{"total":50,"papers":[{"id":"arxiv:2605.22863","title":"Latent Cache Flow: Model-to-Model Communication Without Text","date":"2026-05-19","section":"LLMs: architectures, context, training","quality":-0.148425,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/eb6ed55f9fdbf8d212955b61ff74495737a2ecfacaa3645c7e4402b57e0c3e86/","source_url":"https://arxiv.org/abs/2605.22863","text_available":true},{"id":"arxiv:2404.07143","title":"Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention","date":"2024-04-10","section":"LLMs: architectures, context, training","quality":-0.055248,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/fcdbb3ceff27039e0eeeeac187ebf2570e2dc8b6f58ed5ee278f4259e88cfab1/","source_url":"https://arxiv.org/abs/2404.07143","text_available":true},{"id":"arxiv:2512.15745","title":"LLaDA2.0: Scaling Up Diffusion Language Models to 100B","date":"2025-12-10","section":"LLMs: architectures, context, training","quality":0.154862,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/90a25474fdf076c254ea3ddbbc7ddbc1f2f49fb98065168d66b5ad9d8f7dafaa/","source_url":"https://arxiv.org/abs/2512.15745","text_available":true},{"id":"arxiv:2602.08676","title":"LLaDA2.1: Speeding Up Text Diffusion via Token Editing","date":"2026-02-09","section":"LLMs: architectures, context, training","quality":-0.033511,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/1b6dd6e64e69da1fff43a183af57a467878db80d54f550bceefa049d7bb18878/","source_url":"https://arxiv.org/abs/2602.08676","text_available":true},{"id":"arxiv:2203.08913","title":"Memorizing Transformers","date":"2022-03-16","section":"LLMs: architectures, context, training","quality":0.238047,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/76deb2bc758a8a71e7c5c5ad6f4b45a1527845ec73784adc6f75f77462a596aa/","source_url":"https://arxiv.org/abs/2203.08913","text_available":true},{"id":"arxiv:2507.10524","title":"Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation","date":"2025-07-14","section":"LLMs: architectures, context, training","quality":0.17613,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/7b25702c35f07446cea97d6a98afc489c8fdda54560c05fbeb1b3b139a9da622/","source_url":"https://arxiv.org/abs/2507.10524","text_available":true},{"id":"arxiv:2207.02098","title":"Neural Networks and the Chomsky Hierarchy","date":"2022-07-05","section":"LLMs: architectures, context, training","quality":0.297018,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/6c4e7406c7294ace52a03e4eede4ef1a31cd395dcde0958487fdbb546fa2c026/","source_url":"https://arxiv.org/abs/2207.02098","text_available":true},{"id":"arxiv:2512.13961","title":"Olmo 3","date":"2025-12-15","section":"LLMs: architectures, context, training","quality":0.225076,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/8daa11a9729da9879a7e95c15d4eef3bab8579d2885a14102ed09db111221802/","source_url":"https://arxiv.org/abs/2512.13961","text_available":true},{"id":"arxiv:2608.17981","title":"Recirculation","date":"2026-08-18","section":"LLMs: architectures, context, training","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/fd91ffc957070136795d3728f662c997738234065b624eb720acd8547d2edaf6/","source_url":"https://arxiv.org/abs/2608.17981","text_available":true},{"id":"arxiv:2512.24601","title":"Recursive Language Models","date":"2025-12-31","section":"LLMs: architectures, context, training","quality":0.153868,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/ac41983c934a3432ce7b6531e367b9e639bddbed93d4c6513781e76407d9a8bd/","source_url":"https://arxiv.org/abs/2512.24601","text_available":true},{"id":"arxiv:2306.13575","title":"Scaling MLPs: A Tale of Inductive Bias","date":"2023-06-23","section":"LLMs: architectures, context, training","quality":0.244662,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/d2a2acb2495d23945ce079a4faaef7a8592b53aeff34afe67e5b9ae884791a22/","source_url":"https://arxiv.org/abs/2306.13575","text_available":true},{"id":"arxiv:1710.05941","title":"Searching