Cover Image

VARAN: Variational Inference for Self-Supervised Speech Models Fine-Tuning on Downstream Tasks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Diatlova, Daria, Balagansky, Nikita, Varlamov, Alexander, Spirin, Egor
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

METR: Image Watermarking with Large Number of Unique Messages
by: Varlamov, Alexander, et al.
Published: (2024)

NonverbalTTS: A Public English Corpus of Text-Aligned Nonverbal Vocalizations with Emotion Annotations for Text-to-Speech
by: Borisov, Maksim, et al.
Published: (2025)

Adapting WavLM for Speech Emotion Recognition
by: Diatlova, Daria, et al.
Published: (2024)

Mechanistic Permutability: Match Features Across Layers
by: Balagansky, Nikita, et al.
Published: (2024)

BiSSL: Enhancing the Alignment Between Self-Supervised Pretraining and Downstream Fine-Tuning via Bilevel Optimization
by: Zakarias, Gustav Wagner, et al.
Published: (2024)

Next Embedding Prediction Makes World Models Stronger
by: Bredis, George, et al.
Published: (2026)

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models
by: Laptev, Daniil, et al.
Published: (2025)

TwinTURBO: Semi-Supervised Fine-Tuning of Foundation Models via Mutual Information Decompositions for Downstream Task and Latent Spaces
by: Quétant, Guillaume, et al.
Published: (2025)

Diffusion Language Models Generation Can Be Halted Early
by: Vaina, Sofia Maria Lo Cicero, et al.
Published: (2023)

Memorization in Self-Supervised Learning Improves Downstream Generalization
by: Wang, Wenhao, et al.
Published: (2024)

TAGC: Optimizing Gradient Communication in Distributed Transformer Training
by: Polyakov, Igor, et al.
Published: (2025)

Multi-instance Learning as Downstream Task of Self-Supervised Learning-based Pre-trained Model
by: Matsuishi, Koki, et al.
Published: (2025)

Guided Star-Shaped Masked Diffusion
by: Meshchaninov, Viacheslav, et al.
Published: (2025)

Trust-Region Behavior Blending for On-Policy Distillation
by: Plyusov, Daniil, et al.
Published: (2026)

Task-tailored Pre-processing: Fair Downstream Supervised Learning
by: Sohn, Jinwon, et al.
Published: (2026)

Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning
by: Wang, Changsheng, et al.
Published: (2025)

Windowed SummaryMixing: An Efficient Fine-Tuning of Self-Supervised Learning Models for Low-resource Speech Recognition
by: Menon, Aditya Srinivas, et al.
Published: (2026)

Unlocking the Duality between Flow and Field Matching
by: Shlenskii, Daniil, et al.
Published: (2026)

You Do Not Fully Utilize Transformer's Representation Capacity
by: Gerasimov, Gleb, et al.
Published: (2025)

Kronecker Factorization Improves Efficiency and Interpretability of Sparse Autoencoders
by: Kurochkin, Vadim, et al.
Published: (2025)

Learn Your Reference Model for Real Good Alignment
by: Gorbatovski, Alexey, et al.
Published: (2024)

Teach Old SAEs New Domain Tricks with Boosting
by: Koriagin, Nikita, et al.
Published: (2025)

Smoke and Mirrors in Causal Downstream Tasks
by: Cadei, Riccardo, et al.
Published: (2024)

Anchored Supervised Fine-Tuning
by: Zhu, He, et al.
Published: (2025)

Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Models
by: Zhang, Zhejun, et al.
Published: (2024)

Diversity in Large Language Models under Supervised Fine-Tuning
by: Klypa, Roman, et al.
Published: (2026)

GEM: A Scale-Aware and Distribution-Sensitive Sparse Fine-Tuning Framework for Effective Downstream Adaptation
by: Kang, Sungmin, et al.
Published: (2025)

GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMs
by: Zhelnin, Maxim, et al.
Published: (2024)

Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy
by: Balagansky, Nikita, et al.
Published: (2025)

Erasing the Bias: Fine-Tuning Foundation Models for Semi-Supervised Learning
by: Gan, Kai, et al.
Published: (2024)

Attacking Attention of Foundation Models Disrupts Downstream Tasks
by: Silva, Hondamunige Prasanna, et al.
Published: (2025)

Rotation-Preserving Supervised Fine-Tuning
by: Jin, Hangzhan, et al.
Published: (2026)

Proximal Supervised Fine-Tuning
by: Zhu, Wenhong, et al.
Published: (2025)

Dataset Representativeness and Downstream Task Fairness
by: Borza, Victor, et al.
Published: (2024)

Preserving Diversity in Supervised Fine-Tuning of Large Language Models
by: Li, Ziniu, et al.
Published: (2024)

Coupling Speech Encoders with Downstream Text Models
by: Chelba, Ciprian, et al.
Published: (2024)

Task Priors: Enhancing Model Evaluation by Considering the Entire Space of Downstream Tasks
by: Patel, Niket, et al.
Published: (2025)

Task-Adaptive Parameter-Efficient Fine-Tuning for Weather Foundation Models
by: Cao, Shilei, et al.
Published: (2025)

Steering LLM Reasoning Through Bias-Only Adaptation
by: Sinii, Viacheslav, et al.
Published: (2025)

Panprediction: Optimal Predictions for Any Downstream Task and Loss
by: Balakrishnan, Sivaraman, et al.
Published: (2025)