1 citations · 2 across the 13 of their papers we have counts for
14 papers
OmniVAE: An Audio-Video VAE with Cross-Modal Alignment for Joint Generation
Jun Zhan, Chen Yang, Yitian Gong +23
Recent generative models are moving beyond silent video or standalone audio synthesis toward the joint generation of synchronized audio and video. Despite this progress, jointly ge…
MOVA: Towards Scalable and Synchronized Video-Audio Generation
OpenMOSS Team, Donghua Yu, Mingshu Chen +38
Audio is indispensable for real-world video, yet generation models have largely overlooked audio components. Current approaches to producing audio-visual content often rely on casc…
DiRL: An Efficient Post-Training Framework for Diffusion Language Models
Ying Zhu, Jiaxin Wan, Xiaoran Liu +7
Diffusion Language Models (dLLMs) have emerged as promising alternatives to Auto-Regressive (AR) models. While recent efforts have validated their pre-training potential and accele…
FourierSampler: Unlocking Non-Autoregressive Potential in Diffusion Language Models via Frequency-Guided Generation
Siyang He, Qiqi Wang, Xiaoran Liu +8
Despite the non-autoregressive potential of diffusion language models (dLLMs), existing decoding strategies demonstrate positional bias, failing to fully unlock the potential of ar…
MPJudge: Towards Perceptual Assessment of Music-Induced Paintings
Shiqi Jiang, Tianyi Liang, Huayuan Ye +2
Music induced painting is a unique artistic practice, where visual artworks are created under the influence of music. Evaluating whether a painting faithfully reflects the music th…
Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm
Jingqi Tong, Yurong Mou, Hangcheng Li +11
The "Thinking with Text" and "Thinking with Images" paradigms significantly improve the reasoning abilities of large language models (LLMs) and Vision-Language Models (VLMs). Howev…
IFDECORATOR: Wrapping Instruction Following Reinforcement Learning with Verifiable Rewards
Xu Guo, Tianyi Liang, Tong Jian +6
Reinforcement Learning with Verifiable Rewards (RLVR) improves instruction following capabilities of large language models (LLMs), but suffers from training inefficiency due to ina…
Sel3DCraft: Interactive Visual Prompts for User-Friendly Text-to-3D Generation
Nan Xiang, Tianyi Liang, Haiwen Huang +6
Text-to-3D (T23D) generation has transformed digital content creation, yet remains bottlenecked by blind trial-and-error prompting processes that yield unpredictable results. While…
Music2Palette: Emotion-aligned Color Palette Generation via Cross-Modal Representation Learning
Jiayun Hu, Yueyi He, Tianyi Liang +2
Emotion alignment between music and palettes is crucial for effective multimedia content, yet misalignment creates confusion that weakens the intended message. However, existing me…
RouteWinFormer: A Route-Window Transformer for Middle-range Attention in Image Restoration
Qifan Li, Tianyi Liang, Xingtao Wang +1
Transformer models have recently garnered significant attention in image restoration due to their ability to capture long-range pixel dependencies. However, long-range attention of…
Consensus Entropy: Harnessing Multi-VLM Agreement for Self-Verifying and Self-Improving OCR
Yulong Zhang, Tianyi Liang, Xinyue Huang +5
Optical Character Recognition (OCR) is fundamental to Vision-Language Models (VLMs) and high-quality data generation for LLM training. Yet, despite progress in average OCR accuracy…
CritiQ: Mining Data Quality Criteria from Human Preferences
Honglin Guo, Kai Lv, Qipeng Guo +8
Language model heavily depends on high-quality data for optimal performance. Existing approaches rely on manually designed heuristics, the perplexity of existing models, training c…
GAOKAO-Eval: Does high scores truly reflect strong capabilities in LLMs?
Zhikai Lei, Tianyi Liang, Hanglei Hu +8
Large Language Models (LLMs) are commonly evaluated using human-crafted benchmarks, under the premise that higher scores implicitly reflect stronger human-like performance. However…
TextCenGen: Attention-Guided Text-Centric Background Adaptation for Text-to-Image Generation
Tianyi Liang, Jiangqi Liu, Yifei Huang +4
Text-to-image (T2I) generation has made remarkable progress in producing high-quality images, but a fundamental challenge remains: creating backgrounds that naturally accommodate t…