67 accepted papers
In this paper, we propose **AlphaGRPO**, a novel framework that applies Group Relative Policy Optimization (GRPO) to AR-Diffusion Unified Multimodal Models (UMMs) to enhance multimodal generation capabilities without relying on external knowledge injection. Our approach unlocks the model's intrinsic…
Ensemble attacks integrate the outputs of surrogate models with diverse architectures, which can be combined with various gradient-based attacks to improve adversarial transferability. However, previous work shows unsatisfactory attack performance when transferring across heterogeneous model archite
Multimodal semantic communication systems face a critical challenge in extracting and aligning semantic features across heterogeneous modalities within a unified representation space, particularly under noisy transmission conditions. To address this, we propose Bridge, a cross-modal learning framewo
Current repository agents encounter a reasoning disconnect due to fragmented representations, as existing methods rely on isolated API documentation or dependency graphs that lack semantic depth. We consider repository comprehension and generation to be inverse processes within a unified cycle: gene…
Decentralized stochastic bi-level optimization has been actively studied in recent years. However, existing studies assume that the lower-level loss function is strongly convex, which limits their applicability to many machine learning models. To address this limitation, in this paper, we propose a …
Recent progress in text-to-image generation has greatly advanced visual fidelity and creativity, but it has also imposed higher demands on prompt complexity--particularly in encoding intricate spatial relationships. In such cases, achieving satisfactory results often requires multiple sampling attem
Directly modeling the explicit likelihood of the raw data distribution is a key topic in the machine learning area, which achieves the scaling success in Large Language Models by autoregressive modeling. However, continuous AR modeling over visual pixel data suffers from extremely long sequences and
This paper focuses on the alignment of flow-matching models with human preference. A promising way is fine-tuning by directly backpropagating reward signals through the differentiable generation process of flow matching. However, backpropagating through long trajectories results in prohibitive memor
While Reinforcement Learning from Human Feedback (RLHF) has become a pivotal paradigm for text-to-image generation, its application to image editing remains largely unexplored. A key bottleneck is the lack of a robust general reward model for all editing tasks. Existing edit reward models usually gi
Recent research in long-form video generation has shifted from bidirectional to autoregressive models, yet these methods commonly suffer from error accumulation and a loss of long-term coherence. While attention sink frames have been introduced to mitigate this performance decay, they often induce a
Generating runnable front-end code from UI screenshots is a long-standing goal in automated software engineering. Existing MLLM-based methods predominantly focused on HTML/CSS, leaving multi-framework generation for React/Vue/Angular underexplored. Naively modifying prompts leads to substantial perf…
Large language models excel at generating individual functions or single files of code, yet generating complete repositories from scratch remains a fundamental challenge. This capability is key to building coherent software systems from high-level specifications and realizing the full potential of a…
Diffusion models have revolutionized image and video generation, achieving unprecedented visual quality. However, their reliance on transformer architectures incurs prohibitively high computational costs, particularly when extending generation to long videos. Recent work has explored autoregressive…
Large Audio-language Models (LAMs) have recently enabled powerful speech-based interactions by coupling audio encoders with Large Language Models (LLMs). However, the security of LAMs under adversarial attacks remains underexplored, especially through audio jailbreaks that craft malicious audio prom
Given that Large Language Models (LLMs) are increasingly applied to automate software development, comprehensive software assurance spans three distinct goals: regression prevention, reactive reproduction, and proactive discovery. Current evaluations systematically overlook the third goal. Specifica…
Humans inhabit a physical 4D world, where spatial geometry and semantic content evolve over time, forming a dynamic reality. While current Multimodal Large Language Models (MLLMs) demonstrate strong capabilities in understanding static visual inputs, it remains unclear whether they can effectively "
While preference optimization is crucial for improving visual generative models, how to effectively scale this paradigm for visual generation remains largely unexplored. Current open-source preference datasets typically contain substantial conflicting preference patterns, where winners excel in some…
