Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
Affiliation:
4
0
7
2
A few critical denoising steps in diffusion language models dictate the entire output, and training only these "pivots" dramatically boosts performance.
Achieving 2-3x near-lossless compression of KV caches could revolutionize the efficiency of transformer inference without sacrificing performance.
LLM development is flying blind by ignoring causal inference, leaving models vulnerable to confounding and distribution shifts throughout pretraining, alignment, and evaluation.
Masked diffusion language models can now achieve 21.8x better compute efficiency than autoregressive models, thanks to binary encoding and index shuffling.