Md Rifat Arefin

3 papers · 2024–2025 · 2 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 ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 📈 Trend Setter

Venues

ICML (2) ICLR (1)

Top co-authors

Irina Rish (2) Ravid Shwartz-Ziv (2) Yann LeCun (2) Yan Zhang (1) Oscar Skean (1) Niket Nikul Patel (1) Kenji Kawaguchi (1) Dan Zhao (1) Aristide Baratin (1) Gopeshh Subbaraj (1)

Research topics

Artificial Intelligence (2) Machine Learning (2) Core AI (2) Core Methods (2) Deep Learning (1) Natural Language Processing (1) Architectures (1) Learning Types · Deep Learning (1) Learning Types · Machine Learning (1) Optimization & Theory (1) Resources & Methods (1)

Keywords

information theory (1) unsupervised learning (1) benchmark dataset (1) language model (1) spurious correlation (1) representation collapse (1) object-centric representation (1) hidden representation (1) concept discovery (1) arithmetic reasoning (1) intermediate layer (1) decoder-only transformer (1) embedding quality (1) variance-covariance regularization (1) balancing technique (1) mid-depth embeddings (1)

Papers

Layer by Layer: Uncovering Hidden Representations in Language Models ICML 2025 Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced Reasoning ICLR 2025 Unsupervised Concept Discovery Mitigates Spurious Correlations ICML 2024