arXiv subjects

Yapeng Tian

Publications and source records attributed to Yapeng Tian.

At least 37 records · Page 2Linked to original sources

arXiv2025

Toward Gaze Target Detection of Young Autistic Children

The automatic detection of gaze targets in autistic children through artificial intelligence can be impactful, especially for those who lack access to a sufficient number of professionals to improve their quality of life. This paper introduces a new, real-world AI application for gaze target detection in autistic children, which predicts a child's point of gaze from an activity image. This task is foundational for building automated systems that can measure joint attention-a core challenge in Autism Spectrum Disorder (ASD). To facilitate the study of this challenging application, we collected the first-ever Autism Gaze Target (AGT) dataset. We further propose a novel Socially Aware Coarse-to-Fine (SACF) gaze detection framework that explicitly leverages the social context of a scene to overcome the class imbalance common in autism datasets-a consequence of autistic children's tendency to show reduced gaze to faces. It utilizes a two-pathway architecture with expert models specialized in social and non-social gaze, guided by a context-awareness gate module. The results of our comprehensive experiments demonstrate that our framework achieves new state-of-the-art performance for gaze target detection in this population, significantly outperforming existing methods, especially on the critical minority class of face-directed gaze.

cs.CV↗

arXiv2025

$\texttt{AVROBUSTBENCH}$: Benchmarking the Robustness of Audio-Visual Recognition Models at Test-Time

While recent audio-visual models have demonstrated impressive performance, their robustness to distributional shifts at test-time remains not fully understood. Existing robustness benchmarks mainly focus on single modalities, making them insufficient for thoroughly assessing the robustness of audio-visual models. Motivated by real-world scenarios where shifts can occur $\textit{simultaneously}$ in both audio and visual modalities, we introduce $\texttt{AVROBUSTBENCH}$, a comprehensive benchmark designed to evaluate the test-time robustness of audio-visual recognition models. $\texttt{AVROBUSTBENCH}$ comprises four audio-visual benchmark datasets, $\texttt{AUDIOSET-2C}$, $\texttt{VGGSOUND-2C}$, $\texttt{KINETICS-2C}$, and $\texttt{EPICKITCHENS-2C}$, each incorporating 75 bimodal audio-visual corruptions that are $\textit{co-occurring}$ and $\textit{correlated}$. Through extensive evaluations, we observe that state-of-the-art supervised and self-supervised audio-visual models exhibit declining robustness as corruption severity increases. Furthermore, online test-time adaptation (TTA) methods, on $\texttt{VGGSOUND-2C}$ and $\texttt{KINETICS-2C}$, offer minimal improvements in performance under bimodal corruptions. We further propose $\texttt{AV2C}$, a simple TTA approach enabling on-the-fly cross-modal fusion by penalizing high-entropy samples, which achieves improvements on $\texttt{VGGSOUND-2C}$. We hope that $\texttt{AVROBUSTBENCH}$ will steer the development of more effective and robust audio-visual TTA approaches. Our code is available $\href{https://github.com/sarthaxxxxx/AV-C-Robustness-Benchmark}{here}$.

cs.SD↗

arXiv2025

Self-Improvement in Multimodal Large Language Models: A Survey

Recent advancements in self-improvement for Large Language Models (LLMs) have efficiently enhanced model capabilities without significantly increasing costs, particularly in terms of human effort. While this area is still relatively young, its extension to the multimodal domain holds immense potential for leveraging diverse data sources and developing more general self-improving models. This survey is the first to provide a comprehensive overview of self-improvement in Multimodal LLMs (MLLMs). We provide a structured overview of the current literature and discuss methods from three perspectives: 1) data collection, 2) data organization, and 3) model optimization, to facilitate the further development of self-improvement in MLLMs. We also include commonly used evaluations and downstream applications. Finally, we conclude by outlining open challenges and future research directions.

cs.CL↗

arXiv2025

High-Quality Sound Separation Across Diverse Categories via Visually-Guided Generative Modeling

