Puneet K. Dokania
21 papers · 2015–2025 · 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 ↓+8 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (50) π Conference Polyglot Β· Silver π Academic Marathon Β· Half π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird
π
Grand Slam
ποΈ
Keyword Collector
(106)
β‘
Prolific Year Β· Productive
π₯
Unstoppable Β· Bronze
β
The Questioner
(3)
π
Century Club Β· Bronze
π
Conference Pioneer
π
Trend Setter
Top co-authors
Research topics
Machine Learning
(17)
Deep Learning
(8)
Learning Types Β· Machine Learning
(8)
Optimization & Theory
(8)
Artificial Intelligence
(7)
Computer Vision
(6)
Core AI
(6)
Core Methods
(6)
Learning Types Β· Deep Learning
(4)
Natural Language Processing
(3)
Analysis
(3)
Application Areas
(3)
Generation
(3)
Models
(3)
Architectures
(2)
Keywords
object detection
(2)
large language model
(2)
neural network
(2)
energy minimization
(2)
continual learning
(2)
graph cut
(2)
generative adversarial network
(2)
representation learning
(2)
catastrophic forgetting
(1)
hierarchical classification
(1)
model compression
(1)
uncertainty quantification
(1)
online learning
(1)
interpretability
(1)
question answering
(1)
image generation
(1)
preference alignment
(1)
knowledge distillation
(1)
adversarial robustness
(1)
attention mechanism
(1)
Papers
Mixture of Experts Made Intrinsically Interpretable
ICML 2025
RanDumb: Random Representations Outperform Online Continually Learned Representations
NeurIPS 2024
What Makes and Breaks Safety Fine-tuning? A Mechanistic Study
NeurIPS 2024
Computationally Budgeted Continual Learning: What Does Matter?
CVPR 2023
Graph Inductive Biases in Transformers without Message Passing
ICML 2023
Query-Based Hard-Image Retrieval for Object Detection at Test Time
AAAI 2023
Sample-Dependent Adaptive Temperature Scaling for Improved Calibration
AAAI 2023
Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibration
CVPR 2023
An Impartial Take to the CNN vs Transformer Robustness Contest
ECCV 2022
How Benign is Benign Overfitting ?
ICLR 2021
No Cost Likelihood Manipulation at Test Time for Making Better Mistakes in Deep Networks
ICLR 2021
Progressive Skeletonization: Trimming more fat from a network at initialization
ICLR 2021
GDumb: A Simple Approach that Questions Our Progress in Continual Learning
ECCV 2020
Stable Rank Normalization for Improved Generalization in Neural Networks and GANs
ICLR 2020
Interactive Sketch & Fill: Multiclass Sketch-to-Image Translation
ICCV 2019
Proximal Mean-Field for Neural Network Quantization
ICCV 2019
FlipDial: A Generative Model for Two-Way Visual Dialogue
CVPR 2018
Multi-Agent Diverse Generative Adversarial Networks
CVPR 2018
Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence
ECCV 2018
Rounding-based Moves for Semi-Metric Labeling
JMLR 2016
Parsimonious Labeling
ICCV 2015