Anima Anandkumar

55

Papers

557

Total Citations

Papers (55)

Eureka: Human-Level Reward Design via Coding Large Language Models

Online and Differentially-Private Tensor Decomposition

NeurIPS 2016arXiv

PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees

LeanAgent: Lifelong Learning for Formal Theorem Proving

Guided Diffusion Sampling on Function Spaces with Applications to PDEs

NeurIPS 2025arXiv

A Unified Model for Compressed Sensing MRI Across Undersampling Patterns

Autoformalizing Euclidean Geometry

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

Solving Poisson Equations using Neural Walk-on-Spheres

Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactions

FreeSOLO: Learning To Segment Objects Without Annotations

Not All Labels Are Equal: Rationalizing the Labeling Costs for Training Object Detection

Panoptic SegFormer: Delving Deeper Into Panoptic Segmentation With Transformers

Vision Transformers Are Good Mask Auto-Labelers

Fast Monocular Scene Reconstruction With Global-Sparse Local-Dense Grids

VoxFormer: Sparse Voxel Transformer for Camera-Based 3D Semantic Scene Completion

DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence From Box Supervision

Spacetime Surface Regularization for Neural Dynamic Scene Reconstruction

Fully Attentional Networks with Self-emerging Token Labeling

End-to-end 3D Tracking with Decoupled Queries

FB-BEV: BEV Representation from Forward-Backward View Transformations

FocalFormer3D: Focusing on Hard Instance for 3D Object Detection

AdvDO: Realistic Adversarial Attacks for Trajectory Prediction

Augmenting Deep Classifiers with Polynomial Neural Networks

Fast and Guaranteed Tensor Decomposition via Sketching

Self-Calibrating Neural Radiance Fields

Improving Diffusion Inverse Problem Solving with Decoupled Noise Annealing

Improving Distant 3D Object Detection Using 2D Box Supervision

DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Training

Neural Operators with Localized Integral and Differential Kernels

Equivariant Graph Neural Operator for Modeling 3D Dynamics

Competitive Gradient Descent

Neural Networks with Recurrent Generative Feedback

Multipole Graph Neural Operator for Parametric Partial Differential Equations

Causal Discovery in Physical Systems from Videos

Learning compositional functions via multiplicative weight updates

Convolutional Tensor-Train LSTM for Spatio-Temporal Learning

Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning

Logarithmic Regret Bound in Partially Observable Linear Dynamical Systems

AugMax: Adversarial Composition of Random Augmentations for Robust Training

Coupled Segmentation and Edge Learning via Dynamic Graph Propagation

SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers

Controllable and Compositional Generation with Latent-Space Energy-Based Models

Adversarially Robust 3D Point Cloud Recognition Using Self-Supervisions

Long-Short Transformer: Efficient Transformers for Language and Vision

Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Bounds

Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models

Learning Chaotic Dynamics in Dissipative Systems

MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge

PeRFception: Perception using Radiance Fields

Pre-Trained Language Models for Interactive Decision-Making

MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Training

Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Models

Finite-Time Regret of Thompson Sampling Algorithms for Exponential Family Multi-Armed Bandits

Born Again Neural Networks