Picture for Shrikanth Narayanan

Shrikanth Narayanan

Signal Analysis and Interpretation Lab, University of Southern California, Information Science Institute, University of Southern California

Larger Language Models Don't Care How You Think: Why Chain-of-Thought Prompting Fails in Subjective Tasks

Add code
Sep 10, 2024
Figure 1 for Larger Language Models Don't Care How You Think: Why Chain-of-Thought Prompting Fails in Subjective Tasks
Figure 2 for Larger Language Models Don't Care How You Think: Why Chain-of-Thought Prompting Fails in Subjective Tasks
Figure 3 for Larger Language Models Don't Care How You Think: Why Chain-of-Thought Prompting Fails in Subjective Tasks
Viaarxiv icon

Early Detection of Coffee Leaf Rust Through Convolutional Neural Networks Trained on Low-Resolution Images

Add code
Jul 20, 2024
Figure 1 for Early Detection of Coffee Leaf Rust Through Convolutional Neural Networks Trained on Low-Resolution Images
Figure 2 for Early Detection of Coffee Leaf Rust Through Convolutional Neural Networks Trained on Low-Resolution Images
Figure 3 for Early Detection of Coffee Leaf Rust Through Convolutional Neural Networks Trained on Low-Resolution Images
Figure 4 for Early Detection of Coffee Leaf Rust Through Convolutional Neural Networks Trained on Low-Resolution Images
Viaarxiv icon

Can Synthetic Audio From Generative Foundation Models Assist Audio Recognition and Speech Modeling?

Add code
Jun 13, 2024
Figure 1 for Can Synthetic Audio From Generative Foundation Models Assist Audio Recognition and Speech Modeling?
Figure 2 for Can Synthetic Audio From Generative Foundation Models Assist Audio Recognition and Speech Modeling?
Figure 3 for Can Synthetic Audio From Generative Foundation Models Assist Audio Recognition and Speech Modeling?
Figure 4 for Can Synthetic Audio From Generative Foundation Models Assist Audio Recognition and Speech Modeling?
Viaarxiv icon

Toward Fully-End-to-End Listened Speech Decoding from EEG Signals

Add code
Jun 12, 2024
Figure 1 for Toward Fully-End-to-End Listened Speech Decoding from EEG Signals
Figure 2 for Toward Fully-End-to-End Listened Speech Decoding from EEG Signals
Figure 3 for Toward Fully-End-to-End Listened Speech Decoding from EEG Signals
Figure 4 for Toward Fully-End-to-End Listened Speech Decoding from EEG Signals
Viaarxiv icon

Exploring Speech Foundation Models for Speaker Diarization in Child-Adult Dyadic Interactions

Add code
Jun 12, 2024
Viaarxiv icon

ConPro: Learning Severity Representation for Medical Images using Contrastive Learning and Preference Optimization

Add code
Apr 29, 2024
Viaarxiv icon

The Strong Pull of Prior Knowledge in Large Language Models and Its Impact on Emotion Recognition

Add code
Mar 25, 2024
Viaarxiv icon

Evaluating Atypical Gaze Patterns through Vision Models: The Case of Cortical Visual Impairment

Add code
Feb 15, 2024
Figure 1 for Evaluating Atypical Gaze Patterns through Vision Models: The Case of Cortical Visual Impairment
Figure 2 for Evaluating Atypical Gaze Patterns through Vision Models: The Case of Cortical Visual Impairment
Figure 3 for Evaluating Atypical Gaze Patterns through Vision Models: The Case of Cortical Visual Impairment
Figure 4 for Evaluating Atypical Gaze Patterns through Vision Models: The Case of Cortical Visual Impairment
Viaarxiv icon

Can Text-to-image Model Assist Multi-modal Learning for Visual Recognition with Visual Modality Missing?

Add code
Feb 14, 2024
Viaarxiv icon

Explainable Severity ranking via pairwise n-hidden comparison: a case study of glaucoma

Add code
Dec 05, 2023
Figure 1 for Explainable Severity ranking via pairwise n-hidden comparison: a case study of glaucoma
Figure 2 for Explainable Severity ranking via pairwise n-hidden comparison: a case study of glaucoma
Figure 3 for Explainable Severity ranking via pairwise n-hidden comparison: a case study of glaucoma
Figure 4 for Explainable Severity ranking via pairwise n-hidden comparison: a case study of glaucoma
Viaarxiv icon