Hugging Face Trending Papers
Enabling Dynamic Computation in Looped LMs
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv AI
Sep 16
Comparative Characterization of KV Cache Management Strategies for LLM Inference
arXiv:2604.05012v2 Announce Type: replace-cross Abstract: Efficient inference with Large Language Models (LLMs) increasingly relies on Key-Value (KV) caches to store previously computed key and value...
arXiv AI
Sep 1
KV Admission: Learning What to Write for Efficient Long-Context LLM Inference
arXiv:2512.17452v4 Announce Type: replace-cross Abstract: Long-context LLM inference is bottlenecked by the quadratic attention complexity and linear Key-Value (KV) cache growth. Prior approaches mit...
arXiv Machine Learning
Jul 31
Back from the Future: Key-Value Cache Management by Counter-Causal Surprise
arXiv:2607. 27600v1 Announce Type: new Abstract: Key-value (KV) cache management through compression and eviction strategies has emerged as an important research direction in recent years.
arXiv AI
Sep 15
T-LoopFormer: Token-Level Elastic-Depth Looped Transformers for Latent Reasoning With Dynamic Routing
arXiv:2609.15160v1 Announce Type: new Abstract: Looped Transformers have recently demonstrated strong performance in both reasoning and language tasks by reusing a shared set of parameters across mul...
arXiv AI
Aug 14
vToken: Token-Level Virtualization for Reclaimable KV Caches
arXiv:2608. 13263v1 Announce Type: new Abstract: Large language model serving faces a critical memory bottleneck: the KV cache grows with sequence length and batch size.
arXiv Machine Learning
Oct 28
LSTM-Style Looped Transformers with Shared KV Caches
The paper introduces an LSTM-style transformer that shares a single key–value cache across its recurrent core, reducing parameters by 40.4% compared to an untied model while keeping forward FLOPs similar. It aligns parallel and continuation training passes with a consistency loss, eliminating 81–89% of the continuation‑loss penalty on FineWeb. Experiments across multiple widths and token budgets show that weight tying incurs the smallest loss cost at lower token budgets, highlighting its potential for data‑ and storage‑constrained settings.