Mask$^2$DiT: Dual Mask-based Diffusion Transformer for Multi-Scene Long Video Generation

Sora has unveiled the immense potential of the Diffusion Transformer (DiT) architecture in single-scene video generation. However, the more challenging task of multi-scene video generation, which offers broader applications, remains relatively underexplored. To bridge this gap, we propose Mask$^2$DiT, a novel approach that establishes fine-grained, one-to-one alignment between video segments and their corresponding text annotations. Specifically, we introduce a symmetric binary mask at each attention layer within the DiT architecture, ensuring that each text annotation applies exclusively to its respective video segment while preserving temporal coherence across visual tokens. This attention mechanism enables precise segment-level textual-to-visual alignment, allowing the DiT architecture to effectively handle video generation tasks with a fixed number of scenes. To further equip the DiT architecture with the ability to generate additional scenes based on existing ones, we incorporate a segment-level conditional mask, which conditions each newly generated segment on the preceding video segments, thereby enabling auto-regressive scene extension. Both qualitative and quantitative experiments confirm that Mask$^2$DiT excels in maintaining visual consistency across segments while ensuring semantic alignment between each segment and its corresponding text description. Our project page is https://tianhao-qi.github.io/Mask2DiTProject.

SpaceVLLM: Endowing Multimodal Large Language Model with Spatio-Temporal Video Grounding Capability

Multimodal large language models (MLLMs) have made remarkable progress in either temporal or spatial localization. However, they struggle to perform spatio-temporal video grounding. This limitation stems from two major challenges. Firstly, it is difficult to extract accurate spatio-temporal information of each frame in the video. Secondly, the substantial number of visual tokens makes it challenging to precisely map visual tokens of each frame to their corresponding spatial coordinates. To address these issues, we introduce SpaceVLLM, a MLLM endowed with spatio-temporal video grounding capability. Specifically, we adopt a set of interleaved Spatio-Temporal Aware Queries to capture temporal perception and dynamic spatial information. Moreover, we propose a Query-Guided Space Decoder to establish a corresponding connection between the queries and spatial coordinates. Additionally, due to the lack of spatio-temporal datasets, we construct the Unified Spatio-Temporal Grounding (Uni-STG) dataset, comprising 480K instances across three tasks. This dataset fully exploits the potential of MLLM to simultaneously facilitate localization in both temporal and spatial dimensions. Extensive experiments demonstrate that SpaceVLLM achieves the state-of-the-art performance across 11 benchmarks covering temporal, spatial, spatio-temporal and video understanding tasks, highlighting the effectiveness of our approach. Our code, datasets and model will be released.

OmniPrism: Learning Disentangled Visual Concept for Image Generation

Creative visual concept generation often draws inspiration from specific concepts in a reference image to produce relevant outcomes. However, existing methods are typically constrained to single-aspect concept generation or are easily disrupted by irrelevant concepts in multi-aspect concept scenarios, leading to concept confusion and hindering creative generation. To address this, we propose OmniPrism, a visual concept disentangling approach for creative image generation. Our method learns disentangled concept representations guided by natural language and trains a diffusion model to incorporate these concepts. We utilize the rich semantic space of a multimodal extractor to achieve concept disentanglement from given images and concept guidance. To disentangle concepts with different semantics, we construct a paired concept disentangled dataset (PCD-200K), where each pair shares the same concept such as content, style, and composition. We learn disentangled concept representations through our contrastive orthogonal disentangled (COD) training pipeline, which are then injected into additional diffusion cross-attention layers for generation. A set of block embeddings is designed to adapt each block's concept domain in the diffusion models. Extensive experiments demonstrate that our method can generate high-quality, concept-disentangled results with high fidelity to text prompts and desired concepts.

