paper-with-me

Papers

Text Compression for Efficient Language Generation

2025-03-14 · David Gu, Peter Belcak, Roger Wattenhofer

We challenge the prevailing assumption that LLMs must rely fully on sub-word tokens for high-quality text generation. To this end, we propose the "Generative Pretrained Thoughtformer" (GPTHF), a hierarchical transformer language model capable of text generation by compressing text into sentence embeddings and employing a sentence attention mechanism. GPTHF retains GPT's architecture, modifying only token interactions via dynamic sparse attention masks. Our experiments show that GPTHF achieves an up to an order of magnitude improvement in FLOPs efficiency and a threefold increase in runtime speed compared to equally-sized GPT models in the low-size regime. This is achieved through a unique generation method that caches and reuses sentence embeddings, allowing significant portions of the input to bypass large parts of the network.

📄 PDF Abstract BibTeX arXiv:2503.11426

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingSentenceSentence EmbeddingsText CompressionText Generation

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Linear Warmup With Cosine Annealing Linear Warmup With Cosine Annealing is a learning rate schedule where we increase the learning rate linearly for $n$ updates and then anneal according to a cosine schedule…
Adam 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Can LLMs Maintain Fundamental Abilities under KV Cache Compression?

2025-02-04 · Xiang Liu, Zhenheng Tang, Hong Chen, Peijie Dong 외

This paper investigates an underexplored challenge in large language models (LLMs): the impact of KV cache compression methods on LLMs' fundamental capabilities. Although existing methods achieve impressive compression r…

Arithmetic ReasoningCode GenerationLong-Context UnderstandingSensitivity+1

From Retrieved Context to Runtime Control: Adaptive Compression for Edge-based RAG

2026-08-20 · Zlatan Feric, Amir Taherin, Yanzhi Wang, David Kaeli arxiv

Retrieval-augmented generation (RAG) improves language-model responses by grounding generation in external passages, which comes with overhead: retrieved context lengthens the prompt, increasing prefill work, KV-cache fo…

Natural Questions

AttnComp: Attention-Guided Adaptive Context Compression for Retrieval-Augmented Generation

2025-09-22 · Lvzhou Luo, Yixuan Cao, Ping Luo arxiv

Retrieval-augmented generation improves the factual accuracy of Large Language Models (LLMs) by incorporating external context, but often suffers from irrelevant retrieved content that hinders effectiveness. Context comp…

Q-Filters: Leveraging QK Geometry for Efficient KV Cache Compression

2025-03-04 · Nathan Godey, Alessio Devoto, Yu Zhao, Simone Scardapane 외

Autoregressive language models rely on a Key-Value (KV) Cache, which avoids re-computing past hidden states during generation, making it faster. As model sizes and context lengths grow, the KV Cache becomes a significant…

Text Generation

HiTVideo: Hierarchical Tokenizers for Enhancing Text-to-Video Generation with Autoregressive Large Language Models

2025-03-14 · Ziqin Zhou, Yifan Yang, Yuqing Yang, Tianyu He 외

Text-to-video generation poses significant challenges due to the inherent complexity of video data, which spans both temporal and spatial dimensions. It introduces additional redundancy, abrupt variations, and a domain g…

Text-to-Video GenerationVideo Generation