Challenge: Unlike other modalities, speech has unique temporal dependencies, making efficient inference methods unexplored.
Approach: They propose a weighted token merging framework specifically designed for speech-related tasks to improve the trade-off between efficiency and performance.
Outcome: The proposed method achieves state-of-the-art efficiency-performance trade-off on speech-related tasks.

Similar Papers

MERaLiON-AudioLLM: Advancing Speech and Language Understanding for Singapore (2025.acl-demo)

Copied to clipboard

Challenge: MERaLiON-AudioLLM is the first general-purpose audio-based large language model for multitask learning.
Approach: They introduce MERaLiON-AudioLLM, a general-purpose audio-based large language model for multitask learning with a focus on Singlish understanding.
Outcome: The proposed model exhibits strong generalization across a diverse set of tasks . it is a leading solution for region-specific AI applications.
Efficient Inference for Large Vision-Language Models: Bottlenecks, Techniques, and Prospects (2026.findings-acl)

Copied to clipboard

Challenge: Large Vision-Language Models are hindered by a systemic efficiency barrier known as visual token dominance.
Approach: They propose a systematic taxonomy of efficiency techniques structured around the inference lifecycle . they examine visual encoding, prefilling, and decoding to understand bottlenecks .
Outcome: The proposed techniques reveal how upstream decisions dictate downstream bottlenecks . the proposed techniques include hybrid compression and modality-aware decoding .
Token Pruning in Multimodal Large Language Models: Are We Solving the Right Problem? (2025.findings-acl)

Copied to clipboard

Challenge: Multimodal large language models have shown remarkable performance for cross-modal understanding and generation, yet suffer from severe inference costs.
Approach: They propose to prune redundant tokens in MLLMs to reduce computation and storage costs.
Outcome: The proposed method reduces the computational and storage costs of MLLMs by identifying redundant tokens and pruning them.
WavLLM: Towards Robust and Adaptive Speech Large Language Model (2024.findings-emnlp)

Copied to clipboard

Challenge: Recent advances in large language models (LLMs) have expanded their scope to encompass multimodal functions.
Approach: They propose a robust and adaptive speech large language model with dual encoders . they validate the model on universal speech benchmarks and apply it to specialized speech-question-answer datasets based on a CoT approach .
Outcome: The proposed model achieves state-of-the-art performance across a range of speech tasks on the same model size.
LVPruning: An Effective yet Simple Language-Guided Vision Token Pruning Approach for Multi-modal Large Language Models (2025.findings-naacl)

Copied to clipboard

Challenge: Multi-modal Large Language Models (MLLMs) incur significant computational overhead due to the large number of vision tokens processed, limiting their practicality in resource-constrained environments.
Approach: They propose a language-guided vision token pruning method that can be integrated into existing MLLMs with minimal architectural changes.
Outcome: The proposed method reduces vision tokens by 90% and preserves model performance.
AdaptMerge: Inference Time Adaptive Visual and Language-Guided Token Merging for Efficient Large Multimodal Models (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing token reduction methods ignore image complexity and vision-language interactions, ignoring image complexity.
Approach: They propose a training-free, inference-time token merging strategy that adaptively reduces visual tokens by leveraging feature diversity and language-guided relevance.
Outcome: The proposed approach outperforms state-of-the-art token reduction methods on Google’s Gemma 3 models while achieving reduced computational costs and improved performance.
RedApt: An Adaptor for wav2vec 2 EncodingFaster and Smaller Speech Translation without Quality Compromise (2022.findings-emnlp)

Copied to clipboard

Challenge: Pre-trained speech Transformers in speech translation systems have facilitated state-of-the-art (SotA) results, but their computational cost is high.
Approach: They propose a Reducer Adaptor block that could be seamlessly integrated within any Transformer-based speech encoding architecture.
Outcome: The proposed Reducer Adaptor block outperforms the existing SotA architecture by an average of 0.68 BLEU score on 8 language pairs from Must-C.
EffiVLM-BENCH: A Comprehensive Benchmark for Evaluating Training-Free Acceleration in Large Vision-Language Models (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for accelerating Large Vision-Language Models lack comprehensive evaluation across diverse backbones, benchmarks, and metrics.
Approach: They propose EffiVLM-BENCH framework for evaluating absolute performance and generalization and loyalty.
Outcome: The proposed framework offers insights into optimal strategies for accelerating LVLMs.
Massive End-to-end Speech Recognition Models with Time Reduction (2024.naacl-long)

Copied to clipboard

Challenge: Using the neural architecture of Google’s universal speech model, we reduce the frame rate and speed up training and inference.
Approach: They propose to use the neural architecture of Google’s universal speech model with additional funnel pooling layers to significantly reduce the frame rate and speed up training and inference.
Outcome: The proposed methods work with both connectionist temporal classification (CTC) and RNN-Transducer (RNN-T) and over two domains.
LoPT: Lossless Parallel Tokenization Acceleration for Long Context Inference of Large Language Model (2026.acl-long)

Copied to clipboard

Challenge: Existing parallel tokenization methods suffer from inconsistent results due to boundary artifacts that occur after merging.
Approach: They propose a Lossless Parallel Tokenization framework that ensures output identical to standard sequential tokenization.
Outcome: The proposed method achieves significant speedup while guaranteeing lossless tokenization.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations