{"total":50,"papers":[{"id":"arxiv:2501.00656","title":"2 OLMo 2 Furious","date":"2024-12-31","section":"LLMs: architectures, context, training","quality":0.235048,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/1ca88dba5d5c59e8cb23b2a304e74370b8ec69077b714a30d426300f7ef2a0b9/","source_url":"https://arxiv.org/abs/2501.00656","text_available":true},{"id":"arxiv:2607.02303","title":"A Hippocampus for Linear Attention: An Exact Memory for What the Recurrent State Forgets","date":"2026-07-02","section":"LLMs: architectures, context, training","quality":0.24797,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/499d4b7d5f795ec273c099c3ee7ba3ba4b6efb60063810c5afc4d10082a3168d/","source_url":"https://arxiv.org/abs/2607.02303","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: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: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":"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":"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: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: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:2608.00146","title":"DiffusionGemma Technical Report","date":"2026-07-31","section":"LLMs: architectures, context, training","quality":0.286144,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/90a7b084496cd65968627c115230fc3a5e78005a66b5ebb34547e874754bc82e/","source_url":"https://arxiv.org/abs/2608.00146","text_available":true},{"id":"arxiv:2604.08302","title":"DMax: Aggressive Parallel Decoding for dLLMs","date":"2026-04-09","section":"LLMs: architectures, context, training","quality":0.217022,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/22790263bd218aac28626fe3dab2fcd0ed73ceef94aa8a948bef2cb8bc007f7a/","source_url":"https://arxiv.org/abs/2604.08302","text_available":true},{"id":"arxiv:2511.09149","title":"Enabling Agents to Communicate Entirely in Latent Space","date":"2025-11-12","section":"LLMs: architectures, context, training","quality":0.297245,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/02979751e22005b3284e4d7caa19baae335ca63c9ec46e27d833e95d088e9688/","source_url":"https://arxiv.org/abs/2511.09149","text_available":true},{"id":"arxiv:2504.06225","title":"Encoder-Decoder Gemma: Improving the Quality-Efficiency Trade-Off via Adaptation","date":"2025-04-08","section":"LLMs: architectures, context, training","quality":-0.004879,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/797af53c1331a8303ff731ef2763d562b29b9864407468ebbd7c1a89ab7c0eed/","source_url":"https://arxiv.org/abs/2504.06225","text_available":true},{"id":"arxiv:2510.26622","title":"Encoder-Decoder or Decoder-Only? Revisiting Encoder-Decoder Large Language Model","date":"2025-10-30","section":"LLMs: architectures, context, training","quality":0.064707,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/dc73f87f798d016e2d83acd1d362b4b3525af826e68b055bb5196f120d23e080/","source_url":"https://arxiv.org/abs/2510.26622","text_available":true},{"id":"arxiv:2302.07253","title":"Energy Transformer","date":"2023-02-14","section":"LLMs: architectures, context, training","quality":-0.291157,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/4f82adc1eb9a92ea3160324c195688d3834a4c68c026ffc40e951352c572746b/","source_url":"https://arxiv.org/abs/2302.07253","text_available":true},{"id":"arxiv:2311.06242","title":"Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks","date":"2023-11-10","section":"LLMs: architectures, context, training","quality":0.228032,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/edc2679fff98a10c70395e79c58b56eaf9ec0001691dbca2b33ba94a401a8398/","source_url":"https://arxiv.org/abs/2311.06242","text_available":true},{"id":"arxiv:2002.05202","title":"GLU Variants Improve Transformer","date":"2020-02-12","section":"LLMs: architectures, context, training","quality":-0.585411,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/e052a2974593d29355ab45c301766ac6f5545ac1bc81d605e78d3adc71e9e2e4/","source_url":"https://arxiv.org/abs/2002.05202","text_available":true},{"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: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:2302.14045","title":"Language Is Not All You Need: Aligning Perception with Language Models","date":"2023-02-27","section":"LLMs: architectures, context, training","quality":0.261634,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/fc11ce0896e97836324fcdf28bbcaf2c69f0e5e408a67265741605e450246035/","source_url":"https://arxiv.org/abs/2302.14045","text_available":true},{"id":"arxiv:2609.02737","title":"Language Models Can Control Their Own Attention","date":"2026-09-02","section":"LLMs: architectures, context, training","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/d92e296c1a145dd5abf7d3efa06faf9f01243de35f8f197fc1e6221cba9fe442/","source_url":"https://arxiv.org/abs/2609.02737","text_available":true},{"id":"url:ai.meta.com/research/publications/large-concept-models-language-modeling-in-a-sentence-representation-space","title":"Large Concept Models: Language Modeling in a Sentence Representation Space","date":"2024-12-11","section":"LLMs: architectures, context, training","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a5cd322d52f1966361afb1d5225560e2d3ce4d22a117bd14cfa27ec669e09673/","source_url":"https://ai.meta.com/research/publications/large-concept-models-language-modeling-in-a-sentence-representation-space/","text_available":false},{"id":"arxiv:2502.09992","title":"Large Language Diffusion Models","date":"2025-02-14","section":"LLMs: architectures, context, training","quality":0.498698,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a4863ed6f639560bd2feb6c66c13d1e3ac4cf42f8919a65c9818625cc6b6cde9/","source_url":"https://arxiv.org/abs/2502.09992","text_available":true}],"next":"https://vinnik-dmitry07.github.io/favorite-papers/agents/catalog-2-2.html"}