LMAgent: A Large-scale Multimodal Agents Society for Multi-user Simulation

The believable simulation of multi-user behavior is crucial for understanding complex social systems. Recently, large language models (LLMs)-based AI agents have made significant progress, enabling them to achieve human-like intelligence across various tasks. However, real human societies are often dynamic and complex, involving numerous individuals engaging in multimodal interactions. In this paper, taking e-commerce scenarios as an example, we present LMAgent, a very large-scale and multimodal agents society based on multimodal LLMs. In LMAgent, besides freely chatting with friends, the agents can autonomously browse, purchase, and review products, even perform live streaming e-commerce. To simulate this complex system, we introduce a self-consistency prompting mechanism to augment agents' multimodal capabilities, resulting in significantly improved decision-making performance over the existing multi-agent system. Moreover, we propose a fast memory mechanism combined with the small-world model to enhance system efficiency, which supports more than 10,000 agent simulations in a society. Experiments on agents' behavior show that these agents achieve comparable performance to humans in behavioral indicators. Furthermore, compared with the existing LLMs-based multi-agent system, more different and valuable phenomena are exhibited, such as herd behavior, which demonstrates the potential of LMAgent in credible large-scale social behavior simulations.

A Graph-Based Synthetic Data Pipeline for Scaling High-Quality Reasoning Instructions

Synthesizing high-quality reasoning data for continual training has been proven to be effective in enhancing the performance of Large Language Models (LLMs). However, previous synthetic approaches struggle to easily scale up data and incur high costs in the pursuit of high quality. In this paper, we propose the Graph-based Synthetic Data Pipeline (GSDP), an economical and scalable framework for high-quality reasoning data synthesis. Inspired by knowledge graphs, we extracted knowledge points from seed data and constructed a knowledge point relationships graph to explore their interconnections. By exploring the implicit relationships among knowledge, our method achieves $\times$255 data expansion. Furthermore, GSDP led by open-source models, achieves synthesis quality comparable to GPT-4-0613 while maintaining $\times$100 lower costs. To tackle the most challenging mathematical reasoning task, we present the GSDP-MATH dataset comprising over 1.91 million pairs of math problems and answers. After fine-tuning on GSDP-MATH, GSDP-7B based on Mistral-7B achieves 37.7% accuracy on MATH and 78.4% on GSM8K, demonstrating the effectiveness of our method. The dataset and models trained in this paper will be available.

T-SVG: Text-Driven Stereoscopic Video Generation

The advent of stereoscopic videos has opened new horizons in multimedia, particularly in extended reality (XR) and virtual reality (VR) applications, where immersive content captivates audiences across various platforms. Despite its growing popularity, producing stereoscopic videos remains challenging due to the technical complexities involved in generating stereo parallax. This refers to the positional differences of objects viewed from two distinct perspectives and is crucial for creating depth perception. This complex process poses significant challenges for creators aiming to deliver convincing and engaging presentations. To address these challenges, this paper introduces the Text-driven Stereoscopic Video Generation (T-SVG) system. This innovative, model-agnostic, zero-shot approach streamlines video generation by using text prompts to create reference videos. These videos are transformed into 3D point cloud sequences, which are rendered from two perspectives with subtle parallax differences, achieving a natural stereoscopic effect. T-SVG represents a significant advancement in stereoscopic content creation by integrating state-of-the-art, training-free techniques in text-to-video generation, depth estimation, and video inpainting. Its flexible architecture ensures high efficiency and user-friendliness, allowing seamless updates with newer models without retraining. By simplifying the production pipeline, T-SVG makes stereoscopic video generation accessible to a broader audience, demonstrating its potential to revolutionize the field.

Boosting Semi-Supervised Scene Text Recognition via Viewing and Summarizing

Existing scene text recognition (STR) methods struggle to recognize challenging texts, especially for artistic and severely distorted characters. The limitation lies in the insufficient exploration of character morphologies, including the monotonousness of widely used synthetic training data and the sensitivity of the model to character morphologies. To address these issues, inspired by the human learning process of viewing and summarizing, we facilitate the contrastive learning-based STR framework in a self-motivated manner by leveraging synthetic and real unlabeled data without any human cost. In the viewing process, to compensate for the simplicity of synthetic data and enrich character morphology diversity, we propose an Online Generation Strategy to generate background-free samples with diverse character styles. By excluding background noise distractions, the model is encouraged to focus on character morphology and generalize the ability to recognize complex samples when trained with only simple synthetic data. To boost the summarizing process, we theoretically demonstrate the derivation error in the previous character contrastive loss, which mistakenly causes the sparsity in the intra-class distribution and exacerbates ambiguity on challenging samples. Therefore, a new Character Unidirectional Alignment Loss is proposed to correct this error and unify the representation of the same characters in all samples by aligning the character features in the student model with the reference features in the teacher model. Extensive experiment results show that our method achieves SOTA performance (94.7\% and 70.9\% average accuracy on common benchmarks and Union14M-Benchmark). Code will be available at https://github.com/qqqyd/ViSu.

