| Challenge: | Large language models (LLMs) require massive GPU memory due to their size and parameter count. |
| Approach: | They propose to use anchor-based self-attention network and anchor-basic inference strategy to compress sequence information into an anchor token, reducing the keys/values cache and enhancing inference efficiency. |
| Outcome: | The proposed model reduces the key/value cache and improves inference efficiency by 99% while maintaining similar accuracy levels. |
Similar Papers
LLM in a flash: Efficient Large Language Model Inference with Limited Memory (2024.acl-long)
Copied to clipboard
Keivan Alizadeh, Seyed Iman Mirzadeh, Dmitry Belenko, S. Khatamifard, Minsik Cho, Carlo C Del Mundo, Mohammad Rastegari, Mehrdad Farajtabar
| Challenge: | Large language models (LLMs) have high computational and memory requirements, especially for devices with limited memory. |
| Approach: | They propose a method that stores model parameters in flash memory but brings them on demand to DRAM . authors propose two techniques to optimize for reading data in larger, more contiguous chunks . |
| Outcome: | The proposed method reduces the volume of data transferred from flash and reads data in larger, more contiguous chunks. |
HMT: Hierarchical Memory Transformer for Efficient Long Context Language Processing (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing models that memorize past tokens have “flat” memory architectures that restrict the context window. |
| Approach: | They propose a framework that imitates human memorization behavior by preserving tokens from early input segments, passing memory embeddings along the sequence, and recalling relevant information from history. |
| Outcome: | The proposed framework outperforms existing models in language modeling and question-answering tasks and achieves comparable or superior generation quality to long-context models with 2 57 fewer parameters and 2.5 116 less inference memory. |
Text or Pixels? Evaluating Efficiency and Understanding of LLMs with Visual Text Inputs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | *visual text representations* are a practical and surprisingly effective form of input compression for decoder LLMs. |
| Approach: | They exploit visual representations to render long text inputs as a single image and provide it directly to the model. |
| Outcome: | The proposed method reduces token usage while preserving performance. |
Draft
& Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods for accelerating Large Language Models have been criticized for their inference costs and inefficient decoding. |
| Approach: | They propose a self-speculative decoding approach for accelerating Large Language Models without an auxiliary model. |
| Outcome: | The proposed method achieves a speedup of up to 1.99 with no additional neural network training and no extra memory footprint. |
Embedding-Informed Adaptive Retrieval-Augmented Generation of Large Language Models (2025.coling-main)
Copied to clipboard
| Challenge: | Retrieval-augmented large language models excel in various NLP tasks but are not always helpful when the knowledge required is absent in the model. |
| Approach: | They propose to determine whether the model is knowledgeable on a query via inspecting the (contextualized) pre-trained token embeddings of LLMs. |
| Outcome: | Experiments show that the proposed approach performs better than previous approaches on various benchmarks. |
ARL2: Aligning Retrievers with Black-box Large Language Models via Self-guided Adaptive Relevance Labeling (2024.acl-long)
Copied to clipboard
| Challenge: | Existing retrievers are misaligned with large language models due to separate training processes and inherent black-box nature of LLMs. |
| Approach: | They propose a retriever learning technique that harnesses LLMs as labelers to annotate and score adaptive relevance evidence. |
| Outcome: | Extensive experiments show that ARL2 improves accuracy and reduces the cost of API calls. |
Llama2Vec: Unsupervised Adaptation of Large Language Models for Dense Retrieval (2024.acl-long)
Copied to clipboard
| Challenge: | Dense retrieval requires discriminative embeddings to represent the semantic relationship between query and document. |
| Approach: | They propose an unsupervised approach that performs unsupervised adaptation of large language models for dense retrieval. |
| Outcome: | The proposed model improves on a variety of dense retrieval benchmarks and is available on github. |
Large Language Models as Foundations for Next-Gen Dense Retrieval: A Comprehensive Empirical Assessment (2024.emnlp-main)
Copied to clipboard
| Challenge: | Pre-trained language models have limited generalization capabilities and performance challenges. |
| Approach: | They evaluate 15 different backbone LLMs and non-LLMs to evaluate their performance . larger models and extensive pre-training consistently enhance in-domain accuracy and data efficiency . |
| Outcome: | The results show that larger models and extensive pre-training enhance in-domain accuracy and data efficiency. |
AnchorMem: Anchored Facts with Associative Contexts for Building Memory in Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing memory systems rely on summarization to preserve contextual nuances and obscuring key retrieval features. |
| Approach: | They propose a method that decouples the retrieval unit from the generation context. |
| Outcome: | The proposed method outperforms baseline models on the LoCoMo benchmark. |
RaaS: Reasoning-Aware Attention Sparsity for Efficient LLM Reasoning (2025.findings-acl)
Copied to clipboard
Junhao Hu, Wenrui Huang, Weidong Wang, Zhenwen Li, Tiancheng Hu, Zhixia Liu, Xusheng Chen, Tao Xie, Yizhou Shan
| Challenge: | Large Language Models (LLMs) have demonstrated strong capabilities across various domains, but their large-scale deployment faces a major obstacle: the high computational cost of long-sequence inference. |
| Approach: | They propose an algorithm that retains key-value vectors until they are no longer needed to solve reasoning tasks. |
| Outcome: | The proposed algorithm achieves high accuracy with O(L) time but O(N) memory complexities. |