We propose DAVIS, a Diffusion-based Audio-VIsual Separation framework that solves the audio-visual sound source separation task through generative learning. Existing methods typically frame sound separation as a mask-based regression problem, achieving significant progress. However, they face limitations in capturing the complex data distribution required for high-quality separation of sounds from diverse categories. In contrast, DAVIS circumvents these issues by leveraging potent generative modeling paradigms, specifically Denoising Diffusion Probabilistic Models (DDPM) and the more recent Flow Matching (FM), integrated within a specialized Separation U-Net architecture. Our framework operates by synthesizing the desired separated sound spectrograms directly from a noise distribution, conditioned concurrently on the mixed audio input and associated visual information. The inherent nature of its generative objective makes DAVIS particularly adept at producing high-quality sound separations for diverse sound categories. We present comparative evaluations of DAVIS, encompassing both its DDPM and Flow Matching variants, against leading methods on the standard AVE and MUSIC datasets. The results affirm that both variants surpass existing approaches in separation quality, highlighting the efficacy of our generative framework for tackling the audio-visual source separation task.

cs.CV↗

arXiv2025

ANNIE: Be Careful of Your Robots

The integration of vision-language-action (VLA) models into embodied AI (EAI) robots is rapidly advancing their ability to perform complex, long-horizon tasks in humancentric environments. However, EAI systems introduce critical security risks: a compromised VLA model can directly translate adversarial perturbations on sensory input into unsafe physical actions. Traditional safety definitions and methodologies from the machine learning community are no longer sufficient. EAI systems raise new questions, such as what constitutes safety, how to measure it, and how to design effective attack and defense mechanisms in physically grounded, interactive settings. In this work, we present the first systematic study of adversarial safety attacks on embodied AI systems, grounded in ISO standards for human-robot interactions. We (1) formalize a principled taxonomy of safety violations (critical, dangerous, risky) based on physical constraints such as separation distance, velocity, and collision boundaries; (2) introduce ANNIEBench, a benchmark of nine safety-critical scenarios with 2,400 video-action sequences for evaluating embodied safety; and (3) ANNIE-Attack, a task-aware adversarial framework with an attack leader model that decomposes long-horizon goals into frame-level perturbations. Our evaluation across representative EAI models shows attack success rates exceeding 50% across all safety categories. We further demonstrate sparse and adaptive attack strategies and validate the real-world impact through physical robot experiments. These results expose a previously underexplored but highly consequential attack surface in embodied AI systems, highlighting the urgent need for security-driven defenses in the physical AI era. Code is available at https://github.com/RLCLab/Annie.

cs.AI↗

arXiv2025

VRSight: An AI-Driven Scene Description System to Improve Virtual Reality Accessibility for Blind People

Virtual Reality (VR) is inaccessible to blind people. While research has investigated many techniques to enhance VR accessibility, they require additional developer effort to integrate. As such, most mainstream VR apps remain inaccessible as the industry de-prioritizes accessibility. We present VRSight, an end-to-end system that recognizes VR scenes post hoc through a set of AI models (e.g., object detection, depth estimation, LLM-based atmosphere interpretation) and generates tone-based, spatial audio feedback, empowering blind users to interact in VR without developer intervention. To enable virtual element detection, we further contribute DISCOVR, a VR dataset consisting of 30 virtual object classes from 17 social VR apps, substituting real-world datasets that remain not applicable to VR contexts. Nine participants used VRSight to explore an off-the-shelf VR app (Rec Room), demonstrating its effectiveness in facilitating social tasks like avatar awareness and available seat identification.

cs.HC↗

arXiv2025

From Waveforms to Pixels: A Survey on Audio-Visual Segmentation

Audio-Visual Segmentation (AVS) aims to identify and segment sound-producing objects in videos by leveraging both visual and audio modalities. It has emerged as a significant research area in multimodal perception, enabling fine-grained object-level understanding. In this survey, we present a comprehensive overview of the AVS field, covering its problem formulation, benchmark datasets, evaluation metrics, and the progression of methodologies. We analyze a wide range of approaches, including architectures for unimodal and multimodal encoding, key strategies for audio-visual fusion, and various decoder designs. Furthermore, we examine major training paradigms, from fully supervised learning to weakly supervised and training-free methods. Notably, we provide an extensive comparison of AVS methods across standard benchmarks, highlighting the impact of different architectural choices, fusion strategies, and training paradigms on performance. Finally, we outline the current challenges, such as limited temporal modeling, modality bias toward vision, lack of robustness in complex environments, and high computational demands, and propose promising future directions, including improving temporal reasoning and multimodal fusion, leveraging foundation models for better generalization and few-shot learning, reducing reliance on labeled data through selfand weakly supervised learning, and incorporating higher-level reasoning for more intelligent AVS systems.