It Takes Two: Accurate Gait Recognition in the Wild via Cross-granularity Alignment

Existing studies for gait recognition primarily utilized sequences of either binary silhouette or human parsing to encode the shapes and dynamics of persons during walking. Silhouettes exhibit accurate segmentation quality and robustness to environmental variations, but their low information entropy may result in sub-optimal performance. In contrast, human parsing provides fine-grained part segmentation with higher information entropy, but the segmentation quality may deteriorate due to the complex environments. To discover the advantages of silhouette and parsing and overcome their limitations, this paper proposes a novel cross-granularity alignment gait recognition method, named XGait, to unleash the power of gait representations of different granularity. To achieve this goal, the XGait first contains two branches of backbone encoders to map the silhouette sequences and the parsing sequences into two latent spaces, respectively. Moreover, to explore the complementary knowledge across the features of two representations, we design the Global Cross-granularity Module (GCM) and the Part Cross-granularity Module (PCM) after the two encoders. In particular, the GCM aims to enhance the quality of parsing features by leveraging global features from silhouettes, while the PCM aligns the dynamics of human parts between silhouette and parsing features using the high information entropy in parsing sequences. In addition, to effectively guide the alignment of two representations with different granularity at the part level, an elaborate-designed learnable division mechanism is proposed for the parsing features. Comprehensive experiments on two large-scale gait datasets not only show the superior performance of XGait with the Rank-1 accuracy of 80.5% on Gait3D and 88.3% CCPG but also reflect the robustness of the learned features even under challenging conditions like occlusions and cloth changes.

MILP-StuDio: MILP Instance Generation via Block Structure Decomposition

Mixed-integer linear programming (MILP) is one of the most popular mathematical formulations with numerous applications. In practice, improving the performance of MILP solvers often requires a large amount of high-quality data, which can be challenging to collect. Researchers thus turn to generation techniques to generate additional MILP instances. However, existing approaches do not take into account specific block structures -- which are closely related to the problem formulations -- in the constraint coefficient matrices (CCMs) of MILPs. Consequently, they are prone to generate computationally trivial or infeasible instances due to the disruptions of block structures and thus problem formulations. To address this challenge, we propose a novel MILP generation framework, called Block Structure Decomposition (MILP-StuDio), to generate high-quality instances by preserving the block structures. Specifically, MILP-StuDio begins by identifying the blocks in CCMs and decomposing the instances into block units, which serve as the building blocks of MILP instances. We then design three operators to construct new instances by removing, substituting, and appending block units in the original instances, enabling us to generate instances with flexible sizes. An appealing feature of MILP-StuDio is its strong ability to preserve the feasibility and computational hardness of the generated instances. Experiments on the commonly-used benchmarks demonstrate that using instances generated by MILP-StuDio is able to significantly reduce over 10% of the solving time for learning-based solvers.

Coarse-to-Fine Highlighting: Reducing Knowledge Hallucination in Large Language Models

Generation of plausible but incorrect factual information, often termed hallucination, has attracted significant research interest. Retrieval-augmented language model (RALM) -- which enhances models with up-to-date knowledge -- emerges as a promising method to reduce hallucination. However, existing RALMs may instead exacerbate hallucination when retrieving lengthy contexts. To address this challenge, we propose COFT, a novel \textbf{CO}arse-to-\textbf{F}ine highligh\textbf{T}ing method to focus on different granularity-level key texts, thereby avoiding getting lost in lengthy contexts. Specifically, COFT consists of three components: \textit{recaller}, \textit{scorer}, and \textit{selector}. First, \textit{recaller} applies a knowledge graph to extract potential key entities in a given context. Second, \textit{scorer} measures the importance of each entity by calculating its contextual weight. Finally, \textit{selector} selects high contextual weight entities with a dynamic threshold algorithm and highlights the corresponding paragraphs, sentences, or words in a coarse-to-fine manner. Extensive experiments on the knowledge hallucination benchmark demonstrate the effectiveness of COFT, leading to a superior performance over $30\%$ in the F1 score metric. Moreover, COFT also exhibits remarkable versatility across various long-form tasks, such as reading comprehension and question answering.