Xinyue Zhang

Yizhi Li, Yinghao Ma, Ge Zhang et al.

Recent advancements in multimodal large language models (MLLMs) have aimed to integrate and interpret data across diverse modalities. However, the capacity of these models to concurrently process and reason about multiple modalities remains underexplored, partly due to the lack of comprehensive modality-wise benchmarks. We introduce OmniBench, a novel benchmark designed to rigorously evaluate models' ability to recognize, interpret, and reason across visual, acoustic, and textual inputs simultaneously. We define language models capable of such tri-modal processing as the omni-language models (OLMs). OmniBench is distinguished by high-quality human annotations, ensuring that accurate responses require integrated understanding and reasoning across all three modalities. Our main findings reveal that: i) open-source OLMs exhibit critical limitations in instruction-following and reasoning capabilities within tri-modal contexts; and ii) most baselines models perform poorly (below 50% accuracy) even when provided with alternative textual representations of images or/and audio. These results suggest that the ability to construct a consistent context from text, image, and audio is often overlooked in existing MLLM training paradigms. To address this gap, we curate an instruction tuning dataset of 84.5K training samples, OmniInstruct, for training OLMs to adapt to tri-modal contexts. We advocate for future research to focus on developing more robust tri-modal integration techniques and training strategies to enhance OLMs. Codes, data and live leaderboard could be found at https://m-a-p.ai/OmniBench.

Ruibin Yuan, Hanfeng Lin, Shuyue Guo et al.

We tackle the task of long-form music generation--particularly the challenging \textbf{lyrics-to-song} problem--by introducing YuE, a family of open foundation models based on the LLaMA2 architecture. Specifically, YuE scales to trillions of tokens and generates up to five minutes of music while maintaining lyrical alignment, coherent musical structure, and engaging vocal melodies with appropriate accompaniment. It achieves this through (1) track-decoupled next-token prediction to overcome dense mixture signals, (2) structural progressive conditioning for long-context lyrical alignment, and (3) a multitask, multiphase pre-training recipe to converge and generalize. In addition, we redesign the in-context learning technique for music generation, enabling versatile style transfer (e.g., converting Japanese city pop into an English rap while preserving the original accompaniment) and bidirectional generation. Through extensive evaluation, we demonstrate that YuE matches or even surpasses some of the proprietary systems in musicality and vocal agility. In addition, fine-tuning YuE enables additional controls and enhanced support for tail languages. Furthermore, beyond generation, we show that YuE's learned representations can perform well on music understanding tasks, where the results of YuE match or exceed state-of-the-art methods on the MARBLE benchmark. Keywords: lyrics2song, song generation, long-form, foundation model, music generation

Ruibin Yuan, Ge Zhang, Anqiao Yang et al.

In this paper, we propose to adapt the method of mutual information maximization into the task of Chinese lyrics conditioned melody generation to improve the generation quality and diversity. We employ scheduled sampling and force decoding techniques to improve the alignment between lyrics and melodies. With our method, which we called Diverse Melody Generation (DMG), a sequence-to-sequence model learns to generate diverse melodies heavily depending on the input style ids, while keeping the tonality and improving the alignment. The experimental results of subjective tests show that DMG can generate more pleasing and coherent tunes than baseline methods.

Xiaofang Wang, Guoqiang Xiang, Xinyue Zhang et al.

In this paper, a framework of video face replacement is proposed and it deals with the flicker of swapped face in video sequence. This framework contains two main innovations: 1) the technique of image registration is exploited to align the source and target video faces for eliminating the flicker or jitter of the segmented video face sequence; 2) a fast subpixel image registration method is proposed for farther accuracy and efficiency. Unlike the priori works, it minimizes the overlapping region and takes spatiotemporal coherence into account. Flicker in resulted videos is usually caused by the frequently changed bound of the blending target face and unregistered faces between and along video sequences. The subpixel image registration method is proposed to solve the flicker problem. During the alignment process, integer pixel registration is formulated by maximizing the similarity of images with down sampling strategy speeding up the process and sub-pixel image registration is a single-step image match via analytic method. Experimental results show the proposed algorithm reduces the computation time and gets a high accuracy when conducting experiments on different data sets.