cs.CV↗

arXiv2025

AROMA: Mixed-Initiative AI Assistance for Non-Visual Cooking by Grounding Multi-modal Information Between Reality and Videos

Videos offer rich audiovisual information that can support people in performing activities of daily living (ADLs), but they remain largely inaccessible to blind or low-vision (BLV) individuals. In cooking, BLV people often rely on non-visual cues, such as touch, taste, and smell, to navigate their environment, making it difficult to follow the predominantly audiovisual instructions found in video recipes. To address this problem, we introduce AROMA, an AI system that provides timely responses to the user based on real-time, context-aware assistance by integrating non-visual cues perceived by the user, a wearable camera feed, and video recipe content. AROMA uses a mixed-initiative approach: it responds to user requests while also proactively monitoring the video stream to offer timely alerts and guidance. This collaborative design leverages the complementary strengths of the user and AI system to align the physical environment with the video recipe, helping the user interpret their current cooking state and make sense of the steps. We evaluated AROMA through a study with eight BLV participants and offered insights for designing interactive AI systems to support BLV individuals in performing ADLs.

cs.HC↗

arXiv2025

PRVQL: Progressive Knowledge-guided Refinement for Robust Egocentric Visual Query Localization

Egocentric visual query localization (EgoVQL) focuses on localizing the target of interest in space and time from first-person videos, given a visual query. Despite recent progressive, existing methods often struggle to handle severe object appearance changes and cluttering background in the video due to lacking sufficient target cues, leading to degradation. Addressing this, we introduce PRVQL, a novel Progressive knowledge-guided Refinement framework for EgoVQL. The core is to continuously exploit target-relevant knowledge directly from videos and utilize it as guidance to refine both query and video features for improving target localization. Our PRVQL contains multiple processing stages. The target knowledge from one stage, comprising appearance and spatial knowledge extracted via two specially designed knowledge learning modules, are utilized as guidance to refine the query and videos features for the next stage, which are used to generate more accurate knowledge for further feature refinement. With such a progressive process, target knowledge in PRVQL can be gradually improved, which, in turn, leads to better refined query and video features for localization in the final stage. Compared to previous methods, our PRVQL, besides the given object cues, enjoys additional crucial target information from a video as guidance to refine features, and hence enhances EgoVQL in complicated scenes. In our experiments on challenging Ego4D, PRVQL achieves state-of-the-art result and largely surpasses other methods, showing its efficacy. Our code, model and results will be released at https://github.com/fb-reps/PRVQL.

cs.CV↗

arXiv2025

CLIPErase: Efficient Unlearning of Visual-Textual Associations in CLIP

Machine unlearning (MU) has gained significant attention as a means to remove specific data from trained models without requiring a full retraining process. While progress has been made in unimodal domains like text and image classification, unlearning in multimodal models remains relatively underexplored. In this work, we address the unique challenges of unlearning in CLIP, a prominent multimodal model that aligns visual and textual representations. We introduce CLIPErase, a novel approach that disentangles and selectively forgets both visual and textual associations, ensuring that unlearning does not compromise model performance. CLIPErase consists of three key modules: a Forgetting Module that disrupts the associations in the forget set, a Retention Module that preserves performance on the retain set, and a Consistency Module that maintains consistency with the original model. Extensive experiments on the CIFAR-100 and Flickr30K datasets across four CLIP downstream tasks demonstrate that CLIPErase effectively forgets designated associations in zero-shot tasks for multimodal samples, while preserving the model's performance on the retain set after unlearning.

