Akshat Gupta
24 papers · 2021–2026 · 9 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
π Interdisciplinary Bridge π Conference Polyglot (9) π Renaissance Researcher (8) π Academic Marathon (5) πΊοΈ Taxonomy Completionist (43)
πΊοΈ
Taxonomy Completionist
(43)
π§
Keyword Pioneer
π§¬
Topic Evolution
π
Keyword Champion
(2)
π
Century Club
(22)
π₯
Unstoppable
(5)
ποΈ
Keyword Collector
(86)
β‘
Prolific Year
(7)
Conferences
EMNLP (6)
ACL (5)
COLING (4)
EACL (3)
NAACL (2)
AAAI (1)
CVPR (1)
ICLR (1)
INTERSPEECH (1)
Top co-authors
Research topics
Keywords
large language model
(6)
knowledge editing
(6)
text classification
(4)
ensemble learning
(4)
model editing
(3)
sentiment analysis
(3)
social media
(2)
catastrophic forgetting
(2)
sequential editing
(2)
pos tagging
(2)
intent classification
(2)
spoken language understanding
(2)
low resource language
(2)
data augmentation
(1)
domain adaptation
(1)
embedding learning
(1)
transfer learning
(1)
3d reconstruction
(1)
factual knowledge
(1)
sequence labeling
(1)
Papers
Evolutionary Strategies at Scale lead to Catastrophic Forgetting
ACL 2026
Geometric Interpretation of Layer Normalization and a Comparative Analysis with RMSNorm
EACL 2026
SeqMMR: Sequential Model Merging and LLM Routing for Enhanced Batched Sequential Knowledge Editing
ACL 2025
PokerBench: Training Large Language Models to Become Professional Poker Players
AAAI 2025
Efficient Knowledge Editing via Minimal Precomputation
ACL 2025
InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation
CVPR 2025
Lifelong Knowledge Editing requires Better Regularization
EMNLP 2025
Sylber: Syllabic Embedding Representation of Speech from Raw Audio
ICLR 2025
Rebuilding ROME : Resolving Model Collapse during Sequential Model Editing
EMNLP 2024
A Unified Framework for Model Editing
EMNLP 2024
Self-Assessment Tests are Unreliable Measures of LLM Personality
EMNLP 2024
Model Editing at Scale leads to Gradual and Catastrophic Forgetting
ACL 2024
Unsupervised Domain Adaptation using Lexical Transformations and Label Injection for Twitter Data
ACL 2023
Probing Quantifier Comprehension in Large Language Models: Another Example of Inverse Scaling
EMNLP 2023
AIR-JPMC@SMM4Hβ22: BERT + Ensembling = Too Cool: Using Multiple BERT Models Together for Various COVID-19 Tweet Identification Tasks
COLING 2022
On Building Spoken Language Understanding Systems for Low Resourced Languages
NAACL 2022
TweetFinSent: A Dataset of Stock Sentiments on Twitter
EMNLP 2022
AIR-JPMC@SMM4Hβ22: Classifying Self-Reported Intimate Partner Violence in Tweets with Multiple BERT-based Models
COLING 2022
AIR-JPMC@SMM4Hβ22: Identifying Self-Reported Spanish COVID-19 Symptom Tweets Through Multiple-Model Ensembling
COLING 2022
TransPOS: Transformers for Consolidating Different POS Tagset Datasets
COLING 2022
Intent classification using pre-trained language agnostic embeddings for low resource languages
INTERSPEECH 2022
SJ_AJ@DravidianLangTech-EACL2021: Task-Adaptive Pre-Training of Multilingual BERT models for Offensive Language Identification
EACL 2021
Task-Specific Pre-Training and Cross Lingual Transfer for Sentiment Analysis in Dravidian Code-Switched Languages
EACL 2021
Unsupervised Self-Training for Sentiment Analysis of Code-Switched Data
NAACL 2021