Customization generation techniques have significantly advanced the synthesis of specific concepts across varied contexts. Multi-concept customization emerges as the challenging task within this domain. Existing approaches often rely on training a Low-Rank Adaptations (LoRA) fusion matrix of multiple LoRA to merge various concepts into a single image. However, we identify this straightforward method faces two major challenges: 1) concept confusion, which occurs when the model cannot preserve distinct individual characteristics, and 2) concept vanishing, where the model fails to generate the intended subjects. To address these issues, we introduce LoRA-Composer, a training-free framework designed for seamlessly integrating multiple LoRAs, thereby enhancing the harmony among different concepts within generated images. LoRA-Composer addresses concept vanishing through Concept Injection Constraints, enhancing concept visibility via an expanded cross-attention mechanism. To combat concept confusion, Concept Isolation Constraints are introduced, refining the self-attention computation. Furthermore, Latent Re-initialization is proposed to effectively stimulate concept-specific latent within designated regions. Our extensive testing showcases a notable enhancement in LoRA-Composer's performance compared to standard baselines, especially when eliminating the image-based conditions like canny edge or pose estimations. Code is released at https://github.com/Young98CN/LoRA\_Composer.
Object-goal navigation is a challenging task that requires guiding an agent to specific objects based on first-person visual observations. The ability of agent to comprehend its surroundings plays a crucial role in achieving successful object finding. However, existing knowledge-graph-based navigators often rely on discrete categorical one-hot vectors and vote counting strategy to construct graph representation of the scenes, which results in misalignment with visual images. To provide more accurate and coherent scene descriptions and address this misalignment issue, we propose the Aligning Knowledge Graph with Visual Perception (AKGVP) method for object-goal navigation. Technically, our approach introduces continuous modeling of the hierarchical scene architecture and leverages visual-language pre-training to align natural language description with visual perception. The integration of a continuous knowledge graph architecture and multimodal feature alignment empowers the navigator with a remarkable zero-shot navigation capability. We extensively evaluate our method using the AI2-THOR simulator and conduct a series of experiments to demonstrate the effectiveness and efficiency of our navigator. Code available: https://github.com/nuoxu/AKGVP.
We offer a new perspective on approaching the task of video generation. Instead of directly synthesizing a sequence of frames, we propose to render a video by warping one static image with a generative deformation field (GenDeF). Such a pipeline enjoys three appealing advantages. First, we can sufficiently reuse a well-trained image generator to synthesize the static image (also called canonical image), alleviating the difficulty in producing a video and thereby resulting in better visual quality. Second, we can easily convert a deformation field to optical flows, making it possible to apply explicit structural regularizations for motion modeling, leading to temporally consistent results. Third, the disentanglement between content and motion allows users to process a synthesized video through processing its corresponding static image without any tuning, facilitating many applications like video editing, keypoint tracking, and video segmentation. Both qualitative and quantitative results on three common video generation benchmarks demonstrate the superiority of our GenDeF method.
As an emerging federated learning paradigm, federated distillation enables communication-efficient model training by transmitting only small-scale knowledge during the learning process. To further improve the communication efficiency of federated distillation, we propose a novel technique, ALU, which accumulates multiple rounds of local updates before transferring the knowledge to the central server. ALU drastically decreases the frequency of communication in federated distillation, thereby significantly reducing the communication overhead during the training process. Empirical experiments demonstrate the substantial effect of ALU in improving the communication efficiency of federated distillation.
Story visualization aims to generate a series of images that match the story described in texts, and it requires the generated images to satisfy high quality, alignment with the text description, and consistency in character identities. Given the complexity of story visualization, existing methods drastically simplify the problem by considering only a few specific characters and scenarios, or requiring the users to provide per-image control conditions such as sketches. However, these simplifications render these methods incompetent for real applications. To this end, we propose an automated story visualization system that can effectively generate diverse, high-quality, and consistent sets of story images, with minimal human interactions. Specifically, we utilize the comprehension and planning capabilities of large language models for layout planning, and then leverage large-scale text-to-image models to generate sophisticated story images based on the layout. We empirically find that sparse control conditions, such as bounding boxes, are suitable for layout planning, while dense control conditions, e.g., sketches and keypoints, are suitable for generating high-quality image content. To obtain the best of both worlds, we devise a dense condition generation module to transform simple bounding box layouts into sketch or keypoint control conditions for final image generation, which not only improves the image quality but also allows easy and intuitive user interactions. In addition, we propose a simple yet effective method to generate multi-view consistent character images, eliminating the reliance on human labor to collect or draw character images.
Large Language Models (LLMs) have demonstrated remarkable performance on coding related tasks, particularly on assisting humans in programming and facilitating programming automation. However, existing benchmarks for evaluating the code understanding and generation capacities of LLMs suffer from severe limitations. First, most benchmarks are deficient as they focus on a narrow range of popular programming languages and specific tasks, whereas the real-world software development scenarios show dire need to implement systems with multilingual programming environments to satisfy diverse requirements. Practical programming practices also strongly expect multi-task settings for testing coding capabilities of LLMs comprehensively and robustly. Second, most benchmarks also fail to consider the actual executability and the consistency of execution results of the generated code. To bridge these gaps between existing benchmarks and expectations from practical applications, we introduce CodeScope, an execution-based, multilingual, multi-task, multi-dimensional evaluation benchmark for comprehensively gauging LLM capabilities on coding tasks. CodeScope covers 43 programming languages and 8 coding tasks. It evaluates the coding performance of LLMs from three dimensions (perspectives): difficulty, efficiency, and length. To facilitate execution-based evaluations of code generation, we develop MultiCodeEngine, an automated code execution engine that supports 14 programming languages. Finally, we systematically evaluate and analyze 8 mainstream LLMs on CodeScope tasks and demonstrate the superior breadth and challenges of CodeScope for evaluating LLMs on code understanding and generation tasks compared to other benchmarks. The CodeScope benchmark and datasets are publicly available at https://github.com/WeixiangYAN/CodeScope.
