arXiv subjects

Yunhang Shen

Publications and source records attributed to Yunhang Shen.

At least 37 records · Page 2Linked to original sources

arXiv2025

VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction

Recent Multimodal Large Language Models (MLLMs) have typically focused on integrating visual and textual modalities, with less emphasis placed on the role of speech in enhancing interaction. However, speech plays a crucial role in multimodal dialogue systems, and implementing high-performance in both vision and speech tasks remains a significant challenge due to the fundamental modality differences. In this paper, we propose a carefully designed multi-stage training methodology that progressively trains LLM to understand both visual and speech information, ultimately enabling fluent vision and speech interaction. Our approach not only preserves strong vision-language capacity, but also enables efficient speech-to-speech dialogue capabilities without separate ASR and TTS modules, significantly accelerating multimodal end-to-end response speed. By comparing our method against state-of-the-art counterparts across benchmarks for image, video, and speech tasks, we demonstrate that our model is equipped with both strong visual and speech capabilities, making near real-time vision and speech interaction. Code has been released at https://github.com/VITA-MLLM/VITA.

cs.CV↗

arXiv2025

VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model

With the growing requirement for natural human-computer interaction, speech-based systems receive increasing attention as speech is one of the most common forms of daily communication. However, the existing speech models still experience high latency when generating the first audio token during streaming, which poses a significant bottleneck for deployment. To address this issue, we propose VITA-Audio, an end-to-end large speech model with fast audio-text token generation. Specifically, we introduce a lightweight Multiple Cross-modal Token Prediction (MCTP) module that efficiently generates multiple audio tokens within a single model forward pass, which not only accelerates the inference but also significantly reduces the latency for generating the first audio in streaming scenarios. In addition, a four-stage progressive training strategy is explored to achieve model acceleration with minimal loss of speech quality. To our knowledge, VITA-Audio is the first multi-modal large language model capable of generating audio output during the first forward pass, enabling real-time conversational capabilities with minimal latency. VITA-Audio is fully reproducible and is trained on open-source data only. Experimental results demonstrate that our model achieves an inference speedup of 3~5x at the 7B parameter scale, but also significantly outperforms open-source models of similar model size on multiple benchmarks for automatic speech recognition (ASR), text-to-speech (TTS), and spoken question answering (SQA) tasks.

cs.CL↗

arXiv2025

VITA-E: Natural Embodied Interaction with Concurrent Seeing, Hearing, Speaking, and Acting

Current Vision-Language-Action (VLA) models are often constrained by a rigid, static interaction paradigm, which lacks the ability to see, hear, speak, and act concurrently as well as handle real-time user interruptions dynamically. This hinders seamless embodied collaboration, resulting in an inflexible and unresponsive user experience. To address these limitations, we introduce VITA-E, a novel embodied interaction framework designed for both behavioral concurrency and nearly real-time interruption. The core of our approach is a dual-model architecture where two parallel VLA instances operate as an ``Active Model'' and a ``Standby Model'', allowing the embodied agent to observe its environment, listen to user speech, provide verbal responses, and execute actions, all concurrently and interruptibly, mimicking human-like multitasking capabilities. We further propose a ``model-as-controller'' paradigm, where we fine-tune the VLM to generate special tokens that serve as direct system-level commands, coupling the model's reasoning with the system's behavior. Experiments conducted on a physical humanoid platform demonstrate that VITA-E can reliably handle complex interactive scenarios. Our framework is compatible with various dual-system VLA models, achieving an extremely high success rate on emergency stops and speech interruptions while also successfully performing concurrent speech and action. This represents a significant step towards more natural and capable embodied assistants.

cs.RO↗

arXiv2025

VITA-VLA: Efficiently Teaching Vision-Language Models to Act via Action Expert Distillation

