Tanishq Kumar

5 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 🗺️ Taxonomy Completionist (12) ❓ The Questioner

Venues

ICLR (3) ICML (2)

Top co-authors

Cengiz Pehlevan (3) Blake Bordelon (3) Aditi Raghunathan (2) Samuel J. Gershman (2) Mansheej Paul (1) Kevin Luo (1) Jacob Mitchell Springer (1) Mark Sellke (1) Niklas Muennighoff (1) Sadhika Malladi (1)

Research topics

Machine Learning (5) Optimization & Theory (4) Artificial Intelligence (3) Core AI (3) Deep Learning (2) Architectures (2) Natural Language Processing (1) Application Areas (1) Core Methods (1) Learning Types (1) Resources & Methods (1)

Keywords

representation learning (1) neural tangent kernel (1) feature learning (1) robustness (1) pretraining (1) mutual information (1) gradient descent (1) margin maximization (1) neural representation (1) scaling law (1) model degradation (1) pruning at initialization (1) fine tuning (1) lazy training (1) lottery ticket (1) neural network (1) token budget (1) sparse subnetwork (1) precision training (1) effective parameter count (1)

Papers

Do Mice Grok? Glimpses of Hidden Progress in Sensory Cortex ICLR 2025 Overtrained Language Models Are Harder to Fine-Tune ICML 2025 Scaling Laws for Precision ICLR 2025 Grokking as the transition from lazy to rich training dynamics ICLR 2024 No Free Prune: Information-Theoretic Barriers to Pruning at Initialization ICML 2024