Audio Question Answering (AQA) constitutes a pivotal task in which machines analyze both audio signals and natural language questions to produce precise natural language answers. The significance of possessing high-quality, diverse, and extensive AQA datasets cannot be overstated when aiming for the precision of an AQA system. While there has been notable focus on developing accurate and efficient AQA models, the creation of high-quality, diverse, and extensive datasets for the specific task at hand has not garnered considerable attention. To address this challenge, this work makes several contributions. We introduce a scalable AQA data generation pipeline, denoted as the AQUALLM framework, which relies on Large Language Models (LLMs). This framework utilizes existing audio-caption annotations and incorporates state-of-the-art LLMs to generate expansive, high-quality AQA datasets. Additionally, we present three extensive and high-quality benchmark datasets for AQA, contributing significantly to the progression of AQA research. AQA models trained on the proposed datasets set superior benchmarks compared to the existing state-of-the-art. Moreover, models trained on our datasets demonstrate enhanced generalizability when compared to models trained using human-annotated AQA data. Code and datasets will be accessible on GitHub~\footnote{\url{https://github.com/swarupbehera/AQUALLM}}.
Large-scale Text-to-Image (T2I) diffusion models have revolutionized image generation over the last few years. Although owning diverse and high-quality generation capabilities, translating these abilities to fine-grained image editing remains challenging. In this paper, we propose DiffEditor to rectify two weaknesses in existing diffusion-based image editing: (1) in complex scenarios, editing results often lack editing accuracy and exhibit unexpected artifacts; (2) lack of flexibility to harmonize editing operations, e.g., imagine new content. In our solution, we introduce image prompts in fine-grained image editing, cooperating with the text prompt to better describe the editing content. To increase the flexibility while maintaining content consistency, we locally combine stochastic differential equation (SDE) into the ordinary differential equation (ODE) sampling. In addition, we incorporate regional score-based gradient guidance and a time travel strategy into the diffusion sampling, further improving the editing quality. Extensive experiments demonstrate that our method can efficiently achieve state-of-the-art performance on various fine-grained image editing tasks, including editing within a single image (e.g., object moving, resizing, and content dragging) and across images (e.g., appearance replacing and object pasting). Our source code is released at https://github.com/MC-E/DragonDiffusion.
In this paper, we present an empirical study introducing a nuanced evaluation framework for text-to-image (T2I) generative models, applied to human image synthesis. Our framework categorizes evaluations into two distinct groups: first, focusing on image qualities such as aesthetics and realism, and second, examining text conditions through concept coverage and fairness. We introduce an innovative aesthetic score prediction model that assesses the visual appeal of generated images and unveils the first dataset marked with low-quality regions in generated human images to facilitate automatic defect detection. Our exploration into concept coverage probes the model's effectiveness in interpreting and rendering text-based concepts accurately, while our analysis of fairness reveals biases in model outputs, with an emphasis on gender, race, and age. While our study is grounded in human imagery, this dual-faceted approach is designed with the flexibility to be applicable to other forms of image generation, enhancing our understanding of generative models and paving the way to the next generation of more sophisticated, contextually aware, and ethically attuned generative models. Code and data, including the dataset annotated with defective areas, are available at \href{https://github.com/cure-lab/EvaluateAIGC}{https://github.com/cure-lab/EvaluateAIGC}.
Recently, diffusion models have made significant strides in synthesizing realistic 2D human images based on provided text prompts. Building upon this, researchers have extended 2D text-to-image diffusion models into the 3D domain for generating human textures (UV Maps). However, some important problems about UV Map Generative models are still not solved, i.e., how to generate personalized texture maps for any given face image, and how to define and evaluate the quality of these generated texture maps. To solve the above problems, we introduce a novel method, UVMap-ID, which is a controllable and personalized UV Map generative model. Unlike traditional large-scale training methods in 2D, we propose to fine-tune a pre-trained text-to-image diffusion model which is integrated with a face fusion module for achieving ID-driven customized generation. To support the finetuning strategy, we introduce a small-scale attribute-balanced training dataset, including high-quality textures with labeled text and Face ID. Additionally, we introduce some metrics to evaluate the multiple aspects of the textures. Finally, both quantitative and qualitative analyses demonstrate the effectiveness of our method in controllable and personalized UV Map generation. Code is publicly available via https://github.com/twowwj/UVMap-ID.