Vision-Language Action (VLA) models significantly advance robotic manipulation by leveraging the strong perception capabilities of pretrained vision-language models (VLMs). By integrating action modules into these pretrained models, VLA methods exhibit improved generalization. However, training them from scratch is costly. In this work, we propose a simple yet effective distillation-based framework that equips VLMs with action-execution capability by transferring knowledge from pretrained small action models. Our architecture retains the original VLM structure, adding only an action token and a state encoder to incorporate physical inputs. To distill action knowledge, we adopt a two-stage training strategy. First, we perform lightweight alignment by mapping VLM hidden states into the action space of the small action model, enabling effective reuse of its pretrained action decoder and avoiding expensive pretraining. Second, we selectively fine-tune the language model, state encoder, and action modules, enabling the system to integrate multimodal inputs with precise action generation. Specifically, the action token provides the VLM with a direct handle for predicting future actions, while the state encoder allows the model to incorporate robot dynamics not captured by vision alone. This design yields substantial efficiency gains over training large VLA models from scratch. Compared with previous state-of-the-art methods, our method achieves 97.3% average success rate on LIBERO (11.8% improvement) and 93.5% on LIBERO-LONG (24.5% improvement). In real-world experiments across five manipulation tasks, our method consistently outperforms the teacher model, achieving 82.0% success rate (17% improvement), which demonstrate that action distillation effectively enables VLMs to generate precise actions while substantially reducing training costs.

cs.CV↗

arXiv2025

FlexiReID: Adaptive Mixture of Expert for Multi-Modal Person Re-Identification

Multimodal person re-identification (Re-ID) aims to match pedestrian images across different modalities. However, most existing methods focus on limited cross-modal settings and fail to support arbitrary query-retrieval combinations, hindering practical deployment. We propose FlexiReID, a flexible framework that supports seven retrieval modes across four modalities: rgb, infrared, sketches, and text. FlexiReID introduces an adaptive mixture-of-experts (MoE) mechanism to dynamically integrate diverse modality features and a cross-modal query fusion module to enhance multimodal feature extraction. To facilitate comprehensive evaluation, we construct CIRS-PEDES, a unified dataset extending four popular Re-ID datasets to include all four modalities. Extensive experiments demonstrate that FlexiReID achieves state-of-the-art performance and offers strong generalization in complex scenarios.

cs.CV↗

arXiv2025

Human-MME: A Holistic Evaluation Benchmark for Human-Centric Multimodal Large Language Models

Multimodal Large Language Models (MLLMs) have demonstrated significant advances in visual understanding tasks. However, their capacity to comprehend human-centric scenes has rarely been explored, primarily due to the absence of comprehensive evaluation benchmarks that take into account both the human-oriented granular level and higher-dimensional causal reasoning ability. Such high-quality evaluation benchmarks face tough obstacles, given the physical complexity of the human body and the difficulty of annotating granular structures. In this paper, we propose Human-MME, a curated benchmark designed to provide a more holistic evaluation of MLLMs in human-centric scene understanding. Compared with other existing benchmarks, our work provides three key features: 1. Diversity in human scene, spanning 4 primary visual domains with 15 secondary domains and 43 sub-fields to ensure broad scenario coverage. 2. Progressive and diverse evaluation dimensions, evaluating the human-based activities progressively from the human-oriented granular perception to the higher-dimensional reasoning, consisting of eight dimensions with 19,945 real-world image question pairs and an evaluation suite. 3. High-quality annotations with rich data paradigms, constructing the automated annotation pipeline and human-annotation platform, supporting rigorous manual labeling to facilitate precise and reliable model assessment. Our benchmark extends the single-target understanding to the multi-person and multi-image mutual understanding by constructing the choice, short-answer, grounding, ranking and judgment question components, and complex questions of their combination. The extensive experiments on 17 state-of-the-art MLLMs effectively expose the limitations and guide future MLLMs research toward better human-centric image understanding. All data and code are available at https://github.com/Yuan-Hou/Human-MME.

