Prashant Khanduri
13 papers · 2021–2026 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
π Cross-Pollinator (11) π Interdisciplinary Bridge π Conference Polyglot (5) π§ Keyword Pioneer π Academic Marathon (5)
πΊοΈ
Taxonomy Completionist
(26)
π
Conference Polyglot
(5)
π
Grand Slam
π
Century Club
(12)
π₯
Unstoppable
(5)
ποΈ
Keyword Collector
(54)
Conferences
ICML (6)
NIPS (2)
WACV (2)
AAAI (1)
ECCV (1)
ICLR (1)
Top co-authors
Keywords
federated learning
(3)
bilevel optimization
(3)
stochastic gradient
(2)
sample complexity
(2)
convergence analysis
(2)
medical image segmentation
(2)
communication complexity
(2)
neural network
(2)
computed tomography
(2)
stochastic optimization
(2)
robust classification
(1)
machine unlearning
(1)
decentralized optimization
(1)
constrained optimization
(1)
preference optimization
(1)
linear convergence
(1)
adversarial training
(1)
projected gradient descent
(1)
strong convexity
(1)
strongly convex
(1)
Papers
Not All Tokens Are Meant to Be Forgotten
AAAI 2026
MulModSeg: Enhancing Unpaired Multi-Modal Medical Image Segmentation with Modality-Conditioned Text Embedding and Alternating Training
WACV 2025
AutoProSAM: Automated Prompting SAM for 3D Multi-Organ Segmentation
WACV 2025
Understanding Server-Assisted Federated Learning in the Presence of Incomplete Client Participation
ICML 2024
Fairness-aware Vision Transformer via Debiased Self-Attention
ECCV 2024
Linearly Constrained Bilevel Optimization: A Smoothed Implicit Gradient Approach
ICML 2023
Prometheus: Taming Sample and Communication Complexities in Constrained Decentralized Stochastic Bilevel Learning
ICML 2023
FedAvg Converges to Zero Training Loss Linearly for Overparameterized Multi-Layer Neural Networks
ICML 2023
Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimization
ICML 2022
Anarchic Federated Learning
ICML 2022
Decentralized Learning for Overparameterized Problems: A Multi-Agent Kernel Approximation Approach
ICLR 2022
A Near-Optimal Algorithm for Stochastic Bilevel Optimization via Double-Momentum
NIPS 2021
STEM: A Stochastic Two-Sided Momentum Algorithm Achieving Near-Optimal Sample and Communication Complexities for Federated Learning
NIPS 2021