Luping Liu

ICLR Conference 2025 Conference Paper

Improving Long-Text Alignment for Text-to-Image Diffusion Models

• Luping Liu
• Chao Du
• Tianyu Pang
• Zehan Wang 0001
• Chongxuan Li
• Dong Xu

The rapid advancement of text-to-image (T2I) diffusion models has enabled them to generate unprecedented results from given texts. However, as text inputs become longer, existing encoding methods like CLIP face limitations, and aligning the generated images with long texts becomes challenging. To tackle these issues, we propose LongAlign, which includes a segment-level encoding method for processing long texts and a decomposed preference optimization method for effective alignment training. For segment-level encoding, long texts are divided into multiple segments and processed separately. This method overcomes the maximum input length limits of pretrained encoding models. For preference optimization, we provide decomposed CLIP-based preference models to fine-tune diffusion models. Specifically, to utilize CLIP-based preference models for T2I alignment, we delve into their scoring mechanisms and find that the preference scores can be decomposed into two components: a text-relevant part that measures T2I alignment and a text-irrelevant part that assesses other visual aspects of human preference. Additionally, we find that the text-irrelevant part contributes to a common overfitting problem during fine-tuning. To address this, we propose a reweighting strategy that assigns different weights to these two components, thereby reducing overfitting and enhancing alignment. After fine-tuning $512 \\times 512$ Stable Diffusion (SD) v1.5 for about 20 hours using our method, the fine-tuned SD outperforms stronger foundation models in T2I alignment, such as PixArt-$\\alpha$ and Kandinsky v2.2. The code is available at https://github.com/luping-liu/LongAlign.

ICLR Conference 2025 Conference Paper

OmniBind: Large-scale Omni Multimodal Representation via Binding Spaces

• Zehan Wang 0001
• Ziang Zhang
• Minjie Hong
• Hang Zhang
• Luping Liu
• Rongjie Huang 0001
• Xize Cheng
• Shengpeng Ji

Recently, human-computer interaction with various modalities has shown promising applications, like GPT-4o and Gemini. Meanwhile, multimodal representation models have emerged as the foundation for these versatile multimodal understanding and generation pipeline. Models like CLIP, CLAP and ImageBind can map their specialized modalities into respective joint spaces. To construct a high-quality omni representation space that can be shared and expert in any modality, we propose to merge these advanced models into a unified space in scale. With this insight, we present \textbf{OmniBind}, advanced multimodal joint representation models via fusing knowledge of 14 pre-trained spaces, which support 3D, audio, image, video and language inputs. To alleviate the interference between different knowledge sources in integrated space, we dynamically assign weights to different spaces by learning routers with two objectives: cross-modal overall alignment and language representation decoupling. Notably, since binding and routing spaces only require lightweight networks, OmniBind is extremely training-efficient. Extensive experiments demonstrate the versatility and superiority of OmniBind as an omni representation model, highlighting its great potential for diverse applications, such as any-query and composable multimodal understanding.

NeurIPS Conference 2024 Conference Paper

Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers

• Haifeng Huang
• Yilun Chen
• Zehan Wang
• Rongjie Huang
• Runsen Xu
• Tai WANG
• Luping Liu
• Xize Cheng

Recent advancements in 3D Large Language Models (LLMs) have demonstrated promising capabilities for 3D scene understanding. However, previous methods exhibit deficiencies in general referencing and grounding capabilities for intricate scene comprehension. In this paper, we introduce the use of object identifiers and object-centric representations to interact with scenes at the object level. Specifically, we decompose the input 3D scene into a set of object proposals, each assigned a unique identifier token, which enables efficient object referencing and grounding during user-assistant interactions. Given the scarcity of scene-language data, we model the scene embeddings as a sequence of explicit object-level embeddings, derived from semantic-rich 2D or 3D representations. By employing object identifiers, we transform diverse 3D scene-language tasks into a unified question-answering format, facilitating joint training without the need for additional task-specific heads. With minimal fine-tuning on all downstream tasks, our model significantly outperforms existing methods on benchmarks including ScanRefer, Multi3DRefer, Scan2Cap, ScanQA, and SQA3D.

NeurIPS Conference 2024 Conference Paper

Extending Multi-modal Contrastive Representations

• Ziang Zhang
• Zehan Wang
• Luping Liu
• Rongjie Huang
• Xize Cheng
• Zhenhui Ye
• Wang Lin
• Huadai Liu

Multi-modal contrastive representation (MCR) of more than three modalities is critical in multi-modal learning. Although recent methods showcase impressive achievements, the high dependence on large-scale, high-quality paired data and the expensive training costs limit their further development. Inspired by recent C-MCR, this paper proposes $\textbf{Ex}$tending $\textbf{M}$ultimodal $\textbf{C}$ontrastive $\textbf{R}$epresentation (Ex-MCR), a training-efficient and paired-data-free method to build unified contrastive representation for many modalities. Since C-MCR is designed to learn a new latent space for the two non-overlapping modalities and projects them onto this space, a significant amount of information from their original spaces is lost in the projection process. To address this issue, Ex-MCR proposes to extend one modality's space into the other's, rather than mapping both modalities onto a completely new space. This method effectively preserves semantic alignment in the original space. Experimentally, we extend pre-trained audio-text and 3D-image representations to the existing vision-text space. Without using paired data, Ex-MCR achieves comparable performance to advanced methods on a series of audio-image-text and 3D-image-text tasks and achieves superior performance when used in parallel with data-driven methods. Moreover, semantic alignment also emerges between the extended modalities (e. g. , audio and 3D).