cs.CV↗

arXiv2025

FreSca: Scaling in Frequency Space Enhances Diffusion Models

Latent diffusion models (LDMs) have achieved remarkable success in a variety of image tasks, yet achieving fine-grained, disentangled control over global structures versus fine details remains challenging. This paper explores frequency-based control within latent diffusion models. We first systematically analyze frequency characteristics across pixel space, VAE latent space, and internal LDM representations. This reveals that the "noise difference" term, derived from classifier-free guidance at each step t, is a uniquely effective and semantically rich target for manipulation. Building on this insight, we introduce FreSca, a novel and plug-and-play framework that decomposes noise difference into low- and high-frequency components and applies independent scaling factors to them via spatial or energy-based cutoffs. Essentially, FreSca operates without any model retraining or architectural change, offering model- and task-agnostic control. We demonstrate its versatility and effectiveness in improving generation quality and structural emphasis on multiple architectures (e.g., SD3, SDXL) and across applications including image generation, editing, depth estimation, and video synthesis, thereby unlocking a new dimension of expressive control within LDMs.

cs.CV↗

arXiv2025

SignDiff: Diffusion Model for American Sign Language Production

In this paper, we propose a dual-condition diffusion pre-training model named SignDiff that can generate human sign language speakers from a skeleton pose. SignDiff has a novel Frame Reinforcement Network called FR-Net, similar to dense human pose estimation work, which enhances the correspondence between text lexical symbols and sign language dense pose frames, reduces the occurrence of multiple fingers in the diffusion model. In addition, we propose a new method for American Sign Language Production (ASLP), which can generate ASL skeletal pose videos from text input, integrating two new improved modules and a new loss function to improve the accuracy and quality of sign language skeletal posture and enhance the ability of the model to train on large-scale data. We propose the first baseline for ASL production and report the scores of 17.19 and 12.85 on BLEU-4 on the How2Sign dev/test sets. We evaluated our model on the previous mainstream dataset PHOENIX14T, and the experiments achieved the SOTA results. In addition, our image quality far exceeds all previous results by 10 percentage points in terms of SSIM.

cs.CV↗

arXiv2025

SignLLM: Sign Language Production Large Language Models

In this paper, we propose SignLLM, a multilingual Sign Language Production (SLP) large language model, which includes two novel multilingual SLP modes MLSF and Prompt2LangGloss that allow sign language gestures generation from query texts input and question-style prompts input respectively. Both modes can use a new RL loss based on reinforcement learning and a new RL module named Priority Learning Channel. These RL components can accelerate the training by enhancing the model's capability to sample high-quality data. To train SignLLM, we introduce Prompt2Sign, a comprehensive multilingual sign language dataset, which builds from public data, including American Sign Language (ASL) and seven others. This dataset standardizes information by extracting pose information from sign language videos into a unified compressed format. We extensively evaluate SignLLM, demonstrating that our model achieves state-of-the-art performance on SLP tasks across eight sign languages.

cs.CV↗

arXiv2025

Motion-Grounded Video Reasoning: Understanding and Perceiving Motion at Pixel Level

In this paper, we introduce Motion-Grounded Video Reasoning, a new motion understanding task that requires generating visual answers (video segmentation masks) according to the input question, and hence needs implicit spatiotemporal reasoning and grounding. This task extends existing spatiotemporal grounding work focusing on explicit action/motion grounding, to a more general format by enabling implicit reasoning via questions. To facilitate the development of the new task, we collect a large-scale dataset called GROUNDMORE, which comprises 1,715 video clips, 249K object masks that are deliberately designed with 4 question types (Causal, Sequential, Counterfactual, and Descriptive) for benchmarking deep and comprehensive motion reasoning abilities. GROUNDMORE uniquely requires models to generate visual answers, providing a more concrete and visually interpretable response than plain texts. It evaluates models on both spatiotemporal grounding and reasoning, fostering to address complex challenges in motion-related video reasoning, temporal perception, and pixel-level understanding. Furthermore, we introduce a novel baseline model named Motion-Grounded Video Reasoning Assistant (MORA). MORA incorporates the multimodal reasoning ability from the Multimodal LLM, the pixel-level perception capability from the grounding model (SAM), and the temporal perception ability from a lightweight localization head. MORA achieves respectable performance on GROUNDMORE outperforming the best existing visual grounding baseline model by an average of 21.5% relatively. We hope this novel and challenging task will pave the way for future advancements in robust and general motion understanding via video reasoning segmentation

cs.CV↗

arXiv2025

Do Audio-Visual Segmentation Models Truly Segment Sounding Objects?

