Scholar
Anuj Kumar
Google Scholar ID: _QMxs4kAAAAJ
Meta
NLP
Computer Vision
Speech Recognition
Artificial Intelligence
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
1,927
H-index
17
i10-index
21
Publications
20
Co-authors
31
list available
Publications
8 items
IdeaScientist: Orchestrating Agents for Grounded Scientific Ideation
2026
Cited
0
MemLife: Curating and Reasoning over Long-Term Egocentric Video Memories
2026
Cited
0
MoE-ViE: Mixture of Experts Vision Encoder for Efficient Image and Video Understanding
2026
Cited
0
R3D: Quantitative 3D Spatial Reasoning for Egocentric Wearables
2026
Cited
0
Plan, Watch, Recover: A Benchmark and Architectures for Proactive Procedural Assistance
2026
Cited
0
SaliMory: Orchestrating Cognitive Memory for Conversational Agents
2026
Cited
0
Aligning Paralinguistic Understanding and Generation in Speech LLMs via Multi-Task Reinforcement Learning
2026
Cited
0
Pixel-Grounded Retrieval for Knowledgeable Large Multimodal Models
2026
Cited
0
Co-authors
10 total
Seungwhan Moon
Facebook, Carnegie Mellon University
John Canny
University of California, Berkeley
Akhil Mathur
Meta AI
Mike Lewis
Facebook AI Research
Benoit Dumoulin
Amazon
Duc Bui
Snap Inc.
Florian Metze
Carnegie Mellon University; Meta AI
Yoshua Bengio
Professor of computer science, University of Montreal, Mila, IVADO, CIFAR