9 papers · 1 filter
When to Think and When to Look: Uncertainty-Guided Lookback
Jing Bi, Filippos Bellos, Junjia Guo +8
Test-time thinking (that is, generating explicit intermediate reasoning chains) is known to boost performance in large language models and has recently shown strong gains for large…
DRIFT: Transferring Reasoning Priors for Efficient MLLM Fine-Tuning
Chao Huang, Zeliang Zhang, Jiang Liu +7
Multimodal large language models (MLLMs) have made rapid progress, yet their reasoning ability often lags behind strong text-only LLMs. Bridging this gap typically requires large-s…
High-Quality Sound Separation Across Diverse Categories via Visually-Guided Generative Modeling
Chao Huang, Susan Liang, Yapeng Tian +2
We propose DAVIS, a Diffusion-based Audio-VIsual Separation framework that solves the audio-visual sound source separation task through generative learning. Existing methods typica…
ZeroSep: Separate Anything in Audio with Zero Training
Chao Huang, Yuesheng Ma, Junxuan Huang +6
Audio source separation is fundamental for machines to understand complex acoustic environments and underpins numerous audio applications. Current supervised deep learning approach…
FreSca: Scaling in Frequency Space Enhances Diffusion Models
Chao Huang, Susan Liang, Yunlong Tang +4
Latent diffusion models (LDMs) have achieved remarkable success in a variety of image tasks, yet achieving fine-grained, disentangled control over global structures versus fine det…
BinauralFlow: A Causal and Streamable Approach for High-Quality Binaural Speech Synthesis with Flow Matching Models
Susan Liang, Dejan Markovic, Israel D. Gebru +7
Binaural rendering aims to synthesize binaural audio that mimics natural hearing based on a mono audio and the locations of the speaker and listener. Although many methods have bee…
Learning to Highlight Audio by Watching Movies
Chao Huang, Ruohan Gao, J. M. F. Tsang +5
Recent years have seen a significant increase in video content creation and consumption. Crafting engaging content requires the careful curation of both visual and audio elements.…
Harnessing the Computation Redundancy in ViTs to Boost Adversarial Transferability
Jiani Liu, Zhiyuan Wang, Zeliang Zhang +4
Vision Transformers (ViTs) have demonstrated impressive performance across a range of applications, including many safety-critical tasks. However, their unique architectural proper…
Generative AI for Cel-Animation: A Survey
Yolo Y. Tang, Junjia Guo, Pinxin Liu +14
Traditional Celluloid (Cel) Animation production pipeline encompasses multiple essential steps, including storyboarding, layout design, keyframe animation, inbetweening, and colori…