Ankit Gupta
13 papers · 2020–2025 · 7 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 ↓+5 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (33)
π
Keyword Champion
(2)
π₯
Mega-Team Β· Squad
ποΈ
Keyword Collector
(68)
π
Century Club Β· Bronze
π₯
Unstoppable Β· Bronze
Top co-authors
Research topics
Deep Learning
(11)
Machine Learning
(9)
Architectures
(8)
Artificial Intelligence
(6)
Optimization & Theory Β· Machine Learning
(5)
Natural Language Processing
(4)
Application Areas
(4)
Core AI
(4)
Generation
(3)
Learning Paradigms
(3)
Learning Types
(3)
Optimization & Theory Β· Deep Learning
(3)
Applications
(2)
Core Methods
(2)
Models
(2)
Keywords
state space model
(5)
sequence modeling
(4)
transfer learning
(3)
question answering
(3)
long-range dependency
(3)
language modeling
(2)
denoising objective
(2)
approximate attention
(2)
long-range dependencies
(2)
attention mechanism
(2)
transformer model
(2)
automatic speech recognition
(1)
text summarization
(1)
deep learning
(1)
embedding space
(1)
data augmentation
(1)
benchmark suite
(1)
model alignment
(1)
sparse approximation
(1)
model interpretability
(1)
Papers
Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priors (Extended Abstract)
IJCAI 2025
Exploring the limits of decoder-only models trained on public speech recognition corpora
Interspeech 2024
Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priors
ICLR 2024
5G-IoT Cloud based Demonstration of Real-Time Audio-Visual Speech Enhancement for Multimodal Hearing-aids
Interspeech 2023
Analyzing Transformers in Embedding Space
ACL 2023
Long Range Language Modeling via Gated State Spaces
ICLR 2023
Diagonal State Spaces are as Effective as Structured State Spaces
NeurIPS 2022
On the Parameterization and Initialization of Diagonal State Space Models
NeurIPS 2022
SCROLLS: Standardized CompaRison Over Long Language Sequences
EMNLP 2022
DART: Open-Domain Structured Data Record to Text Generation
NAACL 2021
Memory-efficient Transformers via Top-k Attention
EMNLP 2021
Value-aware Approximate Attention
EMNLP 2021
Injecting Numerical Reasoning Skills into Language Models
ACL 2020