Haonan Lu

Fobo Shi, Peijun Qing, Dong Yang et al.

Prompt engineering is an essential technique for enhancing the abilities of large language models (LLMs) by providing explicit and specific instructions. It enables LLMs to excel in various tasks, such as arithmetic reasoning, question answering, summarization, relation extraction, machine translation, and sentiment analysis. Researchers have been actively exploring different prompt engineering strategies, such as Chain of Thought (CoT), Zero-CoT, and In-context learning. However, an unresolved problem arises from the fact that current approaches lack a solid mathematical solution for determining optimal prompts. To address this issue in prompt engineering, we propose a new and effective approach called Prompt Space. Our methodology utilizes text embeddings to obtain basis vectors by matrix decomposition, and then constructs a space for representing all prompts. Prompt Space significantly outperforms state-of-the-art prompt paradigms on ten public reasoning benchmarks. Notably, without the help of the CoT method and the prompt "Let's think step by step", Prompt Space shows superior performance over the few-shot method. Overall, our approach provides a robust and effective mathematical framework for selecting simple and effective prompts. This advancement marks a significant step towards improving prompt engineering for a wide variety of applications in LLMs. Our code is publicly available at \textcolor{blue}{\url{https://github.com/YouBLEI/Prompt-Space}}

Defeng Xie, Ruichen Wang, Jian Ma et al.

We introduce a new generative system called Edit Everything, which can take image and text inputs and produce image outputs. Edit Everything allows users to edit images using simple text instructions. Our system designs prompts to guide the visual module in generating requested images. Experiments demonstrate that Edit Everything facilitates the implementation of the visual aspects of Stable Diffusion with the use of Segment Anything model and CLIP. Our system is publicly available at https://github.com/DefengXie/Edit_Everything.

Haolin Deng, Xin Zou, Zhiwei Jin et al.

Multimodal hallucination remains a persistent challenge for Vision-Language Models (VLMs). Standard textual Direct Preference Optimization (DPO) often fails to mitigate it due to a lack of explicit visual supervision. While existing works introduce visual preference DPO by contrasting original images against negative ones, they suffer from a theoretically inconsistent objective caused by partition function mismatches and rely on coarse-grained negatives that could enable shortcut learning. In this work, we propose In-Context Visual Contrastive Optimization (IC-VCO). By placing contrastive images within a shared multi-image context, IC-VCO ensures a mathematically rigorous objective. We further introduce Visual Contrast Distillation (VCDist), an auxiliary reliability-gated regularizer that encourages consistency between multi-image contrastive training and single-image inference. Finally, we propose a contrastive sample editing strategy that generates hard negatives via precise semantic perturbations. Experiments on five benchmarks demonstrate IC-VCO's best overall performance and the effectiveness of our sample editing strategy. Code and data are available at https://github.com/OPPO-Mente-Lab/IC-VCO.

Haotian Bai, Yuanhuiyi Lyu, Lutao Jiang et al.

Text-to-3D form plays a crucial role in creating editable 3D scenes for AR/VR. Recent advances have shown promise in merging neural radiance fields (NeRFs) with pre-trained diffusion models for text-to-3D object generation. However, one enduring challenge is their inadequate capability to accurately parse and regenerate consistent multi-object environments. Specifically, these models encounter difficulties in accurately representing quantity and style prompted by multi-object texts, often resulting in a collapse of the rendering fidelity that fails to match the semantic intricacies. Moreover, amalgamating these elements into a coherent 3D scene is a substantial challenge, stemming from generic distribution inherent in diffusion models. To tackle the issue of 'guidance collapse' and further enhance scene consistency, we propose a novel framework, dubbed CompoNeRF, by integrating an editable 3D scene layout with object-specific and scene-wide guidance mechanisms. It initiates by interpreting a complex text into the layout populated with multiple NeRFs, each paired with a corresponding subtext prompt for precise object depiction. Next, a tailored composition module seamlessly blends these NeRFs, promoting consistency, while the dual-level text guidance reduces ambiguity and boosts accuracy. Noticeably, our composition design permits decomposition. This enables flexible scene editing and recomposition into new scenes based on the edited layout or text prompts. Utilizing the open-source Stable Diffusion model, CompoNeRF generates multi-object scenes with high fidelity. Remarkably, our framework achieves up to a \textbf{54\%} improvement by the multi-view CLIP score metric. Our user study indicates that our method has significantly improved semantic accuracy, multi-view consistency, and individual recognizability for multi-object scene generation.

Jian Ma, Yonglin Deng, Chen Chen et al.

Posters play a crucial role in marketing and advertising by enhancing visual communication and brand visibility, making significant contributions to industrial design. With the latest advancements in controllable T2I diffusion models, increasing research has focused on rendering text within synthesized images. Despite improvements in text rendering accuracy, the field of automatic poster generation remains underexplored. In this paper, we propose an automatic poster generation framework with text rendering capabilities leveraging LLMs, utilizing a triple-cross attention mechanism based on alignment learning. This framework aims to create precise poster text within a detailed contextual background. Additionally, the framework supports controllable fonts, adjustable image resolution, and the rendering of posters with descriptions and text in both English and Chinese.Furthermore, we introduce a high-resolution font dataset and a poster dataset with resolutions exceeding 1024 pixels. Our approach leverages the SDXL architecture. Extensive experiments validate our method's capability in generating poster images with complex and contextually rich backgrounds.Codes is available at https://github.com/OPPO-Mente-Lab/GlyphDraw2.

Dong Yang, Peijun Qing, Yang Li et al.

Embedding knowledge graphs (KGs) for multi-hop logical reasoning is a challenging problem due to massive and complicated structures in many KGs. Recently, many promising works projected entities and queries into a geometric space to efficiently find answers. However, it remains challenging to model the negation and union operator. The negation operator has no strict boundaries, which generates overlapped embeddings and leads to obtaining ambiguous answers. An additional limitation is that the union operator is non-closure, which undermines the model to handle a series of union operators. To address these problems, we propose a novel probabilistic embedding model, namely Gamma Embeddings (GammaE), for encoding entities and queries to answer different types of FOL queries on KGs. We utilize the linear property and strong boundary support of the Gamma distribution to capture more features of entities and queries, which dramatically reduces model uncertainty. Furthermore, GammaE implements the Gamma mixture method to design the closed union operator. The performance of GammaE is validated on three large logical query datasets. Experimental results show that GammaE significantly outperforms state-of-the-art models on public benchmarks.

Jian Ma, Chen Chen, Qingsong Xie et al.

Text-to-image diffusion models are well-known for their ability to generate realistic images based on textual prompts. However, the existing works have predominantly focused on English, lacking support for non-English text-to-image models. The most commonly used translation methods cannot solve the generation problem related to language culture, while training from scratch on a specific language dataset is prohibitively expensive. In this paper, we are inspired to propose a simple plug-and-play language transfer method based on knowledge distillation. All we need to do is train a lightweight MLP-like parameter-efficient adapter (PEA) with only 6M parameters under teacher knowledge distillation along with a small parallel data corpus. We are surprised to find that freezing the parameters of UNet can still achieve remarkable performance on the language-specific prompt evaluation set, demonstrating that PEA can stimulate the potential generation ability of the original UNet. Additionally, it closely approaches the performance of the English text-to-image model on a general prompt evaluation set. Furthermore, our adapter can be used as a plugin to achieve significant results in downstream tasks in cross-lingual text-to-image generation. Code will be available at: https://github.com/OPPO-Mente-Lab/PEA-Diffusion

Jian Ma, Junhao Liang, Chen Chen et al.