cs.CV↗

arXiv2025

Contrastive Local Manifold Learning for No-Reference Image Quality Assessment

Image Quality Assessment (IQA) methods typically overlook local manifold structures, leading to compromised discriminative capabilities in perceptual quality evaluation. To address this limitation, we present LML-IQA, an innovative no-reference IQA (NR-IQA) approach that leverages a combination of local manifold learning and contrastive learning. Our approach first extracts multiple patches from each image and identifies the most visually salient region. This salient patch serves as a positive sample for contrastive learning, while other patches from the same image are treated as intra-class negatives to preserve local distinctiveness. Patches from different images also act as inter-class negatives to enhance feature separation. Additionally, we introduce a mutual learning strategy to improve the model's ability to recognize and prioritize visually important regions. Comprehensive experiments across eight benchmark datasets demonstrate significant performance gains over state-of-the-art methods, achieving a PLCC of 0.942 on TID2013 (compared to 0.908) and 0.977 on CSIQ (compared to 0.965).

cs.CV↗

arXiv2025

LLaVA-RadZ: Can Multimodal Large Language Models Effectively Tackle Zero-shot Radiology Recognition?

Recently, Multimodal Large Language Models (MLLMs) have demonstrated exceptional capabilities in visual understanding and reasoning across various vision-language tasks. However, we found that MLLMs cannot process effectively from fine-grained medical image data in the traditional Visual Question Answering (VQA) pipeline, as they do not exploit the captured features and available medical knowledge fully, results in MLLMs usually performing poorly in zero-shot medical disease recognition. Fortunately, this limitation does not indicate that MLLMs are fundamentally incapable of addressing fine-grained recognition tasks. From a feature representation perspective, MLLMs demonstrate considerable potential for tackling such challenging problems. Thus, to address this challenge, we propose LLaVA-RadZ, a simple yet effective framework for zero-shot medical disease recognition via utilizing the existing MLLM features. Specifically, we design an end-to-end training strategy, termed Decoding-Side Feature Alignment Training (DFAT) to take advantage of the characteristics of the MLLM decoder architecture and incorporate modality-specific tokens tailored for different modalities. Additionally, we introduce a Domain Knowledge Anchoring Module (DKAM) to exploit the intrinsic medical knowledge of large models, which mitigates the category semantic gap in image-text alignment. Extensive experiments demonstrate that our LLaVA-RadZ significantly outperforms traditional MLLMs in zero-shot disease recognition, achieving the comparable performance to the well-established and highly-optimized CLIP-based approaches.

cs.CV↗

arXiv2025

Few-Shot Image Quality Assessment via Adaptation of Vision-Language Models

Image Quality Assessment (IQA) remains an unresolved challenge in computer vision due to complex distortions, diverse image content, and limited data availability. Existing Blind IQA (BIQA) methods largely rely on extensive human annotations, which are labor-intensive and costly due to the demanding nature of creating IQA datasets. To reduce this dependency, we propose the Gradient-Regulated Meta-Prompt IQA Framework (GRMP-IQA), designed to efficiently adapt the visual-language pre-trained model, CLIP, to IQA tasks, achieving high accuracy even with limited data. GRMP-IQA consists of two core modules: (i) Meta-Prompt Pre-training Module and (ii) Quality-Aware Gradient Regularization. The Meta Prompt Pre-training Module leverages a meta-learning paradigm to pre-train soft prompts with shared meta-knowledge across different distortions, enabling rapid adaptation to various IQA tasks. On the other hand, the Quality-Aware Gradient Regularization is designed to adjust the update gradients during fine-tuning, focusing the model's attention on quality-relevant features and preventing overfitting to semantic information. Extensive experiments on standard BIQA datasets demonstrate the superior performance to the state-of-the-art BIQA methods under limited data setting. Notably, utilizing just 20% of the training data, GRMP-IQA is competitive with most existing fully supervised BIQA approaches.

cs.CV↗

arXiv2025

From Objects to Events: Unlocking Complex Visual Understanding in Object Detectors via LLM-guided Symbolic Reasoning

