Aman Timalsina

4 papers · 2023–2024 · 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 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (10)

Venues

ICLR (2) ICML (1) NeurIPS (1)

Top co-authors

Christopher Re (4) Atri Rudra (4) Simran Arora (2) Michael Poli (2) James Zou (2) Isys Johnson (2) Sabri Eyuboglu (2) Hermann Kumbong (1) Dan Fu (1) Yoshua Bengio (1)

Research topics

Artificial Intelligence (3) Machine Learning (3) Core AI (3) Deep Learning (2) Application Areas (2) Natural Language Processing (1) Core Methods (1) Generation (1) Learning Paradigms (1) Learning Types (1) Models (1)

Keywords

state space model (2) sequence modeling (1) attention mechanism (1) knowledge distillation (1) language model (1) sequence model (1) inference efficiency (1) parameter efficiency (1) linear attention (1) long-range dependency (1) sliding window attention (1) convolution neural network (1) gated convolution (1) associative recall (1) legendre polynomial (1) orthogonal basis projection (1) perplexity (1) throughput (1) recall (1) model compression (1)

Papers

Simple linear attention language models balance the recall-throughput tradeoff ICML 2024 Zoology: Measuring and Improving Recall in Efficient Language Models ICLR 2024 How to Train your HIPPO: State Space Models with Generalized Orthogonal Basis Projections ICLR 2023 Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions NeurIPS 2023