Large language models(LLMs) with powerful language generation and reasoning capabilities have already achieved success in many domains, e.g., math and code generation. However, due to the lacking of physical world's corpus and knowledge during training, they usually fail to solve many real-life tasks in the urban space. In this paper, we propose CityGPT, a systematic framework for enhancing the capability of LLMs on understanding urban space and solving the related urban tasks by building a city-scale world model in the model. First, we construct a diverse instruction tuning dataset CityInstruction for injecting urban knowledge and enhancing spatial reasoning capability effectively. By using a mixture of CityInstruction and general instruction data, we fine-tune various LLMs (e.g., ChatGLM3-6B, Qwen1.5 and LLama3 series) to enhance their capability without sacrificing general abilities. To further validate the effectiveness of proposed methods, we construct a comprehensive benchmark CityEval to evaluate the capability of LLMs on diverse urban scenarios and problems. Extensive evaluation results demonstrate that small LLMs trained with CityInstruction can achieve competitive performance with commercial LLMs in the comprehensive evaluation of CityEval. The source codes are openly accessible to the research community via https://github.com/tsinghua-fib-lab/CityGPT.
Recent research showcases the considerable potential of conditional diffusion models for generating consistent stories. However, current methods, which predominantly generate stories in an autoregressive and excessively caption-dependent manner, often underrate the contextual consistency and relevance of frames during sequential generation. To address this, we propose a novel Rich-contextual Conditional Diffusion Models (RCDMs), a two-stage approach designed to enhance story generation's semantic consistency and temporal consistency. Specifically, in the first stage, the frame-prior transformer diffusion model is presented to predict the frame semantic embedding of the unknown clip by aligning the semantic correlations between the captions and frames of the known clip. The second stage establishes a robust model with rich contextual conditions, including reference images of the known clip, the predicted frame semantic embedding of the unknown clip, and text embeddings of all captions. By jointly injecting these rich contextual conditions at the image and feature levels, RCDMs can generate semantic and temporal consistency stories. Moreover, RCDMs can generate consistent stories with a single forward inference compared to autoregressive models. Our qualitative and quantitative results demonstrate that our proposed RCDMs outperform in challenging scenarios. The code and model will be available at https://github.com/muzishen/RCDMs.
In this paper, we introduce a new outlier removal method that fully leverages geometric and semantic information, to achieve robust registration. Current semantic-based registration methods only use semantics for point-to-point or instance semantic correspondence generation, which has two problems. First, these methods are highly dependent on the correctness of semantics. They perform poorly in scenarios with incorrect semantics and sparse semantics. Second, the use of semantics is limited only to the correspondence generation, resulting in bad performance in the weak geometry scene. To solve these problems, on the one hand, we propose secondary ground segmentation and loose semantic consistency based on regional voting. It improves the robustness to semantic correctness by reducing the dependence on single-point semantics. On the other hand, we propose semantic-geometric consistency for outlier removal, which makes full use of semantic information and significantly improves the quality of correspondences. In addition, a two-stage hypothesis verification is proposed, which solves the problem of incorrect transformation selection in the weak geometry scene. In the outdoor dataset, our method demonstrates superior performance, boosting a 22.5 percentage points improvement in registration recall and achieving better robustness under various conditions. Our code is available.
CT report generation (CTRG) aims to automatically generate diagnostic reports for 3D volumes, relieving clinicians' workload and improving patient care. Despite clinical value, existing works fail to effectively incorporate diagnostic information from multiple anatomical views and lack related clinical expertise essential for accurate and reliable diagnosis. To resolve these limitations, we propose a novel Multi-view perception Knowledge-enhanced Transformer (MvKeTR) to mimic the diagnostic workflow of clinicians. Just as radiologists first examine CT scans from multiple planes, a Multi-View Perception Aggregator (MVPA) with view-aware attention effectively synthesizes diagnostic information from multiple anatomical views. Then, inspired by how radiologists further refer to relevant clinical records to guide diagnostic decision-making, a Cross-Modal Knowledge Enhancer (CMKE) retrieves the most similar reports based on the query volume to incorporate domain knowledge into the diagnosis procedure. Furthermore, instead of traditional MLPs, we employ Kolmogorov-Arnold Networks (KANs) with learnable nonlinear activation functions as the fundamental building blocks of both modules to better capture intricate diagnostic patterns in CT interpretation. Extensive experiments on the public CTRG-Chest-548K dataset demonstrate that our method outpaces prior state-of-the-art (SOTA) models across almost all metrics. The code will be made publicly available.
