Papers with real-time applications
Task-driven Layerwise Additive Activation Intervention (2025.naacl-short)
Copied to clipboard
| Challenge: | Existing approaches to task adaptation rely heavily on heuristic rules or prompt inputs. |
| Approach: | They propose a layer-wise additive activation intervention framework that steers the LMs’ generation process by identifying and manipulating the activations. |
| Outcome: | The proposed framework improves the accuracy of pretrained LMs and competing baselines on various datasets, demonstrating improvements in the accuracy and sample efficiency of the proposed framework. |
LLMs on a Budget? Say HOLA (2025.emnlp-industry)
Copied to clipboard
Zohaib Hasan Siddiqui, Jiechao Gao, Ebad Shabbir, Mohammad Anas Azeez, Rafiq Ali, Gautam Siddharth Kashyap, Usman Naseem
| Challenge: | Current solutions such as quantization, pruning, and Retrieval-Augmented Generation (RAG) offer only partial optimizations and often sacrifice accuracy, speed, or generality. |
| Approach: | They propose an end-to-end optimization framework for efficient LLM deployment . it leverages Hierarchical Speculative Decoding (HSD) for faster inference without quality loss. |
| Outcome: | HOLA delivers +17.6% EMA on GSM8K, +10.5% MCA on ARC, and reduced latency and memory on edge devices like Jetson Nano. |
Visual Editing with LLM-based Tool Chaining: An Efficient Distillation Approach for Real-Time Applications (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Using natural language as an interaction medium for video editing can mitigate the complexity of video editing. |
| Approach: | They propose a method to fine-tune LLMs for invoking tools in real-time applications by interpreting user stylistic requests in natural language. |
| Outcome: | The proposed model matches the performance of the teacher model significantly, reducing costs and latency. |
PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to reduce memory usage for large language models neglect inter-layer dependency between layers and huge memory consumption in pre-computation. |
| Approach: | They propose a method that compresses the KV cache by layer-wise retaining crucial context. |
| Outcome: | The proposed method reduces memory usage by layer-wise retaining crucial context . it can improve 2.2x throughput compared to Accelerate with over 54% memory reduction . |
DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference (2020.acl-main)
Copied to clipboard
| Challenge: | Large-scale pre-trained language models such as BERT are notorious for being slow in both training and inference. |
| Approach: | They propose a method to accelerate BERT inference by inserting extra classification layers between each transformer layer of BERT. |
| Outcome: | The proposed method saves up to 40% inference time with minimal degradation in model quality. |
A Generic Method for Fine-grained Category Discovery in Natural Language Texts (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for fine-grained category discovery neglect semantic similarities of fine-grain categories. |
| Approach: | They propose a method that detects fine-grained clusters of semantically similar texts guided by a novel objective function. |
| Outcome: | The proposed method surpasses state-of-the-art methods on three benchmark tasks. |
Meta-KD: A Meta Knowledge Distillation Framework for Language Model Compression across Domains (2021.acl-long)
Copied to clipboard
| Challenge: | Pre-trained language models have been successful in NLP tasks, but their large size and long inference time limit their deployment in real-time applications. |
| Approach: | They propose a meta-teacher model that captures transferable knowledge across domains and passes it to students. |
| Outcome: | The proposed model can distill large teacher models into small student models with guidance from the meta-teacher. |
StreamVoice: Streamable Context-Aware Language Modeling for Real-time Zero-Shot Voice Conversion (2024.acl-long)
Copied to clipboard
| Challenge: | Existing LM-based VC models require offline conversion from source semantics to acoustic features, limiting their deployment to real-time applications. |
| Approach: | They propose a streaming LM-based model for zero-shot voice conversion that uses a fully causal context-aware LM with a temporal-independent acoustic predictor to facilitate real-time conversion given arbitrary speaker prompts and source speech. |
| Outcome: | The proposed model achieves comparable performance to non-streaming VC systems while maintaining a fully causal context-aware LM with a temporal-independent acoustic predictor. |
Decoding at the Speed of Thought: Harnessing Parallel Decoding of Lexical Units for LLMs (2024.lrec-main)
Copied to clipboard