Current object detectors excel at entity localization and classification, yet exhibit inherent limitations in event recognition capabilities. This deficiency arises from their architecture's emphasis on discrete object identification rather than modeling the compositional reasoning, inter-object correlations, and contextual semantics essential for comprehensive event understanding. To address this challenge, we present a novel framework that expands the capability of standard object detectors beyond mere object recognition to complex event understanding through LLM-guided symbolic reasoning. Our key innovation lies in bridging the semantic gap between object detection and event understanding without requiring expensive task-specific training. The proposed plug-and-play framework interfaces with any open-vocabulary detector while extending their inherent capabilities across architectures. At its core, our approach combines (i) a symbolic regression mechanism exploring relationship patterns among detected entities and (ii) a LLM-guided strategically guiding the search toward meaningful expressions. These discovered symbolic rules transform low-level visual perception into interpretable event understanding, providing a transparent reasoning path from objects to events with strong transferability across domains.We compared our training-free framework against specialized event recognition systems across diverse application domains. Experiments demonstrate that our framework enhances multiple object detector architectures to recognize complex events such as illegal fishing activities (75% AUROC, +8.36% improvement), construction safety violations (+15.77%), and abnormal crowd behaviors (+23.16%). Code is available at \href{https://github.com/MAC-AutoML/SymbolicDet}{here}.

cs.CV↗

arXiv2025

Adaptive Feature Selection for No-Reference Image Quality Assessment by Mitigating Semantic Noise Sensitivity

The current state-of-the-art No-Reference Image Quality Assessment (NR-IQA) methods typically rely on feature extraction from upstream semantic backbone networks, assuming that all extracted features are relevant. However, we make a key observation that not all features are beneficial, and some may even be harmful, necessitating careful selection. Empirically, we find that many image pairs with small feature spatial distances can have vastly different quality scores, indicating that the extracted features may contain a significant amount of quality-irrelevant noise. To address this issue, we propose a Quality-Aware Feature Matching IQA Metric (QFM-IQM) that employs an adversarial perspective to remove harmful semantic noise features from the upstream task. Specifically, QFM-IQM enhances the semantic noise distinguish capabilities by matching image pairs with similar quality scores but varying semantic features as adversarial semantic noise and adaptively adjusting the upstream task's features by reducing sensitivity to adversarial noise perturbation. Furthermore, we utilize a distillation framework to expand the dataset and improve the model's generalization ability. Our approach achieves superior performance to the state-of-the-art NR-IQA methods on eight standard IQA datasets.

cs.CV↗

arXiv2025

Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis

In the quest for artificial general intelligence, Multi-modal Large Language Models (MLLMs) have emerged as a focal point in recent advancements. However, the predominant focus remains on developing their capabilities in static image understanding. The potential of MLLMs in processing sequential visual data is still insufficiently explored, highlighting the absence of a comprehensive, high-quality assessment of their performance. In this paper, we introduce Video-MME, the first-ever full-spectrum, Multi-Modal Evaluation benchmark of MLLMs in Video analysis. Our work distinguishes from existing benchmarks through four key features: 1) Diversity in video types, spanning 6 primary visual domains with 30 subfields to ensure broad scenario generalizability; 2) Duration in temporal dimension, encompassing both short-, medium-, and long-term videos, ranging from 11 seconds to 1 hour, for robust contextual dynamics; 3) Breadth in data modalities, integrating multi-modal inputs besides video frames, including subtitles and audios, to unveil the all-round capabilities of MLLMs; 4) Quality in annotations, utilizing rigorous manual labeling by expert annotators to facilitate precise and reliable model assessment. 900 videos with a total of 254 hours are manually selected and annotated by repeatedly viewing all the video content, resulting in 2,700 question-answer pairs. With Video-MME, we extensively evaluate various state-of-the-art MLLMs, including GPT-4 series and Gemini 1.5 Pro, as well as open-source image models like InternVL-Chat-V1.5 and video models like LLaVA-NeXT-Video. Our experiments reveal that Gemini 1.5 Pro is the best-performing commercial model, significantly outperforming the open-source models. Our dataset along with these findings underscores the need for further improvements in handling longer sequences and multi-modal data. Project Page: https://video-mme.github.io

