The paper introduces a compression framework for the Whisper automatic speech recognition model that jointly optimizes six deployment dimensions—model size, temporal resolution, encoder token stride, low‑rank adaptation capacity, weight precision, and sparsity pattern—using NSGA‑III. The optimization targets three objectives: word error rate, inference FLOPs, and memory footprint. Evaluating 1,680 configurations, the study identifies compression combinations that outperform single‑axis scaling and notes that 1:4 structured sparsity cannot maintain acceptable accuracy within the tested budgets.
By Vyom Agarwal, Mokshda Gangrade, Siddharth Pal, Jerry Wu
arXiv:2609.38106v1 Announce Type: cross
Abstract: Speech-LLMs are expensive to run, making compression important for real-world deployment. However, compressed models are usually selected using aggre...
By Ganesh Pavan Kartikeya Bharadwaj Kolluri, Michael Kampouridis, Ravi Shekhar
arXiv:2607. 18280v1 Announce Type: cross Abstract: Large language models (LLMs) are often compressed through static parameter pruning or dynamic token-level computation, yet aggressive sparsification can trigger rapid performance degradation beyond an essential sparsity boundary.
By Chao Han, Haozhe Hu, Xiaoyu Shen
arXiv:2509. 14230v2 Announce Type: replace Abstract: While structured pruning presents a highly effective pathway for accelerating Large Language Model (LLM) inference, existing methods frequently suffer from significant performance degradation and demand computationally retraining to recover capabilities.
By Mengting Ai, Tianxin Wei, Sirui Chen, Jingrui He
arXiv:2608.30927v1 Announce Type: cross
Abstract: Whisper exposes speech through a fixed 1500-token encoder interface, now a default representation for ASR decoders and Whisper-based speech language...
By Chanhee Cho, Junhyuk Choi, Bugeun Kim
X-AuT is a progressive framework for compressing the audio encoder of speech large language models. It selects layer combinations via short behavioral probes and restores performance through representation alignment, cross‑scale distillation, scheduled student‑policy supervision, and LoRA finetuning, while keeping the language‑model backbone frozen. On ten Chinese–English benchmarks, reducing Qwen3‑ASR‑0.6B’s encoder from 18 to 16 layers lowers macro‑average error from 5.61% to 5.27%, and a 14‑layer model achieves 5.75% error with 20.7% fewer parameters.
By Haojun Zhang, Yi Zou, Min Chen, Qize Yu, Lianrui Fan, Xini Ding, Hao Li, Shuchang Zhou, Xianming Liu, Shiyu Huang
arXiv:2608. 06630v1 Announce Type: new Abstract: Pruning reduces the inference cost of large language models, but existing criteria primarily preserve large activations or reconstruct layer outputs.
By Linghao Kong, Inimai Subramanian, Micah Adler, Dan Alistarh, Dan Gutfreund, Nir Shavit
arXiv:2504.04342v2 Announce Type: replace
Abstract: Scaling up model parameters and training data consistently improves the performance of large language models (LLMs), but at the cost of rapidly gro...
By Ayan Sengupta, Siddhant Chaudhary, Tanmoy Chakraborty
arXiv:2603. 05121v2 Announce Type: replace-cross Abstract: Speech Large Language Models route speech encoder representations into an LLM decoder that typically accounts for over 90% of total parameters.
By Adel Moumen, Guangzhi Sun, Philip C Woodland
The paper introduces the "Compression Trinity," a unified framework that jointly applies sparsity, quantization, and low‑rank approximations to compress large language models. It presents several methods—MKOR, SLoPe, OPTIMA, PATCH, and SLiM—that leverage these three pillars to accelerate training, reduce memory bandwidth, and recover accuracy, achieving significant speedups and accuracy gains over existing techniques. The results demonstrate that combining all three compression strategies is essential for efficient, scalable, high‑performance LLM deployment.
By Mohammad Mozaffari
The paper introduces a reparameterization technique that injects feature noise to jointly optimize speech model performance and computational complexity during training. Unlike traditional pruning, this method dynamically adjusts model size for a desired performance‑complexity trade‑off without heuristic weight removal. The authors validate their approach with a synthetic example and two real‑world applications—voice activity detection and audio anti‑spoofing—providing publicly available code for further research.
By Esteban G\'omez, Tom B\"ackstr\"om
arXiv:2607. 13330v1 Announce Type: cross Abstract: Diffusion-based text-to-audio generative models such as AudioLDM achieve high perceptual quality and strong semantic consistency; however, their practical deployment is hindered by the substantial computational cost of the U-Net denoising backbone.
By Arshdeep Singh, Yi Yuan, Yun Chen, Wenwu Wang, Mark D. Plumbley