Prompt Compression via Activation Aggregation
arXiv:2607.08399v1 Announce Type: new Abstract: Large language models process prompts by propagating activations through dozens of layers before generating a response. We ask whether the…
Read the full articleYou might also wanna read
PromptEmbedder: A Dual-LLM Framework for Efficient, Architecture-Agnostic Text Embedding
Large Language Models (LLMs) have demonstrated remarkable efficacy in text embedding, yet current adaptation methods like LoRA face signific
arxiv.org·1mo ago
RAGP: A Graph-Based Prompt Compression Method Using Lévy Walk-Guided Pruning
Existing prompt compression methods treat text as flat token sequences, failing to capture the distributed nature of important information,
arxiv.org·7d ago
LK Losses: A New Training Objective to Optimize Acceptance Rate in Speculative Decoding for LLMs
Speculative decoding accelerates autoregressive large language model (LLM) inference by using a lightweight draft model to propose candidate
arxiv.org·1mo ago
Expected Attention: KV Cache Compression Method for Efficient LLM Inference
Memory consumption of the Key-Value (KV) cache represents a major bottleneck for efficient large language model inference. While attention-s
arxiv.org·9mo ago
Research Proves Transformer Language Models Are Injective and Invertible
Transformer components such as non-linear activations and normalization are inherently non-injective, suggesting that different inputs could
arxiv.org·8mo ago
Fast-dLLM: Training-Free Acceleration Method for Diffusion Language Models Using KV Cache and Parallel Decoding
Diffusion-based large language models (Diffusion LLMs) have shown promise for non-autoregressive text generation with parallel decoding capa
arxiv.org·8mo ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.