Varun Kumar
18 papers · 2019–2026 · 8 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 ↓+7 more ↓ Show less ↑
🗺️ Taxonomy Completionist (53) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird
👥
Mega-Team · Squad
🧬
Topic Evolution
🚀
Conference Pioneer
🔥
Unstoppable · Bronze
❓
The Questioner
💎
Century Club · Bronze
🗃️
Keyword Collector
(90)
Top co-authors
Research topics
Artificial Intelligence
(14)
Machine Learning
(14)
Core AI
(13)
Deep Learning
(9)
Application Areas
(9)
Natural Language Processing
(8)
Learning Types · Machine Learning
(6)
Generation
(4)
Learning Types · Deep Learning
(4)
Optimization & Theory · Machine Learning
(4)
Applications
(3)
Models
(3)
Core Methods
(2)
Learning Paradigms
(2)
Optimization & Theory · Deep Learning
(2)
Keywords
code generation
(4)
large language model
(4)
code completion
(3)
intent classification
(2)
language model
(2)
data augmentation
(2)
reinforcement learning
(2)
abstract syntax tree
(2)
few-shot learning
(1)
semi-supervised learning
(1)
representation learning
(1)
knowledge distillation
(1)
object detection
(1)
topic modeling
(1)
text classification
(1)
benchmark evaluation
(1)
ambiguity resolution
(1)
bayesian inference
(1)
conditional generation
(1)
text generation
(1)
Papers
CODESTRUCT: Code Agents over Structured Action Spaces
ACL 2026
Empowering Multi-Turn Tool-Integrated Agentic Reasoning with Group Turn Policy Optimization
ACL 2026
SpecAgent: A Speculative Retrieval and Forecasting Agent for Code Completion
ACL 2026
Planning-Aware Code Infilling via Horizon-Length Prediction
EMNLP 2025
Fewer Truncations Improve Language Modeling
ICML 2024
LeDex: Training LLMs to Better Self-Debug and Explain Code
NeurIPS 2024
Reasoning in Token Economies: Budget-Aware Evaluation of LLM Reasoning Strategies
EMNLP 2024
A Static Evaluation of Code Completion by Large Language Models
ACL 2023
Multi-lingual Evaluation of Code Generation Models
ICLR 2023
ReCode: Robustness Evaluation of Code Generation Models
ACL 2023
Resolving Ambiguities in Text-to-Image Generative Models
ACL 2023
Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal
ACL 2022
On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language Representations
ACL 2022
Industry Scale Semi-Supervised Learning for Natural Language Understanding
NAACL 2021
Data Augmentation using Pre-trained Transformer Models
AACL 2020
A Closer Look At Feature Space Data Augmentation For Few-Shot Intent Classification
EMNLP 2019
SpaceNet MVOI: A Multi-View Overhead Imagery Dataset
ICCV 2019
Why Didn’t You Listen to Me? Comparing User Control of Human-in-the-Loop Topic Models
ACL 2019