KV cache eviction must decide which entries carry information that the rest of the cache can no longer supply. A natural way to estimate this is a learnable gate: give each cached entry a gate on its attention weight and train the gate on the model's own objective. The gate belongs inside the normalizing softmax, where...
Hao Gu, Xin-Tong Yang, Zhi-Wei Li et al.· 0 citations
EC-MobiLLM adopts a server-assisted side-tuning paradigm to minimize on-device overhead and pioneers non-blocking asynchronous collaboration to accelerate training, and introduces adaptive feature alignment to support collaboration across heterogeneous backbones, aligning with practical needs in real-world deployments.
Xing-Ke Yang, Liang Li, Si-Cong Li et al.· 3 citations
Proxy Manifold Alignment (PMA), a novel attack against E2EO in privacy-preserving LLMs, which employs Word2Vec to model the co-occurrence patterns within the obfuscated stream and the public corpus independently, and constructs two proxy vector embeddings.
Si-Cong Li, Ling-Feng Yao, Xing-Ke Yang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.