TISDiSS: A Training-Time and Inference-Time Scalable Framework for Discriminative Source Separation

• URL: http://arxiv.org/abs/2509.15666v3
• Date: Tue, 14 Oct 2025 07:59:00 GMT
• Title: TISDiSS: A Training-Time and Inference-Time Scalable Framework for Discriminative Source Separation
• Authors: Yongsheng Feng, Yuetonghui Xu, Jiehui Luo, Hongjia Liu, Xiaobing Li, Feng Yu, Wei Li,
• Abstract summary: We propose Training-Time and Inference-Time Scalable Discriminative Source Separation (TISDiSS)<n>TISDiSS integrates early-split multi-loss supervision, shared- parameter design, and dynamic inference repetitions.<n> Experiments on standard speech separation benchmarks demonstrate state-of-the-art performance with a reduced parameter count.
• Score: 7.238310342477333
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Source separation is a fundamental task in speech, music, and audio processing, and it also provides cleaner and larger data for training generative models. However, improving separation performance in practice often depends on increasingly large networks, inflating training and deployment costs. Motivated by recent advances in inference-time scaling for generative modeling, we propose Training-Time and Inference-Time Scalable Discriminative Source Separation (TISDiSS), a unified framework that integrates early-split multi-loss supervision, shared-parameter design, and dynamic inference repetitions. TISDiSS enables flexible speed-performance trade-offs by adjusting inference depth without retraining additional models. We further provide systematic analyses of architectural and training choices and show that training with more inference repetitions improves shallow-inference performance, benefiting low-latency applications. Experiments on standard speech separation benchmarks demonstrate state-of-the-art performance with a reduced parameter count, establishing TISDiSS as a scalable and practical framework for adaptive source separation. Code is available at https://github.com/WingSingFung/TISDiSS.

Related papers

• DiRL: An Efficient Post-Training Framework for Diffusion Language Models [54.405206032785706]
  Diffusion Language Models (dLLMs) have emerged as promising alternatives to Auto-Regressive (AR) models.<n>Existing methods suffer from computational inefficiency and objective mismatches between training and inference.<n>We introduce DiRL, an efficient post-training framework that tightly integrates FlexAttention-accelerated blockwise training with LMDeploy-optimized inference.
  arXiv  Detail & Related papers  (2025-12-23T08:33:19Z)
• SPaRFT: Self-Paced Reinforcement Fine-Tuning for Large Language Models [51.74498855100541]
  Large language models (LLMs) have shown strong reasoning capabilities when fine-tuned with reinforcement learning (RL)<n>We propose textbfSPaRFT, a self-paced learning framework that enables efficient learning based on the capability of the model being trained.
  arXiv  Detail & Related papers  (2025-08-07T03:50:48Z)
• AdaLRS: Loss-Guided Adaptive Learning Rate Search for Efficient Foundation Model Pretraining [12.630306478872043]
  We propose textbfAdaLRS, a plug-in-and-play adaptive learning rate search algorithm that conducts online optimal learning rate search.<n>Experiments show that AdaLRS adjusts suboptimal learning rates to the neighborhood of optimum with marked efficiency and effectiveness.
  arXiv  Detail & Related papers  (2025-06-16T09:14:01Z)
• Boosting All-in-One Image Restoration via Self-Improved Privilege Learning [72.35265021054471]
  Self-Improved Privilege Learning (SIPL) is a novel paradigm that overcomes limitations by extending the utility of privileged information (PI) beyond training into the inference stage.<n>Central to SIPL is Proxy Fusion, a lightweight module incorporating a learnable Privileged Dictionary.<n>Extensive experiments demonstrate that SIPL significantly advances the state-of-the-art on diverse all-in-one image restoration benchmarks.
  arXiv  Detail & Related papers  (2025-05-30T04:36:52Z)
• ToReMi: Topic-Aware Data Reweighting for Dynamic Pre-Training Data Selection [28.75333303894706]
  ToReMi is a novel framework that adjusts training sample weights according to their topical associations and observed learning patterns.<n>Our experiments reveal that ToReMi variants consistently achieve superior performance over conventional pre-training approaches.
  arXiv  Detail & Related papers  (2025-04-01T12:06:42Z)
• UniSTD: Towards Unified Spatio-Temporal Learning across Diverse Disciplines [64.84631333071728]
  We introduce bfUnistage, a unified Transformer-based framework fortemporal modeling.<n>Our work demonstrates that a task-specific vision-text can build a generalizable model fortemporal learning.<n>We also introduce a temporal module to incorporate temporal dynamics explicitly.
  arXiv  Detail & Related papers  (2025-03-26T17:33:23Z)
• The Fine Line: Navigating Large Language Model Pretraining with Down-streaming Capability Analysis [27.310894780313618]
  This paper undertakes a comprehensive comparison of model capabilities at various pretraining intermediate checkpoints. We confirm that specific downstream metrics exhibit similar training dynamics across models of different sizes. In addition to our core findings, we've reproduced Amber and OpenLLaMA, releasing their intermediate checkpoints.
  arXiv  Detail & Related papers  (2024-04-01T16:00:01Z)
• Take the Bull by the Horns: Hard Sample-Reweighted Continual Training Improves LLM Generalization [165.98557106089777]
  A key challenge is to enhance the capabilities of large language models (LLMs) amid a looming shortage of high-quality training data. Our study starts from an empirical strategy for the light continual training of LLMs using their original pre-training data sets. We then formalize this strategy into a principled framework of Instance-Reweighted Distributionally Robust Optimization.
  arXiv  Detail & Related papers  (2024-02-22T04:10:57Z)
• Scalable Federated Unlearning via Isolated and Coded Sharding [76.12847512410767]
  Federated unlearning has emerged as a promising paradigm to erase the client-level data effect. This paper proposes a scalable federated unlearning framework based on isolated sharding and coded computing.
  arXiv  Detail & Related papers  (2024-01-29T08:41:45Z)
• Federated Learning over Hierarchical Wireless Networks: Training Latency Minimization via Submodel Partitioning [15.311309249848739]
  Hierarchical independent submodel training (HIST) is a new FL methodology that aims to address these issues in hierarchical cloud-edge-client networks.<n>We demonstrate how HIST can be augmented with over-the-air computation (AirComp) to further enhance the efficiency of the model aggregation over the edge cells.
  arXiv  Detail & Related papers  (2023-10-27T04:42:59Z)
• Time-sensitive Learning for Heterogeneous Federated Edge Intelligence [52.83633954857744]
  We investigate real-time machine learning in a federated edge intelligence (FEI) system. FEI systems exhibit heterogenous communication and computational resource distribution. We propose a time-sensitive federated learning (TS-FL) framework to minimize the overall run-time for collaboratively training a shared ML model.
  arXiv  Detail & Related papers  (2023-01-26T08:13:22Z)
• Efficient Augmentation for Imbalanced Deep Learning [8.38844520504124]
  We study a convolutional neural network's internal representation of imbalanced image data. We measure the generalization gap between a model's feature embeddings in the training and test sets, showing that the gap is wider for minority classes. This insight enables us to design an efficient three-phase CNN training framework for imbalanced data.
  arXiv  Detail & Related papers  (2022-07-13T09:43:17Z)
• Data splitting improves statistical performance in overparametrized regimes [0.0]
  Distributed learning is a common strategy to reduce the overall training time by exploiting multiple computing devices. We show that in this regime, data splitting has a regularizing effect, hence improving statistical performance and computational complexity.
  arXiv  Detail & Related papers  (2021-10-21T08:10:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.