{"total":415,"papers":[{"id":"url:ai.meta.com/research/publications/code-llama-open-foundation-models-for-code","title":"Code Llama: Open Foundation Models for Code","date":"2023-08-24","section":"LLMs: architectures, context, training","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/0dc2d6030e514e45150f64f511c0f50fc010fdc1ddae0bdca7edcd189b084d41/","source_url":"https://ai.meta.com/research/publications/code-llama-open-foundation-models-for-code/","text_available":false},{"id":"url:herasight-project.webflow.io/technical-paper/cogpgt-1","title":"CogPGT: a genetic predictor of IQ","date":"2025-10-21","section":"NeuroAI","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/3ccf175c2a340d33ed83aa5332121192c0557fefb5764d3dd4a3bc0765bf8aaa/","source_url":"https://herasight-project.webflow.io/technical-paper/cogpgt-1","text_available":false},{"id":"arxiv:2501.14082","title":"Communicating Activations Between Language Model Agents","date":"2025-01-23","section":"LLMs: architectures, context, training","quality":0.117038,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/e67d4addcda44093e242074332925d000726f87bd9538f6b318bdfc454a7dc13/","source_url":"https://arxiv.org/abs/2501.14082","text_available":true},{"id":"arxiv:2007.02789","title":"Comparing representational geometries using whitened unbiased-distance-matrix similarity","date":"2020-07-06","section":"Representation alignment","quality":0.698414,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/1c8778896169013495269ae2f98737d8338cf63d6943e50f134deef61ddf7e62/","source_url":"https://arxiv.org/abs/2007.02789","text_available":true},{"id":"arxiv:2508.16204","title":"Competition and Attraction Improve Model Fusion","date":"2025-08-22","section":"Agents, open-endedness, AGI","quality":0.062343,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/0f52994edd8aa2b6a99e8b34ed0599f3bec5b5c3e95483c526e104a1a509a457/","source_url":"https://arxiv.org/abs/2508.16204","text_available":true},{"id":"arxiv:2502.06807","title":"Competitive Programming with Large Reasoning Models","date":"2025-02-03","section":"Reasoning and the \"physics\" of language models","quality":-0.255672,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/d1e6e9343805a99e3ba9032540f71dd4fc3436db1425ff988c9639e0c3641c8c/","source_url":"https://arxiv.org/abs/2502.06807","text_available":true},{"id":"arxiv:2509.14234","title":"Compute as Teacher: Turning Inference Compute Into Reference-Free Supervision","date":"2025-09-17","section":"Post-training","quality":0.066281,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a6f1443a7e55dd6421fdbe43e65e19c1962a19b135d737fd67f414d3324ce85e/","source_url":"https://arxiv.org/abs/2509.14234","text_available":true},{"id":"arxiv:2308.08708","title":"Consciousness in Artificial Intelligence: Insights from the Science of Consciousness","date":"2023-08-17","section":"AI safety and consciousness","quality":-0.0297,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/e7d3e0c10e0ae2d2d2d5a65d4df9b37db6e65fe2ef82355a9235738ff15f907e/","source_url":"https://arxiv.org/abs/2308.08708","text_available":true},{"id":"arxiv:2501.18837","title":"Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming","date":"2025-01-31","section":"AI safety and consciousness","quality":0.128536,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/c73837c3edb5465ee3f7cc7c6e16d23e16bdbdef5e1448aeaad2135dfd87de07/","source_url":"https://arxiv.org/abs/2501.18837","text_available":true},{"id":"arxiv:2108.06325","title":"Continual Backprop: Stochastic Gradient Descent with Persistent Randomness","date":"2021-08-13","section":"Data, training, optimization","quality":-0.471382,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/73c90c52bffd8b5b2485d93607350545d822f361c29d3c0063b8d3025576e793/","source_url":"https://arxiv.org/abs/2108.06325","text_available":true},{"id":"arxiv:2403.05175","title":"Continual Learning and Catastrophic Forgetting","date":"2024-03-08","section":"Data, training, optimization","quality":-0.26995,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/3ed9ae586e8898d0235553d62c5f002609d3d112cbec54cc46655d19ff736400/","source_url":"https://arxiv.org/abs/2403.05175","text_available":true},{"id":"arxiv:2510.27688","title":"Continuous Autoregressive Language Models","date":"2025-10-31","section":"LLMs: architectures, context, training","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/e954d29144273a3d9e4c1a5ac4fc43a163b8701659926e2bfa94011507f51414/","source_url":"https://arxiv.org/abs/2510.27688","text_available":true},{"id":"url:pub.sakana.ai/ctm","title":"Continuous