← Authors

Karttikeya Mangalam

28 papers · 2018–2025 · 9 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (12) 🌍 Conference Polyglot (9) πŸƒ Academic Marathon (7) 🌈 Renaissance Researcher (9) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (61) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🀝 Dynamic Duo (16) 🧬 Topic Evolution πŸ† Keyword Champion (2) πŸ‘₯ Mega-Team (85) πŸ’Ž Century Club (28) πŸ—ƒοΈ Keyword Collector (131) πŸ”₯ Unstoppable (6) ❓ The Questioner ⚑ Prolific Year (5) πŸš€ Conference Pioneer

Conferences

CVPR (11) ICCV (4) NIPS (4) ECCV (3) ACL (2) ICML (1) INTERSPEECH (1) NAACL (1) WACV (1)

Top co-authors

Jitendra Malik (16) Yanghao Li (6) Christoph Feichtenhofer (6) Trevor Darrell (5) haoqi fan (5) Harshayu Girase (4) Bo Xiong (4) Kurt Keutzer (3) Chao-Yuan Wu (3) Chen Zhao (3)

Research topics

Representation (1)

Keywords

vision transformer (5) video understanding (5) action recognition (3) image classification (3) model compression (3) large language model (3) action forecasting (2) benchmark dataset (2) pedestrian prediction (2) trajectory forecasting (2) representation learning (2) efficient computing (2) multimodal learning (2) video recognition (2) transformer architecture (2) trajectory prediction (2) memory efficiency (2) video classification (2) graph matching (1) scene understanding (1)

Papers

UPSC2M: Benchmarking Adaptive Learning from Two Million MCQ Attempts ACL 2025
LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement ACL 2024
Re-evaluating the Need for Visual Signals in Unsupervised Grammar Induction NAACL 2024
xT: Nested Tokenization for Larger Context in Large Images ICML 2024
Do Vision and Language Encoders Represent the World Similarly? CVPR 2024
Adaptive Human Trajectory Prediction via Latent Corridors ECCV 2024
Sequential Modeling Enables Scalable Learning for Large Vision Models CVPR 2024
Dr2Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient Finetuning CVPR 2024
Latency Matters: Real-Time Action Forecasting Transformer CVPR 2023
Diffusion Models as Masked Autoencoders ICCV 2023
Speculative Decoding with Big Little Decoder NIPS 2023
EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding NIPS 2023
Re2TAL: Rewiring Pretrained Video Backbones for Reversible Temporal Action Localization CVPR 2023
Squeezeformer: An Efficient Transformer for Automatic Speech Recognition NIPS 2022
Bringing Image Scene Structure to Video via Frame-Clip Consistency of Object Tokens NIPS 2022
MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition CVPR 2022
Reversible Vision Transformers CVPR 2022
MViTv2: Improved Multiscale Vision Transformers for Classification and Detection CVPR 2022
Object-Region Video Transformers CVPR 2022
Ego4D: Around the World in 3,000 Hours of Egocentric Video CVPR 2022
Multiscale Vision Transformers ICCV 2021
LOKI: Long Term and Key Intentions for Trajectory Prediction ICCV 2021
From Goals, Waypoints & Paths to Long Term Human Trajectory Forecasting ICCV 2021
Disentangling Human Dynamics for Pedestrian Locomotion Forecasting with Noisy Supervision WACV 2020
It is not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction ECCV 2020
Long-term Human Motion Prediction with Scene Context ECCV 2020
Future Person Localization in First-Person Videos CVPR 2018
Learning Spontaneity to Improve Emotion Recognition in Speech INTERSPEECH 2018