Out-of-distribution (OOD) detection is a crucial task in reliable and safety-critical applications. Previous studies primarily focus on developing score functions while neglecting the design of decision rules based on these scores. A recent work (Ma et al., 2024) is the first to highlight this issu…
Tabular prediction, a well-established problem in machine learning, has consistently garnered significant research attention within academia and industry. Recently, with the rapid development of large language models (LLMs), there has been increasing exploration of how to apply LLMs to tabular predi…
Large Language Models (LLMs) often struggle with complex reasoning tasks due to insufficient in-depth insights in their training data, which are frequently absent in publicly available documents. This paper introduces the Chain of Methodologies (CoM), a simple and innovative iterative prompting fram…
Image fusion seeks to seamlessly integrate foreground objects with background scenes, producing realistic and harmonious fused images. Unlike existing methods that directly insert objects into the background, adaptive and interactive fusion remains a challenging yet appealing task. It requires the f…
Incorporating privacy regulations and business requirements, enterprises should securely manage unstructured textual data from diverse domains. Sensitive information classification is a critical component of data security, but it poses challenges due to complex textual contexts. With the ever-increa…
Existing methods for code generation use code snippets as seed data, restricting the complexity and diversity of the synthesized data. In this paper, we introduce a novel feature tree-based synthesis framework, which revolves around hierarchical code features derived from high-level abstractions of…
Federated learning, as a distributed learning framework, aims to develop a global model while preserving client privacy. However, heterogeneity of client data leads to fairness issues and reduced performance. Techniques like parameter decoupling and prototype learning appear promising, yet challenge
Federated learning is vulnerable to model poisoning attacks in which malicious participants compromise the global model by altering the model updates. Current defense strategies are divided into three types: aggregation-based methods, validation dataset-based methods, and update distance-based metho
The rapid advancement of Large Vision-Language models (LVLMs) has demonstrated a spectrum of emergent capabilities. Nevertheless, current models only focus on the visual content of a single scenario, while their ability to associate instances across different scenes has not yet been explored, which…
Large Language Models (LLMs) aligned with human feedback have recently garnered significant attention. However, it remains vulnerable to jailbreak attacks, where adversaries manipulate prompts to induce harmful outputs. Exploring jailbreak attacks enables us to investigate the vulnerabilities of LLM…
Interpretability and consistency have long been crucial factors in MRI reconstruction. While interpretability has been significantly innovated with the emerging deep unfolding networks, current solutions still suffer from inconsistency issues and produce inferior anatomical structures. Especially in…
Deep unfolding network (DUN) based pansharpening has shed new light on high-resolution/spectrum image acquisition, serving as a computational alternative to physical devices. While with both merits of deep feature learning and acceptable interpretability enjoyed, current pansharpening necessitates s…
The significance of visual emotion distribution learning (VEDL) has surged, particularly with the growing inclination to convey emotions through images. The key of VEDL lies in capturing both low- and high-level features within the same visual content, thus promoting the model for salient and subtle…
Machine-generated text detection is critical for preventing misuse of large language models (LLMs). Although LLMs have recently excelled at mimicking human writing styles, they still suffer from factual hallucinations manifested as entity-relation inconsistencies with real-world knowledge. Current d
Visual anomaly detection is significant in safety-critical and reliability-sensitive scenarios. Prior studies mainly emphasize the design and training of scoring functions, while little effort has been devoted to constructing decision rules based on these score functions. A recent work Ma et al. (2…
Real-time video analytics (VA) presents challenges due to its computational intensity and latency sensitivity, especially when processed on mobile devices with limited local resources. We propose to offload VA tasks to edge servers with diverse computational capabilities. We present a "detect + trac…
