Picture for Mingda Zhang

Mingda Zhang

Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps

Add code
Jan 16, 2025
Viaarxiv icon

Neptune: The Long Orbit to Benchmarking Long Video Understanding

Add code
Dec 12, 2024
Figure 1 for Neptune: The Long Orbit to Benchmarking Long Video Understanding
Figure 2 for Neptune: The Long Orbit to Benchmarking Long Video Understanding
Figure 3 for Neptune: The Long Orbit to Benchmarking Long Video Understanding
Figure 4 for Neptune: The Long Orbit to Benchmarking Long Video Understanding
Viaarxiv icon

Reliable Poisoned Sample Detection against Backdoor Attacks Enhanced by Sharpness Aware Minimization

Add code
Nov 18, 2024
Viaarxiv icon

OmnixR: Evaluating Omni-modality Language Models on Reasoning across Modalities

Add code
Oct 16, 2024
Viaarxiv icon

BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning

Add code
Jan 26, 2024
Viaarxiv icon

Defenses in Adversarial Machine Learning: A Survey

Add code
Dec 13, 2023
Figure 1 for Defenses in Adversarial Machine Learning: A Survey
Figure 2 for Defenses in Adversarial Machine Learning: A Survey
Figure 3 for Defenses in Adversarial Machine Learning: A Survey
Figure 4 for Defenses in Adversarial Machine Learning: A Survey
Viaarxiv icon

Video Summarization: Towards Entity-Aware Captions

Add code
Dec 01, 2023
Figure 1 for Video Summarization: Towards Entity-Aware Captions
Figure 2 for Video Summarization: Towards Entity-Aware Captions
Figure 3 for Video Summarization: Towards Entity-Aware Captions
Figure 4 for Video Summarization: Towards Entity-Aware Captions
Viaarxiv icon

VDC: Versatile Data Cleanser for Detecting Dirty Samples via Visual-Linguistic Inconsistency

Add code
Sep 28, 2023
Viaarxiv icon

Video Timeline Modeling For News Story Understanding

Add code
Sep 23, 2023
Viaarxiv icon

Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples

Add code
Jul 20, 2023
Viaarxiv icon