{"total":415,"papers":[{"id":"arxiv:2003.01859","title":"Applications of deep learning in stock market prediction: recent progress","date":"2020-02-29","section":"Finance","quality":-0.722603,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/524c5cd6ea249552053f530cd3a818510c330d82c7845410c4d74c4e648b8669/","source_url":"https://arxiv.org/abs/2003.01859","text_available":true},{"id":"arxiv:2304.15004","title":"Are Emergent Abilities of Large Language Models a Mirage?","date":"2023-04-28","section":"Reasoning and the \"physics\" of language models","quality":0.369634,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/d7cd8c081ad54f2fdaa2211a4b49dc21f6ff2db7282e287546d210ef90e84323/","source_url":"https://arxiv.org/abs/2304.15004","text_available":true},{"id":"arxiv:2410.21272","title":"Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics","date":"2024-10-28","section":"Reasoning and the \"physics\" of language models","quality":0.602412,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/397b826ba289bd4f14f457562942cb092c38550a4c49451e95ffcc7b376c8cb0/","source_url":"https://arxiv.org/abs/2410.21272","text_available":true},{"id":"arxiv:2402.12483","title":"Artifacts or Abduction: How Do LLMs Answer Multiple-Choice Questions Without the Question?","date":"2024-02-19","section":"Retrieval, embeddings, benchmarks","quality":-0.037184,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/1b9723010e10f9e91a6a9cc14c735ef6b1ff56c29c55c1204eeb18b6a43b7f15/","source_url":"https://arxiv.org/abs/2402.12483","text_available":true},{"id":"arxiv:2112.03978","title":"Attractor and integrator networks in the brain","date":"2021-12-07","section":"NeuroAI","quality":0.136698,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/23ad84d7f32b6f14b2e6d5af2302b4a78e56350dff242bee3a4021d4b7373f7f/","source_url":"https://arxiv.org/abs/2112.03978","text_available":true},{"id":"url:transformer-circuits.pub/2025/attribution-graphs/biology.html","title":"Attribution graphs, the biology of the model","date":"2025-03-27","section":"AI safety and consciousness","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/8b3e14c537e89eed9a4402e9c14094d69913ed24d45fdab1a82ba4b8280660e2/","source_url":"https://transformer-circuits.pub/2025/attribution-graphs/biology.html","text_available":false},{"id":"arxiv:2408.08435","title":"Automated Design of Agentic Systems","date":"2024-08-15","section":"Agents, open-endedness, AGI","quality":0.129553,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/c9890d5668d1c1b33e29569b74626fd586f456af6a97c657b8c99895c90f59a5/","source_url":"https://arxiv.org/abs/2408.08435","text_available":true},{"id":"arxiv:2608.09888","title":"BDH-CQ: In-Context Learning with Recurrent Latent Reasoning","date":"2026-08-10","section":"Post-training","quality":-0.339191,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/f0c77a8a0f50254e9efdf9a511e08fc2a40677bfa029864bdd0a9cbce561c666/","source_url":"https://arxiv.org/abs/2608.09888","text_available":true},{"id":"arxiv:1910.01708","title":"Benchmarking Batch Deep Reinforcement Learning Algorithms","date":"2019-10-03","section":"Reinforcement learning","quality":-0.5589,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/ce9cb9b764eb7fdaf1aa766cb24e6abaec20a00445ad5af5a6dacb5af3ad3ddc/","source_url":"https://arxiv.org/abs/1910.01708","text_available":true},{"id":"arxiv:2603.05454","title":"Beyond Scattered Acceptance: Fast and Coherent Inference for DLMs via Longest Stable Prefixes","date":"2026-03-05","section":"LLMs: architectures, context, training","quality":0.057813,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/303994b6470f9a9063fca1f6980da95344903a409e61de83c6b35e99146b6329/","source_url":"https://arxiv.org/abs/2603.05454","text_available":true},{"id":"arxiv:2506.01939","title":"Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning","date":"2025-06-02","section":"Post-training","quality":0.275648,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/e0f4a55bca612bce5895b6b98f89b0efc14cbd8cf45946a7743347cf6daee1a1/","source_url":"https://arxiv.org/abs/2506.01939","text_available":true},{"id":"arxiv:2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","date":"2022-06-09","section":"Retrieval, embeddings, benchmarks","quality":0.491414,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/70882486c1f8c46cb7b26cf100847f770eb7b39b69dee56b8a21141141ef814d/","source_url":"https://arxiv.org/abs/2206.04615","text_available":true},{"id":"arxiv:2411.03820","title":"Beyond The Rainbow: High Performance Deep Reinforcement Learning on a Desktop