Inspired by the impressive reasoning capabilities demonstrated by reinforcement learning approaches like DeepSeek-R1, recent emerging research has begun exploring the use of reinforcement learning (RL) to enhance vision-language models (VLMs) for multimodal reasoning tasks. However, most existing mu…
Text-to-video models have made remarkable advancements through optimization on high-quality text-video pairs, where the textual prompts play a pivotal role in determining quality of output videos. However, achieving the desired output often entails multiple revisions and iterative inference to refin…
Contract review is a critical process to protect the rights and interests of the parties involved. However, this process is time-consuming, labor-intensive, and costly, especially when a contract faces multiple rounds of review. To accelerate the contract review and promote the completion of transac…
Model inversion and adversarial attacks in semantic communication pose risks, such as content leaks, alterations, and prediction inaccuracies, which threaten security and reliability. This paper introduces, from an attacker's viewpoint, a novel framework called RepObE (Representation Learning-Enhanc
Recent advancement in text-to-image models and corresponding personalized technologies enables individuals to generate high-quality and imaginative images. However, they often suffer from limitations when generating images with resolutions outside of their trained domain. To overcome this limitation…
Preference learning extends the performance of Code LLMs beyond traditional supervised fine-tuning by leveraging relative quality comparisons. In existing approaches, a set of n candidate solutions is evaluated based on test case success rates, with the candidate demonstrating a higher pass rate bei
Large Language Models (LLMs), constrained by limited context windows, often face significant performance degradation when reasoning over long contexts. To address this, Retrieval-Augmented Generation (RAG) retrieves and reasons over chunks but frequently sacrifices logical coherence due to its relia
Sentiment analysis is rapidly advancing by utilizing various data modalities (e.g., text, video, and audio). However, most existing techniques only learn the atomic-level features that reflect strong correlations, while ignoring more complex compositions in multimodal data. Moreover, they also negle…
The demand for video analytics is increasing rapidly. Due to the limited computational and network resources on edge servers, adjusting video configurations such as resolution and frame rate has become an effective strategy to reduce computational and transmission costs. However, this can also compr…
"To enhance the controllability of text-to-image diffusion models, existing efforts like ControlNet incorporated image-based conditional controls. In this paper, we reveal that existing methods still face significant challenges in generating images that align with the image conditional controls. To…
"We introduce , an Autoregressive model for Visual Entity Recognition. Our model extends an autoregressive Multimodal Large Language Model by employing retrieval augmented constrained generation. It mitigates low performance on out-of-domain entities while excelling in queries that require visual re…
Recently, a series of diffusion-aware distillation algorithms have emerged to alleviate the computational overhead associated with the multi-step inference process of Diffusion Models (DMs). Current distillation techniques often dichotomize into two distinct aspects: i) ODE Trajectory Preservation;…
Visual Grounding (VG) aims to locate the most relevant object or region in an image according to a natural language query. Existing methods in VG utilize fixed image and text representations to capture cross-modal semantic consistency, which limits the flexibility in adjusting image representations…
The compressed sensing MRI aims to recover high-fidelity images from undersampled k-space data, which enables MRI acceleration and meanwhile mitigates problems caused by prolonged acquisition time, such as physiological motion artifacts, patient discomfort, and delayed medical care. In this regard,…
Video-based facial analysis is important for autonomous agents to understand human expressions and sentiments. However, limited labeled data is available to learn effective facial representations. This paper proposes a novel self-supervised face-centric pretraining framework, called PrefAce, which l…
Image inpainting is in full bloom accompanied by the progress of convolutional neural networks (CNNs) and transformers, revolutionizing the practical management of abnormity disposal, image editing, etc. However, due to the ever-mounting image resolutions and missing areas, the challenges of distort…
Latent diffusion models (LDM) have revolutionized text-to-image generation, leading to the proliferation of various advanced models and diverse downstream applications. However, despite these significant advancements, current diffusion models still suffer from several limitations, including inferior…
