{"total":415,"papers":[{"id":"arxiv:2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","date":"2020-06-29","section":"LLMs: architectures, context, training","quality":0.112975,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/d119844a2dce8a3b156558743b90add84774d00894634b6478d03abb4f5216f9/","source_url":"https://arxiv.org/abs/2006.16236","text_available":true},{"id":"arxiv:2608.27448","title":"TTPO: Test-Time Policy Optimization","date":"2026-08-27","section":"Post-training","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/3473ad1e90105976912e40eabe716441e830da401749e9d85b5162e1c7bbd964/","source_url":"https://arxiv.org/abs/2608.27448","text_available":true},{"id":"arxiv:2504.16084","title":"TTRL: Test-Time Reinforcement Learning","date":"2025-04-22","section":"Post-training","quality":0.322393,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/ad54dd58d24afdfefc8aa5087d07c4aab2143e90ef06f6f7db8d3f3333452c48/","source_url":"https://arxiv.org/abs/2504.16084","text_available":true},{"id":"arxiv:2503.20783","title":"Understanding R1-Zero-Like Training: A Critical Perspective","date":"2025-03-26","section":"Post-training","quality":0.335057,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/b49a056f3ce8e269dd65e3b11605927f3c4d0ef074bc68e0b1d7f84e6c9c6c6a/","source_url":"https://arxiv.org/abs/2503.20783","text_available":true},{"id":"arxiv:2604.02288","title":"Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing","date":"2026-04-02","section":"Post-training","quality":0.005794,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/3d1160029d321f2069016f7702d4ebebee0de6cd31a8f296ee220abd6f69c99b/","source_url":"https://arxiv.org/abs/2604.02288","text_available":true},{"id":"arxiv:2211.10869","title":"UniMASK: Unified Inference in Sequential Decision Problems","date":"2022-11-20","section":"Reinforcement learning","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/919bff55efff4ed3549bd106b843afa3d140b32938f5283c77821d7fd569452e/","source_url":"https://arxiv.org/abs/2211.10869","text_available":true},{"id":"arxiv:2512.14693","title":"Universal Reasoning Model","date":"2025-12-16","section":"Reasoning and the \"physics\" of language models","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/fcb1a389a132d64ca93fac5551d8f8b653c5e093908cb515e2a2d901524941a7/","source_url":"https://arxiv.org/abs/2512.14693","text_available":true},{"id":"arxiv:1807.03819","title":"Universal Transformers","date":"2018-07-10","section":"LLMs: architectures, context, training","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/1d843516d980c3404cb622a2a490edb535a3afe27a85a980335a54b5fcd2220a/","source_url":"https://arxiv.org/abs/1807.03819","text_available":true},{"id":"arxiv:2604.21999","title":"Universal Transformers Need Memory: Depth-State Trade-offs in Adaptive Recursive Reasoning","date":"2026-04-23","section":"Reasoning and the \"physics\" of language models","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/963f6bb396c25bff462a25854c82e7d92b77803fa60c891fadd9963cc56c8fea/","source_url":"https://arxiv.org/abs/2604.21999","text_available":true},{"id":"arxiv:2305.01625","title":"Unlimiformer: Long-Range Transformers with Unlimited Length Input","date":"2023-05-02","section":"LLMs: architectures, context, training","quality":0.178118,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/618496c3ed89cfd0171d97f92a102cd2a37c2cdb1c00a197683ee69421fe7279/","source_url":"https://arxiv.org/abs/2305.01625","text_available":true},{"id":"arxiv:2506.10139","title":"Unsupervised Elicitation of Language Models","date":"2025-06-11","section":"Post-training","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/f27ae3b426a87310071610dedea4c144b50b1be183434e32486b31562f9a3da9/","source_url":"https://arxiv.org/abs/2506.10139","text_available":true},{"id":"arxiv:2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","date":"2020-06-17","section":"Self-supervised learning and vision","quality":0.412639,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/6601018611a96dff6f5324f2e4f39f62484917cf4d8f8a8d5baa7f4be1deb433/","source_url":"https://arxiv.org/abs/2006.09882","text_available":true},{"id":"arxiv:2502.15840","title":"Vending-Bench: A Benchmark for Long-Term Coherence of Autonomous