MétaCan
← all works

Generative Adversarial Networks

2014· preprint· en· 4,572 citations· W4298289240 on OpenAlex· 10.48550/arxiv.1406.2661

Why is this work in the frame?

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

Canadian funderA Canadian agency funded it. The work may carry no Canadian affiliation at all.

No Canadian affiliation. An affiliation-only frame — the usual design — would never have seen this work. It is one of the works that make the case for inverting the frame.

Abstract

Large Language Models (LLMS) rely on Key-Value (KV) caches to store attention context during autoregressive decoding. In long-sequence settings, the KV cache can consume large amounts of VRAM and become a practical bottleneck for throughput . We introduce KVHALO, an auxiliary reconstruction model that restores higher-fidelity KV tensors from a compressed cache state when required, reducing persistent memory footprint during inference. In our evaluation, KVHALO achieves up to 91.85% directional cosine alignment at convergence and reduces long-context degradation relative to a low-bit baseline under our stress-test workloads. We used HRM instead of other architectures, which allowed for higher-quality results in only 18,600 steps.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

The record

Venue
arXiv (Cornell University)
Topic
Generative Adversarial Networks and Image Synthesis
Field
Computer Science
Canadian institutions
Funders
Compute CanadaCanada Research ChairsCanadian Institute for Advanced Research
Keywords
Discriminative modelMinimaxComputer scienceInferenceArtificial intelligencePerceptronGenerative grammarMachine learningSample (material)Generative modelMistakeArtificial neural networkMathematical optimizationMathematics
Has abstract in OpenAlex
yes