ICML Conference 2024 Conference Paper

FreeBind: Free Lunch in Unified Multimodal Space via Knowledge Fusion

• Zehan Wang 0001
• Ziang Zhang
• Xize Cheng
• Rongjie Huang 0001
• Luping Liu
• Zhenhui Ye
• Haifeng Huang 0001
• Yang Zhao 0022

Unified multi-model representation spaces are the foundation of multimodal understanding and generation. However, the billions of model parameters and catastrophic forgetting problems make it challenging to further enhance pre-trained unified spaces. In this work, we propose FreeBind, an idea that treats multimodal representation spaces as basic units, and freely augments pre-trained unified space by integrating knowledge from extra expert spaces via “space bonds". Specifically, we introduce two kinds of basic space bonds: 1) Space Displacement Bond and 2) Space Combination Bond. Based on these basic bonds, we design Complex Sequential & Parallel Bonds to effectively integrate multiple spaces simultaneously. Benefiting from the modularization concept, we further propose a coarse-to-fine customized inference strategy to flexibly adjust the enhanced unified space for different purposes. Experimentally, we bind ImageBind with extra image-text and audio-text expert spaces, resulting in three main variants: ImageBind++, InternVL_IB, and InternVL_IB++. These resulting spaces outperform ImageBind on 5 audio-image-text downstream tasks across 9 datasets. Moreover, via customized inference, it even surpasses the advanced audio-text and image-text expert spaces. Our code and checkpoints are released at https: //github. com/zehanwang01/FreeBind

JBHI Journal 2024 Journal Article

HCT: Chinese Medical Machine Reading Comprehension Question-Answering via Hierarchically Collaborative Transformer

• Meiling Wang
• Xiaohai He
• Luping Liu
• Qingmao Fang
• Mei Zhang
• Honggang Chen
• Yan Liu

Chinese medical machine reading comprehension question-answering (cMed-MRCQA) is a critical component of the intelligence question-answering task, focusing on the Chinese medical domain question-answering task. Its purpose enable machines to analyze and understand the given text and question and then extract the accurate answer. To enhance cMed-MRCQA performance, it is essential to possess a profound comprehension and analysis of the context, deduce concealed information from the textual content and, subsequently, precisely determine the answer's span. The answer span has predominantly been defined by language items, with sentences employed in most instances. However, it is worth noting that sentences may not be properly split to varying degrees in various languages, making it challenging for the model to predict the answer zone. To alleviate this issue, this paper presents a novel architecture called HCT based on a H ierarchically C ollaborative T ransformer. Specifically, we presented a hierarchical collaborative method to locate the boundaries of sentence and answer spans separately. First, we designed a hierarchical encoding module to obtain the local semantic features of the corpus; second, we proposed a sentence-level self-attention module and a fused interaction-attention module to get the global information about the text. Finally, the model is trained by combining loss functions. Extensive experiments were conducted on the public dataset CMedMRC and the reconstruction dataset eMedicine to validate the effectiveness of the proposed method. Experimental results showed that the proposed method performed better than the state-of-the-art methods. Using the F1 metric, our model scored 90. 4% on the CMedMRC and 73. 2% on eMedicine.

ICML Conference 2024 Conference Paper

InstructSpeech: Following Speech Editing Instructions via Large Language Models

• Rongjie Huang 0001
• Ruofan Hu 0002
• Yongqi Wang
• Zehan Wang 0001
• Xize Cheng
• Ziyue Jiang 0001
• Zhenhui Ye
• Dongchao Yang

Instruction-guided speech editing aims to follow the user’s natural language instruction to manipulate the semantic and acoustic attributes of a speech. In this work, we construct triplet paired data (instruction, input speech, output speech) to alleviate data scarcity and train a multi-task large language model named InstructSpeech. To mitigate the challenges of accurately executing user’s instructions, we 1) introduce the learned task embeddings with a fine-tuned Flan-T5-XL to guide the generation process towards the correct generative task; 2) include an extensive and diverse set of speech editing and processing tasks to enhance model capabilities; 3) investigate chain-of-thought reasoning for free-form semantic content editing; and 4) propose a hierarchical adapter that effectively updates a small portion of parameters for generalization to new tasks. To assess instruction speech editing in greater depth, we introduce a benchmark evaluation with contrastive instruction-speech pre-training (CISP) to test the speech quality and instruction-speech alignment faithfulness. Experimental results demonstrate that InstructSpeech achieves state-of-the-art results in eleven tasks, for the first time unlocking the ability to edit speech’s acoustic and semantic attributes following a user’s instruction. Audio samples are available at https: //InstructSpeech. github. io