Agents","date":"2025-02-21","section":"Agents, open-endedness, AGI","quality":-0.282468,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/3e821cc90ae1748114d12211bc9209146fea5b544c192e41be419dd6dc9ee2b4/","source_url":"https://arxiv.org/abs/2502.15840","text_available":true},{"id":"url:transformer-circuits.pub/2026/workspace","title":"Verbalizable Representations Form a Global Workspace in Language Models (Anthropic, July 2026)","date":"2026-07-06","section":"Representation alignment","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/b6c69421d0c8f654965b5b9a91d899bdefd1fadd309f7cd192d6620adf3af3eb/","source_url":"https://transformer-circuits.pub/2026/workspace/","text_available":false},{"id":"arxiv:2105.04906","title":"VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning","date":"2021-05-11","section":"Self-supervised learning and vision","quality":-0.071959,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/822b6414fb02bd6c746e0d559fd3dcc60766476142ebae7795b02bc6c45223ce/","source_url":"https://arxiv.org/abs/2105.04906","text_available":true},{"id":"arxiv:2606.02572","title":"VISReg: Variance-Invariance-Sketching Regularization for JEPA training","date":"2026-06-01","section":"Self-supervised learning and vision","quality":0.33919,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/262c1938984761f99c55d9ae1237e686b2d6ab94b69d7181d11dceab2a7210fb/","source_url":"https://arxiv.org/abs/2606.02572","text_available":true},{"id":"url:openai.com/research/weak-to-strong-generalization","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","date":"2023-12-14","section":"AI safety and consciousness","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/fb7b23a617dce974dbb70db824c97c1de84afa11e1e290d5cb9f5bd88857e762/","source_url":"https://openai.com/research/weak-to-strong-generalization","text_available":false},{"id":"arxiv:2606.23740","title":"Weight-Space Geometry of Offline Reasoning Training","date":"2026-06-26","section":"Post-training","quality":-0.244397,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/e4479f0d0930797db9347855247f1c640a12d96f63d43b83ba9635561e3ff352/","source_url":"https://arxiv.org/abs/2606.23740","text_available":true},{"id":"arxiv:2511.15593","title":"What Does It Take to Be a Good AI Research Agent? Studying the Role of Ideation Diversity","date":"2025-11-19","section":"Agents, open-endedness, AGI","quality":-0.444708,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/be2cc7f3c48da553c3ae6c2de2a5474a30deb993704a409d471ac0570b91dcab/","source_url":"https://arxiv.org/abs/2511.15593","text_available":true},{"id":"arxiv:2607.23379","title":"When Activation Oracles Learn Not to Read: Concept-Specific Blind Spots in Fine-Tuned Oracles","date":"2026-07-25","section":"AI safety and consciousness","quality":0.085385,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a90f5a062f6ed3f603a48433557f8d622d5e5e5007884638f465243b87f67ac5/","source_url":"https://arxiv.org/abs/2607.23379","text_available":true},{"id":"arxiv:2607.07847","title":"When Does Continual Learning Require Learning","date":"2026-07-08","section":"Post-training","quality":0.0211,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/86e88c6cf21a66879eab5c156913fc85d14eb69c394c78c33c0e81d144e528eb/","source_url":"https://arxiv.org/abs/2607.07847","text_available":true},{"id":"arxiv:2605.26379","title":"When Does LeJEPA Learn a World Model?","date":"2026-05-25","section":"Self-supervised learning and vision","quality":0.621282,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/f140b8fcc13ea085ce6ad170e090380c8d373416f791960778c4b216f6e5c8f6/","source_url":"https://arxiv.org/abs/2605.26379","text_available":true},{"id":"arxiv:2510.00184","title":"Why Can't Transformers Learn Multiplication? Reverse-Engineering Reveals Long-Range Dependency Pitfalls","date":"2025-09-30","section":"Reasoning and the \"physics\" of language models","quality":0.062547,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/7e395b2ae5bfc2a4d8bfc1e8669b4f324739b6a9b11161cba150bfdffc31746c/","source_url":"https://arxiv.org/abs/2510.00184","text_available":true},{"id":"arxiv:2603.24472","title":"Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?","date":"2026-03-25","section":"Post-training","quality":-0.15648,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/d99edb6fac2f4ad6d63e98ec0a2952187ed2ae190604fbed3507b3ed56d57315/","source_url":"https://arxiv.org/abs/2603.24472","text_available":true}],"next":"https://vinnik-dmitry07.github.io/favorite-papers/agents/catalog-0-18.html"}