Manjesh Kumar Hanawal
10 papers · 2020–2025 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π§ Keyword Pioneer π Interdisciplinary Bridge π Conference Polyglot (7) π Academic Marathon (5) π Cross-Pollinator (10)
π
Renaissance Researcher
(6)
πΊοΈ
Taxonomy Completionist
(23)
π
Century Club
(10)
Conferences
ACL (2)
EMNLP (2)
NIPS (2)
AACL (1)
EACL (1)
ICLR (1)
IJCNLP (1)
Top co-authors
Keywords
early exit
(4)
vision-language model
(3)
model compression
(3)
imitation learning
(2)
inference acceleration
(2)
multi-armed bandit
(2)
regret bound
(2)
knowledge distillation
(2)
autoregressive decoding
(2)
self-speculative decoding
(2)
model robustness
(1)
adversarial training
(1)
efficient inference
(1)
weak supervision
(1)
unsupervised domain adaptation
(1)
text classification
(1)
adversarial adaptation
(1)
rule-based learning
(1)
upper confidence bound
(1)
image captioning
(1)
Papers
FREE: Fast and Robust Vision Language Models with Early Exits
ACL 2025
BEEM: Boosting Performance of Early Exit DNNs using Multi-Exit Classifiers as Experts
ICLR 2025
FastVLM: Self-Speculative Decoding for Fast Vision-Language Model Inference
AACL 2025
FastVLM: Self-Speculative Decoding for Fast Vision-Language Model Inference
IJCNLP 2025
FAIR: Filtering of Automatically Induced Rules
EACL 2024
CeeBERT: Cross-Domain Inference in Early Exit BERT
ACL 2024
DAdEE: Unsupervised Domain Adaptation in Early Exit PLMs
EMNLP 2024
CapEEN: Image Captioning with Early Exits and Knowledge Distillation
EMNLP 2024
Stochastic Multi-Armed Bandits with Control Variates
NIPS 2021
Online Algorithm for Unsupervised Sequential Selection with Contextual Information
NIPS 2020