Delta N-gram introduces a forward‑only write path into a language model’s native hashed N‑gram table, preserving the pretrained table while adding evidence through a sparse patch Δ. The method uses a 4.1 M‑parameter writer that emits gated targets per event and applies a block‑averaged delta rule to keep each row a convex combination of its old value and the new targets. Experiments on a 0.6 B prototype and Qwen3.8‑Flash‑Next show that the delta writer maintains more document‑specific memory and reduces drift compared to online gradient writes, achieving stable performance over thousands of writes. whyItMatters":"The approach allows continual updates to a language model’s memory without altering its pretrained parameters, enabling efficient, stable, and document‑specific knowledge retention during inference."
arXiv:2610.33025v1 Announce Type: cross Abstract: Letting a language model take gradient steps on the text it is reading, known as dynamic evaluation, lowers its loss on the rest of the document. Its...
arXiv:2609.24635v1 Announce Type: new Abstract: When a language model reads an operation such as "Swap the contents of Box F and Box B", its forward pass writes keys and values for those tokens into...
arXiv:2610.14754v1 Announce Type: new Abstract: Hybrid language models interleave Gated DeltaNet (GDN) layers, whose recurrent memory has a fixed size, with full-attention layers, whose key-value (KV...
arXiv:2607. 27539v2 Announce Type: replace Abstract: Exact deletion from persistent language-model memory depends on whether a record's effect remains addressable after later computation.
arXiv:2607. 27539v1 Announce Type: new Abstract: Exact deletion from persistent language-model memory depends on how that memory represents a record.
A transformer language model performs a bounded amount of computation per token, and recent work by Vishal Sikka, former CEO of Infosys, argues that this bound limits which tasks a model can carry out...
The paper introduces Galahad, a memory layer that stores a transformer language model’s key‑value state for blocks of text, allowing subsequent requests to reuse previously computed attention rather than recomputing it. On seven real‑world datasets, 98.7% of prompt tokens were already read, and with Galahad the model could attend to an entire 97,000‑token corpus, achieving 98–100% recall on a 100‑fact test while reducing inference time and energy consumption dramatically. The approach was validated across 30 models and all runtimes, demonstrating that stateful inference can replace stateless serving without loss of accuracy.
arXiv:2609.06872v1 Announce Type: new Abstract: When a user asks an assistant to forget a record, the test is whether the memory now matches the state it would hold if the record had never been store...
arXiv:2608.30376v1 Announce Type: cross Abstract: Recurrent, attention-free sequence models share a structural weakness: a fading state cannot perform exact recall of something seen once, far in the...
The paper investigates how block‑diffusion language models can use a constant‑size cache to enable efficient parallel decoding. By employing sequence mixers that summarize completed blocks into a reusable state and a block‑causal training objective, the authors pretrain three 3B block‑diffusion denoisers (attention, Mamba, and hybrid) on 300 B tokens. The resulting state‑space cache remains O(1) in memory and latency regardless of context length, yielding significant speed‑up and memory savings compared to traditional attention‑based caches, especially at very long sequences.
The paper investigates how to inject knowledge into addressed memory modules of language models. Using controlled experiments on GPT‑2 and production‑memory tests on Qwen3.8‑Flash‑Next‑FP8 and DeepSeek‑V4.1‑Flash, the authors compare row‑only and row‑plus‑projection updates, with and without fixed module‑residual anchoring. Results show that while anchoring reduces drift, lexical hits do not guarantee entity‑specific retrieval, and first‑token rankings alone do not ensure full answer success, indicating that writable memory is feasible but limited in scope.
The paper introduces LatentPort, a method that allows a language model to transfer its live memory to another model without requiring the receiver to reread the context. Experiments on a Qwen3.5 4B-to-9B sibling pair show that adding a Gated DeltaNet (GDN) persistent-state package reduces negative log‑likelihood by 0.747 nats/token and improves performance across 64 PG19 documents. The study also demonstrates that direct recurrent and convolution reuse outperforms learned GDN maps, and a 434,176‑parameter correction further narrows the performance gap to the native 9B model.