cs.CV↗

arXiv2025

VITA: Towards Open-Source Interactive Omni Multimodal LLM

The remarkable multimodal capabilities and interactive experience of GPT-4o underscore their necessity in practical applications, yet open-source models rarely excel in both areas. In this paper, we introduce VITA, the first-ever open-source Multimodal Large Language Model (MLLM) adept at simultaneous processing and analysis of Video, Image, Text, and Audio modalities, and meanwhile has an advanced multimodal interactive experience. Starting from Mixtral 8x7B as a language foundation, we expand its Chinese vocabulary followed by bilingual instruction tuning. We further endow the language model with visual and audio capabilities through two-stage multi-task learning of multimodal alignment and instruction tuning. VITA demonstrates robust foundational capabilities of multilingual, vision, and audio understanding, as evidenced by its strong performance across a range of both unimodal and multimodal benchmarks. Beyond foundational capabilities, we have made considerable progress in enhancing the natural multimodal human-computer interaction experience. VITA is the first step for the open-source community to explore the seamless integration of multimodal understanding and interaction. While there is still lots of work to be done on VITA to get close to close-source counterparts, we hope that its role as a pioneer can serve as a cornerstone for subsequent research. Project Page: https://vita-home.github.io.

cs.CV↗

arXiv2025

Zooming from Context to Cue: Hierarchical Preference Optimization for Multi-Image MLLMs

Multi-modal Large Language Models (MLLMs) excel at single-image tasks but struggle with multi-image understanding due to cross-modal misalignment, leading to hallucinations (context omission, conflation, and misinterpretation). Existing methods using Direct Preference Optimization (DPO) constrain optimization to a solitary image reference within the input sequence, neglecting holistic context modeling. We propose Context-to-Cue Direct Preference Optimization (CcDPO), a multi-level preference optimization framework that enhances per-image perception in multi-image settings by zooming into visual clues -- from sequential context to local details. It features: (i) Context-Level Optimization : Re-evaluates cognitive biases underlying MLLMs' multi-image context comprehension and integrates a spectrum of low-cost global sequence preferences for bias mitigation. (ii) Needle-Level Optimization : Directs attention to fine-grained visual details through region-targeted visual prompts and multimodal preference supervision. To support scalable optimization, we also construct MultiScope-42k, an automatically generated dataset with high-quality multi-level preference pairs. Experiments show that CcDPO significantly reduces hallucinations and yields consistent performance gains across general single- and multi-image tasks.

cs.CV↗

arXiv2025

What You Perceive Is What You Conceive: A Cognition-Inspired Framework for Open Vocabulary Image Segmentation

Open vocabulary image segmentation tackles the challenge of recognizing dynamically adjustable, predefined novel categories at inference time by leveraging vision-language alignment. However, existing paradigms typically perform class-agnostic region segmentation followed by category matching, which deviates from the human visual system's process of recognizing objects based on semantic concepts, leading to poor alignment between region segmentation and target concepts. To bridge this gap, we propose a novel Cognition-Inspired Framework for open vocabulary image segmentation that emulates the human visual recognition process: first forming a conceptual understanding of an object, then perceiving its spatial extent. The framework consists of three core components: (1) A Generative Vision-Language Model (G-VLM) that mimics human cognition by generating object concepts to provide semantic guidance for region segmentation. (2) A Concept-Aware Visual Enhancer Module that fuses textual concept features with global visual representations, enabling adaptive visual perception based on target concepts. (3) A Cognition-Inspired Decoder that integrates local instance features with G-VLM-provided semantic cues, allowing selective classification over a subset of relevant categories. Extensive experiments demonstrate that our framework achieves significant improvements, reaching $27.2$ PQ, $17.0$ mAP, and $35.3$ mIoU on A-150. It further attains $56.2$, $28.2$, $15.4$, $59.2$, $18.7$, and $95.8$ mIoU on Cityscapes, Mapillary Vistas, A-847, PC-59, PC-459, and PAS-20, respectively. In addition, our framework supports vocabulary-free segmentation, offering enhanced flexibility in recognizing unseen categories. Code will be public.

cs.CV↗

arXiv2025

Pseudo-Label Quality Decoupling and Correction for Semi-Supervised Instance Segmentation