PC","date":"2024-11-06","section":"Reinforcement learning","quality":0.211995,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/8bcc96ef608c017d3ddb7ded7dc9e3b760390f7df441214eeee08a2586c981ea/","source_url":"https://arxiv.org/abs/2411.03820","text_available":true},{"id":"arxiv:2305.19452","title":"Bigger, Better, Faster: Human-level Atari with human-level efficiency","date":"2023-05-30","section":"Reinforcement learning","quality":0.228173,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/727a7ee43fd005401d34d4591a2f49d85175f9366ebf2c9e7a862b340787614e/","source_url":"https://arxiv.org/abs/2305.19452","text_available":true},{"id":"arxiv:2405.14862","title":"Bitune: Leveraging Bidirectional Attention to Improve Decoder-Only LLMs","date":"2024-05-23","section":"LLMs: architectures, context, training","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/314c3b36ea56b4a34d8f177db2dd33f45710b14aa245cb3e779c51ec76e795de/","source_url":"https://arxiv.org/abs/2405.14862","text_available":true},{"id":"arxiv:2606.31779","title":"Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers","date":"2026-06-30","section":"Reasoning and the \"physics\" of language models","quality":0.291912,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/bf07d5c19e507d9ec91a48f9067e6c29fbe8965d001923e2de0e96da143c72e1/","source_url":"https://arxiv.org/abs/2606.31779","text_available":true},{"id":"arxiv:2510.03215","title":"Cache-to-Cache: Direct Semantic Communication Between Large Language Models","date":"2025-10-03","section":"LLMs: architectures, context, training","quality":0.499296,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/b5a2a7fccb7e223ec3c3769c18189f6a6e4c18e2b074567db94cd7db2450723b/","source_url":"https://arxiv.org/abs/2510.03215","text_available":true},{"id":"arxiv:2311.16452","title":"Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine","date":"2023-11-28","section":"Retrieval, embeddings, benchmarks","quality":0.058276,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/8e8303d0328f412b165c8cdfca91debf742ea45ed7865a0d96ee3905e5bba919/","source_url":"https://arxiv.org/abs/2311.16452","text_available":true},{"id":"arxiv:2505.21444","title":"Can Large Reasoning Models Self-Train?","date":"2025-05-27","section":"Reasoning and the \"physics\" of language models","quality":-0.120113,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/206224ca50098e0bdc230140722feec107cfc90c1cef2ed8d3ed52355ef56bca/","source_url":"https://arxiv.org/abs/2505.21444","text_available":true},{"id":"arxiv:2312.10549","title":"Catastrophic Forgetting in Deep Learning: A Comprehensive Taxonomy","date":"2023-12-16","section":"Data, training, optimization","quality":-0.651376,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/890b8ca392bd314b377271caffd70091a482d479f8cc7747c31633479b2e87d8/","source_url":"https://arxiv.org/abs/2312.10549","text_available":true},{"id":"arxiv:2509.09675","title":"CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models","date":"2025-09-11","section":"Reinforcement learning","quality":0.1136,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/f5581044978796ff7f35cb68c27963d3abbb391d35d88173ff7801242cbb1f7a/","source_url":"https://arxiv.org/abs/2509.09675","text_available":true},{"id":"arxiv:2606.18543","title":"CEO-Bench: Can Agents Play the Long Game?","date":"2026-06-16","section":"Retrieval, embeddings, benchmarks","quality":0.174568,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/696d7ac1dfd7539fbe8147ed713574b8eb5a7400a35e96805c7f0c9add99165c/","source_url":"https://arxiv.org/abs/2606.18543","text_available":true},{"id":"url:ai.googleblog.com/2022/11/characterizing-emergent-phenomena-in.html","title":"Characterizing emergent phenomena in LLMs (Google Research)","date":"2022-11-10","section":"Reasoning and the \"physics\" of language models","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/749249d7d689468b1404142d896fe5bd9048709780cc20f3a0f984a02bcc3aca/","source_url":"https://ai.googleblog.com/2022/11/characterizing-emergent-phenomena-in.html","text_available":false},{"id":"url:transformer-circuits.pub/2025/attribution-graphs/methods.html","title":"Circuit tracing / attribution graphs (methods)","date":"2025-03-27","section":"AI safety and consciousness","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/7d4ba254716fd13d3a1ffb6518788e304eaa7077bd9d7bce201094eb293518b4/","source_url":"https://transformer-circuits.pub/2025/attribution-graphs/methods.html","text_available":false}],"next":"https://vinnik-dmitry07.github.io/favorite-papers/agents/catalog-0-3.html"}