Aditya Rawal
8 papers · 2019–2025 · 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 ↓+2 more ↓ Show less ↑
🏃 Academic Marathon · Sprint 🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge · Bronze 🌍 Conference Polyglot · Silver 🗺️ Taxonomy Completionist (31)
📈
Trend Setter
🗃️
Keyword Collector
(50)
Top co-authors
Research topics
Machine Learning
(8)
Artificial Intelligence
(7)
Core AI
(7)
Learning Types · Machine Learning
(6)
Deep Learning
(5)
Application Areas
(4)
Optimization & Theory
(3)
Architectures
(2)
Learning Paradigms · Machine Learning
(2)
Learning Paradigms · Artificial Intelligence
(2)
Learning Types · Deep Learning
(2)
Models
(2)
Reinforcement Learning
(1)
Applications
(1)
Methods
(1)
Keywords
continual learning
(2)
large language model
(2)
instruction following
(2)
reinforcement learning
(2)
model merging
(2)
multi-task learning
(1)
knowledge distillation
(1)
zero-shot learning
(1)
model calibration
(1)
curriculum learning
(1)
catastrophic forgetting
(1)
preference optimization
(1)
incremental learning
(1)
neural architecture search
(1)
network architecture
(1)
adversarial training
(1)
adversarial robustness
(1)
synthetic data generation
(1)
gradient descent
(1)
contrastive learning
(1)
Papers
Sequence-level Large Language Model Training with Contrastive Preference Optimization
NAACL 2025
Split-Merge: Scalable and Memory-Efficient Merging of Expert LLMs
EMNLP 2025
DEM: Distribution Edited Model for Training with Mixed Data Distributions
EMNLP 2024
Extreme Miscalibration and the Illusion of Adversarial Robustness
ACL 2024
Memory Efficient Continual Learning with Transformers
NeurIPS 2022
Enhanced POET: Open-ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions
ICML 2020
Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data
ICML 2020
Backpropamine: training self-modifying neural networks with differentiable neuromodulated plasticity
ICLR 2019