3 papers indexed here
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Looped Language Models (LoopLMs) improve parameter efficiency by recursively reusing shared Transformer modules, yet their repeated computation over evolving recurrent states poses new challenges for low-bit deployment. Existing post-training quantization (PTQ) methods, largely designed for feed-forward Transformers, f...
All for 1-Bit (AF1) is proposed, a genuine 1-bit PTQ framework for LLMs that consistently outperforms existing binarization-based PTQ methods in perplexity and zero-shot accuracy, providing a practical path toward deployable genuine 1-bit compression for LLMs.
ACE is proposed, a training-free, calibration-free, and checkpoint-preserving framework for token-adaptive expert skipping in MoE-based LLMs that consistently outperforms existing static and dynamic baselines.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