Unlike traditional visual segmentation, audio-visual segmentation (AVS) requires the model not only to identify and segment objects but also to determine whether they are sound sources. Recent AVS approaches, leveraging transformer architectures and powerful foundation models like SAM, have achieved impressive performance on standard benchmarks. Yet, an important question remains: Do these models genuinely integrate audio-visual cues to segment sounding objects? In this paper, we systematically investigate this issue in the context of robust AVS. Our study reveals a fundamental bias in current methods: they tend to generate segmentation masks based predominantly on visual salience, irrespective of the audio context. This bias results in unreliable predictions when sounds are absent or irrelevant. To address this challenge, we introduce AVSBench-Robust, a comprehensive benchmark incorporating diverse negative audio scenarios including silence, ambient noise, and off-screen sounds. We also propose a simple yet effective approach combining balanced training with negative samples and classifier-guided similarity learning. Our extensive experiments show that state-of-theart AVS methods consistently fail under negative audio conditions, demonstrating the prevalence of visual bias. In contrast, our approach achieves remarkable improvements in both standard metrics and robustness measures, maintaining near-perfect false positive rates while preserving highquality segmentation performance.

cs.SD↗

arXiv2024

Joint Co-Speech Gesture and Expressive Talking Face Generation using Diffusion with Adapters

Recent advances in co-speech gesture and talking head generation have been impressive, yet most methods focus on only one of the two tasks. Those that attempt to generate both often rely on separate models or network modules, increasing training complexity and ignoring the inherent relationship between face and body movements. To address the challenges, in this paper, we propose a novel model architecture that jointly generates face and body motions within a single network. This approach leverages shared weights between modalities, facilitated by adapters that enable adaptation to a common latent space. Our experiments demonstrate that the proposed framework not only maintains state-of-the-art co-speech gesture and talking head generation performance but also significantly reduces the number of parameters required.

cs.CV↗

arXiv2024

VinTAGe: Joint Video and Text Conditioning for Holistic Audio Generation

Recent advances in audio generation have focused on text-to-audio (T2A) and video-to-audio (V2A) tasks. However, T2A or V2A methods cannot generate holistic sounds (onscreen and off-screen). This is because T2A cannot generate sounds aligning with onscreen objects, while V2A cannot generate semantically complete (offscreen sounds missing). In this work, we address the task of holistic audio generation: given a video and a text prompt, we aim to generate both onscreen and offscreen sounds that are temporally synchronized with the video and semantically aligned with text and video. Previous approaches for joint text and video-to-audio generation often suffer from modality bias, favoring one modality over the other. To overcome this limitation, we introduce VinTAGe, a flow-based transformer model that jointly considers text and video to guide audio generation. Our framework comprises two key components: a Visual-Text Encoder and a Joint VT-SiT model. To reduce modality bias and improve generation quality, we employ pretrained uni-modal text-to-audio and video-to-audio generation models for additional guidance. Due to the lack of appropriate benchmarks, we also introduce VinTAGe-Bench, a dataset of 636 video-text-audio pairs containing both onscreen and offscreen sounds. Our comprehensive experiments on VinTAGe-Bench demonstrate that joint text and visual interaction is necessary for holistic audio generation. Furthermore, VinTAGe achieves state-of-the-art results on the VGGSound benchmark. Our source code and pre-trained models will be released. Demo is available at: https://www.youtube.com/watch?v=QmqWhUjPkJI.

cs.CV↗

arXiv2024

Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach

Self-improvement in multimodal large language models (MLLMs) is crucial for enhancing their reliability and robustness. However, current methods often rely heavily on MLLMs themselves as judges, leading to high computational costs and potential pitfalls like reward hacking and model collapse. This paper introduces a novel, model-level judge-free self-improvement framework. Our approach employs a controlled feedback mechanism while eliminating the need for MLLMs in the verification loop. We generate preference learning pairs using a controllable hallucination mechanism and optimize data quality by leveraging lightweight, contrastive language-image encoders to evaluate and reverse pairs when necessary. Evaluations across public benchmarks and our newly introduced IC dataset designed to challenge hallucination control demonstrate that our model outperforms conventional techniques. We achieve superior precision and recall with significantly lower computational demands. This method offers an efficient pathway to scalable self-improvement in MLLMs, balancing performance gains with reduced resource requirements.

cs.CL↗