LLMs: architectures, context, training — page 1

• 2 OLMo 2 Furious
  arxiv:2501.00656 · 2024-12-31 · text available
• A Hippocampus for Linear Attention: An Exact Memory for What the Recurrent State Forgets
  arxiv:2607.02303 · 2026-07-02 · text available
• Beyond Scattered Acceptance: Fast and Coherent Inference for DLMs via Longest Stable Prefixes
  arxiv:2603.05454 · 2026-03-05 · text available
• Bitune: Leveraging Bidirectional Attention to Improve Decoder-Only LLMs
  arxiv:2405.14862 · 2024-05-23 · text available
• Cache-to-Cache: Direct Semantic Communication Between Large Language Models
  arxiv:2510.03215 · 2025-10-03 · text available
• Code Llama: Open Foundation Models for Code
  url:ai.meta.com/research/publications/code-llama-open-foundation-models-for-code · 2023-08-24 · metadata only
• Communicating Activations Between Language Model Agents
  arxiv:2501.14082 · 2025-01-23 · text available
• Continuous Autoregressive Language Models
  arxiv:2510.27688 · 2025-10-31 · text available
• Continuous Thought Machines
  url:pub.sakana.ai/ctm · 2025-05-08 · metadata only
• Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse
  arxiv:2608.03893 · 2026-08-04 · text available
• DiffusionGemma Technical Report
  arxiv:2608.00146 · 2026-07-31 · text available
• DMax: Aggressive Parallel Decoding for dLLMs
  arxiv:2604.08302 · 2026-04-09 · text available
• Enabling Agents to Communicate Entirely in Latent Space
  arxiv:2511.09149 · 2025-11-12 · text available
• Encoder-Decoder Gemma: Improving the Quality-Efficiency Trade-Off via Adaptation
  arxiv:2504.06225 · 2025-04-08 · text available
• Encoder-Decoder or Decoder-Only? Revisiting Encoder-Decoder Large Language Model
  arxiv:2510.26622 · 2025-10-30 · text available
• Energy Transformer
  arxiv:2302.07253 · 2023-02-14 · text available
• Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks
  arxiv:2311.06242 · 2023-11-10 · text available
• GLU Variants Improve Transformer
  arxiv:2002.05202 · 2020-02-12 · text available
• Hierarchical Latent Prediction for Language Models
  arxiv:2608.05806 · 2026-08-06 · text available
• Hyena Hierarchy: Towards Larger Convolutional Language Models
  arxiv:2302.10866 · 2023-02-21 · text available
• Language Is Not All You Need: Aligning Perception with Language Models
  arxiv:2302.14045 · 2023-02-27 · text available
• Language Models Can Control Their Own Attention
  arxiv:2609.02737 · 2026-09-02 · text available
• Large Concept Models: Language Modeling in a Sentence Representation Space
  url:ai.meta.com/research/publications/large-concept-models-language-modeling-in-a-sentence-representation-space · 2024-12-11 · metadata only
• Large Language Diffusion Models
  arxiv:2502.09992 · 2025-02-14 · text available