Semi-Supervised Instance Segmentation (SSIS) involves classifying and grouping image pixels into distinct object instances using limited labeled data. This learning paradigm usually faces a significant challenge of unstable performance caused by noisy pseudo-labels of instance categories and pixel masks. We find that the prevalent practice of filtering instance pseudo-labels assessing both class and mask quality with a single score threshold, frequently leads to compromises in the trade-off between the qualities of class and mask labels. In this paper, we introduce a novel Pseudo-Label Quality Decoupling and Correction (PL-DC) framework for SSIS to tackle the above challenges. Firstly, at the instance level, a decoupled dual-threshold filtering mechanism is designed to decouple class and mask quality estimations for instance-level pseudo-labels, thereby independently controlling pixel classifying and grouping qualities. Secondly, at the category level, we introduce a dynamic instance category correction module to dynamically correct the pseudo-labels of instance categories, effectively alleviating category confusion. Lastly, we introduce a pixel-level mask uncertainty-aware mechanism at the pixel level to re-weight the mask loss for different pixels, thereby reducing the impact of noise introduced by pixel-level mask pseudo-labels. Extensive experiments on the COCO and Cityscapes datasets demonstrate that the proposed PL-DC achieves significant performance improvements, setting new state-of-the-art results for SSIS. Notably, our PL-DC shows substantial gains even with minimal labeled data, achieving an improvement of +11.6 mAP with just 1% COCO labeled data and +15.5 mAP with 5% Cityscapes labeled data. The code will be public.

cs.CV↗

arXiv2025

BUFF: Bayesian Uncertainty Guided Diffusion Probabilistic Model for Single Image Super-Resolution

Super-resolution (SR) techniques are critical for enhancing image quality, particularly in scenarios where high-resolution imagery is essential yet limited by hardware constraints. Existing diffusion models for SR have relied predominantly on Gaussian models for noise generation, which often fall short when dealing with the complex and variable texture inherent in natural scenes. To address these deficiencies, we introduce the Bayesian Uncertainty Guided Diffusion Probabilistic Model (BUFF). BUFF distinguishes itself by incorporating a Bayesian network to generate high-resolution uncertainty masks. These masks guide the diffusion process, allowing for the adjustment of noise intensity in a manner that is both context-aware and adaptive. This novel approach not only enhances the fidelity of super-resolved images to their original high-resolution counterparts but also significantly mitigates artifacts and blurring in areas characterized by complex textures and fine details. The model demonstrates exceptional robustness against complex noise patterns and showcases superior adaptability in handling textures and edges within images. Empirical evidence, supported by visual results, illustrates the model's robustness, especially in challenging scenarios, and its effectiveness in addressing common SR issues such as blurring. Experimental evaluations conducted on the DIV2K dataset reveal that BUFF achieves a notable improvement, with a +0.61 increase compared to baseline in SSIM on BSD100, surpassing traditional diffusion approaches by an average additional +0.20dB PSNR gain. These findings underscore the potential of Bayesian methods in enhancing diffusion processes for SR, paving the way for future advancements in the field.

cs.CV↗

arXiv2025

Aligning Multimodal LLM with Human Preference: A Survey

Large language models (LLMs) can handle a wide variety of general tasks with simple prompts, without the need for task-specific training. Multimodal Large Language Models (MLLMs), built upon LLMs, have demonstrated impressive potential in tackling complex tasks involving visual, auditory, and textual data. However, critical issues related to truthfulness, safety, o1-like reasoning, and alignment with human preference remain insufficiently addressed. This gap has spurred the emergence of various alignment algorithms, each targeting different application scenarios and optimization goals. Recent studies have shown that alignment algorithms are a powerful approach to resolving the aforementioned challenges. In this paper, we aim to provide a comprehensive and systematic review of alignment algorithms for MLLMs. Specifically, we explore four key aspects: (1) the application scenarios covered by alignment algorithms, including general image understanding, multi-image, video, and audio, and extended multimodal applications; (2) the core factors in constructing alignment datasets, including data sources, model responses, and preference annotations; (3) the benchmarks used to evaluate alignment algorithms; and (4) a discussion of potential future directions for the development of alignment algorithms. This work seeks to help researchers organize current advancements in the field and inspire better alignment methods. The project page of this paper is available at https://github.com/BradyFU/Awesome-Multimodal-Large-Language-Models/tree/Alignment.

cs.CV↗