Sadhika Malladi
17 papers · 2021–2025 · 3 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 ↓+5 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (31) π£ Hot Topic Early Bird π Conference Polyglot Β· Bronze π€ Dynamic Duo (10)
π
Triple Crown
β‘
Prolific Year Β· Productive
π₯
Unstoppable Β· Bronze
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(79)
Venues
Top co-authors
Research topics
Machine Learning
(14)
Artificial Intelligence
(11)
Core AI
(10)
Optimization & Theory Β· Machine Learning
(8)
Natural Language Processing
(6)
Application Areas
(5)
Deep Learning
(4)
Learning Types
(4)
Learning Paradigms
(3)
Optimization & Theory Β· Deep Learning
(3)
Resources & Methods
(3)
Applications
(2)
Mathematics & Optimization
(1)
Core Methods
(1)
Generation
(1)
Keywords
neural network optimization
(3)
language model alignment
(2)
learning rate
(2)
in-context learning
(2)
machine unlearning
(2)
direct preference optimization
(2)
language model fine-tuning
(2)
stochastic differential equation
(2)
fine tuning
(2)
language model
(2)
stochastic gradient descent
(2)
model safety
(1)
visual reasoning
(1)
preference learning
(1)
benchmark evaluation
(1)
transformer
(1)
pretraining
(1)
sample complexity
(1)
text classification
(1)
reinforcement learning from human feedback
(1)
Papers
Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws
ICLR 2025
Metadata Conditioning Accelerates Language Model Pre-training
ICML 2025
MUSE: Machine Unlearning Six-Way Evaluation for Language Models
ICLR 2025
Overtrained Language Models Are Harder to Fine-Tune
ICML 2025
Progressive distillation induces an implicit curriculum
ICLR 2025
Provable unlearning in topic modeling and downstream tasks
ICLR 2025
Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization
ICLR 2025
CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs
NeurIPS 2024
LESS: Selecting Influential Data for Targeted Instruction Tuning
ICML 2024
Preference Learning Algorithms Do Not Learn Preference Rankings
NeurIPS 2024
The Marginal Value of Momentum for Small Learning Rate SGD
ICLR 2024
Trainable Transformer in Transformer
ICML 2024
A Kernel-Based View of Language Model Fine-Tuning
ICML 2023
Fine-Tuning Language Models with Just Forward Passes
NeurIPS 2023
On the SDEs and Scaling Rules for Adaptive Gradient Algorithms
NeurIPS 2022
A Mathematical Exploration of Why Language Models Help Solve Downstream Tasks
ICLR 2021
On the Validity of Modeling SGD with Stochastic Differential Equations (SDEs)
NeurIPS 2021