Recent progress in personalized image generation using diffusion models has been significant. However, development in the area of open-domain and non-fine-tuning personalized image generation is proceeding rather slowly. In this paper, we propose Subject-Diffusion, a novel open-domain personalized image generation model that, in addition to not requiring test-time fine-tuning, also only requires a single reference image to support personalized generation of single- or multi-subject in any domain. Firstly, we construct an automatic data labeling tool and use the LAION-Aesthetics dataset to construct a large-scale dataset consisting of 76M images and their corresponding subject detection bounding boxes, segmentation masks and text descriptions. Secondly, we design a new unified framework that combines text and image semantics by incorporating coarse location and fine-grained reference image control to maximize subject fidelity and generalization. Furthermore, we also adopt an attention control mechanism to support multi-subject generation. Extensive qualitative and quantitative results demonstrate that our method outperforms other SOTA frameworks in single, multiple, and human customized image generation. Please refer to our \href{https://oppo-mente-lab.github.io/subject_diffusion/}{project page}

Zhijia Liang, Jiaming Li, Weikai Chen et al.

Streaming video reasoning requires models to operate in a setting where history grows without bound while meaningful evidence remains scarce. In such a landscape, relevant signal is like an oasis-small, critical, and easily lost in a desert of redundancy. Enlarging memory only widens the desert; aggressive compression dries up the oasis. The real difficulty lies in discovering where to look, not how much to remember. We therefore introduce OASIS, a novel framework for streaming video reasoning that tackles this challenge through structured, on-demand retrieval. It organizes streaming history into hierarchical events and performs reasoning as controlled refinement-short-context inference first, followed by semantically grounded retrieval only when uncertainty arises. As the retrieval is driven by high-level intent rather than embedding similarity, the retrieved memory is substantially more accurate and less noisy. Additionally, the mechanism is plug-and-play, training-free, and readily attaches to different streaming MLLM backbones. Experiments across multiple benchmarks and backbones show that OASIS achieves strong gains in long-horizon accuracy and compositional reasoning with bounded token cost and low request delay. Code is available at https://github.com/Solus-sano/OASIS.

Luyuan Zhang, Siyuan Li, Zedong Wang et al.

Most visual tokenizers for image generation are bifurcated into two families with complementary limitations: continuous VAEs offer high-fidelity reconstruction but suffer from dense, entangled latents that are poorly suited for semantic control, whereas discrete VQ-based models enable autoregressive generation yet struggle with gradient sparsity, unstable training, and codebook collapse. In this work, we introduce MergeTok, a unified tokenizer that jointly optimizes continuous (VAE) and discrete (VQ) tokenizers within a encoder-decoder architecture, leveraging token merging techniques as a semantic bridge. By clustering similar tokens during encoding, MergeTok establishes a structural prior that provides dual supervision signals: (i) it imposes merged-token semantic alignment in the VAE branch, regularizing its latent space toward disentangled, semantic-aware representations; (ii) it derives group-wise constraints, promoting intra-group diversity and inter-group exclusivity that stabilize VQ training. MergeTok shows competitive reconstruction and generation performance on ImageNet-256, with substantially lower rFID than strong VAE and VQ models under matched token budgets, while producing semantically-organized token representations compatible with both autoregressive and diffusion generators. This shows that a single architecture can endow visual tokenizers with robust semantic organization and generator-friendly discreteness.

Xiaoming Ren, Ru Zhen, Chao Li et al.

Inspired by the development of OpenClaw, there is a growing demand for mobile-based personal agents capable of handling complex and intuitive interactions. In this technical report, we introduce X-OmniClaw, a unified mobile agent designed for multimodal understanding and interaction in the Android ecosystem. This unified architecture of perception, memory, and action enables the agent to handle complex mobile tasks with high contextual awareness. Specifically, Omni Perception provides a unified multimodal ingress pipeline that integrates UI states, real-world visual contexts, and speech inputs, leveraging a temporal alignment module to decompose raw data into structured multimodal intent representations. Omni Memory leverages multimodal memory optimization to enhance personalized intelligence by integrating runtime working memory for task continuity with long-term personal memory distilled from local data, enabling highly context-aware and personalized interactions. Finally, Omni Action employs a hybrid grounding strategy that combines structural XML metadata with visual perception for robust interaction. Through Behavior Cloning and Trajectory Replay, the system captures user navigation as reusable skills, enabling precise direct-access execution. Demonstrations across diverse scenarios show that X-OmniClaw effectively enhances interaction efficiency and task reliability, providing a practical architectural blueprint for the next generation of mobile-native personal assistants.

Jian Ma, Mingjun Zhao, Chen Chen et al.

Recent breakthroughs in the field of language-guided image generation have yielded impressive achievements, enabling the creation of high-quality and diverse images based on user instructions.Although the synthesis performance is fascinating, one significant limitation of current image generation models is their insufficient ability to generate text coherently within images, particularly for complex glyph structures like Chinese characters. To address this problem, we introduce GlyphDraw, a general learning framework aiming to endow image generation models with the capacity to generate images coherently embedded with text for any specific language.We first sophisticatedly design the image-text dataset's construction strategy, then build our model specifically on a diffusion-based image generator and carefully modify the network structure to allow the model to learn drawing language characters with the help of glyph and position information.Furthermore, we maintain the model's open-domain image synthesis capability by preventing catastrophic forgetting by using parameter-efficient fine-tuning techniques.Extensive qualitative and quantitative experiments demonstrate that our method not only produces accurate language characters as in prompts, but also seamlessly blends the generated text into the background.Please refer to our \href{https://1073521013.github.io/glyph-draw.github.io/}{project page}. \end{abstract}

Zhengxian Wu, Kai Shi, Chuanrui Zhang et al.

Recent progress in multimodal large language models has led to strong performance on reasoning tasks, but these improvements largely rely on high-quality annotated data or teacher-model distillation, both of which are costly and difficult to scale. To address this, we propose an unsupervised self-evolution training framework for multimodal reasoning that achieves stable performance improvements without using human-annotated answers or external reward models. For each input, we sample multiple reasoning trajectories and jointly model their within group structure. We use the Actor's self-consistency signal as a training prior, and introduce a bounded Judge based modulation to continuously reweight trajectories of different quality. We further model the modulated scores as a group level distribution and convert absolute scores into relative advantages within each group, enabling more robust policy updates. Trained with Group Relative Policy Optimization (GRPO) on unlabeled data, our method consistently improves reasoning performance and generalization on five mathematical reasoning benchmarks, offering a scalable path toward self-evolving multimodal models. The code are available at https://github.com/OPPO-Mente-Lab/LLM-Self-Judge.

MiniMax, Aili Chen, Aonian Li et al.

We introduce the MiniMax-M2 series, a family of Mixture-of-Experts language models built around the principle that mini activations can unleash maximum real-world intelligence. The flagship M2 contains 229.9B total parameters with only 9.8B activated per token. Designed end-to-end for agentic deployment, the M2 series rests on three components: (i) agent-driven data pipelines producing large-scale, verifiable trajectories across agentic coding and agentic cowork, each grounded in an executable workspace and an artifact-aligned reward; (ii) Forge, a scalable agent-native RL system that adapts to long-horizon agent trajectories, paired with windowed-FIFO scheduling, prefix-tree merging, inference optimization, and a clean training-inference-agent decoupling that supports both white-box and black-box agents; (iii) the latest M2.7 checkpoint takes an early step toward self-evolution -- autonomously debugging training runs and modifying its own scaffold. Across M2 through M2.7, this combination translates a mini-activation footprint into frontier-tier performance on agentic coding, deep search, office-task, and reasoning benchmarks.

