Ajmal Saeed Mian

3DSMT: A Hybrid Spiking Mamba-Transformer for Point Cloud Analysis

NatADiff: Adversarial Boundary Guidance for Natural Adversarial Diffusion

Disentangled Hierarchical VAE for 3D Human-Human Interaction Generation

Intriguing Bias-Variance Tradeoff in Diffusion Models

Enhancing Physical Plausibility in Video Generation by Reasoning the Implausibility

SpikeNet: Sparse Spike-Driven Mask Vector Transformer for Energy-Efficient and Stable Spiking Point Cloud Processing

A Backdoor-based Explainable AI Benchmark for High Fidelity Evaluation of Attributions

Avatar Concept Slider: Controllable Editing of Concepts in 3D Human Avatars

CymbaDiff: Structured Spatial Diffusion for Sketch-based 3D Semantic Urban Scene Generation

Dynamic Model Editing to Rectify Unreliable Behavior in Neural Networks

Motion-Grounded Video Reasoning: Understanding and Perceiving Motion at Pixel Level

Diffusion-based Extreme Image Compression with Compressed Feature Initialization