Kartik Gupta
8 papers · 2017–2025 · 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 ↓+3 more ↓ Show less ↑
π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (22) π£ Hot Topic Early Bird
π
Keyword Champion
(2)
β
The Questioner
(2)
π
Trend Setter
Top co-authors
Research topics
Deep Learning
(6)
Machine Learning
(6)
Application Areas
(4)
Learning Types
(3)
Optimization & Theory Β· Deep Learning
(3)
Techniques
(3)
Artificial Intelligence
(2)
Computer Vision
(2)
Mathematics & Optimization
(2)
Core AI Β· Artificial Intelligence
(2)
Optimization
(2)
Optimization & Theory Β· Machine Learning
(2)
Analysis
(1)
Architectures
(1)
Core AI Β· Computer Vision
(1)
Keywords
neural network quantization
(3)
straight-through estimator
(2)
model compression
(2)
neural network optimization
(1)
constrained optimization
(1)
feature representation
(1)
probability estimation
(1)
markov chain monte carlo
(1)
gradient descent
(1)
probabilistic matrix factorization
(1)
robust pca
(1)
generalization ability
(1)
matrix completion
(1)
low-rank matrix
(1)
mirror descent
(1)
closed-form solution
(1)
projected gradient descent
(1)
kolmogorov-smirnov test
(1)
adversarial attack
(1)
out-of-distribution detection
(1)
Papers
Can We Predict Performance of Large Models across Vision-Language Tasks?
ICML 2025
Reducing the Side-Effects of Oscillations in Training of Quantized YOLO Networks
WACV 2024
The First to Know: How Token Distributions Reveal Hidden Knowledge in Large Vision-Language Models?
ECCV 2024
Towards Optimal Feature-Shaping Methods for Out-of-Distribution Detection
ICLR 2024
Improved Gradient-Based Adversarial Attacks for Quantized Networks
AAAI 2022
Calibration of Neural Networks using Splines
ICLR 2021
Mirror Descent View for Neural Network Quantization
AISTATS 2021
Nearly Optimal Robust Matrix Completion
ICML 2017