{"list":"other","total":57,"rows":[{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"2006.11477","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","created":"2020-06-20","cited_by_count":3905},{"id":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342},{"id":"2110.13900","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","created":"2021-10-26","cited_by_count":1657},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"id":"1912.06670","title":"Common Voice: A Massively-Multilingual Speech Corpus","created":"2019-12-13","cited_by_count":1384},{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120},{"id":"2306.01708","title":"TIES-Merging: Resolving Interference When Merging Models","created":"2023-06-02","cited_by_count":818},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797},{"id":"2402.09353","title":"DoRA: Weight-Decomposed Low-Rank Adaptation","created":"2024-02-14","cited_by_count":758},{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739},{"id":"2105.01051","title":"SUPERB: Speech processing Universal PERformance Benchmark","created":"2021-05-03","cited_by_count":666},{"id":"2012.03411","title":"MLS: A Large-Scale Multilingual Dataset for Speech Research","created":"2020-12-07","cited_by_count":476},{"id":"2107.04734","title":"Layer-wise Analysis of a Self-supervised Speech Representation Model","created":"2021-07-10","cited_by_count":298},{"id":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260},{"id":"1904.03240","title":"An Unsupervised Autoregressive Model for Speech Representation Learning","created":"2019-04-05","cited_by_count":186},{"id":"2309.06256","title":"Mitigating the Alignment Tax of RLHF","created":"2023-09-12","cited_by_count":183},{"id":"2004.12651","title":"Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting","created":"2020-04-27","cited_by_count":170},{"id":"1909.09116","title":"Self-Training for End-to-End Speech Recognition","created":"2019-09-19","cited_by_count":129},{"id":"2111.02735","title":"A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding","created":"2021-11-04","cited_by_count":82},{"id":"2012.06659","title":"DeCoAR 2.0: Deep Contextualized Acoustic Representations with Vector Quantization","created":"2020-12-11","cited_by_count":77},{"id":"2203.06849","title":"SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities","created":"2022-03-14","cited_by_count":77},{"id":"2305.10615","title":"ML-SUPERB: Multilingual Speech Universal PERformance Benchmark","created":"2023-05-18","cited_by_count":71},{"id":"2407.06322","title":"MagMax: Leveraging Model Merging for Seamless Continual Learning","created":"2024-07-08","cited_by_count":67},{"id":"2406.11385","title":"MetaGPT: Merging Large Language Models Using Model Exclusive Task Arithmetic","created":"2024-06-17","cited_by_count":53},{"id":"2307.08286","title":"Going Beyond Linear Mode Connectivity: The Layerwise Linear Feature Connectivity","created":"2023-07-17","cited_by_count":50},{"id":"2110.06309","title":"Exploring Wav2vec 2.0 fine-tuning for improved speech emotion recognition","created":"2021-10-12","cited_by_count":49},{"id":"2404.09385","title":"A Large-Scale Evaluation of Speech Foundation Models","created":"2024-04-15","cited_by_count":40},{"id":"2010.13826","title":"Semi-Supervised Spoken Language Understanding via Self-Supervised Speech and Language Model Pretraining","created":"2020-10-26","cited_by_count":35},{"id":"1911.00202","title":"Forget Me Not: Reducing Catastrophic Forgetting for Domain Adaptation in Reading Comprehension","created":"2019-11-01","cited_by_count":27},{"id":"2210.06175","title":"Exploring Efficient-tuning Methods in Self-supervised Speech Models","created":"2022-10-10","cited_by_count":26},{"id":"2210.08634","title":"SUPERB @ SLT 2022: Challenge on Generalization and Efficiency of Self-Supervised Speech Representation Learning","created":"2022-10-16","cited_by_count":26},{"id":"2309.17230","title":"Spurious Feature Diversification Improves Out-of-distribution Generalization","created":"2023-09-29","cited_by_count":26},{"id":"2407.03994","title":"Unlocking the Potential of Model Merging for Low-Resource Languages","created":"2024-07-04","cited_by_count":19},{"id":"2310.02720","title":"Multi-resolution HuBERT: Multi-resolution Speech Self-Supervised Learning with Masked Unit Prediction","created":"2023-10-04","cited_by_count":17},{"id":"2406.10283","title":"Attentive Merging of Hidden Embeddings from Pre-trained Speech Model for Anti-spoofing Detection","created":"2024-06-12","cited_by_count":17},{"id":"2211.09944","title":"MelHuBERT: A simplified HuBERT on Mel spectrograms","created":"2022-11-17","cited_by_count":16},{"id":"2306.01385","title":"Task-Agnostic Structured Pruning of Speech Representation Models","created":"2023-06-02","cited_by_count":15},{"id":"2407.13771","title":"Training-Free Model Merging for Multi-target Domain Adaptation","created":"2024-07-18","cited_by_count":15},{"id":"2004.06684","title":"Multi-Resolution A*","created":"2020-04-14","cited_by_count":13},{"id":"2302.12757","title":"Ensemble knowledge distillation of self-supervised speech models","created":"2023-02-24","cited_by_count":12},{"id":"2310.05513","title":"Findings of the 2023 ML-SUPERB Challenge: Pre-Training and Evaluation over More Languages and Beyond","created":"2023-10-09","cited_by_count":10},{"id":"2402.13018","title":"EMO-SUPERB: An In-depth Look at Speech Emotion Recognition","created":"2024-02-20","cited_by_count":10},{"id":"2309.07707","title":"CoLLD: Contrastive Layer-to-layer Distillation for Compressing Multilingual Pre-trained Speech Encoders","created":"2023-09-14","cited_by_count":9},{"id":"2309.13860","title":"Fast-HuBERT: An Efficient Training Framework for Self-Supervised Speech Representation Learning","created":"2023-09-25","cited_by_count":9},{"id":"2305.19011","title":"MiniSUPERB: Lightweight Benchmark for Self-supervised Speech Models","created":"2023-05-30","cited_by_count":8},{"id":"2212.08542","title":"Context-aware Fine-tuning of Self-supervised Speech Models","created":"2022-12-16","cited_by_count":7},{"id":"2409.02302","title":"Speech Foundation Model Ensembles for the Controlled Singing Voice Deepfake Detection (CtrSVDD) Challenge 2024","created":"2024-09-03","cited_by_count":7},{"id":"2409.11274","title":"Task Arithmetic for Language Expansion in Speech Translation","created":"2024-09-17","cited_by_count":6},{"id":"2110.09930","title":"Speech Representation Learning Through Self-supervised Pretraining And Multi-task Finetuning","created":"2021-10-18","cited_by_count":4},{"id":"2205.00334","title":"Engineering flexible machine learning systems by traversing functionally-invariant paths","created":"2022-04-30","cited_by_count":4},{"id":"2406.05464","title":"DAISY: Data Adaptive Self-Supervised Early Exit for Speech Representation Models","created":"2024-06-08","cited_by_count":4},{"id":"2407.00766","title":"An Attribute Interpolation Method in Speech Synthesis by Model Merging","created":"2024-06-30","cited_by_count":4},{"id":"2407.00756","title":"Less Forgetting for Better Generalization: Exploring Continual-learning Fine-tuning Methods for Speech Self-supervised Representations","created":"2024-06-30","cited_by_count":3},{"id":"2406.17935","title":"Sequential Editing for Lifelong Training of Speech Recognition Models","created":"2024-06-25","cited_by_count":1}],"next_cursor":null}