Sijia Li, Chen Chen, Haonan Lu

Diffusion-model-based text-guided image generation has recently made astounding progress, producing fascinating results in open-domain image manipulation tasks. Few models, however, currently have complete zero-shot capabilities for both global and local image editing due to the complexity and diversity of image manipulation tasks. In this work, we propose a method with a mixture-of-expert (MOE) controllers to align the text-guided capacity of diffusion models with different kinds of human instructions, enabling our model to handle various open-domain image manipulation tasks with natural language instructions. First, we use large language models (ChatGPT) and conditional image synthesis models (ControlNet) to generate a large number of global image transfer dataset in addition to the instruction-based local image editing dataset. Then, using an MOE technique and task-specific adaptation training on a large-scale dataset, our conditional diffusion model can edit images globally and locally. Extensive experiments demonstrate that our approach performs surprisingly well on various image manipulation tasks when dealing with open-domain images and arbitrary human instructions. Please refer to our project page: [https://oppo-mente-lab.github.io/moe_controller/]

Youbo Lei, Feifei He, Chen Chen et al.

Due to the success of large-scale visual-language pretraining (VLP) models and the widespread use of image-text retrieval in industry areas, it is now critically necessary to reduce the model size and streamline their mobile-device deployment. Single- and dual-stream model structures are commonly used in image-text retrieval with the goal of closing the semantic gap between textual and visual modalities. While single-stream models use deep feature fusion to achieve more accurate cross-model alignment, dual-stream models are better at offline indexing and fast inference.We propose a Multi-teacher Cross-modality Alignment Distillation (MCAD) technique to integrate the advantages of single- and dual-stream models. By incorporating the fused single-stream features into the image and text features of the dual-stream model, we formulate new modified teacher similarity distributions and features. Then, we conduct both distribution and feature distillation to boost the capability of the student dual-stream model, achieving high retrieval performance without increasing inference complexity.Extensive experiments demonstrate the remarkable performance and high efficiency of MCAD on image-text retrieval tasks. Furthermore, we implement a lightweight CLIP model on Snapdragon/Dimensity chips with only $\sim$100M running memory and $\sim$8.0ms search latency, achieving the mobile-device application of VLP models.

Fan Yang, Sicheng Zhao, Yanhao Zhang et al.

Recent advancements in autonomous driving, augmented reality, robotics, and embodied intelligence have necessitated 3D perception algorithms. However, current 3D perception methods, especially specialized small models, exhibit poor generalization in open scenarios. On the other hand, multimodal large language models (MLLMs) excel in general capacity but underperform in 3D tasks, due to weak 3D local spatial object perception, poor text-based geometric numerical output, and inability to handle camera focal variations. To address these challenges, we propose the following solutions: Spatial-Enhanced Local Feature Mining for better spatial feature extraction, 3D Query Token-Derived Info Decoding for precise geometric regression, and Geometry Projection-Based 3D Reasoning for handling camera focal length variations. We employ parameter-efficient fine-tuning for a pre-trained MLLM and develop LLMI3D, a powerful 3D perception MLLM. Additionally, we have constructed the IG3D dataset, which provides fine-grained descriptions and question-answer annotations. Extensive experiments demonstrate that our LLMI3D achieves state-of-the-art performance, outperforming other methods by a large margin.

Zhenyi Liao, Qingsong Xie, Yanhao Zhang et al.

Increasing attention has been placed on improving the reasoning capacities of multi-modal large language models (MLLMs). As the cornerstone for AI agents that function in the physical realm, video-based visual-spatial intelligence (VSI) emerges as one of the most pivotal reasoning capabilities of MLLMs. This work conducts a first, in-depth study on improving the visual-spatial reasoning of MLLMs via R1-Zero-like training. Technically, we first identify that the visual-spatial reasoning capacities of small- to medium-sized Qwen2-VL models cannot be activated via Chain of Thought (CoT) prompts. We then incorporate GRPO training for improved visual-spatial reasoning, using the carefully curated VSI-100k dataset, following DeepSeek-R1-Zero. During the investigation, we identify the necessity to keep the KL penalty (even with a small value) in GRPO. With just 120 GPU hours, our vsGRPO-2B model, fine-tuned from Qwen2-VL-2B, can outperform the base model by 12.1% and surpass GPT-4o. Moreover, our vsGRPO-7B model, fine-tuned from Qwen2-VL-7B, achieves performance comparable to that of the best open-source model LLaVA-NeXT-Video-72B. Additionally, we compare vsGRPO to supervised fine-tuning and direct preference optimization baselines and observe strong performance superiority. The code and dataset will be available soon.

Yuxiang Zhou, Jichang Li, Yanhao Zhang et al.

Mobile agents show immense potential, yet current state-of-the-art (SoTA) agents exhibit inadequate success rates on real-world, long-horizon, cross-application tasks. We attribute this bottleneck to the agents' excessive reliance on static, internal knowledge within MLLMs, which leads to two critical failure points: 1) strategic hallucinations in high-level planning and 2) operational errors during low-level execution on user interfaces (UI). The core insight of this paper is that high-level planning and low-level UI operations require fundamentally distinct types of knowledge. Planning demands high-level, strategy-oriented experiences, whereas operations necessitate low-level, precise instructions closely tied to specific app UIs. Motivated by these insights, we propose Mobile-Agent-RAG, a novel hierarchical multi-agent framework that innovatively integrates dual-level retrieval augmentation. At the planning stage, we introduce Manager-RAG to reduce strategic hallucinations by retrieving human-validated comprehensive task plans that provide high-level guidance. At the execution stage, we develop Operator-RAG to improve execution accuracy by retrieving the most precise low-level guidance for accurate atomic actions, aligned with the current app and subtask. To accurately deliver these knowledge types, we construct two specialized retrieval-oriented knowledge bases. Furthermore, we introduce Mobile-Eval-RAG, a challenging benchmark for evaluating such agents on realistic multi-app, long-horizon tasks. Extensive experiments demonstrate that Mobile-Agent-RAG significantly outperforms SoTA baselines, improving task completion rate by 11.0% and step efficiency by 10.2%, establishing a robust paradigm for context-aware, reliable multi-agent mobile automation.

Jian Ma, Qirong Peng, Xu Guo et al.

Text-to-image (T2I) models are well known for their ability to produce highly realistic images, while multimodal large language models (MLLMs) are renowned for their proficiency in understanding and integrating multiple modalities. However, currently there is no straightforward and efficient framework to transfer the multimodal comprehension abilities of MLLMs to T2I models to enable them to understand multimodal inputs. In this paper, we propose the X2I framework, which endows Diffusion Transformer (DiT) models with the capability to comprehend various modalities, including multilingual text, screenshot documents, images, videos, and audio. X2I is trained using merely 100K English corpus with 160 GPU hours. Building on the DiT teacher model, we adopt an innovative distillation method to extract the inference capabilities of the teacher model and design a lightweight AlignNet structure to serve as an intermediate bridge. Compared to the teacher model, X2I shows a decrease in performance degradation of less than 1\% while gaining various multimodal understanding abilities, including multilingual to image, image to image, image-text to image, video to image, audio to image, and utilizing creative fusion to enhance imagery. Furthermore, it is applicable for LoRA training in the context of image-text to image generation, filling a void in the industry in this area. We further design a simple LightControl to enhance the fidelity of instructional image editing. Finally, extensive experiments demonstrate the effectiveness, efficiency, multifunctionality, and transferability of our X2I. The open-source code and checkpoints for X2I can be found at the following link: https://github.com/OPPO-Mente-Lab/X2I.

