arXiv Machine Learning
SketchSSM: Write to the Full State, Read from a Compact Sketch
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
5d ago
History Replays Itself: Unleashing Long-Context Capability in Linear Attention
arXiv:2610.15715v1 Announce Type: new Abstract: Linear attention promises the efficiency needed for long-context language modelling, yet its fixed-size recurrent state must simultaneously support ong...
arXiv Machine Learning
Oct 9
Read What Matters: Query-Adaptive Quantization for KV Caches
The paper introduces ReadKV, a query‑adaptive quantization method for KV caches that stores keys and values in progressive codes, allowing each decoding query to allocate different precision prefixes for keys and values. By optimizing a calibrated distortion objective under fixed budgets, ReadKV achieves near‑optimal allocation and demonstrates that query‑dependent access can outperform any query‑independent reader at the same read budget. Experiments on six base models show that reading only four bits on average from an eight‑bit cache increases perplexity by at most 0.66% while reducing logical reads and retained capacity compared to a 16‑bit cache, and it achieves lower latency than existing codecs on an NVIDIA A10G.
arXiv AI
Sep 1
DASC: Decay-Aware State Compression for Hybrid Linear-Attention Serving
arXiv:2608.30386v1 Announce Type: cross Abstract: Hybrid linear-attention architectures have recently scaled to large open-weight models, offering quality competitive with full attention while substa...
arXiv AI
5d ago
GateSight: Recurrent Memory Anticipates Attention Memory for Query-Agnostic KV Eviction in Hybrid LLMs
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 Machine Learning
Sep 24
DeltaS: Reading the Gated Linear Attention State for KV Cache Eviction in Streaming Video
DeltaS is a query‑agnostic, training‑free method for evicting key‑value cache entries in hybrid video‑language models that combine linear and full attention. It uses the change in the recurrent state of gated‑delta linear attention—called state drift—to decide which video chunks to keep, selecting those that induce larger normalized state changes. In experiments with a fixed memory budget, DeltaS outperforms position‑, attention‑, and key‑value‑based eviction signals, improving performance by 2.1 points on average across six long‑video benchmarks and 5.6 points on the longest benchmark, while adding only 1.9% of the forward‑pass cost.
arXiv Computation and Language
5d ago
ReaDy: Recurrent States as Dynamic Context for Speculative Drafting in Hybrid Linear Attention Large Language Models
arXiv:2610.20503v1 Announce Type: new Abstract: Speculative decoding accelerates autoregressive generation by drafting multiple tokens per step, yet feature-based drafters rely on target hidden featu...