Shagun Sodhani

18 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 ↓

+6 more ↓

🗺️ Taxonomy Completionist (45) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird

🧬 Topic Evolution ⚡ Prolific Year · Productive 🔥 Unstoppable · Bronze ❓ The Questioner (2) 💎 Century Club · Bronze 🗃️ Keyword Collector (88)

Venues

ICLR (8) ICML (4) EMNLP (3) CVPR (1) L4DC (1) NeurIPS (1)

Top co-authors

Amy Zhang (9) Joelle Pineau (6) Sarath Chandar (3) Roberta Raileanu (2) Anirudh Goyal (2) Mikael Henaff (2) Gabriele Prato (2) Doina Precup (2) Pierre-Luc Bacon (2) Sergey Levine (2)

Research topics

Artificial Intelligence (13) Machine Learning (13) Learning Types · Machine Learning (13) Core AI (12) Deep Learning (8) Reinforcement Learning (8) Methods (8) Core Methods (5) Learning Types · Deep Learning (5) Architectures (4) Natural Language Processing (3) Optimization & Theory · Machine Learning (3) Application Areas (2) Learning Paradigms (2) Optimization & Theory · Deep Learning (2)

Keywords

reinforcement learning (5) representation learning (5) large language model (4) multi-task learning (3) offline reinforcement learning (2) transfer learning (2) systematic generalization (2) multi-task reinforcement learning (2) benchmark evaluation (2) state abstraction (2) visual representation (2) self-supervised learning (2) computer vision (1) network architecture (1) continual learning (1) feature learning (1) contrastive learning (1) knowledge distillation (1) data augmentation (1) attention mechanism (1)

Papers

MaestroMotif: Skill Design from Artificial Intelligence Feedback ICLR 2025 Do Large Language Models Know How Much They Know? EMNLP 2024 Harnessing small projectors and multiple views for efficient vision pretraining NeurIPS 2024 Motif: Intrinsic Motivation from Artificial Intelligence Feedback ICLR 2024 TorchRL: A data-driven decision-making library for PyTorch ICLR 2024 When should we prefer Decision Transformers for Offline Reinforcement Learning? ICLR 2024 EpiK-Eval: Evaluation for Language Models as Epistemic Models EMNLP 2023 VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training ICLR 2023 Block Contextual MDPs for Continual Learning L4DC 2022 Robust Policy Learning over Multiple Uncertainty Sets ICML 2022 The Neural Race Reduction: Dynamics of Abstraction in Gated Networks ICML 2022 IIRC: Incremental Implicitly-Refined Classification CVPR 2021 Learning Robust State Abstractions for Hidden-Parameter Block MDPs ICLR 2021 Multi-Task Reinforcement Learning with Context-based Representations ICML 2021 Recurrent Independent Mechanisms ICLR 2021 Invariant Causal Prediction for Block MDPs ICML 2020 Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives ICLR 2020 CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Text EMNLP 2019