Ruizhi Yu, Keyang Zhong, Peng Liu et al.

Live streaming commerce has become a prominent form of broadcasting in the modern era. To facilitate more efficient and convenient product promotions for streamers, we present Click-to-Ask, an AI-driven assistant for live streaming commerce with complementary offline and online components. The offline module processes diverse multimodal product information, transforming complex inputs into structured product data and generating compliant promotional copywriting. During live broadcasts, the online module enables real-time responses to viewer inquiries by allowing streamers to click on questions and leveraging both the structured product information generated by the offline module and an event-level historical memory maintained in a streaming architecture. This system significantly reduces the time needed for promotional preparation, enhances content engagement, and enables prompt interaction with audience inquiries, ultimately improving the effectiveness of live streaming commerce. On our collected dataset of TikTok live stream frames, the proposed method achieves a Question Recognition Accuracy of 0.913 and a Response Quality score of 0.876, demonstrating considerable potential for practical application. The video demonstration can be viewed here: https://www.youtube.com/shorts/mWIXK-SWhiE.

Zikang Liu, Longteng Guo, Handong Li et al.

Real-time understanding of continuous video streams is essential for interactive assistants and multimodal agents operating in dynamic environments. However, most existing video reasoning approaches follow a batch paradigm that defers reasoning until the full video context is observed, resulting in high latency and growing computational cost that are incompatible with streaming scenarios. In this paper, we introduce ThinkStream, a framework for streaming video reasoning based on a Watch--Think--Speak paradigm that enables models to incrementally update their understanding as new video observations arrive. At each step, the model performs a short reasoning update and decides whether sufficient evidence has accumulated to produce a response. To support long-horizon streaming, we propose Reasoning-Compressed Streaming Memory (RCSM), which treats intermediate reasoning traces as compact semantic memory that replaces outdated visual tokens while preserving essential context. We further train the model using a Streaming Reinforcement Learning with Verifiable Rewards scheme that aligns incremental reasoning and response timing with the requirements of streaming interaction. Experiments on multiple streaming video benchmarks show that ThinkStream significantly outperforms existing online video models while maintaining low latency and memory usage. Code, models and data will be released at https://github.com/johncaged/ThinkStream

Nan Wang, Zhiwei Jin, Chen Chen et al.

Document understanding and GUI interaction are among the highest-value applications of Vision-Language Models (VLMs), yet they impose exceptionally heavy computational burden: fine-grained text and small UI elements demand high-resolution inputs that produce tens of thousands of visual tokens. We observe that this cost is largely wasteful -- across document and GUI benchmarks, only 22--71\% of image patches are pixel-unique, the rest being exact duplicates of another patch in the same image. We propose \textbf{PixelPrune}, which exploits this pixel-level redundancy through predictive-coding-based compression, pruning redundant patches \emph{before} the Vision Transformer (ViT) encoder. Because it operates in pixel space prior to any neural computation, PixelPrune accelerates both the ViT encoder and the downstream LLM, covering the full inference pipeline. The method is training-free, requires no learnable parameters, and supports pixel-lossless compression ($τ{=}0$) as well as controlled lossy compression ($τ{>}0$). Experiments across three model scales and document and GUI benchmarks show that PixelPrune maintains competitive task accuracy while delivering up to 4.2$\times$ inference speedup and 1.9$\times$ training acceleration. Code is available at https://github.com/OPPO-Mente-Lab/PixelPrune.

Jian Ma, Xujie Zhu, Zihao Pan et al.

Existing open-source datasets for arbitrary-instruction image editing remain suboptimal, while a plug-and-play editing module compatible with community-prevalent generative models is notably absent. In this paper, we first introduce the X2Edit Dataset, a comprehensive dataset covering 14 diverse editing tasks, including subject-driven generation. We utilize the industry-leading unified image generation models and expert models to construct the data. Meanwhile, we design reasonable editing instructions with the VLM and implement various scoring mechanisms to filter the data. As a result, we construct 3.7 million high-quality data with balanced categories. Second, to better integrate seamlessly with community image generation models, we design task-aware MoE-LoRA training based on FLUX.1, with only 8\% of the parameters of the full model. To further improve the final performance, we utilize the internal representations of the diffusion model and define positive/negative samples based on image editing types to introduce contrastive learning. Extensive experiments demonstrate that the model's editing performance is competitive among many excellent models. Additionally, the constructed dataset exhibits substantial advantages over existing open-source datasets. The open-source code, checkpoints, and datasets for X2Edit can be found at the following link: https://github.com/OPPO-Mente-Lab/X2Edit.

Kuo Wang, Quanlong Zheng, Junlin Xie et al.

Video Multimodal Large Language Models~(Video-MLLM) have achieved remarkable advancements in video understanding tasks. However, constrained by the context length limitation in the underlying LLMs, existing Video-MLLMs typically exhibit suboptimal performance on long video scenarios. To understand extended input frames, common solutions span token compression and streaming inference techniques, which sacrifice feature granularity or inference efficiency. Differently, to efficiently achieve comprehensive understanding of longer frame inputs, we draw ideas from MoE and propose a training-free approach \textbf{Free-MoRef}, which instantly multiplexes the context perception capabilities of Video-MLLMs within one inference pass. Specifically, Free-MoRef reconstructs the vision tokens into several short sequences as multi-references. Subsequently, we introduce MoRef-attention, which gathers clues from the multi-reference chunks in parallel to summarize unified query activations. After the shadow layers in LLMs, a reference fusion step is derived to compose a final mixed reasoning sequence with key tokens from parallel chunks, which compensates the cross-reference vision interactions that are neglected in MoRef-attention. By splitting and fusing the long vision token sequences, Free-MoRef achieves improved performance under much lower computing costs in reasoning multiplexed context length, demonstrating strong efficiency and effectiveness. Experiments on VideoMME, MLVU, LongVideoBench show that Free-MoRef achieves full perception of 2$\times$ to 8$\times$ longer input frames without compression on a single A100 GPU while keeping instant responses, thereby bringing significant performance gains, even surpassing dedicatedly trained long-video-MLLMs. Codes are available at https://github.com/wkfdb/Free-MoRef

Qingsong Xie, Zhao Zhang, Zhe Huang et al.

Image tokenization has significantly advanced visual generation and multimodal modeling, particularly when paired with autoregressive models. However, current methods face challenges in balancing efficiency and fidelity: high-resolution image reconstruction either requires an excessive number of tokens or compromises critical details through token reduction. To resolve this, we propose Latent Consistency Tokenizer (Layton) that bridges discrete visual tokens with the compact latent space of pre-trained Latent Diffusion Models (LDMs), enabling efficient representation of 1024x1024 images using only 256 tokens-a 16 times compression over VQGAN. Layton integrates a transformer encoder, a quantized codebook, and a latent consistency decoder. Direct application of LDM as the decoder results in color and brightness discrepancies. Thus, we convert it to latent consistency decoder, reducing multi-step sampling to 1-2 steps for direct pixel-level supervision. Experiments demonstrate Layton's superiority in high-fidelity reconstruction, with 10.8 reconstruction Frechet Inception Distance on MSCOCO-2017 5K benchmark for 1024x1024 image reconstruction. We also extend Layton to a text-to-image generation model, LaytonGen, working in autoregression. It achieves 0.73 score on GenEval benchmark, surpassing current state-of-the-art methods. Project homepage: https://github.com/OPPO-Mente-Lab/Layton

Mingxiong Lin, Zhangquan Gong, Maowen Tang et al.

