◍wovepaper
SearchResearchersInstitutions
Sign in
institution

Science Club

United States

1 paper here
fields
  • cs.LG1
ROR 02zvcx647OpenAlex

affiliations via OpenAlex

researchers with a paper here
  • Anupriya Sharma1 · h 0
  • Dr. Deepanshu Mishra1 · h 0
  • Haoan Wang1 · h 9
  • Rishi Bhatia1 · h 3
  • Saipraveen Vabbilisetty1 · h 0
  • S. Alugubelli1 · h 0
  • Shashank Kapadia1 · h 1
collaborating institutions
  • Walmart (United States)US1 paper
Showing cs.LGShow all

2 papers · 1 filter

cs.LG2026

LEAP: Layer-wise Exit-Aware Pretraining for Efficient Transformer Inference

Shashank Kapadia, Deep Naryan Mishra, Sujal Reddy Alugubelli +4

Layer-aligned distillation and convergence-based early exit represent two predominant computational efficiency paradigms for transformer inference; yet we establish that they exhib…

cs.LG2026

SAGE: Sign-Adaptive Gradient for Memory-Efficient LLM Optimization

Wooin Lee, Hyun-Tae Kim

The AdamW optimizer, while standard for LLM pretraining, is a critical memory bottleneck, consuming optimizer states equivalent to twice the model's size. Although light-state opti…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.