The paradigm of large-scale pre-training followed by downstream fine-tuning has been widely employed in various object detection algorithms. In this paper, we reveal discrepancies in data, model, and task between the pre-training and fine-tuning procedure in existing practices, which implicitly limi…
Diffusion models are emerging expressive generative models, in which a large number of time steps (inference steps) are required for a single image generation. To accelerate such tedious process, reducing steps uniformly is considered as an undisputed principle of diffusion models. We consider that…
Previous entity disambiguation (ED) methods adopt a discriminative paradigm, where prediction is made based on matching scores between mention context and candidate entities using length-limited encoders. However, these methods often struggle to capture explicit discourse-level dependencies, result…
Recently, open-vocabulary learning has emerged to accomplish segmentation for arbitrary categories of text-based descriptions, which popularizes the segmentation system to more general-purpose application scenarios. However, existing methods devote to designing specialized architectures or parameter…
Generative approaches powered by large language models (LLMs) have demonstrated emergent abilities in tasks that require complex reasoning abilities. Yet the generative nature still makes the generated content suffer from hallucinations, thus unsuitable for entity-centric tasks like entity linking (…
Recently, Visual Question Answering(VQA), which is required to generate the answer by understanding both visual and textual content, has attracted considerable research interest. Most existing works extract visual features with the CNN network and learn its feature embedding with an attention mechan…
Recent years have witnessed the prevailing progress of Generative Adversarial Networks (GANs) in image-to-image translation. However, the success of these GAN models hinges on ponderous computational costs and labor-expensive training data. Current efficient GAN learning techniques often fall into t…
Image-level weakly supervised semantic segmentation (WSSS) is a fundamental yet challenging computer vision task facilitating scene understanding and automatic driving. Most existing methods resort to classification-based Class Activation Maps (CAMs) to play as the initial pseudo labels, which tend…
Effectively integrating knowledge into end-to-end task-oriented dialog systems remains a challenge. It typically requires incorporation of an external knowledge base (KB) and capture of the intrinsic semantics of the dialog history. Recent research shows promising results by using Sequence-to-Sequen…
"Albeit with varying degrees of progress in the field of Semi-Supervised Semantic Segmentation, most of its recent successes are involved in unwieldy models and the lightweight solution is still not yet explored. We find that existing knowledge distillation techniques pay more attention to pixel-lev…
"The vanilla self-attention mechanism inherently relies on pre-defined and steadfast computational dimensions. Such inflexibility restricts it from possessing context-oriented generalization that can bring more contextual cues and graphic representations. To mitigate this issue, we propose a Scalabl…
Multi-label document classification, associating one document instance with a set of relevant labels, is attracting more and more research attention. Existing methods explore the incorporation of information beyond text, such as document metadata or label structure. These approaches however either s…
Generative Adversarial Networks (GANs) have witnessed prevailing success in yielding outstanding images, however, they are burdensome to deploy on resource-constrained devices due to ponderous computational costs and hulking memory usage. Although recent efforts on compressing GANs have acquired rem…
Recently, a series of algorithms have been explored for GAN compression, which aims to reduce tremendous computational overhead and memory usages when deploying GANs on resource-constrained edge devices. However, most of the existing GAN compression work only focuses on how to compress the generator…
Spoken language understanding, usually including intent detection and slot filling, is a core component to build a spoken dialog system. Recent research shows promising results by jointly learning of those two tasks based on the fact that slot filling and intent detection are sharing semantic knowle…
In this paper, we introduce a novel task, referred to as Weakly-Supervised Spatio-Temporal Anomaly Detection (WSSTAD) in surveillance video. Specifically, given an untrimmed video, WSSTAD aims to localize a spatio-temporal tube (i.e., a sequence of bounding boxes at consecutive times) that encloses…
Submodularity is an important property of set functions and has been extensively studied in the literature. It models set functions that exhibit a diminishing returns property, where the marginal value of adding an element to a set decreases as the set expands. This notion has been generalized to co…