5 papers
TP-Blend: Textual-Prompt Attention Pairing for Precise Object-Style Blending in Diffusion Models
Xin Jin, Yichuan Zhong, Yapeng Tian
Current text-conditioned diffusion editors handle single object replacement well but struggle when a new object and a new style must be introduced simultaneously. We present Twin-P…
Object-WIPER : Training-Free Object and Associated Effect Removal in Videos
Saksham Singh Kushwaha, Sayan Nag, Yapeng Tian +1
In this paper, we introduce Object-WIPER, a training-free framework for removing dynamic objects and their associated visual effects from videos, and inpainting them with semantica…
Vision Token Reduction via Attention-Driven Self-Compression for Efficient Multimodal Large Language Models
Omer Faruk Deniz, Ruiyu Mao, Ruochen Li +2
Multimodal Large Language Models (MLLMs) incur significant computational cost from processing numerous vision tokens through all LLM layers. Prior pruning methods operate either be…
: Benchmarking the Robustness of Audio-Visual Recognition Models at Test-Time
Sarthak Kumar Maharana, Saksham Singh Kushwaha, Baoming Zhang +4
While recent audio-visual models have demonstrated impressive performance, their robustness to distributional shifts at test-time remains not fully understood. Existing robustness…
VinTAGe: Joint Video and Text Conditioning for Holistic Audio Generation
Saksham Singh Kushwaha, Yapeng Tian
Recent advances in audio generation have focused on text-to-audio (T2A) and video-to-audio (V2A) tasks. However, T2A or V2A methods cannot generate holistic sounds (onscreen and of…