arXiv:2603. 23571v2 Announce Type: replace-cross Abstract: Effective navigation intelligence relies on long-term memory to support both immediate generalization and sustained adaptation.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
arXiv:2608. 12435v1 Announce Type: new Abstract: Transformers owe much of their strong long-context retrieval capability to a token-level memory that grows with context length.
arXiv:2609.32453v2 Announce Type: replace-cross Abstract: Robotic manipulation is inherently history-dependent, yet most pretrained robotic policies condition on only the current observation or a sho...
arXiv:2607. 11614v1 Announce Type: cross Abstract: Extending the context length of large language models (LLMs) is critical for many real-world applications, yet standard transformers remain constrained by quadratic compute and linear memory scaling.
The paper introduces Navigation World Models (NWMs) that predict action‑conditioned visual futures for planning. It examines two key design challenges: choosing an effective visual representation and efficiently modeling observation history for repeated queries. The authors propose a conditional flow‑transformer framework, compare five frozen visual representations, and develop Cached‑Linear and Balanced GDN architectures to reduce redundant history computation and improve memory usage, demonstrating their effectiveness on RECON, SACSoN, and SCAND benchmarks.
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.
arXiv:2607. 25357v1 Announce Type: cross Abstract: Long-context recall in linear-time sequence models highlights a tradeoff in how they write to memory.