Sarthak Mittal
13 papers · 2020–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (26) π Interdisciplinary Bridge π§ Keyword Pioneer π Cross-Pollinator (13) π Renaissance Researcher (5)
π
Conference Polyglot
(5)
π
Academic Marathon
(5)
π
Century Club
(13)
β
The Questioner
(2)
Conferences
ICML (6)
NIPS (3)
ICLR (2)
ACL (1)
UAI (1)
Top co-authors
Keywords
diffusion model
(3)
variational inference
(2)
semi-supervised learning
(1)
multimodal learning
(1)
attention mechanism
(1)
machine translation
(1)
multilingual translation
(1)
generative model
(1)
inductive bia
(1)
text-to-image generation
(1)
out-of-distribution generalization
(1)
posterior inference
(1)
semi-supervised classification
(1)
amortized inference
(1)
energy function
(1)
data augmentation
(1)
offline reinforcement learning
(1)
recurrent neural network
(1)
reinforcement learning
(1)
representation learning
(1)
Papers
In-Context Learning and Occamβs Razor
ICML 2025
Does learning the right latent variables necessarily improve in-context learning?
ICML 2025
Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction
ICLR 2025
Learning Condensed Graph via Differentiable Atom Mapping for Reaction Yield Prediction
ICML 2025
Amortizing intractable inference in diffusion models for vision, language, and control
NIPS 2024
Iterated Denoising Energy Matching for Sampling from Boltzmann Densities
ICML 2024
Improved off-policy training of diffusion samplers
NIPS 2024
MixupE: Understanding and improving Mixup from directional derivative perspective
UAI 2023
Diffusion Based Representation Learning
ICML 2023
Leveraging Synthetic Targets for Machine Translation
ACL 2023
Is a Modular Architecture Enough?
NIPS 2022
Compositional Attention: Disentangling Search and Retrieval
ICLR 2022
Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules
ICML 2020