arXiv:2607. 02980v1 Announce Type: cross Abstract: Scaling modern large language models (LLMs) to long contexts is limited by the quadratic computation cost, and poor length extrapolation of dense attention.
By Xiang Hu, Xinyu Wei, Hao Gu, Minshen Zhang, Tian Liang, Huayang Li, Lei Zhu, Yan Wang, Sirui Han, Yushi Bai, Kewei Tu, Haitao Mi, Leo Liang
RPMem introduces a two‑stage architecture that compiles each session into a model‑independent latent memory and then consolidates it with retained memory via a task‑trained recurrent gate. The consolidated memory is mapped to backbone‑specific low‑rank adaptation (LoRA) parameters, enabling the memory to transfer when the backbone is replaced. Across three long‑term memory benchmarks and five diverse backbones, RPMem achieves broad generalization with near‑constant update cost and memory footprint, outperforming existing parametric and text‑based baselines on the PERMA benchmark.
By Fanyu Zhao, Ruike Cao, Liang Dong, Fugen Yao, Jian Xu, Guanjun Jiang, Han Zhang, Yifei Zhao, Yinsheng Li
arXiv:2606. 13115v1 Announce Type: cross Abstract: While Large Language Models (LLMs) have advanced open-domain dialogue systems, maintaining long-term consistency remains a challenge due to inherent limitations in long-context reasoning and the inefficiency of processing extensive raw text.
By Minjun Choi, Yoonjin Jang, Sangwon Youn, Youngjoong Ko
The paper investigates how attention dynamics evolve across recurrent depth in language models, finding that attention support stabilizes early while hidden states and outputs take longer. It proposes WISE, a training‑free method that uses full attention in early steps and then reuses the discovered sparse working set for later steps, preserving performance on multi‑hop QA tasks. Experiments show that WISE maintains quality up to 2K context, offers measurable speedups, and highlights the importance of recurrent discovery of attention support.
By Ke Wan, Chen Chen
The paper introduces a family of adapters that enhance language model reasoning by adding selective state-space control at token and context levels. The token-level MaLoRA makes the adapter’s scaling factor dynamic and recurrent, improving over static low‑rank adaptation. The context-level MaRA tracks cross‑segment reasoning state and retrieves relevant segments, outperforming an eight‑billion‑parameter dense retriever and boosting reasoning accuracy by an average of +6.4 F1 over LoRA.
By Atahan Dokme, Larry Heck
arXiv:2609.36529v1 Announce Type: new
Abstract: Recurrent neural networks (RNNs) compress the historical context into a memory state of fixed size, thus allowing for constant-time inference. The memo...
By Oliver Sieberling, Bharat Runwal, David Jin, Ryan Chin, Rameswar Panda, Yoon Kim