06-07","section":"NeuroAI","quality":-0.205336,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/ba3b17d3a842215ec4711276a82a2bde19e633bc2e2b9a36ca4c2b072d468444/","source_url":"https://arxiv.org/abs/2606.08720","text_available":true},{"id":"arxiv:2304.09355","title":"To Compress or Not to Compress- Self-Supervised Learning and Information Theory: A Review","date":"2023-04-19","section":"Self-supervised learning and vision","quality":-0.3926,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/6de01284dffdeadbd92020fc614ff702f27bc9c49215a1658ea3ca8a4a0c36ce/","source_url":"https://arxiv.org/abs/2304.09355","text_available":true},{"id":"arxiv:2607.05609","title":"To Retain or to Adapt? Generalizing Continual Learning","date":"2026-07-06","section":"Post-training","quality":0.077814,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/de2d99f43688431acd6fa456a50322ed0f00aa30d884a6767719f8a73b3b7c45/","source_url":"https://arxiv.org/abs/2607.05609","text_available":true},{"id":"arxiv:2210.08340","title":"Toward Next-Generation Artificial Intelligence: Catalyzing the NeuroAI Revolution","date":"2022-10-15","section":"NeuroAI","quality":-0.054113,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/7e67e1f87352a71473f443d1e0ca0682eb8496db1682a89345b3fd54126e2d35/","source_url":"https://arxiv.org/abs/2210.08340","text_available":true},{"id":"arxiv:2512.18552","title":"Toward Training Superintelligent Software Agents through Self-Play SWE-RL","date":"2025-12-21","section":"Agents, open-endedness, AGI","quality":-0.239509,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/da99b397e01b725186243c38a2dc6072d3a5c81bd8f759e898f04ad09aa0f4b1/","source_url":"https://arxiv.org/abs/2512.18552","text_available":true},{"id":"arxiv:2601.14525","title":"Towards Execution-Grounded Automated AI Research","date":"2026-01-20","section":"Post-training","quality":0.042877,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/895006e818735c9a565dbe99ae31404366eefd6bdc2278612271c65a8493e4a5/","source_url":"https://arxiv.org/abs/2601.14525","text_available":true},{"id":"arxiv:2501.16142","title":"Towards General-Purpose Model-Free Reinforcement Learning","date":"2025-01-27","section":"Reinforcement learning","quality":-0.125258,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/e9034f15fcd4385d96ab7cb30b3a0a011716ad52d13c7b87b84e17fb6e3398db/","source_url":"https://arxiv.org/abs/2501.16142","text_available":true},{"id":"arxiv:2304.01433","title":"TPU v4: An Optically Reconfigurable Supercomputer for Machine Learning with Hardware Support for Embeddings","date":"2023-04-04","section":"Other","quality":0.015316,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/eb01c6279da01afe0e0bb6c4035117303abd37996d3aa65326f44cdccaa5a6fc/","source_url":"https://arxiv.org/abs/2304.01433","text_available":true},{"id":"url:anthropic.com/research/tracing-thoughts-language-model","title":"Tracing thoughts of a language model / Circuit tracing (Anthropic)","date":"2025-03-27","section":"AI safety and consciousness","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/6817b4eca1b10533ef10b19c81e7c61b3877f963641fea2a81c5a46f68a233cf/","source_url":"https://www.anthropic.com/research/tracing-thoughts-language-model","text_available":false},{"id":"url:epochai.org/blog/training-compute-of-frontier-ai-models-grows-by-4-5x-per-year","title":"Training compute of frontier models grows 4–5x/year (Epoch AI)","date":"2024-05-28","section":"Data, training, optimization","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/71c5b7caa35fdfeb366308b4e7bd2f1a3d8fc0296aae4bee1d69762d38512c65/","source_url":"https://epochai.org/blog/training-compute-of-frontier-ai-models-grows-by-4-5x-per-year","text_available":false},{"id":"arxiv:2412.06769","title":"Training Large Language Models to Reason in a Continuous Latent Space","date":"2024-12-09","section":"Reasoning and the \"physics\" of language models","quality":0.149043,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/68c71dc1a042dedd5e3c4d9c1ad32c9d046fd31b8dc79080bd6dff1c9800abc7/","source_url":"https://arxiv.org/abs/2412.06769","text_available":true},{"id":"arxiv:2406.11741","title":"Transcendence: Generative Models Can Outperform The Experts That Train Them","date":"2024-06-17","section":"Reasoning and the \"physics\" of language models","quality":0.099613,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/009cee51dbce762b177f0413e99ef4c30535501f77f54ed03aeb95de376319fd/","source_url":"https://arxiv.org/abs/2406.11741","text_available":true},{"id":"arxiv:2404.09173","title":"TransformerFAM: Feedback attention is working memory","date":"2024-04-14","section":"LLMs: architectures, context, training","quality":-0.082563,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/cbd04248dee4a37ffe8957d53e0b260196e25a477e8aa86db09efcd9fee74326/","source_url":"https://arxiv.org/abs/2404.09173","text_available":true}],"next":"https://vinnik-dmitry07.github.io/favorite-papers/agents/catalog-0-17.html"}