Sarthak Mittal
13 papers · 2020–2025 · 5 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 ↓+3 more ↓ Show less ↑
🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (31) 🌍 Conference Polyglot · Silver 🗃️ Keyword Collector (78)
❓
The Questioner
(2)
🌈
Renaissance Researcher
(5)
💎
Century Club · Bronze
Venues
Top co-authors
Research topics
Machine Learning
(13)
Deep Learning
(9)
Learning Types · Machine Learning
(6)
Core Methods
(5)
Models
(5)
Optimization & Theory
(5)
Artificial Intelligence
(4)
Core AI
(4)
Learning Types · Deep Learning
(4)
Architectures
(3)
Application Areas
(2)
Knowledge & Reasoning
(1)
Mathematics & Optimization
(1)
Natural Language Processing
(1)
Reinforcement Learning
(1)
Keywords
diffusion model
(4)
in-context learning
(2)
transformer architecture
(2)
variational inference
(2)
attention mechanism
(2)
text-to-image generation
(1)
multimodal learning
(1)
reinforcement learning
(1)
multilingual translation
(1)
semi-supervised classification
(1)
offline reinforcement learning
(1)
model architecture
(1)
data augmentation
(1)
out-of-distribution generalization
(1)
model complexity
(1)
reinforcement learning from human feedback
(1)
posterior inference
(1)
data compression
(1)
machine translation
(1)
semi-supervised learning
(1)
Papers
Does learning the right latent variables necessarily improve in-context learning?
ICML 2025
In-Context Learning and Occam’s Razor
ICML 2025
Learning Condensed Graph via Differentiable Atom Mapping for Reaction Yield Prediction
ICML 2025
Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction
ICLR 2025
Amortizing intractable inference in diffusion models for vision, language, and control
NeurIPS 2024
Improved off-policy training of diffusion samplers
NeurIPS 2024
Iterated Denoising Energy Matching for Sampling from Boltzmann Densities
ICML 2024
Diffusion Based Representation Learning
ICML 2023
Leveraging Synthetic Targets for Machine Translation
ACL 2023
MixupE: Understanding and improving Mixup from directional derivative perspective
UAI 2023
Compositional Attention: Disentangling Search and Retrieval
ICLR 2022
Is a Modular Architecture Enough?
NeurIPS 2022
Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules
ICML 2020