Get started
Author

Vithursan Thangarasa

Observed name: Thangarasa, Vithursan
OpenAlex ID: A5022019488
RevBiFPN: The Fully Reversible Bidirectional Feature Pyramid Network
2022 · Chiley, Vitaliy, Thangarasa, Vithursan, et al. · arXiv (Cornell University) · 12
PDF
Enabling Continual Learning with Differentiable Hebbian Plasticity
2020 · Vithursan Thangarasa, Thomas Miconi, et al. · International Joint Conference on Neural Networks (IJCNN) · 11
PDF
SPDF: Sparse Pre-training and Dense Fine-tuning for Large Language Models
2023 · Thangarasa, Vithursan, Gupta, Abhay, et al. · arXiv (Cornell University) · 9
PDF
Self-Paced Learning with Adaptive Deep Visual Embeddings
2018 · Thangarasa, Vithursan, Taylor, Graham W. · arXiv (Cornell University) · 7
PDF
Introducing v0.5 of the AI Safety Benchmark from MLCommons
2024 · Vidgen, Bertie, Agrawal, Adarsh, et al. · arXiv (Cornell University) · 5
PDF
MediSwift: Efficient Sparse Pre-trained Biomedical Language Models
2024 · Vithursan Thangarasa, Mahmoud Salem, et al. · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · 3
PDF
DREAM: Drafting with Refined Target Features and Entropy-Adaptive Cross-Attention Fusion for Multimodal Speculative Decoding
2025 · Yunhai Hu, Tianhua Xia, et al. · neural information processing systems · 1
PDF
Differentiable Hebbian Consolidation for Continual Lifelong Learning
2019 · Vithursan Thangarasa · The Atrium (University of Guelph) · 1
PDF
DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation
2026 · Association for Computational Linguistics 2026, Bao, Bo, et al. · Underline Science Inc.
DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation
2026 · Liu, Zining, Hu, Yunhai, et al. · arXiv (Cornell University)
PDF
DREAM-R: Multimodal Speculative Reasoning with RL-Based Refined Drafting, Precise Verification, and Fully Parallel Execution
2026 · Hu, Yunhai, Liu, Zining, et al. · arXiv (Cornell University)
PDF
CodeQuant: Unified Clustering and Quantization for Enhanced Outlier Smoothing in Low-Precision Mixture-of-Experts
2026 · Yin, Xiangyang, Liu, Xingyu, et al. · arXiv (Cornell University)
PDF
DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation
2026 · Zining Liu, Yunhai Hu, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
SD$^2$: Self-Distilled Sparse Drafters
2025 · Lasby, Mike, Sinnadurai, Nish, et al. · arXiv (Cornell University)
PDF
MASSV: Multimodal Adaptation and Self-Data Distillation for Speculative Decoding of Vision-Language Models
2025 · Mugilan Ganesan, Shane Segal, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)
PDF
Self-Data Distillation for Recovering Quality in Pruned Large Language Models
2024 · Thangarasa, Vithursan, Venkatesh, Ganesh, et al. · arXiv (Cornell University)
PDF
Sparse-IFT: Sparse Iso-FLOP Transformations for Maximizing Training Efficiency
2023 · Thangarasa, Vithursan, Saxena, Shreyas, et al. · arXiv (Cornell University)
PDF
Differentiable Hebbian Consolidation for Continual Learning
2019 · Vithursan Thangarasa, Thomas Miconi, et al.
LEAP: Learning Embeddings for Adaptive Pace
2018 · Vithursan Thangarasa, Graham W. Taylor
Works count: 21
Citation count: 55
H-index: 5
I10-index: 2
Year
Topic
Type