Ashutosh Kumar
10 papers · 2019–2026 · 6 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 ↓+2 more ↓ Show less ↑
🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (24) 🌍 Conference Polyglot · Silver ❓ The Questioner
💎
Century Club · Bronze
⚡
Prolific Year · Productive
Top co-authors
Research topics
Artificial Intelligence
(5)
Core AI
(5)
Deep Learning
(4)
Machine Learning
(4)
Computer Vision
(3)
Learning Types
(3)
Natural Language Processing
(2)
Application Areas
(2)
Applications · Natural Language Processing
(2)
Core Methods
(2)
Techniques
(2)
Mathematics & Optimization
(1)
Analysis
(1)
Applications · Computer Vision
(1)
Architectures
(1)
Keywords
text classification
(2)
vision-language model
(2)
generative model
(2)
knowledge distillation
(2)
intent classification
(1)
data augmentation
(1)
sentiment analysis
(1)
video understanding
(1)
model calibration
(1)
visual grounding
(1)
sample complexity
(1)
paraphrase generation
(1)
paraphrase detection
(1)
pre-trained model
(1)
diffusion model
(1)
social media analysis
(1)
contrastive learning
(1)
discrete diffusion
(1)
vision-language pre-training
(1)
submodular optimization
(1)
Papers
CaST-Bench: Benchmarking Causal Chain-Grounded Spatio-Temporal Reasoning for Video Question Answering
CVPR 2026
InstAP: Instance-Aware Vision-Language Pre-Train for Spatial-Temporal Understanding
CVPR 2026
Investigating Vaccine Buyer’s Remorse: Post-Vaccination Decision Regret in COVID-19 Social Media Using Politically Diverse Human Annotation
AAAI 2026
SkillSight: Efficient First-Person Skill Assessment with Gaze
CVPR 2026
TrajTok: Learning Trajectory Tokens Enhances Video Understanding
CVPR 2026
Generative or Discriminative? Revisiting Text Classification in the Era of Transformers
EMNLP 2025
Moonshine: Distilling Game Content Generators into Steerable Generative Models
AAAI 2025
WTS: A Pedestrian-Centric Traffic Video Dataset for Fine-grained Spatial-Temporal Understanding
ECCV 2024
Striking a Balance: Alleviating Inconsistency in Pre-trained Models for Symmetric Classification Tasks
ACL 2022
Submodular Optimization-based Diverse Paraphrasing and its Effectiveness in Data Augmentation
NAACL 2019