Latent Diffusion Models (LDMs) capture the dynamic evolution of latent variables over time, blending patterns and multimodality in a generative system. Despite the proficiency of LDM in various applications, such as text-to-image generation, facilitated by robust text encoders and a variational autoencoder, the critical need to deploy large generative models on edge devices compels a search for more compact yet effective alternatives. Post Training Quantization (PTQ), a method to compress the operational size of deep learning models, encounters challenges when applied to LDM due to temporal and structural complexities. This study proposes a quantization strategy that efficiently quantize LDMs, leveraging Signal-to-Quantization-Noise Ratio (SQNR) as a pivotal metric for evaluation. By treating the quantization discrepancy as relative noise and identifying sensitive part(s) of a model, we propose an efficient quantization approach encompassing both global and local strategies. The global quantization process mitigates relative quantization noise by initiating higher-precision quantization on sensitive blocks, while local treatments address specific challenges in quantization-sensitive and time-sensitive modules. The outcomes of our experiments reveal that the implementation of both global and local treatments yields a highly efficient and effective Post Training Quantization (PTQ) of LDMs.
Target-speaker automatic speech recognition (ASR) aims to transcribe the desired speech of a target speaker from multi-talker overlapped utterances. Most of the existing target-speaker ASR (TS-ASR) methods involve either training from scratch or fully fine-tuning a pre-trained model, leading to significant training costs and becoming inapplicable to large foundation models. This work leverages prompt tuning, a parameter-efficient fine-tuning approach, to extend Whisper, a large-scale single-talker ASR model, to TS-ASR. Experimental results show that prompt tuning can achieve performance comparable to state-of-the-art full fine-tuning approaches while only requiring about 1% of task-specific model parameters. Notably, the original Whisper's features, such as inverse text normalization and timestamp prediction, are retained in target-speaker ASR, keeping the generated transcriptions natural and informative.
With the continuous development of deep learning (DL), the task of multimodal dialogue emotion recognition (MDER) has recently received extensive research attention, which is also an essential branch of DL. The MDER aims to identify the emotional information contained in different modalities, e.g., text, video, and audio, in different dialogue scenes. However, existing research has focused on modeling contextual semantic information and dialogue relations between speakers while ignoring the impact of event relations on emotion. To tackle the above issues, we propose a novel Dialogue and Event Relation-Aware Graph Convolutional Neural Network for Multimodal Emotion Recognition (DER-GCN) method. It models dialogue relations between speakers and captures latent event relations information. Specifically, we construct a weighted multi-relationship graph to simultaneously capture the dependencies between speakers and event relations in a dialogue. Moreover, we also introduce a Self-Supervised Masked Graph Autoencoder (SMGAE) to improve the fusion representation ability of features and structures. Next, we design a new Multiple Information Transformer (MIT) to capture the correlation between different relations, which can provide a better fuse of the multivariate information between relations. Finally, we propose a loss optimization strategy based on contrastive learning to enhance the representation learning ability of minority class features. We conduct extensive experiments on the IEMOCAP and MELD benchmark datasets, which verify the effectiveness of the DER-GCN model. The results demonstrate that our model significantly improves both the average accuracy and the f1 value of emotion recognition.
Text-to-3D generation has made remarkable progress recently, particularly with methods based on Score Distillation Sampling (SDS) that leverages pre-trained 2D diffusion models. While the usage of classifier-free guidance is well acknowledged to be crucial for successful optimization, it is considered an auxiliary trick rather than the most essential component. In this paper, we re-evaluate the role of classifier-free guidance in score distillation and discover a surprising finding: the guidance alone is enough for effective text-to-3D generation tasks. We name this method Classifier Score Distillation (CSD), which can be interpreted as using an implicit classification model for generation. This new perspective reveals new insights for understanding existing techniques. We validate the effectiveness of CSD across a variety of text-to-3D tasks including shape generation, texture synthesis, and shape editing, achieving results superior to those of state-of-the-art methods. Our project page is https://xinyu-andy.github.io/Classifier-Score-Distillation
Human motion synthesis is a fundamental task in computer animation. Recent methods based on diffusion models or GPT structure demonstrate commendable performance but exhibit drawbacks in terms of slow sampling speeds and error accumulation. In this paper, we propose \emph{Motion Flow Matching}, a novel generative model designed for human motion generation featuring efficient sampling and effectiveness in motion editing applications. Our method reduces the sampling complexity from thousand steps in previous diffusion models to just ten steps, while achieving comparable performance in text-to-motion and action-to-motion generation benchmarks. Noticeably, our approach establishes a new state-of-the-art Fr\'echet Inception Distance on the KIT-ML dataset. What is more, we tailor a straightforward motion editing paradigm named \emph{sampling trajectory rewriting} leveraging the ODE-style generative models and apply it to various editing scenarios including motion prediction, motion in-between prediction, motion interpolation, and upper-body editing. Our code will be released.