ICML Conference 2023 Conference Paper

Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models

• Rongjie Huang 0001
• Jiawei Huang 0008
• Dongchao Yang
• Yi Ren 0006
• Luping Liu
• Mingze Li
• Zhenhui Ye
• Jinglin Liu

Large-scale multimodal generative modeling has created milestones in text-to-image and text-to-video generation. Its application to audio still lags behind for two main reasons: the lack of large-scale datasets with high-quality text-audio pairs, and the complexity of modeling long continuous audio data. In this work, we propose Make-An-Audio with a prompt-enhanced diffusion model that addresses these gaps by 1) introducing pseudo prompt enhancement with a distill-then-reprogram approach, it alleviates data scarcity with orders of magnitude concept compositions by using language-free audios; 2) leveraging spectrogram autoencoder to predict the self-supervised audio representation instead of waveforms. Together with robust contrastive language-audio pretraining (CLAP) representations, Make-An-Audio achieves state-of-the-art results in both objective and subjective benchmark evaluation. Moreover, we present its controllability and generalization for X-to-Audio with "No Modality Left Behind", for the first time unlocking the ability to generate high-definition, high-fidelity audios given a user-defined modality input. Audio samples are available at https: //Make-An-Audio. github. io

NeurIPS Conference 2023 Conference Paper

PTQD: Accurate Post-Training Quantization for Diffusion Models

• Yefei He
• Luping Liu
• Jing Liu
• Weijia Wu
• Hong Zhou
• Bohan Zhuang

Diffusion models have recently dominated image synthesis and other related generative tasks. However, the iterative denoising process is expensive in computations at inference time, making diffusion models less practical for low-latency and scalable real-world applications. Post-training quantization of diffusion models can significantly reduce the model size and accelerate the sampling process without requiring any re-training. Nonetheless, applying existing post-training quantization methods directly to low-bit diffusion models can significantly impair the quality of generated samples. Specifically, for each denoising step, quantization noise leads to deviations in the estimated mean and mismatches with the predetermined variance schedule. Moreover, as the sampling process proceeds, the quantization noise may accumulate, resulting in a low signal-to-noise ratio (SNR) during the later denoising steps. To address these challenges, we propose a unified formulation for the quantization noise and diffusion perturbed noise in the quantized denoising process. Specifically, we first disentangle the quantization noise into its correlated and residual uncorrelated parts regarding its full-precision counterpart. The correlated part can be easily corrected by estimating the correlation coefficient. For the uncorrelated part, we subtract the bias from the quantized results to correct the mean deviation and calibrate the denoising variance schedule to absorb the excess variance resulting from quantization. Moreover, we introduce a mixed-precision scheme for selecting the optimal bitwidth for each denoising step, which prioritizes lower bitwidths to expedite early denoising steps, while ensuring that higher bitwidths maintain a high signal-to-noise ratio (SNR) in the later steps. Extensive experiments demonstrate that our method outperforms previous post-training quantized diffusion models in generating high-quality samples, with only a $0. 06$ increase in FID score compared to full-precision LDM-4 on ImageNet $256\times256$, while saving $19. 9\times$ bit operations. Code is available at [https: //github. com/ziplab/PTQD](https: //github. com/ziplab/PTQD).

AIIM Journal 2022 Journal Article

Medical visual question answering based on question-type reasoning and semantic space constraint

• Meiling Wang
• Xiaohai He
• Luping Liu
• Linbo Qing
• Honggang Chen
• Yan Liu
• Chao Ren

ICLR Conference 2022 Conference Paper

Pseudo Numerical Methods for Diffusion Models on Manifolds

• Luping Liu
• Yi Ren 0006
• Zhijie Lin 0001
• Zhou Zhao 0001

Denoising Diffusion Probabilistic Models (DDPMs) can generate high-quality samples such as image and audio samples. However, DDPMs require hundreds to thousands of iterations to produce a sample. Several prior works have successfully accelerated DDPMs through adjusting the variance schedule (e.g., Improved Denoising Diffusion Probabilistic Models) or the denoising equation (e.g., Denoising Diffusion Implicit Models (DDIMs)). However, these acceleration methods cannot maintain the quality of samples and even introduce new noise at high speedup rate, which limit their practicability. To accelerate the inference process while keeping the sample quality, we provide a new perspective that DDPMs should be treated as solving differential equations on manifolds. Under such a perspective, we propose pseudo numerical methods for diffusion models (PNDMs). Specifically, we figure out how to solve differential equations on manifolds and show that DDIMs are simple cases of pseudo numerical methods. We change several classical numerical methods to corresponding pseudo numerical methods and find that pseudo linear multi-step method is the best method in most situations. According to our experiments, by directly using pre-trained models on Cifar10, CelebA and LSUN, PNDMs can generate higher quality synthetic images with only 50 steps compared with 1000-step DDIMs (20x speedup), significantly outperform DDIMs with 250 steps (by around 0.4 in FID) and have good generalization on different variance schedules.