Harshit Kumar
17 papers · 2018–2026 · 9 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
π Interdisciplinary Bridge π Conference Polyglot (9) π Academic Marathon (7) π Renaissance Researcher (7) πΊοΈ Taxonomy Completionist (36)
π£
Hot Topic Early Bird
π
Conference Polyglot
(9)
π
Academic Marathon
(7)
π₯
Mega-Team
(40)
π
Century Club
(16)
ποΈ
Keyword Collector
(70)
β
The Questioner
π₯
Unstoppable
(8)
Conferences
AAAI (4)
EMNLP (3)
ICLR (2)
ICML (2)
IJCNLP (2)
ACL (1)
COLING (1)
L4DC (1)
SEMEVAL (1)
Top co-authors
Keywords
data augmentation
(4)
dialogue act
(3)
negation detection
(3)
source-free domain adaptation
(3)
class prototype
(3)
unsupervised domain adaptation
(3)
multi-task learning
(2)
deep learning
(2)
response selection
(2)
conversation modeling
(2)
attention mechanism
(2)
question answering
(1)
ensemble learning
(1)
knowledge representation
(1)
semantic processing
(1)
domain adaptation
(1)
reinforcement learning
(1)
semantic matching
(1)
information extraction
(1)
contextual representation
(1)
Papers
Scalable and Efficient Large-Scale Log Analysis with LLMs: An IT Software Support Case Study
AAAI 2026
A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Attention Networks
ICML 2025
Has the Deep Neural Network learned the Stochastic Process? An Evaluation Viewpoint
ICLR 2025
ITBench: Evaluating AI Agents across Diverse Real-World IT Automation Tasks
ICML 2025
Sparse Spiking Neural Network: Exploiting Heterogeneity in Timescales for Pruning Recurrent SNN
ICLR 2024
AutoMixer for Improved Multivariate Time-Series Forecasting on Business and IT Observability Data
AAAI 2024
Learning locally interacting discrete dynamical systems: Towards data-efficient and scalable prediction
L4DC 2024
End-to-End Deep Reinforcement Learning for Conversation Disentanglement
AAAI 2023
Picking Pearl from Seabed: Extracting Artefacts from Noisy Issue Triaging Collaborative Conversations for Hybrid Cloud Services
AAAI 2022
IITK at SemEval-2021 Task 10: Source-Free Unsupervised Domain Adaptation using Class Prototypes
IJCNLP 2021
VeeAlign: Multifaceted Context Representation Using Dual Attention for Ontology Alignment
EMNLP 2021
IITK at SemEval-2021 Task 10: Source-Free Unsupervised Domain Adaptation using Class Prototypes
SEMEVAL 2021
IITK at SemEval-2021 Task 10: Source-Free Unsupervised Domain Adaptation using Class Prototypes
ACL 2021
Neural Conversational QA: Learning to Reason vs Exploiting Patterns
EMNLP 2020
A Practical Dialogue-Act-Driven Conversation Model for Multi-Turn Response Selection
IJCNLP 2019
A Practical Dialogue-Act-Driven Conversation Model for Multi-Turn Response Selection
EMNLP 2019
Dialogue-act-driven Conversation Model : An Experimental Study
COLING 2018