Skip to content
conftrace_

Sachin Mehta

17 papers · 2018–2025 · 7 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 ↓
+7 more ↓ πŸ—ΊοΈ Taxonomy Completionist (38) πŸƒ Academic Marathon Β· Sprint 🌍 Conference Polyglot Β· Silver πŸŒ‰ Interdisciplinary Bridge Β· Silver 🐣 Hot Topic Early Bird
🧬 Topic Evolution 🀝 Dynamic Duo (10) πŸ“ˆ Trend Setter πŸš€ Conference Pioneer πŸ’Ž Century Club Β· Bronze πŸ”₯ Unstoppable Β· Bronze πŸ—ƒοΈ Keyword Collector (87)

Venues

ICLR (6) EMNLP (4) ECCV (2) ICML (2) ACL (1) CVPR (1) ICCV (1)

Top co-authors

Mohammad Rastegari (10) Hannaneh Hajishirzi (8) Oncel Tuzel (5) Mehrdad Farajtabar (5) Fartash Faghri (4) Hadi Pouransari (4) Raviteja Vemulapalli (3) Ali Farhadi (3) Linda Shapiro (2) Rik Koncel-Kedziorski (2)

Research topics

Deep Learning (10) Machine Learning (10) Artificial Intelligence (8) Core AI (7) Application Areas (6) Natural Language Processing (5) Architectures (5) Computer Vision (4) Optimization & Theory (4) Techniques (4) Generation (3) Learning Types (3) Models (3) Applications (2) Core Methods (2)

Keywords

language modeling (4) model compression (3) parameter efficiency (3) transformer architecture (2) convolutional neural network (2) efficient computing (2) machine translation (2) continual learning (2) semantic segmentation (1) knowledge transfer (1) catastrophic forgetting (1) knowledge distillation (1) medical imaging (1) data augmentation (1) dynamic routing (1) object detection (1) visual reasoning (1) model architecture (1) adversarial robustness (1) multimodal learning (1)

Papers

CtrlSynth: Controllable Image Text Synthesis for Data-Efficient Multimodal Learning ICML 2025 SeedLM: Compressing LLM Weights into Seeds of Pseudo-Random Generators ICLR 2025 TiC-LM: A Web-Scale Benchmark for Time-Continual LLM Pretraining ACL 2025 Knowledge Transfer from Vision Foundation Models for Efficient Training of Small Task-specific Models ICML 2024 ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models ICLR 2024 TiC-CLIP: Continual Training of CLIP Models ICLR 2024 Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Reinforcement ICCV 2023 SHARCS: Efficient Transformers Through Routing with Dynamic Width Sub-networks EMNLP 2023 MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer ICLR 2022 SPIN: An Empirical Evaluation on Sharing Parameters of Isotropic Networks ECCV 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 ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation ECCV 2018 Pyramidal Recurrent Unit for Language Modeling EMNLP 2018