Reinforcement Learning with Verifiable Rewards (RLVR) has become the standard paradigm for LLM mathematical reasoning, with Group Relative Policy Optimization (GRPO) serving as the dominant algorithm. We identify two overlooked inefficiencies inherent in GRPO. First, a fixed KL coefficient overly restricts policy exploration at moments when the model needs to diverge significantly from the reference policy. Second, uniform question sampling overlooks that moderately difficult problems produce the most informative gradient signals. We propose FG-ExPO, short for Frontier-Guided Exploration-Prioritized Policy Optimization, which integrates two lightweight components. Accuracy-Conditioned KL Scaling (AKL) adjusts the KL penalty strength through a smooth nonlinear function of batch average accuracy, loosening the constraint when the model performs poorly and strengthening it when the model achieves satisfactory results. Gaussian Curriculum Sampling (GCS) assigns sampling weights to questions following a Gaussian distribution centered at a moderate accuracy level around 0.5, focusing model training on its learning frontier. We conduct evaluations on DeepSeek-R1-Distill-Qwen-1.5B and Qwen3-8B-Base across six mainstream mathematical reasoning benchmarks. Experimental results demonstrate that FG-ExPO consistently outperforms vanilla GRPO. It delivers an absolute improvement of 13.34 on the AIME 2025 pass@32 metric, rising from 63.33 percent to 76.67 percent, and obtains an average pass@32 gain of 2.66 on the 8B model. The substantially larger performance gains observed on pass@32 compared to pass@1 verify that FG-ExPO enlarges the model's effective exploration space under a fixed inference budget.

Jian Ma, Qirong Peng, Xujie Zhu et al.

Diffusion Transformers (DiTs) have shown exceptional performance in image generation, yet their large parameter counts incur high computational costs, impeding deployment in resource-constrained settings. To address this, we propose Pluggable Pruning with Contiguous Layer Distillation (PPCL), a flexible structured pruning framework specifically designed for DiT architectures. First, we identify redundant layer intervals through a linear probing mechanism combined with the first-order differential trend analysis of similarity metrics. Subsequently, we propose a plug-and-play teacher-student alternating distillation scheme tailored to integrate depth-wise and width-wise pruning within a single training phase. This distillation framework enables flexible knowledge transfer across diverse pruning ratios, eliminating the need for per-configuration retraining. Extensive experiments on multiple Multi-Modal Diffusion Transformer architecture models demonstrate that PPCL achieves a 50\% reduction in parameter count compared to the full model, with less than 3\% degradation in key objective metrics. Notably, our method maintains high-quality image generation capabilities while achieving higher compression ratios, rendering it well-suited for resource-constrained environments. The open-source code, checkpoints for PPCL can be found at the following link: https://github.com/OPPO-Mente-Lab/Qwen-Image-Pruning.

Mingxiong Lin, Zhangquan Gong, Maowen Tang et al.

Reinforcement Learning with Verifiable Rewards (RLVR) has become the standard paradigm for LLM mathematical reasoning, where Group Relative Policy Optimization (GRPO) serves as the mainstream algorithm. We point out two understudied inefficiencies existing in GRPO. First, the fixed KL penalty coefficient overly restricts policy exploration at stages where the model requires significant deviation from the reference policy. Second, uniform sampling of training questions ignores that moderately difficult problems provide the most informative gradient signals for optimization. We propose Exploration-Prioritized Policy Optimization (EXPO) with two lightweight plug-in modules. The Accuracy-Conditioned KL Scaling (AKL) dynamically adjusts KL regularization strength through a smooth nonlinear function of batch average accuracy, relaxing the penalty when the model underperforms and strengthening it when the model achieves good results. The Gaussian Curriculum Sampling (GCS) assigns sampling weights to questions following a Gaussian distribution centered at moderate accuracy around 0.5, focusing training on the model's learning frontier. We conduct extensive experiments on DeepSeek-R1-Distill-Qwen-1.5B and Qwen3-8B-Base over six mathematical reasoning benchmarks. The results show EXPO steadily surpasses vanilla GRPO. It obtains an absolute gain of 13.34 on AIME 2025 pass@32, rising from 63.33 percent to 76.67 percent, and achieves an average pass@32 improvement of 2.66 on the 8B model. The much larger performance gains on pass@32 compared with pass@1 demonstrate that EXPO effectively enlarges the model's exploration boundary under a fixed inference cost budget.

Kai Shi, Jun Yang, Ni Yang et al.

Mobile Phone Agents (MPAs) have emerged as a promising research direction due to their broad applicability across diverse scenarios. While Multimodal Large Language Models (MLLMs) serve as the foundation for MPAs, their effectiveness in handling multiple mobile phone tasks simultaneously remains limited. Although multitask supervised fine-tuning (SFT) is widely adopted for multitask learning, existing approaches struggle to determine optimal training data compositions for peak performance. To address this challenge, we propose DaMo (Data Mixture Optimizer) - a novel solution employing a trainable network that predicts optimal data mixtures by forecasting downstream task performance for any given dataset ratio. To support comprehensive evaluation, we introduce PhoneAgentBench, the first specialized benchmark to evaluate MLLMs on multimodal mobile phone tasks, comprising 1235 QA pairs spanning diverse real-world industrial mobile application scenarios. Demonstrating strong predictive capability (R^2=0.81) in small-scale pilot experiments, DaMo efficiently extrapolates optimal data mixing configurations. Our results show DaMo achieves a 3.38% performance improvement on PhoneAgentBench compared to alternative methods. Furthermore, extensive experiments across established benchmarks including BFCL-v3, MME-Reasoning, MME-Perception, and OCRBench reveal DaMo's superior generalization, outperforming other approaches by 2.57% in terms of average score. When used solely for MLLM optimization on the BFCL-v3 task, DaMo improves the metrics by 12.47% than other methods. Notably, DaMo maintains robust scalability, preserving its effectiveness when applied to other model architectures. The code and dataset are available at https://github.com/OPPO-Mente-Lab/DaMo.git

Zhiwei Jin, Xiaohui Song, Nan Wang et al.

In recent years, while cloud-based MLLMs such as QwenVL, InternVL, GPT-4o, Gemini, and Claude Sonnet have demonstrated outstanding performance with enormous model sizes reaching hundreds of billions of parameters, they significantly surpass the limitations in memory, power consumption, and computing capacity of edge devices such as mobile phones. This paper introduces AndesVL, a suite of mobile-side MLLMs with 0.6B to 4B parameters based on Qwen3's LLM and various visual encoders. We comprehensively outline the model architectures, training pipeline, and training data of AndesVL, which achieves first-tier performance across a wide range of open-source benchmarks, including fields such as text-rich image understanding, reasoning and math, multi-image comprehension, general VQA, hallucination mitigation, multilingual understanding, and GUI-related tasks when compared with state-of-the-art models of a similar scale. Furthermore, we introduce a 1+N LoRA architecture alongside a Quantization-Aware LoRA Fine-Tuning (QALFT) framework to facilitate efficient task adaptation and model compression during mobile-side deployment of AndesVL. Moreover, utilizing our cache eviction algorithm -- OKV -- along with customized speculative decoding and compression strategies, we achieve a 6.7x peak decoding speedup ratio, up to 30.9% memory reduction, and 1.8 bits-per-weight when deploying AndesVL-4B on MediaTek Dimensity 9500 chips. We release all models on https://huggingface.co/OPPOer.