This study presents Poison-RAG, a framework for adversarial data poisoning attacks targeting retrieval-augmented generation (RAG)-based recommender systems. Poison-RAG manipulates item metadata, such as tags and descriptions, to influence recommendation outcomes. Using item metadata generated through a large language model (LLM) and embeddings derived via the OpenAI API, we explore the impact of adversarial poisoning attacks on provider-side, where attacks are designed to promote long-tail items and demote popular ones. Two attack strategies are proposed: local modifications, which personalize tags for each item using BERT embeddings, and global modifications, applying uniform tags across the dataset. Experiments conducted on the MovieLens dataset in a black-box setting reveal that local strategies improve manipulation effectiveness by up to 50\%, while global strategies risk boosting already popular items. Results indicate that popular items are more susceptible to attacks, whereas long-tail items are harder to manipulate. Approximately 70\% of items lack tags, presenting a cold-start challenge; data augmentation and synthesis are proposed as potential defense mechanisms to enhance RAG-based systems' resilience. The findings emphasize the need for robust metadata management to safeguard recommendation frameworks. Code and data are available at https://github.com/atenanaz/Poison-RAG.
The development of Text-to-Video (T2V) generation has made motion transfer possible, enabling the control of video motion based on existing footage. However, current methods have two limitations: 1) struggle to handle multi-subjects videos, failing to transfer specific subject motion; 2) struggle to preserve the diversity and accuracy of motion as transferring to subjects with varying shapes. To overcome these, we introduce \textbf{ConMo}, a zero-shot framework that disentangle and recompose the motions of subjects and camera movements. ConMo isolates individual subject and background motion cues from complex trajectories in source videos using only subject masks, and reassembles them for target video generation. This approach enables more accurate motion control across diverse subjects and improves performance in multi-subject scenarios. Additionally, we propose soft guidance in the recomposition stage which controls the retention of original motion to adjust shape constraints, aiding subject shape adaptation and semantic transformation. Unlike previous methods, ConMo unlocks a wide range of applications, including subject size and position editing, subject removal, semantic modifications, and camera motion simulation. Extensive experiments demonstrate that ConMo significantly outperforms state-of-the-art methods in motion fidelity and semantic consistency. The code is available at https://github.com/Andyplus1/ConMo.
We introduce CrossWKV, a novel cross-attention mechanism for the state-based RWKV-7 model, designed to enhance the expressive power of text-to-image generation. Leveraging RWKV-7's linear-complexity Weighted Key-Value (WKV) architecture, CrossWKV integrates text and image modalities in a single pass, utilizing a generalized delta rule with vector-valued gating and low-rank adaptations (LoRA) to achieve superior cross-modal alignment. Unlike Transformer-based models, CrossWKV's non-diagonal, input-dependent transition matrix enables it to represent complex functions beyond the $\mathrm{TC}^0$ complexity class, including all regular languages, as demonstrated by its ability to perform state-tracking tasks like $S_5$ permutation modeling. Evaluated within the Diffusion in RWKV-7 (DIR-7) on datasets such as LAION-5B and ImageNet, CrossWKV achieves a Frechet Inception Distance (FID) of 2.88 and a CLIP score of 0.33 on ImageNet 256x256, matching state-of-the-art performance while offering robust generalization across diverse prompts. The model's enhanced expressivity, combined with constant memory usage and linear scaling, positions it as a powerful solution for advanced cross-modal tasks, with potential applications in high-resolution generation and dynamic state manipulation.Code at https://github.com/TorchRWKV/flash-linear-attention
Reconstructing 3D objects from a single image is a long-standing challenge, especially under real-world occlusions. While recent diffusion-based view synthesis models can generate consistent novel views from a single RGB image, they generally assume fully visible inputs and fail when parts of the object are occluded. This leads to inconsistent views and degraded 3D reconstruction quality. To overcome this limitation, we propose an end-to-end framework for occlusion-aware multi-view generation. Our method directly synthesizes six structurally consistent novel views from a single partially occluded image, enabling downstream 3D reconstruction without requiring prior inpainting or manual annotations. We construct a self-supervised training pipeline using the Pix2Gestalt dataset, leveraging occluded-unoccluded image pairs and pseudo-ground-truth views to teach the model structure-aware completion and view consistency. Without modifying the original architecture, we fully fine-tune the view synthesis model to jointly learn completion and multi-view generation. Additionally, we introduce the first benchmark for occlusion-aware reconstruction, encompassing diverse occlusion levels, object categories, and mask patterns. This benchmark provides a standardized protocol for evaluating future methods under partial occlusions. Our code is available at https://github.com/Quyans/DeOcc123.
