3 papers
eess.AS2026
VIB-AVSR: Variational Information Bottleneck for Noise-Robust LLM-Based Audio-Visual Speech Recognition
Piyush Arora, Navlika Singh, Umberto Cappellazzo +2
Audio-Visual Speech Recognition takes two input modalities, acoustic and visual streams, where visual information from lip movements aids recognition when audio is noisy. Recently,…
cs.CV2025
BLADE: Bias-Linked Adaptive DEbiasing
Piyush Arora, Navlika Singh, Vasubhya Diwan +1
Neural networks have revolutionized numerous fields, yet they remain vulnerable to a critical flaw: the tendency to learn implicit biases, spurious correlations between certain att…
cs.CV2025
When Big Models Train Small Ones: Label-Free Model Parity Alignment for Efficient Visual Question Answering using Small VLMs
Abhirama Subramanyam Penamakuri, Navlika Singh, Piyush Arora +1
Large Vision-Language Models (L-VLMs) have demonstrated remarkable performance in various vision and language tasks, including visual question answering (VQA). However, their high…