Irina Rish

11

Papers

52

Total Citations

Papers (11)

Context is Key: A Benchmark for Forecasting with Essential Textual Information

Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching

Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced Reasoning

Surprising Effectiveness of pretraining Ternary Language Model at Scale

Unsupervised Concept Discovery Mitigates Spurious Correlations

Parametric Scattering Networks

Online Fast Adaptation and Knowledge Accumulation (OSAKA): a New Approach to Continual Learning

Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization

NeurIPS 2021arXiv

Adversarial Feature Desensitization

NeurIPS 2021arXiv

Continual Learning In Environments With Polynomial Mixing Times

NeurIPS 2022arXiv

Maximum State Entropy Exploration using Predecessor and Successor Representations

NeurIPS 2023arXiv