Zhenhua Liu, Tong Zhu, Chuanyuan Tan et al.

Large Language Models (LLMs) have shown their impressive capabilities, while also raising concerns about the data contamination problems due to privacy issues and leakage of benchmark datasets in the pre-training phase. Therefore, it is vital to detect the contamination by checking whether an LLM has been pre-trained on the target texts. Recent studies focus on the generated texts and compute perplexities, which are superficial features and not reliable. In this study, we propose to utilize the probing technique for pre-training data detection by examining the model's internal activations. Our method is simple and effective and leads to more trustworthy pre-training data detection. Additionally, we propose ArxivMIA, a new challenging benchmark comprising arxiv abstracts from Computer Science and Mathematics categories. Our experiments demonstrate that our method outperforms all baselines, and achieves state-of-the-art performance on both WikiMIA and ArxivMIA, with additional experiments confirming its efficacy (Our code and dataset are available at https://github.com/zhliu0106/probing-lm-data).

Ruichen Wang, Zekang Chen, Chen Chen et al.

Recent text-to-image (T2I) diffusion models show outstanding performance in generating high-quality images conditioned on textual prompts. However, they fail to semantically align the generated images with the prompts due to their limited compositional capabilities, leading to attribute leakage, entity leakage, and missing entities. In this paper, we propose a novel attention mask control strategy based on predicted object boxes to address these issues. In particular, we first train a BoxNet to predict a box for each entity that possesses the attribute specified in the prompt. Then, depending on the predicted boxes, a unique mask control is applied to the cross- and self-attention maps. Our approach produces a more semantically accurate synthesis by constraining the attention regions of each token in the prompt to the image. In addition, the proposed method is straightforward and effective and can be readily integrated into existing cross-attention-based T2I generators. We compare our approach to competing methods and demonstrate that it can faithfully convey the semantics of the original text to the generated content and achieve high availability as a ready-to-use plugin. Please refer to https://github.com/OPPOMente-Lab/attention-mask-control.

Mingxiang Chen, Zhanguo Chang, Haonan Lu et al.

Most of the achievements in artificial intelligence so far were accomplished by supervised learning which requires numerous annotated training data and thus costs innumerable manpower for labeling. Unsupervised learning is one of the effective solutions to overcome such difficulties. In our work, we propose AugNet, a new deep learning training paradigm to learn image features from a collection of unlabeled pictures. We develop a method to construct the similarities between pictures as distance metrics in the embedding space by leveraging the inter-correlation between augmented versions of samples. Our experiments demonstrate that the method is able to represent the image in low dimensional space and performs competitively in downstream tasks such as image classification and image similarity comparison. Specifically, we achieved over 60% and 27% accuracy on the STL10 and CIFAR100 datasets with unsupervised clustering, respectively. Moreover, unlike many deep-learning-based image retrieval algorithms, our approach does not require access to external annotated datasets to train the feature extractor, but still shows comparable or even better feature representation ability and easy-to-use characteristics. In our evaluations, the method outperforms all the state-of-the-art image retrieval algorithms on some out-of-domain image datasets. The code for the model implementation is available at https://github.com/chenmingxiang110/AugNet.

Yifan Wang, Yafei Liu, Chufan Shi et al.

Instruction tuning effectively optimizes Large Language Models (LLMs) for downstream tasks. Due to the changing environment in real-life applications, LLMs necessitate continual task-specific adaptation without catastrophic forgetting. Considering the heavy computational cost, replay-based Continual Learning (CL) methods are the simplest and most widely used for LLMs to address the forgetting issue. However, traditional replay-based methods do not fully utilize instructions to customize the replay strategy. In this work, we propose a novel paradigm called Instruction-based Continual Learning (InsCL). InsCL dynamically replays previous data based on task similarity, calculated by Wasserstein Distance with instructions. Moreover, we further introduce an Instruction Information Metric (InsInfo) to quantify the complexity and diversity of instructions. According to InsInfo, InsCL guides the replay process more inclined to high-quality data. We conduct extensive experiments over 16 tasks with different training orders, observing consistent performance improvements of InsCL. When all tasks have been trained, InsCL achieves performance gains of 3.0 Relative Gain compared with Random Replay, and 27.96 Relative Gain compared with No Replay.

Dingkun Zhang, Sijia Li, Chen Chen et al.

In the era of AIGC, the demand for low-budget or even on-device applications of diffusion models emerged. In terms of compressing the Stable Diffusion models (SDMs), several approaches have been proposed, and most of them leveraged the handcrafted layer removal methods to obtain smaller U-Nets, along with knowledge distillation to recover the network performance. However, such a handcrafting manner of layer removal is inefficient and lacks scalability and generalization, and the feature distillation employed in the retraining phase faces an imbalance issue that a few numerically significant feature loss terms dominate over others throughout the retraining process. To this end, we proposed the layer pruning and normalized distillation for compressing diffusion models (LAPTOP-Diff). We, 1) introduced the layer pruning method to compress SDM's U-Net automatically and proposed an effective one-shot pruning criterion whose one-shot performance is guaranteed by its good additivity property, surpassing other layer pruning and handcrafted layer removal methods, 2) proposed the normalized feature distillation for retraining, alleviated the imbalance issue. Using the proposed LAPTOP-Diff, we compressed the U-Nets of SDXL and SDM-v1.5 for the most advanced performance, achieving a minimal 4.0% decline in PickScore at a pruning ratio of 50% while the comparative methods' minimal PickScore decline is 8.2%.

Hongjian Liu, Qingsong Xie, TianXiang Ye et al.

The iterative sampling procedure employed by diffusion models (DMs) often leads to significant inference latency. To address this, we propose Stochastic Consistency Distillation (SCott) to enable accelerated text-to-image generation, where high-quality and diverse generations can be achieved within just 2-4 sampling steps. In contrast to vanilla consistency distillation (CD) which distills the ordinary differential equation solvers-based sampling process of a pre-trained teacher model into a student, SCott explores the possibility and validates the efficacy of integrating stochastic differential equation (SDE) solvers into CD to fully unleash the potential of the teacher. SCott is augmented with elaborate strategies to control the noise strength and sampling process of the SDE solver. An adversarial loss is further incorporated to strengthen the consistency constraints in rare sampling steps. Empirically, on the MSCOCO-2017 5K dataset with a Stable Diffusion-V1.5 teacher, SCott achieves an FID of 21.9 with 2 sampling steps, surpassing that of the 1-step InstaFlow (23.4) and the 4-step UFOGen (22.1). Moreover, SCott can yield more diverse samples than other consistency models for high-resolution image generation, with up to 16% improvement in a qualified metric.

Fan Yang, Ru Zhen, Jianing Wang et al.

