{"total":415,"papers":[{"id":"arxiv:2608.05806","title":"Hierarchical Latent Prediction for Language Models","date":"2026-08-06","section":"LLMs: architectures, context, training","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/991d6d0a05c5eaa5f6c94943be460ba2a65770ccae4997df9544bb772604d430/","source_url":"https://arxiv.org/abs/2608.05806","text_available":true},{"id":"arxiv:2506.21734","title":"Hierarchical Reasoning Model","date":"2025-06-26","section":"Reasoning and the \"physics\" of language models","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/3604312101ff09ab9903e7d6a32c7b2b8a9a7ece6a9d145d04ea01c9d13ffa3a/","source_url":"https://arxiv.org/abs/2506.21734","text_available":true},{"id":"arxiv:2503.21676","title":"How do language models learn facts? Dynamics, curricula and hallucinations","date":"2025-03-27","section":"Reasoning and the \"physics\" of language models","quality":0.304138,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/2ef59e7bcfcfc0e4bab638835504ad8a0d2f50665a9797edc09e8628e9b3c0b6/","source_url":"https://arxiv.org/abs/2503.21676","text_available":true},{"id":"arxiv:2406.11813","title":"How Do Large Language Models Acquire Factual Knowledge During Pretraining?","date":"2024-06-17","section":"Reasoning and the \"physics\" of language models","quality":0.09754,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a7b36ce24eb2182e7f0bba96c0cddcfe6efe610b830d5e8ad8aac2b7d14696c0/","source_url":"https://arxiv.org/abs/2406.11813","text_available":true},{"id":"arxiv:2505.24832","title":"How much do language models memorize?","date":"2025-05-30","section":"Data, training, optimization","quality":0.266715,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/1d14faeb604373b83ad90ae653998a11cc09492020341f29419e0deed45a300c/","source_url":"https://arxiv.org/abs/2505.24832","text_available":true},{"id":"url:educatingsilicon.com/2024/05/09/how-much-llm-training-data-is-there-in-the-limit","title":"How much LLM training data is there, in the limit?","date":"2024-05-09","section":"Data, training, optimization","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/1b8290cc5831de1490685a90105ebb81f55a67ebb3178e4fabac47caac2bcb43/","source_url":"https://www.educatingsilicon.com/2024/05/09/how-much-llm-training-data-is-there-in-the-limit/","text_available":false},{"id":"arxiv:2009.11848","title":"How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks","date":"2020-09-24","section":"Data, training, optimization","quality":0.221265,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/bd1a0149b2db51763f5d8c949f315e618ad47d5f1e2976b08a049f2bed2fbc4c/","source_url":"https://arxiv.org/abs/2009.11848","text_available":true},{"id":"arxiv:2302.10866","title":"Hyena Hierarchy: Towards Larger Convolutional Language Models","date":"2023-02-21","section":"LLMs: architectures, context, training","quality":0.423283,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/617c7279bfc8f8250cb7fb2d0bb4a2f7be1d1d692516fd45f80c7229632b16c7/","source_url":"https://arxiv.org/abs/2302.10866","text_available":true},{"id":"arxiv:2603.19461","title":"Hyperagents","date":"2026-03-19","section":"Agents, open-endedness, AGI","quality":0.02014,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/17eec8a15debc212b5530f117dd8ba8bad339590729cbbc4f75a47755ebcb544/","source_url":"https://arxiv.org/abs/2603.19461","text_available":true},{"id":"arxiv:2111.07832","title":"iBOT: Image BERT Pre-Training with Online Tokenizer","date":"2021-11-15","section":"Self-supervised learning and vision","quality":0.136624,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/2bd0269c0872fc518db65c2ca98dd30b5d38701f79b0a72fec2ed49648ba589f/","source_url":"https://arxiv.org/abs/2111.07832","text_available":true},{"id":"arxiv:2602.09000","title":"iGRPO: Self-Feedback-Driven LLM Reasoning","date":"2026-02-09","section":"Post-training","quality":-0.04492,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/1cd6a66823fe24e8e2d83e817177d3a1e8cda1d7d5b59a4397f8669bee6306ae/","source_url":"https://arxiv.org/abs/2602.09000","text_available":true},{"id":"arxiv:2208.10442","title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks","date":"2022-08-22","section":"Self-supervised learning and vision","quality":0.235929,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/51f033b7e43981722ced32d8001d10cdd68eafee7e0dad056b9001eeca29f358/","source_url":"https://arxiv.org/abs/2208.10442","text_available":true},{"id":"arxiv:2304.05977","title":"ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation","date":"2023-04-12","section":"Self-supervised learning and