Recently, unified speech-text models, such as SpeechGPT, VioLA, and AudioPaLM, have achieved remarkable performance on speech tasks. These models convert continuous speech signals into discrete tokens (speech discretization) and merge text and speech tokens into a shared vocabulary. Then they train a single decoder-only Transformer on a mixture of speech tasks. Specifically, all these models utilize Loss Masking on the input speech tokens for the ASR task, which means that these models do not explicitly model the dependency between the speech tokens. In this paper, we attempt to model the sequence of speech tokens in an autoregressive manner like text. However, we find that applying the conventional cross-entropy loss on input speech tokens does not consistently improve the ASR performance over Loss Masking. Therefore, we propose a novel approach denoted Smoothed Label Distillation (SLD), which introduces a KL divergence loss with smoothed labels on the input speech tokens to effectively model speech tokens. Experiments demonstrate that our SLD approach alleviates the limitations of the cross-entropy loss and consistently outperforms Loss Masking for decoder-only Transformer based ASR using different speech discretization methods.
The dilemma between plasticity and stability presents a significant challenge in Incremental Learning (IL), especially in the exemplar-free scenario where accessing old-task samples is strictly prohibited during the learning of a new task. A straightforward solution to this issue is learning and storing an independent model for each task, known as Single Task Learning (STL). Despite the linear growth in model storage with the number of tasks in STL, we empirically discover that averaging these model parameters can potentially preserve knowledge across all tasks. Inspired by this observation, we propose a Dual-Learner framework with Cumulative Parameter Averaging (DLCPA). DLCPA employs a dual-learner design: a plastic learner focused on acquiring new-task knowledge and a stable learner responsible for accumulating all learned knowledge. The knowledge from the plastic learner is transferred to the stable learner via cumulative parameter averaging. Additionally, several task-specific classifiers work in cooperation with the stable learner to yield the final prediction. Specifically, when learning a new task, these modules are updated in a cyclic manner: i) the plastic learner is initially optimized using a self-supervised loss besides the supervised loss to enhance the feature extraction robustness; ii) the stable learner is then updated with respect to the plastic learner in a cumulative parameter averaging manner to maintain its task-wise generalization; iii) the task-specific classifier is accordingly optimized to align with the stable learner. Experimental results on CIFAR-100 and Tiny-ImageNet show that DLCPA outperforms several state-of-the-art exemplar-free baselines in both Task-IL and Class-IL settings.
Topic segmentation is critical for obtaining structured documents and improving downstream tasks such as information retrieval. Due to its ability of automatically exploring clues of topic shift from abundant labeled data, recent supervised neural models have greatly promoted the development of long document topic segmentation, but leaving the deeper relationship between coherence and topic segmentation underexplored. Therefore, this paper enhances the ability of supervised models to capture coherence from both logical structure and semantic similarity perspectives to further improve the topic segmentation performance, proposing Topic-aware Sentence Structure Prediction (TSSP) and Contrastive Semantic Similarity Learning (CSSL). Specifically, the TSSP task is proposed to force the model to comprehend structural information by learning the original relations between adjacent sentences in a disarrayed document, which is constructed by jointly disrupting the original document at topic and sentence levels. Moreover, we utilize inter- and intra-topic information to construct contrastive samples and design the CSSL objective to ensure that the sentences representations in the same topic have higher similarity, while those in different topics are less similar. Extensive experiments show that the Longformer with our approach significantly outperforms old state-of-the-art (SOTA) methods. Our approach improve $F_1$ of old SOTA by 3.42 (73.74 -> 77.16) and reduces $P_k$ by 1.11 points (15.0 -> 13.89) on WIKI-727K and achieves an average relative reduction of 4.3% on $P_k$ on WikiSection. The average relative $P_k$ drop of 8.38% on two out-of-domain datasets also demonstrates the robustness of our approach.
By comparing the original and target prompts in editing task, we can obtain numerous editing pairs, each comprising an object and its corresponding editing target. To allow editability while maintaining fidelity to the input image, existing editing methods typically involve a fixed number of inversion steps that project the whole input image to its noisier latent representation, followed by a denoising process guided by the target prompt. However, we find that the optimal number of inversion steps for achieving ideal editing results varies significantly among different editing pairs, owing to varying editing difficulties. Therefore, the current literature, which relies on a fixed number of inversion steps, produces sub-optimal generation quality, especially when handling multiple editing pairs in a natural image. To this end, we propose a new image editing paradigm, dubbed Object-aware Inversion and Reassembly (OIR), to enable object-level fine-grained editing. Specifically, we design a new search metric, which determines the optimal inversion steps for each editing pair, by jointly considering the editability of the target and the fidelity of the non-editing region. We use our search metric to find the optimal inversion step for each editing pair when editing an image. We then edit these editing pairs separately to avoid concept mismatch. Subsequently, we propose an additional reassembly step to seamlessly integrate the respective editing results and the non-editing region to obtain the final edited image. To systematically evaluate the effectiveness of our method, we collect two datasets for benchmarking single- and multi-object editing, respectively. Experiments demonstrate that our method achieves superior performance in editing object shapes, colors, materials, categories, etc., especially in multi-object editing scenarios.