AIGC images are prevalent across various fields, yet they frequently suffer from quality issues like artifacts and unnatural textures. Specialized models aim to predict defect region heatmaps but face two primary challenges: (1) lack of explainability, failing to provide reasons and analyses for subtle defects, and (2) inability to leverage common sense and logical reasoning, leading to poor generalization. Multimodal large language models (MLLMs) promise better comprehension and reasoning but face their own challenges: (1) difficulty in fine-grained defect localization due to the limitations in capturing tiny details, and (2) constraints in providing pixel-wise outputs necessary for precise heatmap generation. To address these challenges, we propose HEIE: a novel MLLM-Based Hierarchical Explainable Image Implausibility Evaluator. We introduce the CoT-Driven Explainable Trinity Evaluator, which integrates heatmaps, scores, and explanation outputs, using CoT to decompose complex tasks into subtasks of increasing difficulty and enhance interpretability. Our Adaptive Hierarchical Implausibility Mapper synergizes low-level image features with high-level mapper tokens from LLMs, enabling precise local-to-global hierarchical heatmap predictions through an uncertainty-based adaptive token approach. Moreover, we propose a new dataset: Expl-AIGI-Eval, designed to facilitate interpretable implausibility evaluation of AIGC images. Our method demonstrates state-of-the-art performance through extensive experiments. Our project is at https://yfthu.github.io/HEIE/.

Siyuan Li, Luyuan Zhang, Zedong Wang et al.

Masked Image Modeling (MIM) with Vector Quantization (VQ) has achieved great success in both self-supervised pre-training and image generation. However, most existing methods struggle to address the trade-off in shared latent space for generation quality vs. representation learning and efficiency. To push the limits of this paradigm, we propose MergeVQ, which incorporates token merging techniques into VQ-based generative models to bridge the gap between image generation and visual representation learning in a unified architecture. During pre-training, MergeVQ decouples top-k semantics from latent space with the token merge module after self-attention blocks in the encoder for subsequent Look-up Free Quantization (LFQ) and global alignment and recovers their fine-grained details through cross-attention in the decoder for reconstruction. As for the second-stage generation, we introduce MergeAR, which performs KV Cache compression for efficient raster-order prediction. Extensive experiments on ImageNet verify that MergeVQ as an AR generative model achieves competitive performance in both visual representation learning and image generation tasks while maintaining favorable token efficiency and inference speed. The code and model will be available at https://apexgen-x.github.io/MergeVQ.

Nan Wang, Yafei Liu, Chen Chen et al.

Recent advancements in language modeling have enabled the translation of natural language into code, and the use of execution feedback to improve code generation. However, these methods often rely heavily on pre-existing test cases, which may not always be available or comprehensive. In this work, we propose a novel approach that concurrently trains a code generation model and a test generation model, utilizing execution feedback to refine and enhance the performance of both. We introduce two strategies for test and code data augmentation and a new scoring function for code and test ranking. We experiment on the APPS dataset and demonstrate that our approach can effectively generate and augment test cases, filter and synthesize correct code solutions, and rank the quality of generated code and tests. The results demonstrate that our models, when iteratively trained with an increasing number of test cases and code solutions, outperform those trained on the original dataset.

Chunlin Zhong, Qiuxia Hou, Zhangjun Zhou et al.

Video captioning aims to generate comprehensive and coherent descriptions of the video content, contributing to the advancement of both video understanding and generation. However, existing methods often suffer from motion-detail imbalance, as models tend to overemphasize one aspect while neglecting the other. This imbalance results in incomplete captions, which in turn leads to a lack of consistency in video understanding and generation. To address this issue, we propose solutions from two aspects: 1) Data aspect: We constructed the Harmonizing Motion-Detail 270K (HMD-270K) dataset through a two-stage pipeline: Motion-Detail Fusion (MDF) and Fine-Grained Examination (FGE). 2) Optimization aspect: We introduce the Caption Set Equivalence Reward (CSER) based on Group Relative Policy Optimization (GRPO). CSER enhances completeness and accuracy in capturing both motion and details through unit-to-set matching and bidirectional validation. Based on the HMD-270K supervised fine-tuning and GRPO post-training with CSER, we developed OwlCap, a powerful video captioning multi-modal large language model (MLLM) with motion-detail balance. Experimental results demonstrate that OwlCap achieves significant improvements compared to baseline models on two benchmarks: the detail-focused VDC (+4.2 Acc) and the motion-focused DREAM-1K (+4.6 F1). The HMD-270K dataset and OwlCap model will be publicly released to facilitate video captioning research community advancements.

Ruichen Wang, Junliang Zhang, Qingsong Xie et al.

Recently, diffusion models have exhibited superior performance in the area of image inpainting. Inpainting methods based on diffusion models can usually generate realistic, high-quality image content for masked areas. However, due to the limitations of diffusion models, existing methods typically encounter problems in terms of semantic consistency between images and text, and the editing habits of users. To address these issues, we present PainterNet, a plugin that can be flexibly embedded into various diffusion models. To generate image content in the masked areas that highly aligns with the user input prompt, we proposed local prompt input, Attention Control Points (ACP), and Actual-Token Attention Loss (ATAL) to enhance the model's focus on local areas. Additionally, we redesigned the MASK generation algorithm in training and testing dataset to simulate the user's habit of applying MASK, and introduced a customized new training dataset, PainterData, and a benchmark dataset, PainterBench. Our extensive experimental analysis exhibits that PainterNet surpasses existing state-of-the-art models in key metrics including image quality and global/local text consistency.

Yuechen Wang, Yuming Qiao, Dan Meng et al.

Multimodal Retrieval-Augmented Generation (mRAG) has emerged as a promising solution to address the temporal limitations of Multimodal Large Language Models (MLLMs) in real-world scenarios like news analysis and trending topics. However, existing approaches often suffer from rigid retrieval strategies and under-utilization of visual information. To bridge this gap, we propose E-Agent, an agent framework featuring two key innovations: a mRAG planner trained to dynamically orchestrate multimodal tools based on contextual reasoning, and a task executor employing tool-aware execution sequencing to implement optimized mRAG workflows. E-Agent adopts a one-time mRAG planning strategy that enables efficient information retrieval while minimizing redundant tool invocations. To rigorously assess the planning capabilities of mRAG systems, we introduce the Real-World mRAG Planning (RemPlan) benchmark. This novel benchmark contains both retrieval-dependent and retrieval-independent question types, systematically annotated with essential retrieval tools required for each instance. The benchmark's explicit mRAG planning annotations and diverse question design enhance its practical relevance by simulating real-world scenarios requiring dynamic mRAG decisions. Experiments across RemPlan and three established benchmarks demonstrate E-Agent's superiority: 13% accuracy gain over state-of-the-art mRAG methods while reducing redundant searches by 37%.

Weihong Li, Shaohua Dong, Haonan Lu et al.

In this paper, we explore adapter tuning and introduce a novel dual-adapter architecture for spatio-temporal multimodal tracking, dubbed DMTrack. The key of our DMTrack lies in two simple yet effective modules, including a spatio-temporal modality adapter (STMA) and a progressive modality complementary adapter (PMCA) module. The former, applied to each modality alone, aims to adjust spatio-temporal features extracted from a frozen backbone by self-prompting, which to some extent can bridge the gap between different modalities and thus allows better cross-modality fusion. The latter seeks to facilitate cross-modality prompting progressively with two specially designed pixel-wise shallow and deep adapters. The shallow adapter employs shared parameters between the two modalities, aiming to bridge the information flow between the two modality branches, thereby laying the foundation for following modality fusion, while the deep adapter modulates the preliminarily fused information flow with pixel-wise inner-modal attention and further generates modality-aware prompts through pixel-wise inter-modal attention. With such designs, DMTrack achieves promising spatio-temporal multimodal tracking performance with merely \textbf{0.93M} trainable parameters. Extensive experiments on five benchmarks show that DMTrack achieves state-of-the-art results. Code will be available.

Yu Lei, Bingde Liu, Qingsong Xie et al.

