Karttikeya Mangalam
28 papers · 2018–2025 · 9 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 ↓+12 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (56) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird
π€
Dynamic Duo
(16)
π§¬
Topic Evolution
π
Keyword Champion
(2)
π₯
Mega-Team Β· Legion
π¬
Deep Specialist
(10)
π
Conference Pioneer
π₯
Unstoppable Β· Bronze
β
The Questioner
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
π
Renaissance Researcher
(7)
ποΈ
Keyword Collector
(135)
Top co-authors
Research topics
Deep Learning
(17)
Architectures
(13)
Machine Learning
(12)
Computer Vision
(11)
Artificial Intelligence
(10)
Core AI
(10)
Analysis
(7)
Application Areas
(6)
Learning Types Β· Machine Learning
(5)
Optimization & Theory
(5)
Processing
(5)
Techniques
(5)
Natural Language Processing
(4)
Core Methods
(4)
Learning Types Β· Deep Learning
(4)
Keywords
vision transformer
(6)
video understanding
(5)
model compression
(3)
image classification
(3)
action recognition
(3)
large language model
(3)
action forecasting
(2)
benchmark dataset
(2)
pedestrian prediction
(2)
trajectory forecasting
(2)
representation learning
(2)
efficient computing
(2)
video recognition
(2)
transformer architecture
(2)
multimodal learning
(2)
trajectory prediction
(2)
memory efficiency
(2)
video classification
(2)
scene understanding
(1)
feature extraction
(1)
Papers
UPSC2M: Benchmarking Adaptive Learning from Two Million MCQ Attempts
ACL 2025
Adaptive Human Trajectory Prediction via Latent Corridors
ECCV 2024
Do Vision and Language Encoders Represent the World Similarly?
CVPR 2024
Dr2Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient Finetuning
CVPR 2024
LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement
ACL 2024
Re-evaluating the Need for Visual Signals in Unsupervised Grammar Induction
NAACL 2024
Sequential Modeling Enables Scalable Learning for Large Vision Models
CVPR 2024
xT: Nested Tokenization for Larger Context in Large Images
ICML 2024
Diffusion Models as Masked Autoencoders
ICCV 2023
EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding
NeurIPS 2023
Latency Matters: Real-Time Action Forecasting Transformer
CVPR 2023
Re2TAL: Rewiring Pretrained Video Backbones for Reversible Temporal Action Localization
CVPR 2023
Speculative Decoding with Big Little Decoder
NeurIPS 2023
Bringing Image Scene Structure to Video via Frame-Clip Consistency of Object Tokens
NeurIPS 2022
Ego4D: Around the World in 3,000 Hours of Egocentric Video
CVPR 2022
MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition
CVPR 2022
MViTv2: Improved Multiscale Vision Transformers for Classification and Detection
CVPR 2022
Object-Region Video Transformers
CVPR 2022
Reversible Vision Transformers
CVPR 2022
Squeezeformer: An Efficient Transformer for Automatic Speech Recognition
NeurIPS 2022
From Goals, Waypoints & Paths to Long Term Human Trajectory Forecasting
ICCV 2021
LOKI: Long Term and Key Intentions for Trajectory Prediction
ICCV 2021
Multiscale Vision Transformers
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