#language-models
- A Systematic Analysis of Hybrid Linear Attention: 72-Model Study ByteDance Seed research
- Program-as-Weights: Compile-Once Adapter Paradigm Matches 32B Models at 1/50 the Memory research
- Hidden Decoding at Scale: A New Axis for LLM Capacity Without Backbone Growth research
- LLM-Driven Formal Mathematics Review: Where Current Systems Fall Short UCLA research
- Cola DLM: Continuous Latent Diffusion Language Model with Competitive Scaling research
- Formalizing Latent Thoughts: Axiomatic Framework for Evaluating LLM Reasoning Representations University of British Columbia research