Text-to-3D generation based on score distillation of pre-trained 2D diffusion models has gained increasing interest, with variational score distillation (VSD) as a remarkable example. VSD proves that vanilla score distillation can be improved by introducing an extra score-based model, which characterizes the distribution of images rendered from 3D models, to correct the distillation gradient. Despite the theoretical foundations, VSD, in practice, is likely to suffer from slow and sometimes ill-posed convergence. In this paper, we perform an in-depth investigation of the interplay between the introduced score model and the 3D model, and find that there exists a mismatching problem between LoRA and 3D distributions in practical implementation. We can simply adjust their optimization order to improve the generation quality. By doing so, the score model looks ahead to the current 3D state and hence yields more reasonable corrections. Nevertheless, naive lookahead VSD may suffer from unstable training in practice due to the potential over-fitting. To address this, we propose to use a linearized variant of the model for score distillation, giving rise to the Linearized Lookahead Variational Score Distillation ($L^2$-VSD). $L^2$-VSD can be realized efficiently with forward-mode autodiff functionalities of existing deep learning libraries. Extensive experiments validate the efficacy of $L^2$-VSD, revealing its clear superiority over prior score distillation-based methods. We also show that our method can be seamlessly incorporated into any other VSD-based text-to-3D framework.

Qi Wu, Quanlong Zheng, Yanhao Zhang et al.

With the rapid development of multimodal models, the demand for assessing video understanding capabilities has been steadily increasing. However, existing benchmarks for evaluating video understanding exhibit significant limitations in coverage, task diversity, and scene adaptability. These shortcomings hinder the accurate assessment of models' comprehensive video understanding capabilities. To tackle this challenge, we propose a hierarchical and holistic video understanding (H2VU) benchmark designed to evaluate both general video and online streaming video comprehension. This benchmark contributes three key features: Extended video duration: Spanning videos from brief 3-second clips to comprehensive 1.5-hour recordings, thereby bridging the temporal gaps found in current benchmarks. Comprehensive assessment tasks: Beyond traditional perceptual and reasoning tasks, we have introduced modules for countercommonsense comprehension and trajectory state tracking. These additions test the models' deep understanding capabilities beyond mere prior knowledge. Enriched video data: To keep pace with the rapid evolution of current AI agents, we have expanded first-person streaming video datasets. This expansion allows for the exploration of multimodal models' performance in understanding streaming videos from a first-person perspective. Extensive results from H2VU reveal that existing multimodal large language models (MLLMs) possess substantial potential for improvement in our newly proposed evaluation tasks. We expect that H2VU will facilitate advancements in video understanding research by offering a comprehensive and in-depth analysis of MLLMs.

Qingsong Xie, Zhenyi Liao, Zhijie Deng et al.

Distilling latent diffusion models (LDMs) into ones that are fast to sample from is attracting growing research interest. However, the majority of existing methods face two critical challenges: (1) They hinge on long training using a huge volume of real data. (2) They routinely lead to quality degradation for generation, especially in text-image alignment. This paper proposes a novel training-efficient Latent Consistency Model (TLCM) to overcome these challenges. Our method first accelerates LDMs via data-free multistep latent consistency distillation (MLCD), and then data-free latent consistency distillation is proposed to efficiently guarantee the inter-segment consistency in MLCD. Furthermore, we introduce bags of techniques, e.g., distribution matching, adversarial learning, and preference learning, to enhance TLCM's performance at few-step inference without any real data. TLCM demonstrates a high level of flexibility by enabling adjustment of sampling steps within the range of 2 to 8 while still producing competitive outputs compared to full-step approaches. Notably, TLCM enjoys the data-free merit by employing synthetic data from the teacher for distillation. With just 70 training hours on an A100 GPU, a 3-step TLCM distilled from SDXL achieves an impressive CLIP Score of 33.68 and an Aesthetic Score of 5.97 on the MSCOCO-2017 5K benchmark, surpassing various accelerated models and even outperforming the teacher model in human preference metrics. We also demonstrate the versatility of TLCMs in applications including image style transfer, controllable generation, and Chinese-to-image generation.

Hao Ai, Zidong Cao, Haonan Lu et al.

360 images, with a field-of-view (FoV) of 180x360, provide immersive and realistic environments for emerging virtual reality (VR) applications, such as virtual tourism, where users desire to create diverse panoramic scenes from a narrow FoV photo they take from a viewpoint via portable devices. It thus brings us to a technical challenge: `How to allow the users to freely create diverse and immersive virtual scenes from a narrow FoV image with a specified viewport?' To this end, we propose a transformer-based 360 image outpainting framework called Dream360, which can generate diverse, high-fidelity, and high-resolution panoramas from user-selected viewports, considering the spherical properties of 360 images. Compared with existing methods, e.g., [3], which primarily focus on inputs with rectangular masks and central locations while overlooking the spherical property of 360 images, our Dream360 offers higher outpainting flexibility and fidelity based on the spherical representation. Dream360 comprises two key learning stages: (I) codebook-based panorama outpainting via Spherical-VQGAN (S-VQGAN), and (II) frequency-aware refinement with a novel frequency-aware consistency loss. Specifically, S-VQGAN learns a sphere-specific codebook from spherical harmonic (SH) values, providing a better representation of spherical data distribution for scene modeling. The frequency-aware refinement matches the resolution and further improves the semantic consistency and visual fidelity of the generated results. Our Dream360 achieves significantly lower Frechet Inception Distance (FID) scores and better visual fidelity than existing methods. We also conducted a user study involving 15 participants to interactively evaluate the quality of the generated results in VR, demonstrating the flexibility and superiority of our Dream360 framework.

Yiqi Lin, Hao Wu, Ruichen Wang et al.

Generating and editing a 3D scene guided by natural language poses a challenge, primarily due to the complexity of specifying the positional relations and volumetric changes within the 3D space. Recent advancements in Large Language Models (LLMs) have demonstrated impressive reasoning, conversational, and zero-shot generation abilities across various domains. Surprisingly, these models also show great potential in realizing and interpreting the 3D space. In light of this, we propose a novel language-guided interactive 3D generation system, dubbed LI3D, that integrates LLMs as a 3D layout interpreter into the off-the-shelf layout-to-3D generative models, allowing users to flexibly and interactively generate visual content. Specifically, we design a versatile layout structure base on the bounding boxes and semantics to prompt the LLMs to model the spatial generation and reasoning from language. Our system also incorporates LLaVA, a large language and vision assistant, to provide generative feedback from the visual aspect for improving the visual quality of generated content. We validate the effectiveness of LI3D, primarily in 3D generation and editing through multi-round interactions, which can be flexibly extended to 2D generation and editing. Various experiments demonstrate the potential benefits of incorporating LLMs in generative AI for applications, e.g., metaverse. Moreover, we benchmark the layout reasoning performance of LLMs with neural visual artist tasks, revealing their emergent ability in the spatial layout domain.

Weixuan Wang, Xiaoling Cai, Chong Hsuan Huang et al.

In this paper, we describe approaches for developing Emily, an emotion-affective open-domain chatbot. Emily can perceive a user's negative emotion state and offer supports by positively converting the user's emotion states. This is done by finetuning a pretrained dialogue model upon data capturing dialogue contexts and desirable emotion states transition across turns. Emily can differentiate a general open-domain dialogue utterance with questions relating to personal information. By leveraging a question-answering approach based on knowledge graphs to handle personal information, Emily maintains personality consistency. We evaluate Emily against a few state-of-the-art open-domain chatbots and show the effects of the proposed approaches in emotion affecting and addressing personality inconsistency.