Camouflage is a common visual phenomenon, which refers to hiding the foreground objects into the background images, making them briefly invisible to the human eye. Previous work has typically been implemented by an iterative optimization process. However, these methods struggle in 1) efficiently generating camouflage images using foreground and background with arbitrary structure; 2) camouflaging foreground objects to regions with multiple appearances (e.g. the junction of the vegetation and the mountains), which limit their practical application. To address these problems, this paper proposes a novel Location-free Camouflage Generation Network (LCG-Net) that fuse high-level features of foreground and background image, and generate result by one inference. Specifically, a Position-aligned Structure Fusion (PSF) module is devised to guide structure feature fusion based on the point-to-point structure similarity of foreground and background, and introduce local appearance features point-by-point. To retain the necessary identifiable features, a new immerse loss is adopted under our pipeline, while a background patch appearance loss is utilized to ensure that the hidden objects look continuous and natural at regions with multiple appearances. Experiments show that our method has results as satisfactory as state-of-the-art in the single-appearance regions and are less likely to be completely invisible, but far exceed the quality of the state-of-the-art in the multi-appearance regions. Moreover, our method is hundreds of times faster than previous methods. Benefitting from the unique advantages of our method, we provide some downstream applications for camouflage generation, which show its potential. The related code and dataset will be released at https://github.com/Tale17/LCG-Net.
Large Language Models (LLMs) have demonstrated exceptional coding capability. However, as another critical component of programming proficiency, the debugging capability of LLMs remains relatively unexplored. Previous evaluations of LLMs' debugging ability are significantly limited by the risk of data leakage, the scale of the dataset, and the variety of tested bugs. To overcome these deficiencies, we introduce `DebugBench', an LLM debugging benchmark consisting of 4,253 instances. It covers four major bug categories and 18 minor types in C++, Java, and Python. To construct DebugBench, we collect code snippets from the LeetCode community, implant bugs into source data with GPT-4, and assure rigorous quality checks. We evaluate two commercial and four open-source models in a zero-shot scenario. We find that (1) while closed-source models exhibit inferior debugging performance compared to humans, open-source models relatively lower pass rate scores; (2) the complexity of debugging notably fluctuates depending on the bug category; (3) incorporating runtime feedback has a clear impact on debugging performance which is not always helpful. As an extension, we also compare LLM debugging and code generation, revealing a strong correlation between them for closed-source models. These findings will benefit the development of LLMs in debugging.
Model merging is a technique that combines multiple large pretrained models into a single model with enhanced performance and broader task adaptability. It has gained popularity in large pretrained model development due to its ability to bypass the need for original training data and further training processes. However, most existing model merging approaches focus solely on exploring the parameter space, merging models with identical architectures. Merging within the architecture space, despite its potential, remains in its early stages due to the vast search space and the challenges of layer compatibility. This paper marks a significant advance toward more flexible and comprehensive model merging techniques by modeling the architecture-space merging process as a reinforcement learning task. We train policy and value networks using offline sampling of weight vectors, which are then employed for the online optimization of merging strategies. Moreover, a multi-objective optimization paradigm is introduced to accommodate users' diverse task preferences, learning the Pareto front of optimal models to offer customized merging suggestions. Experimental results across multiple tasks, including text translation, mathematical reasoning, and code generation, validate the effectiveness and superiority of the proposed framework in model merging. The code will be made publicly available after the review process.