vision","quality":0.42693,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/8244b779cf69cdaae850b1714a9f3d2f3388571e65bc93c56b03cb1f58c0f6dc/","source_url":"https://arxiv.org/abs/2304.05977","text_available":true},{"id":"arxiv:2512.16902","title":"In-Context Algebra","date":"2025-12-18","section":"Reasoning and the \"physics\" of language models","quality":0.332516,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/5aa7087a88619eafd156aad9217e16f6d1ce284c65534322239be0e02f04e553/","source_url":"https://arxiv.org/abs/2512.16902","text_available":true},{"id":"arxiv:2312.13327","title":"In-Context Reinforcement Learning for Variable Action Spaces","date":"2023-12-20","section":"Reinforcement learning","quality":-0.055241,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/03e08bdf5d5c670f49cce235ed39b6ddb047bc31370ae7d24b68d13f81e232f6/","source_url":"https://arxiv.org/abs/2312.13327","text_available":true},{"id":"url:safe-lip-9a8.notion.site/incorrect-baseline-evaluations-call-into-question-recent-llm-rl-claims-2012f1fbf0ee8094ab8ded1953c15a37","title":"Incorrect Baseline Evaluations Call into Question Recent LLM-RL Claims","date":"2025-05-29","section":"Reasoning and the \"physics\" of language models","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/17c7ec29547cede3305ca35bc8596b82f5c03a03cc697d8e8702c40431b2a1bd/","source_url":"https://safe-lip-9a8.notion.site/Incorrect-Baseline-Evaluations-Call-into-Question-Recent-LLM-RL-Claims-2012f1fbf0ee8094ab8ded1953c15a37","text_available":false},{"id":"acl:2025.acl-long.126","title":"INVESTORBENCH: A Benchmark for Financial Decision-Making Tasks with LLM-based Agent","date":"2025-07-01","section":"Finance","quality":-0.178248,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/f71b6d3b384030032d1a701195d7c5af5874f1b3e87a5db8ab0073648c1190cd/","source_url":"https://aclanthology.org/2025.acl-long.126/","text_available":true},{"id":"arxiv:2603.19426","title":"Is Evaluation Awareness Just Format Sensitivity? Limitations of Probe-Based Evidence under Controlled Prompt Structure","date":"2026-03-19","section":"AI safety and consciousness","quality":-0.292022,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/7f8dc25d398b7b7c0016c33d829b3613ec6d66554ba5b49dbfc2362ce8621032/","source_url":"https://arxiv.org/abs/2603.19426","text_available":true},{"id":"url:cell.com/iscience/fulltext/s2589-0042(25)00289-5","title":"Is my red your red? Evaluating structural correspondences of color qualia (iScience 2025)","date":"2024-08-14","section":"NeuroAI","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/910740a96cf39f468bf81936b578d1da6c80ed4f0d1533ac7faa9c220b1b931f/","source_url":"https://www.cell.com/iscience/fulltext/S2589-0042(25)00289-5","text_available":false},{"id":"arxiv:2206.13353","title":"Is Power-Seeking AI an Existential Risk?","date":"2022-06-16","section":"AI safety and consciousness","quality":0.002809,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/21192da140d682c8aacb0e8dfccbbf481a855b35ee245ee548f905eb993754d4/","source_url":"https://arxiv.org/abs/2206.13353","text_available":true},{"id":"arxiv:2504.01928","title":"Is the Reversal Curse a Binding Problem? Uncovering Limitations of Transformers from a Basic Generalization Failure","date":"2025-04-02","section":"Reasoning and the \"physics\" of language models","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/b18365db218c3406643d59ec371727d81993de9d22541f1bd099f3f5ff15b94c/","source_url":"https://arxiv.org/abs/2504.01928","text_available":true},{"id":"arxiv:2510.00977","title":"It Takes Two: Your GRPO Is Secretly DPO","date":"2025-10-01","section":"Post-training","quality":-0.095378,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/575241376f2282c1929931f107a0ce60fd25f0a5388ecfea6b9abbbed2f03ca6/","source_url":"https://arxiv.org/abs/2510.00977","text_available":true},{"id":"arxiv:2508.07629","title":"Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization","date":"2025-08-11","section":"Post-training","quality":-0.228184,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a232533e4e78ad28d2ffe9fafe799b66cf626b18ad523d0088d9cc12f1ba1b76/","source_url":"https://arxiv.org/abs/2508.07629","text_available":true},{"id":"arxiv:2407.15017","title":"Knowledge Mechanisms in Large Language Models: A Survey and Perspective","date":"2024-07-22","section":"Reasoning and the \"physics\" of language models","quality":-0.200172,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/8900dc2821aa61e59c5b1219cf9eb36dfaabf303c17d0064deaca653b5ec9a77/","source_url":"https://arxiv.org/abs/2407.15017","text_available":true}],"next":"https://vinnik-dmitry07.github.io/favorite-papers/agents/catalog-0-8.html"}