Anima Anandkumar

Latest

• FALCON: Fourier Adaptive Learning and Control for Disturbance Rejection Under Extreme Turbulence
• Calibrated Uncertainty Quantification for Operator Learning via Conformal Prediction
• Multi-Grid Tensorized Fourier Neural Operator for High-Resolution PDEs
• Equivariant Graph Neural Operator for Modeling 3D Dynamics
• Neural Operators with Localized Integral and Differential Kernels
• Improving Distant 3D Object Detection Using 2D Box Supervision
• PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees
• AI-driven emulation of ocean dynamics on sub-seasonal scales
• Guaranteed Approximation Bounds for Mixed-Precision Neural Operators
• Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo
• Neural operators for accelerating scientific simulations and design
• Fast Training of Diffusion Models with Masked Transformers
• Geometry-informed neural operator for large-scale 3D PDEs
• Physics-informed neural operators with exact differentiation on arbitrary geometries
• 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
• Fully Attentional Networks with Self-emerging Token Labeling
• Fast Sampling of Diffusion Models via Operator Learning
• I^2SB: Image-to-Image Schrödinger Bridge
• Vision Transformers Are Good Mask Auto-Labelers
• VoxFormer: Sparse voxel transformer for camera-based 3D semantic scene completion
• Prismer: A Vision-Language Model with An Ensemble of Experts
• MinVIS: A minimal video instance segmentation framework without video-based training
• Test-time prompt tuning for zero-shot generalization in vision-language models
• Diffusion Models for Adversarial Purification
• Panoptic SegFormer: Delving deeper into panoptic segmentation with transformers
• M$^2$BEV: Multi-camera joint 3D detection and segmentation with unified birds-eye view representation
• Controllable and Compositional Generation with Latent-Space Energy-Based Models
• Coupled Segmentation and Edge Learning via Dynamic Graph Propagation
• SegFormer: Simple and efficient design for semantic segmentation with transformers
• DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision
• Generating and Characterizing Scenarios for Safety Testing of Autonomous Vehicles
• Angular Visual Hardness