Vithursan Thangarasa
5 papers · 2023–2026 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
๐
Conference Polyglot ยท Bronze
๐
Interdisciplinary Bridge ยท Silver
๐บ๏ธ
Taxonomy Completionist
(11)
๐ฃ
Hot Topic Early Bird
Top co-authors
Research topics
Keywords
model compression
(3)
vision-language model
(2)
speculative decoding
(2)
weight sparsity
(2)
sparse pre-training
(2)
neural architecture search
(1)
efficient computing
(1)
sparsity
(1)
dynamic sparse training
(1)
feature distillation
(1)
model efficiency
(1)
domain-specific model
(1)
biomedical language model
(1)
multimodal generation
(1)
large language model
(1)
dense fine-tuning
(1)
dense layer
(1)
hyperparameters
(1)
iso-flop transformations
(1)
ramanujan graph properties
(1)
Papers
DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation
ACL 2026
MASSV: Multimodal Adaptation and Self-Data Distillation for Speculative Decoding of Vision-Language Models
EMNLP 2025
MediSwift: Efficient Sparse Pre-trained Biomedical Language Models
ACL 2024
Sparse-IFT: Sparse Iso-FLOP Transformations for Maximizing Training Efficiency
ICML 2024
SPDF: Sparse Pre-training and Dense Fine-tuning for Large Language Models
UAI 2023