Search Results for author:
Found 23 papers, 15 papers with code
MoHAVE: Mixture of Hierarchical Audio-Visual Experts for Robust Speech Recognition
Audio-visual speech recognition (AVSR) has become critical for enhancing speech recognition in noisy environments by integrating both auditory and visual modalities.
Relaxed Recursive Transformers: Effective Parameter Sharing with Layer-wise LoRA
In this work, we revisit "layer tying" as form of parameter sharing in Transformers, and introduce novel methods for converting existing LLMs into smaller "Recursive Transformers" that share parameters across layers, with minimal loss of performance.
Automated Filtering of Human Feedback Data for Aligning Text-to-Image Diffusion Models
Fine-tuning text-to-image diffusion models with human feedback is an effective method for aligning model behavior with human intentions.
VACoDe: Visual Augmented Contrastive Decoding
To address this issue, previous studies have focused on mitigating hallucinations by employing contrastive decoding (CD) with augmented images, which amplifies the contrast with the original image.
Hard Prompts Made Interpretable: Sparse Entropy Regularization for Prompt Tuning with RL
With the advent of foundation models, prompt tuning has positioned itself as an important technique for directing model behaviors and eliciting desired responses.
Learning Video Temporal Dynamics with Cross-Modal Attention for Robust Audio-Visual Speech Recognition
Cross-modal attention modules are introduced to enrich video features with audio information so that speech variability can be taken into account when training on the video temporal dynamics.
Block Transformer: Global-to-Local Language Modeling for Fast Inference
We introduce the Block Transformer which adopts hierarchical global-to-local modeling to autoregressive transformers to mitigate the inference bottlenecks associated with self-attention.
Fine-tuned In-Context Learning Transformers are Excellent Tabular Data Classifiers
Based on this observation, we propose to pretrain ICL-transformers on a new forest dataset generator which creates datasets that are unrealistic, but have complex decision boundaries.
RepAugment: Input-Agnostic Representation-Level Augmentation for Respiratory Sound Classification
To address this, we propose RepAugment, an input-agnostic representation-level augmentation technique that outperforms SpecAugment, but is also suitable for respiratory sound classification with waveform pretrained models.
Stethoscope-guided Supervised Contrastive Learning for Cross-domain Adaptation on Respiratory Sound Classification
Despite the remarkable advances in deep learning technology, achieving satisfactory performance in lung sound classification remains a challenge due to the scarcity of available data.
Ranked #8 on
Audio Classification
on ICBHI Respiratory Sound Database
(using extra training data)
Carpe Diem: On the Evaluation of World Knowledge in Lifelong Language Models
The dynamic nature of knowledge in an ever-changing world presents challenges for language models trained on static data; the model in the real world often requires not only acquiring new knowledge but also overwriting outdated information into updated ones.
Fine-Tuning the Retrieval Mechanism for Tabular Deep Learning
While interests in tabular deep learning has significantly grown, conventional tree-based models still outperform deep learning methods.
Adversarial Fine-tuning using Generated Respiratory Sound to Address Class Imbalance
In this work, we propose a straightforward approach to augment imbalanced respiratory sound data using an audio diffusion model as a conditional neural vocoder.
Ranked #7 on
Audio Classification
on ICBHI Respiratory Sound Database
(using extra training data)
Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding
To tackle the high inference latency exhibited by autoregressive language models, previous studies have proposed an early-exiting framework that allocates adaptive computation paths for each token based on the complexity of generating the subsequent token.
Patch-Mix Contrastive Learning with Audio Spectrogram Transformer on Respiratory Sound Classification
Respiratory sound contains crucial information for the early diagnosis of fatal lung diseases.
Ranked #6 on
Audio Classification
on ICBHI Respiratory Sound Database
(using extra training data)
Re-thinking Federated Active Learning based on Inter-class Diversity
In this work, we first demonstrate that the superiority of two selector models depends on the global and local inter-class diversity.
Coreset Sampling from Open-Set for Fine-Grained Self-Supervised Learning
Fortunately, the recent self-supervised learning (SSL) is a promising approach to pretrain a model without annotations, serving as an effective initialization for any downstream tasks.
Self-Contrastive Learning
This paper proposes a novel contrastive learning framework, called Self-Contrastive (SelfCon) Learning, that self-contrasts within multiple outputs from the different levels of a multi-exit network.
Self-Contrastive Learning: Single-viewed Supervised Contrastive Framework using Sub-network
To this end, we propose Self-Contrastive (SelfCon) learning, which self-contrasts within multiple outputs from the different levels of a single network.
Preservation of the Global Knowledge by Not-True Distillation in Federated Learning
In federated learning, a strong global model is collaboratively learned by aggregating clients' locally trained models.
Accurate and Fast Federated Learning via Combinatorial Multi-Armed Bandits
Federated learning has emerged as an innovative paradigm of collaborative machine learning.
MixCo: Mix-up Contrastive Learning for Visual Representation
Contrastive learning has shown remarkable results in recent self-supervised approaches for visual representation.
SIPA: A Simple Framework for Efficient Networks
With the success of deep learning in various fields and the advent of numerous Internet of Things (IoT) devices, it is essential to lighten models suitable for low-power devices.
