Anima Anandkumar
Caltech professor and former NVIDIA director of ML research; pioneer in tensor methods and AI for science.
- Role
- professor
- Currently at
- Independent
- twitter.com/AnimaAnandkumar
- Scholar
- scholar.google.com/citations
- Papers
- 38
Cite
Notes
Only stored in your browser.
Authored papers
38Operator Learning Using Weak Supervision from Walk-on-Spheres
arXiv 2026
R-KV: Redundancy-aware KV Cache Compression for Training-Free Reasoning Models Acceleration
arXiv 2025
Guided Diffusion Sampling on Function Spaces with Applications to PDEs
arXiv 2025
HeadInfer: Memory-Efficient LLM Inference by Head-wise Offloading
arXiv 2025
Robust Representation Consistency Model via Contrastive Denoising
arXiv 2025
Principled Approaches for Extending Neural Architectures to Function Spaces for Operator Learning
arXiv 2025
GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
arXiv 2024
A Unified Model for Compressed Sensing MRI Across Undersampling Patterns
CVPR 2025 1
LeanAgent: Lifelong Learning for Formal Theorem Proving
arXiv 2024
Pretraining Codomain Attention Neural Operators for Solving Multiphysics PDEs
arXiv 2024
Mini-Sequence Transformer: Optimizing Intermediate Memory for Long Sequences Training
arXiv 2024
CARE: a Benchmark Suite for the Classification and Retrieval of Enzymes
arXiv 2024
Fully Attentional Networks with Self-emerging Token Labeling
fully-attentional-networks-with-self-emerging
ChatGPT Based Data Augmentation for Improved Parameter-Efficient Debiasing of LLMs
arXiv 2024
Multi-Modal Self-Supervised Learning for Surgical Feedback Effectiveness Assessment
arXiv 2024
Improving Diffusion Inverse Problem Solving with Decoupled Noise Annealing
CVPR 2025 1
T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching
arXiv 2024
DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Training
arXiv 2024
Automating Feedback Analysis in Surgical Training: Detection, Categorization, and Assessment
arXiv 2024
Voyager: An Open-Ended Embodied Agent with Large Language Models
arXiv 2023
LeanDojo: Theorem Proving with Retrieval-Augmented Language Models
leandojo-theorem-proving-with-retrieval
Eureka: Human-Level Reward Design via Coding Large Language Models
arXiv 2023
FB-BEV: BEV Representation from Forward-Backward View Transformations
ICCV 2023 1
VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion
CVPR 2023 1
Prismer: A Vision-Language Model with Multi-Task Experts
arXiv 2023
Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo
arXiv 2023
A Text-guided Protein Design Framework
arXiv 2023
MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge
arXiv 2022
Multi-modal Molecule Structure-text Model for Text-based Retrieval and Editing
arXiv 2022
Diffusion Models for Adversarial Purification
arXiv 2022
Fast Sampling of Diffusion Models via Operator Learning
arXiv 2022
VIMA: General Robot Manipulation with Multimodal Prompts
arXiv 2022
Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models
arXiv 2022
Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactions
CVPR 2022 1
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers
NeurIPS 2021 12
Neural Operator: Learning Maps Between Function Spaces
arXiv 2021
Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers
CVPR 2022 1
ZerO Initialization: Initializing Neural Networks with only Zeros and Ones
zero-initialization-initializing-residual
Affiliations
Previously
Frequent co-authors
10from 38 papers