new

Get trending papers in your email inbox once a day!

Get trending papers in your email inbox!

Daily Papers

byAK and the research community

Sep 27

Submitted by

akhaliq

QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models

·
9 authors

Submitted by

akhaliq

LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models

·
20 authors

Submitted by

akhaliq

DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models

·
7 authors

Submitted by

akhaliq

Efficient Post-training Quantization with FP8 Formats

·
6 authors

2

Submitted by

akhaliq

Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models

·
8 authors