Skip to content
conftrace_

Chanakya Ekbote

4 papers · 2023–2025 · 3 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 🗺️ Taxonomy Completionist (16)

Venues

NeurIPS (2) ACL (1) ICML (1)

Top co-authors

Paul Pu Liang (2) Marco Bondaschi (1) Ashok Vardhan Makkuva (1) Sandeep Polisetty (1) SUNDARARAJAN SELLAMANICKAM (1) Hyeji Kim (1) Ramakrishna Bairi (1) Liu Ziyin (1) Jaewoo Lee (1) Ajinkya Deshpande (1)

Research topics

Deep Learning (3) Machine Learning (3) Artificial Intelligence (2) Architectures (2) Core AI (2) Learning Types · Deep Learning (2) Optimization & Theory · Deep Learning (2) Application Areas (1) Core Methods (1) Learning Types · Machine Learning (1) Optimization & Theory · Machine Learning (1)

Keywords

unsupervised learning (1) contrastive learning (1) embedding learning (1) multimodal learning (1) graph representation (1) model pruning (1) markov chain (1) multimodal representation learning (1) learning dynamics (1) next-token prediction (1) multimodal large language model (1) weight pruning (1) token pruning (1) parameter efficiency (1) layer-wise pruning (1) parameter initialization (1) global minimum (1) node representation (1) node representation learning (1) local minimum (1)

Papers

TAMP: Token-Adaptive Layerwise Pruning in Multimodal Large Language Models ACL 2025 Understanding the Emergence of Multimodal Representation Alignment ICML 2025 Local to Global: Learning Dynamics and Effect of Initialization for Transformers NeurIPS 2024 FiGURe: Simple and Efficient Unsupervised Node Representations with Filter Augmentations NeurIPS 2023