Chenxi Sun, Hongzhi Zhang, Zijia Lin, Jingyuan Zhang, Fuzheng Zhang, Zhongyuan Wang, Bin Chen, Chengru Song, Di Zhang, Kun Gai, Deyi Xiong
| Challenge: | Large language models have demonstrated exceptional capability in natural language understanding and generation, but their generation speed is limited by the inherently sequential nature of their decoding process. |
| Approach: | They propose a method that accelerates decoding process without sacrificing quality . they propose lexical unit decoding, which can be integrated with other methods . |
| Outcome: | The proposed method significantly reduces decoding time while maintaining quality while maintaining output quality. |
Knowledge Distillation with Reptile Meta-Learning for Pretrained Language Model Compression (2022.coling-1)
Copied to clipboard
| Challenge: | Knowledge distillation (KD) can transfer knowledge from the original model into a compact model to achieve model compression. |
| Approach: | They propose a knowledge distillation method with reptile meta-learning to facilitate the transfer of knowledge from the teacher to the student. |
| Outcome: | Extensive experiments on the GLUE benchmark show the proposed method performs better than previous methods. |
Incremental Transformer: Efficient Encoder for Incremented Text Over MRC and Conversation Tasks (2025.coling-main)
Copied to clipboard
| Challenge: | Existing encoders that encode incremented inputs have to re-encode the whole text to obtain the encoding of the extended input. |
| Approach: | They propose an efficient encoder dedicated for faster encoding of incremented input . it takes only added input as input but attends to cached representations of original input a lower layer . |
| Outcome: | The proposed encoder achieves 6.2x speedup over current encoders . it takes only added input as input but attends to cached representations of original input . |
Phonotomizer: A Compact, Unsupervised, Online Training Approach to Real-Time, Multilingual Phonetic Segmentation (2025.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to phonetic segmentation are hierarchical and end-to-end . many mistakes in final output stem from subtle segmenter perturbations . |
| Approach: | They propose a phonetic segmentation system that trains on raw sound files alone . it can modulate computational exactness and reduce acoustic model size, they argue . |
| Outcome: | The proposed method reduces the size of the acoustic model and training epochs. |
MARIO-0.5B: A Multi-Agent Lightweight Model for Real-Time Open Information Extraction in Low-Resource Settings (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models have shown remarkable capabilities in open information extraction, but their resource requirements often restrict their deployment in resource-constrained industrial settings. |
| Approach: | They introduce an ultra-lightweight large language model trained on instruction-based samples in Chinese, English, Korean, and Russian. |
| Outcome: | The proposed model outperforms large-scale models with up to 70B parameters, reducing computational resources by 140x and delivering 11x faster response times. |
Mitigating Sequential Dependencies: A Survey of Algorithms and Systems for Generation-Refinement Frameworks in Autoregressive Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Sequential dependencies present a fundamental bottleneck in deploying large-scale autoregressive models . |
| Approach: | They analyze methods based on generation strategies and refinement mechanisms . they examine deployment strategies across computing environments and explore applications spanning text, images, and speech generation. |
| Outcome: | The proposed frameworks can be used to improve the quality of autoregressive models. |
Fast, Not Fancy: Rethinking G2P with Rich Data and Statistical Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | specific disambiguation strategies introduce additional latency, making them unsuitable for real-time applications. |
| Approach: | They propose a semi-automated pipeline for constructing homograph-focused datasets . they introduce a HomoRich dataset and advocate for a paradigm shift . |
| Outcome: | The proposed pipeline improves a state-of-the-art deep learning-based G2P system for Persian. |
Robust Utility-Preserving Text Anonymization Based on Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Existing techniques face challenges of re-identification ability of large language models . anonymizing text that contains sensitive information is crucial for a wide range of applications . |
| Approach: | They propose a framework that integrates three key LLM components to perform anonymization. |
| Outcome: | The proposed model outperforms baselines while maintaining greater data utility in downstream tasks. |