Knowledge Distillation (KD) has emerged as a prominent technique for model compression. However, conventional KD approaches primarily focus on homogeneous architectures with identical tokenizers, constraining their applicability in cross-architecture scenarios. As for the cross-tokenizer KD, the differences in the tokenizers give rise to two fundamental challenges: (1) sequence misalignment caused by divergent tokenization strategies, and (2) mismatched vocabulary size and composition. While existing probability-matching methods attempt to address these issues, their efficacy remains limited due to suboptimal alignment in both the sequence and vocabulary aspects. To overcome these limitations, we propose Contextual Dynamic Mapping (CDM), a novel cross-tokenizer distillation framework that employs contextual information to enhance sequence alignment precision and dynamically improves vocabulary mapping. We evaluated the effectiveness of our approach across five advanced and widely-used model families (i.e, LLama3, Phi3, Gemma2, OPT and Qwen2), which were configured into three distinct teacher-student pairs. Our method shows significant advantages over existing cross-tokenizer distillation baselines across diverse benchmarks, including instruction-following, code generation and math. Notably, our analysis reveals that combining conventional same-tokenizer distillation and cross-tokenizer distillation through CDM yields further performance improvements. The code is available at https://github.com/pppa2019/ContexualDynamicMapping
Large Language Models (LLMs) are powerful tools, capable of leveraging their training on natural language to write stories, generate code, and answer questions. But can they generate functional video game levels? Game levels, with their complex functional constraints and spatial relationships in more than one dimension, are very different from the kinds of data an LLM typically sees during training. Datasets of game levels are also hard to come by, potentially taxing the abilities of these data-hungry models. We investigate the use of LLMs to generate levels for the game Sokoban, finding that LLMs are indeed capable of doing so, and that their performance scales dramatically with dataset size. We also perform preliminary experiments on controlling LLM level generators and discuss promising areas for future work.
Energy-based models (EBMs) exhibit a variety of desirable properties in predictive tasks, such as generality, simplicity and compositionality. However, training EBMs on high-dimensional datasets remains unstable and expensive. In this paper, we present a Manifold EBM (M-EBM) to boost the overall performance of unconditional EBM and Joint Energy-based Model (JEM). Despite its simplicity, M-EBM significantly improves unconditional EBMs in training stability and speed on a host of benchmark datasets, such as CIFAR10, CIFAR100, CelebA-HQ, and ImageNet 32x32. Once class labels are available, label-incorporated M-EBM (M-JEM) further surpasses M-EBM in image generation quality with an over 40% FID improvement, while enjoying improved accuracy. The code can be found at https://github.com/sndnyang/mebm.
This paper introduces ModelScopeT2V, a text-to-video synthesis model that evolves from a text-to-image synthesis model (i.e., Stable Diffusion). ModelScopeT2V incorporates spatio-temporal blocks to ensure consistent frame generation and smooth movement transitions. The model could adapt to varying frame numbers during training and inference, rendering it suitable for both image-text and video-text datasets. ModelScopeT2V brings together three components (i.e., VQGAN, a text encoder, and a denoising UNet), totally comprising 1.7 billion parameters, in which 0.5 billion parameters are dedicated to temporal capabilities. The model demonstrates superior performance over state-of-the-art methods across three evaluation metrics. The code and an online demo are available at \url{https://modelscope.cn/models/damo/text-to-video-synthesis/summary}.
We introduce a multimodal dataset where users express preferences through images. These images encompass a broad spectrum of visual expressions ranging from landscapes to artistic depictions. Users request recommendations for books or music that evoke similar feelings to those captured in the images, and recommendations are endorsed by the community through upvotes. This dataset supports two recommendation tasks: title generation and multiple-choice selection. Our experiments with large foundation models reveal their limitations in these tasks. Particularly, vision-language models show no significant advantage over language-only counterparts that use descriptions, which we hypothesize is due to underutilized visual capabilities. To better harness these abilities, we propose the chain-of-imagery prompting, which results in notable improvements. We release our code and datasets.