for Activation Functions","date":"2017-10-16","section":"LLMs: architectures, context, training","quality":0.112054,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/8815985e018dbc2066450e5afbb9260b48d5b03a4f41bc23285755ccf3185454/","source_url":"https://arxiv.org/abs/1710.05941","text_available":true},{"id":"arxiv:2606.06574","title":"Skip a Layer or Loop It? Learning Program-of-Layers in LLMs","date":"2026-06-04","section":"LLMs: architectures, context, training","quality":0.192674,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/5abe08b6c82ce9a4010a09d82dbee40f8b4b0f88539bf8911ae36048a97bb917/","source_url":"https://arxiv.org/abs/2606.06574","text_available":true},{"id":"arxiv:2412.13663","title":"Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference","date":"2024-12-18","section":"LLMs: architectures, context, training","quality":0.288117,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/ae6c000a40b751c4486e08fd61f5f7788d8bb57f0838e234e27a5a67f894e923/","source_url":"https://arxiv.org/abs/2412.13663","text_available":true},{"id":"arxiv:2512.14856","title":"T5Gemma 2: Seeing, Reading, and Understanding Longer","date":"2025-12-16","section":"LLMs: architectures, context, training","quality":-0.289423,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/e982edc00d6b6d9e20d11b62004bb8e91131e2d7f717eca944a9914897f273b6/","source_url":"https://arxiv.org/abs/2512.14856","text_available":true},{"id":"arxiv:2407.21783","title":"The Llama 3 Herd of Models","date":"2024-07-31","section":"LLMs: architectures, context, training","quality":0.075302,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/de3cebb4c28bc5d41a843279f219dca14476284991ea5c7c0aeab7068a40e306/","source_url":"https://arxiv.org/abs/2407.21783","text_available":true},{"id":"url:people.idsia.ch/~juergen/most-cited-neural-nets.html","title":"The most cited neural nets of the 20th century (Schmidhuber)","date":"2021-12-01","section":"LLMs: architectures, context, training","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a07ae08185ac4ab008e5384d2dab1a6ce15cf327b9414fb3ccc3afa8e5ac914a/","source_url":"https://people.idsia.ch/~juergen/most-cited-neural-nets.html","text_available":false},{"id":"arxiv:2604.17121","title":"The Topological Trouble With Transformers","date":"2026-04-18","section":"LLMs: architectures, context, training","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/7f9d762bbe192e1208f6d7dc289b7e79c23d4bdde0b1b3999ff5fda55b0dcd1a/","source_url":"https://arxiv.org/abs/2604.17121","text_available":true},{"id":"arxiv:2404.09173","title":"TransformerFAM: Feedback attention is working memory","date":"2024-04-14","section":"LLMs: architectures, context, training","quality":-0.082563,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/cbd04248dee4a37ffe8957d53e0b260196e25a477e8aa86db09efcd9fee74326/","source_url":"https://arxiv.org/abs/2404.09173","text_available":true},{"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: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: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:2608.11676","title":"XBridge: Entity-Grounded Latent Bridge for Heterogeneous LLM Communication","date":"2026-08-12","section":"LLMs: architectures, context, training","quality":0.249727,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a1cbafd1249485a1818a70256d0d3ac5806d55b6900f005e9098c57d37918e44/","source_url":"https://arxiv.org/abs/2608.11676","text_available":true},{"id":"arxiv:2405.04517","title":"xLSTM: Extended Long Short-Term Memory","date":"2024-05-07","section":"LLMs: architectures, context, training","quality":-0.312713,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/40fd3e03894caeb940ad2021fb4052c0d2e809706b5022f7454072997b8ba2d5/","source_url":"https://arxiv.org/abs/2405.04517","text_available":true}],"next":"https://vinnik-dmitry07.github.io/favorite-papers/agents/catalog-2-3.html"}