Sachin Mehta
17 papers · 2018–2025 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+10 more ↓ Show less ↑
π Interdisciplinary Bridge π Renaissance Researcher (5) π Conference Polyglot (7) π Academic Marathon (7) πΊοΈ Taxonomy Completionist (32)
πΊοΈ
Taxonomy Completionist
(32)
π§
Keyword Pioneer
π£
Hot Topic Early Bird
π§¬
Topic Evolution
π€
Dynamic Duo
(10)
π
Trend Setter
π
Conference Pioneer
π₯
Unstoppable
(8)
ποΈ
Keyword Collector
(52)
π
Century Club
(17)
Conferences
ICLR (6)
EMNLP (4)
ECCV (2)
ICML (2)
ACL (1)
CVPR (1)
ICCV (1)
Top co-authors
Keywords
efficient computing
(2)
language modeling
(2)
transformer architecture
(1)
catastrophic forgetting
(1)
semantic segmentation
(1)
adversarial robustness
(1)
medical imaging
(1)
efficient inference
(1)
knowledge distillation
(1)
data augmentation
(1)
object detection
(1)
multimodal learning
(1)
visual reasoning
(1)
dynamic routing
(1)
continual learning
(1)
model compression
(1)
adaptive inference
(1)
convolutional neural network
(1)
long short-term memory
(1)
neural network architecture
(1)
Papers
TiC-LM: A Web-Scale Benchmark for Time-Continual LLM Pretraining
ACL 2025
SeedLM: Compressing LLM Weights into Seeds of Pseudo-Random Generators
ICLR 2025
CtrlSynth: Controllable Image Text Synthesis for Data-Efficient Multimodal Learning
ICML 2025
Knowledge Transfer from Vision Foundation Models for Efficient Training of Small Task-specific Models
ICML 2024
TiC-CLIP: Continual Training of CLIP Models
ICLR 2024
ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models
ICLR 2024
SHARCS: Efficient Transformers Through Routing with Dynamic Width Sub-networks
EMNLP 2023
Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Reinforcement
ICCV 2023
SPIN: An Empirical Evaluation on Sharing Parameters of Isotropic Networks
ECCV 2022
MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer
ICLR 2022
DeLighT: Deep and Light-weight Transformer
ICLR 2021
Iconary: A Pictionary-Based Game for Testing Multimodal Communication with Drawings and Text
EMNLP 2021
DeFINE: Deep Factorized Input Token Embeddings for Neural Sequence Modeling
ICLR 2020
MedICaT: A Dataset of Medical Images, Captions, and Textual References
EMNLP 2020
ESPNetv2: A Light-Weight, Power Efficient, and General Purpose Convolutional Neural Network
CVPR 2019
Pyramidal Recurrent Unit for Language Modeling
EMNLP 2018
ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation
ECCV 2018