Kushal Tirumala
7 papers · 2022–2025 · 4 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 ↓
๐
Conference Polyglot ยท Bronze
๐
Interdisciplinary Bridge ยท Bronze
๐บ๏ธ
Taxonomy Completionist
(18)
๐ฃ
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Keywords
large language model
(2)
zero-shot learning
(1)
image generation
(1)
natural language processing
(1)
model evaluation
(1)
multimodal learning
(1)
web corpus
(1)
efficient computing
(1)
dataset collection
(1)
generalization bound
(1)
diffusion model
(1)
multimodal dataset
(1)
data selection
(1)
parameter-efficient fine-tuning
(1)
next-token prediction
(1)
training dynamics
(1)
causal language modeling
(1)
clip model
(1)
benchmark framework
(1)
masked language modeling
(1)
Papers
The Unreasonable Ineffectiveness of the Deeper Layers
ICLR 2025
Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model
ICLR 2025
Effective pruning of web-scale datasets based on complexity of concept clusters
ICLR 2024
D4: Improving LLM Pretraining via Document De-Duplication and Diversification
NeurIPS 2023
Dynatask: A Framework for Creating Dynamic AI Benchmark Tasks
ACL 2022
Investigating Generalization by Controlling Normalized Margin
ICML 2022
Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models
NeurIPS 2022