This paper introduces a novel approach to enhance the capabilities of Large Language Models (LLMs) in processing and understanding extensive text sequences, a critical aspect in applications requiring deep comprehension and synthesis of large volumes of information. Recognizing the inherent challenges in extending the context window for LLMs, primarily built on Transformer architecture, we propose a new model architecture, referred to as Zebra. This architecture efficiently manages the quadratic time and memory complexity issues associated with full attention in the Transformer by employing grouped local-global attention layers. Our model, akin to a zebra's alternating stripes, balances local and global attention layers, significantly reducing computational requirements and memory consumption. Comprehensive experiments, including pretraining from scratch, continuation of long context adaptation training, and long instruction tuning, are conducted to evaluate the Zebra's performance. The results show that Zebra achieves comparable or superior performance on both short and long sequence benchmarks, while also enhancing training and inference efficiency.
Engineering design knowledge is embodied in natural language text through intricate placement of entities and relationships. Ontological constructs of design knowledge often limit the performances of NLP techniques to extract design knowledge. Also, large-language models could be less useful for generating and explicating design knowledge, as these are trained predominantly on common-sense text. In this article, we present the constituents of design knowledge based on empirical observations from patent documents. We obtain a sample of 33,881 patents and populate over 24 million facts from the sentences in these. We conduct Zipf distribution analyses using the frequencies of unique entities and relationships that are present in the facts thus populated. While the literal entities cannot be generalised from the sample of patents, the relationships largely capture attributes ('of'), structure ('in', 'with'), purpose ('to', 'for'), hierarchy ('include'), exemplification ('such as'), and behaviour ('to', 'from'). The analyses reveal that over half of entities and relationships could be generalised to 64 and 24 linguistic syntaxes respectively, while hierarchical relationships include 75 syntaxes. These syntaxes represent the linguistic basis of engineering design knowledge. We combine facts within each patent into a knowledge graph, from which we discover motifs that are statistically over-represented subgraph patterns. Across all patents in the sample, we identify eight patterns that could be simplified into sequence [->...->], aggregation [->...<-], and hierarchy [<-...->] that form the structural basis of engineering design knowledge. We propose regulatory precepts for concretising abstract entities and relationships within subgraphs, while also explicating hierarchical structures. These precepts could be useful for better construction and management of knowledge in a design environment.
Controllable text generation (CTG) aims to generate text with desired attributes, and decoding-time-based methods have shown promising performance on this task. However, in this paper, we identify the phenomenon of Attribute Collapse for the first time. It causes the fluency of generated text to rapidly decrease when the control strength exceeds a critical value, rendering the text completely unusable. This limitation hinders the effectiveness of decoding methods in achieving high levels of controllability. To address this problem, we propose a novel lightweight decoding framework named Air-Decoding. Its main idea is reconstructing the attribute distributions to balance the weights between attribute words and non-attribute words to generate more fluent text. Specifically, we train prefixes by prefix-tuning to obtain attribute distributions. Then we design a novel attribute distribution reconstruction method to balance the obtained distributions and use the reconstructed distributions to guide language models for generation, effectively avoiding the issue of Attribute Collapse. Experiments on multiple CTG tasks prove that our method achieves a new state-of-the-art control performance.
Recently, Large Multi-modal Models (LMMs) have demonstrated their ability to understand the visual contents of images given the instructions regarding the images. Built upon the Large Language Models (LLMs), LMMs also inherit their abilities and characteristics such as in-context learning where a coherent sequence of images and texts are given as the input prompt. However, we identify a new limitation of off-the-shelf LMMs where a small fraction of incoherent images or text descriptions mislead LMMs to only generate biased output about the hijacked context, not the originally intended context. To address this, we propose a pre-filtering method that removes irrelevant contexts via GPT-4V, based on its robustness towards distribution shift within the contexts. We further investigate whether replacing the hijacked visual and textual contexts with the correlated ones via GPT-4V and text-to-image models can help yield coherent responses.
We introduce the new task of generating Illustrated Instructions, i.e., visual instructions customized to a user's needs. We identify desiderata unique to this task, and formalize it through a suite of automatic and human evaluation metrics, designed to measure the validity, consistency, and efficacy of the generations. We combine the power of large language models (LLMs) together with strong text-to-image generation diffusion models to propose a simple approach called StackedDiffusion, which generates such illustrated instructions given text as input. The resulting model strongly outperforms baseline approaches and state-of-the-art multimodal LLMs; and in 30% of cases, users even prefer it to human-generated articles. Most notably, it enables various new and exciting applications far beyond what static articles on the web can provide, such as personalized instructions complete with intermediate steps and pictures in response to a user's individual situation.