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
arXiv:2607. 07953v1 Announce Type: cross Abstract: Self-attention lets each token retrieve information from the full context, but its quadratic cost in sequence length limits training and inference at long context.
By Tommaso Cerruti, Tim Rieder, George Rowlands, Lingfeng Jin, Imanol Schlag
arXiv:2603. 22016v3 Announce Type: replace-cross Abstract: Large Reasoning Models (LRMs) often reach a correct solution before their long Chain-of-Thought trace ends, yet continue with redundant verification, repeated attempts, or unnecessary exploration that wastes computation and can even overturn the correct answer.
By Xinyan Wang, Xiaogeng Liu, Ming Pei, Chaowei Xiao
arXiv:2609.38169v1 Announce Type: cross
Abstract: Linear attention replaces growing KV caches with fixed-size recurrent states, yet these persistent states can become a substantial memory bottleneck...
By Bingchen Yao, Haobo Xu, Haokun Lin, Yichen Wu, Ziyu Guo, Renrui Zhang, Zhichao Lu, Zhenan Sun, Ying Wei
arXiv:2609.13458v1 Announce Type: cross
Abstract: Embodied language grounding requires more than identifying the referent of an instruction: recovered semantics must also control the action an agent...
By Baosheng Jin, Yushen Liang, Hua Shen
arXiv:2607. 10110v1 Announce Type: new Abstract: Recent work on looped language models suggests that many reasoning problems benefit from greater computational depth rather than from additional independent parameters.
By Zhenxuan Yu, Takeshi Kojima, Yutaka Matsuo, Yusuke Iwasawa
arXiv:2606. 17511v1 Announce Type: cross Abstract: Robot learning and embodied agents now require simulation to serve as a shared execution substrate linking control, skills, and planning, not only as a renderer, controller testbed, or fixed task environment.
By Haoran Lu, Songling Liu, Yue Chen, Guo Ye, Mutian Shen, Shuyang Yu, Yu Xiao, Jihai Zhao, Shang Wu, Jianshu Zhang, Xiangtian Gui, Chuye Hong, Yuran Wang, Maojiang Su, Jiayi Wang, Ruihai Wu, Zhaoran Wang, Han Liu