10 papers
Confidence-Modulated Speculative Decoding for Large Language Models
Jaydip Sen, Subhasis Dasgupta, Hetvi Waghela
Speculative decoding has emerged as an effective approach for accelerating autoregressive inference by parallelizing token generation through a draft-then-verify paradigm. However,…
Multi-Amateur Contrastive Decoding for Text Generation
Jaydip Sen, Subhasis Dasgupta, Hetvi Waghela
Contrastive Decoding (CD) has emerged as an effective inference-time strategy for enhancing open-ended text generation by exploiting the divergence in output probabilities between…
Adversarial Text Generation with Dynamic Contextual Perturbation
Hetvi Waghela, Jaydip Sen, Sneha Rakshit +1
Adversarial attacks on Natural Language Processing (NLP) models expose vulnerabilities by introducing subtle perturbations to input text, often leading to misclassification while m…
Context-Enhanced Contrastive Search for Improved LLM Text Generation
Jaydip Sen, Rohit Pandey, Hetvi Waghela
Recently, Large Language Models (LLMs) have demonstrated remarkable advancements in Natural Language Processing (NLP). However, generating high-quality text that balances coherence…
Adversarial Robustness through Dynamic Ensemble Learning
Hetvi Waghela, Jaydip Sen, Sneha Rakshit
Adversarial attacks pose a significant threat to the reliability of pre-trained language models (PLMs) such as GPT, BERT, RoBERTa, and T5. This paper presents Adversarial Robustnes…
Robust Image Classification: Defensive Strategies against FGSM and PGD Adversarial Attacks
Hetvi Waghela, Jaydip Sen, Sneha Rakshit
Adversarial attacks, particularly the Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD) pose significant threats to the robustness of deep learning models in im…