The paper introduces DAMP, a decay‑aware mixed‑precision quantization scheme for recurrent‑state representations in GDN and KDA language models. By identifying high‑risk channels through quantization‑error energy and decay persistence, DAMP stores these channels at higher precision while compressing the rest to INT8, achieving a 9.9‑bit average precision. Experiments on Qwen3.6‑35B and Kimi‑Linear‑48B show a 69.1% reduction in recurrent‑state storage, up to 2.01× faster state‑update kernels, and up to 10.9% lower full‑model TPOT while preserving accuracy close to the FP32 baseline.
By Tao Zhang, Jianchao Tan, Pingwei Sun, Yanqi Yu, Zixu Jiang, Yuchen Xie, Xunliang Cai, Ziqian Zeng
The paper introduces CHASE, a cache‑hole‑adapted skip‑exit mechanism for looped state‑space language models, specifically Looped Mamba and Looped Hybrid Mamba‑Transformer. It shows that looping these architectures improves performance on controlled reasoning tasks and remains competitive in pre‑training benchmarks while using fewer distinct parameters. The cache‑hole adaptation allows selective skipping of recurrent steps during inference, maintaining perplexity close to full computation and achieving significant speedups.
By Zhenxuan Yu, Takeshi Kojima, Yutaka Matsuo, Yusuke Iwasawa
arXiv:2609.26708v1 Announce Type: new
Abstract: Quantization-aware distillation (QAD) restores much of the short-form question-answering performance lost to sub-3-bit quantization, yet leaves mathema...
By Yuanteng Chen, Zhilei Liu, Peisong Wang, Yuantian Shao, Chuangyi Li, Weining Wang, Shuang Qiu, Gang Li, Jing Liu, Jian Cheng
arXiv:2607. 03876v1 Announce Type: new Abstract: With the rise of small quantized GGUF-based language models and their increasing use for on-device inference tasks, we have seen the growing need for an approach capable of reliably delivering these models at scale even under severe memory bandwidth constraints such as those imposed by pure CPU implementations.
By Sadra Saremi
arXiv:2607. 03574v1 Announce Type: cross Abstract: AI systems increasingly propose executable scientific models whose value depends on both their symbolic structure and their fitted continuous parameters.
By Lucas Sheneman
arXiv:2601.14945v3 Announce Type: replace-cross
Abstract: Large-scale Vision-Language-Action (VLA) models offer semantic generalization but suffer from high inference latency because they adopt a low...
By Yuteng Sun, Haoran Wang, Ruofei Bai, Zhengguo Li, Jun Li, Meng Yee Michael Chuah, Wei Yun Yau