Thought Machines","date":"2025-05-08","section":"LLMs: architectures, context, training","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/2d6fdb072de0d3edb79a12bb935f300e9fe9b517f681e39459a39db71cfd44f8/","source_url":"https://pub.sakana.ai/ctm/","text_available":false},{"id":"arxiv:2405.01012","title":"Correcting Biased Centered Kernel Alignment Measures in Biological and Artificial Neural Networks","date":"2024-05-02","section":"Representation alignment","quality":-0.505307,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a961d84a4ef2fcab54a7b1f632d950182fa2353e0c4d8a0107320f996f943d35/","source_url":"https://arxiv.org/abs/2405.01012","text_available":true},{"id":"doi:10.1038/s41467-021-26568-2","title":"Correspondence between neuroevolution and gradient descent","date":"2021-11-02","section":"NeuroAI","quality":-0.324167,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/21875123ceb4116f9890b5b8d70154234ec0aa1bb29c70d3439a48aad10629b0/","source_url":"https://doi.org/10.1038/s41467-021-26568-2","text_available":true},{"id":"arxiv:2303.07103","title":"Could a Large Language Model be Conscious?","date":"2023-03-04","section":"AI safety and consciousness","quality":-0.249629,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/066af7a709204ed7ece7130b13781997ec7b3a9be7f1881c6fc2bd9aa00cea33/","source_url":"https://arxiv.org/abs/2303.07103","text_available":true},{"id":"arxiv:2212.14034","title":"Cramming: Training a Language Model on a Single GPU in One Day","date":"2022-12-28","section":"Data, training, optimization","quality":-0.087484,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/cb243af26cd29bcc3d04b00cc68393b3c4b3dfc535c3dd228b44f12e5df26c46/","source_url":"https://arxiv.org/abs/2212.14034","text_available":true},{"id":"arxiv:2506.03106","title":"Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback","date":"2025-06-03","section":"Post-training","quality":0.423423,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/b16b5772846ee30548a2d2c9cce1833ca3af6beb01c4a58f2dd5a69d809d55d4/","source_url":"https://arxiv.org/abs/2506.03106","text_available":true},{"id":"arxiv:2608.03893","title":"Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse","date":"2026-08-04","section":"LLMs: architectures, context, training","quality":0.145329,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/c29465e80f45097327908d15926fd9b4a3c4c50431b2d525eb5aa9b92446fb2a/","source_url":"https://arxiv.org/abs/2608.03893","text_available":true},{"id":"arxiv:2506.06632","title":"Curriculum Reinforcement Learning from Easy to Hard Tasks Improves LLM Reasoning","date":"2025-06-07","section":"Post-training","quality":0.051441,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/79fda9609f9b88bb71f71f531b63ea6b5237d1c889b7ae59e9ca07c12dbe70d1/","source_url":"https://arxiv.org/abs/2506.06632","text_available":true},{"id":"arxiv:1506.01186","title":"Cyclical Learning Rates for Training Neural Networks","date":"2015-06-03","section":"Data, training, optimization","quality":-0.406646,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/e05cf550191656c287184521d0ff011092f5ed6baa72e50f3a5bfd25d0f5986a/","source_url":"https://arxiv.org/abs/1506.01186","text_available":true},{"id":"arxiv:2503.14476","title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","date":"2025-03-18","section":"Post-training","quality":-0.315765,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/548e934b912ef84691ace63bf1cfd670e7b0257d9d6986dde926f569e7b2f8b7/","source_url":"https://arxiv.org/abs/2503.14476","text_available":true},{"id":"arxiv:2505.22954","title":"Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents","date":"2025-05-29","section":"Agents, open-endedness, AGI","quality":0.058379,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/c29f716871f80314868b5647692de387f26e12166b93bd362915fd272b6e081c/","source_url":"https://arxiv.org/abs/2505.22954","text_available":true},{"id":"url:researchgate.net/publication/331273826","title":"Deep Adaptive Input Normalization for Time Series Forecasting","date":"2019-02-21","section":"Finance","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/e7482e041dc46f5d374c9ced6ed698a894a7c99f7c69582938cf7fd59c9e3668/","source_url":"https://www.researchgate.net/publication/331273826","text_available":false}],"next":"https://vinnik-dmitry07.github.io/favorite-papers/agents/catalog-0-4.html"}