Enhancing Gaze Reasoning in Vision Foundation Models for Gaze Following

Gaze following requires both scene understanding and gaze reasoning to localize the gaze target of an in-scene person. Recently, vision foundation models (VFMs) have demonstrated strong performance on this task, enabling simpler architectures while outperforming prior methods. However, we observe a key limitation of VFM-based approaches: while VFMs substantially improve scene understanding, they contribute little to gaze reasoning. As a result, existing methods often rely on semantically salient objects rather than true gaze cues, leading to degraded performance when targets are not salient. To address this, we propose a novel training mechanism to enhance gaze reasoning in VFMs for gaze following. Our method includes: (1) a head-conditioned local LoRA, which enables localized adaptation to preserve scene token learning while improving head token learning for gaze reasoning; and (2) an out-of-cone penalty, which injects gaze cues into head tokens while aligning them with scene tokens. Experiments on the GazeFollow and VAT datasets demonstrate that our method achieves state-of-the-art performance, with particularly strong improvements when gaze targets are not semantically salient. Our findings offer valuable insights for advancing future gaze following research. We will release the code once the paper is accepted.

Avoiding Over-smoothing in Social Media Rumor Detection with Pre-trained Propagation Tree Transformer

Deep learning techniques for rumor detection typically utilize Graph Neural Networks (GNNs) to analyze post relations. These methods, however, falter due to over-smoothing issues when processing rumor propagation structures, leading to declining performance. Our investigation into this issue reveals that over-smoothing is intrinsically tied to the structural characteristics of rumor propagation trees, in which the majority of nodes are 1-level nodes. Furthermore, GNNs struggle to capture long-range dependencies within these trees. To circumvent these challenges, we propose a Pre-Trained Propagation Tree Transformer (P2T3) method based on pure Transformer architecture. It extracts all conversation chains from a tree structure following the propagation direction of replies, utilizes token-wise embedding to infuse connection information and introduces necessary inductive bias, and pre-trains on large-scale unlabeled datasets. Experiments indicate that P2T3 surpasses previous state-of-the-art methods in multiple benchmark datasets and performs well under few-shot conditions. P2T3 not only avoids the over-smoothing issue inherent in GNNs but also potentially offers a large model or unified multi-modal scheme for future social media research.

CineSRD: Leveraging Visual, Acoustic, and Linguistic Cues for Open-World Visual Media Speaker Diarization

Traditional speaker diarization systems have primarily focused on constrained scenarios such as meetings and interviews, where the number of speakers is limited and acoustic conditions are relatively clean. To explore open-world speaker diarization, we extend this task to the visual media domain, encompassing complex audiovisual programs such as films and TV series. This new setting introduces several challenges, including long-form video understanding, a large number of speakers, cross-modal asynchrony between audio and visual cues, and uncontrolled in-the-wild variability. To address these challenges, we propose Cinematic Speaker Registration & Diarization (CineSRD), a unified multimodal framework that leverages visual, acoustic, and linguistic cues from video, speech, and subtitles for speaker annotation. CineSRD first performs visual anchor clustering to register initial speakers and then integrates an audio language model for speaker turn detection, refining annotations and supplementing unregistered off-screen speakers. Furthermore, we construct and release a dedicated speaker diarization benchmark for visual media that includes Chinese and English programs. Experimental results demonstrate that CineSRD achieves superior performance on the proposed benchmark and competitive results on conventional datasets, validating its robustness and generalizability in open-world visual media settings.

From Utterance to Vividity: Training Expressive Subtitle Translation LLM via Adaptive Local Preference Optimization

The rapid development of Large Language Models (LLMs) has significantly enhanced the general capabilities of machine translation. However, as application scenarios become more complex, the limitations of LLMs in vertical domain translations are gradually becoming apparent. In this study, we focus on how to construct translation LLMs that meet the needs of domain customization. We take visual media subtitle translation as our topic and explore how to train expressive and vivid translation LLMs. We investigated the situations of subtitle translation and other domains of literal and liberal translation, verifying the reliability of LLM as reward model and evaluator for translation. Additionally, to train an expressive translation LLM, we constructed and released a multidirectional subtitle parallel corpus dataset and proposed the Adaptive Local Preference Optimization (ALPO) method to address fine-grained preference alignment. Experimental results demonstrate that ALPO achieves outstanding performance in multidimensional evaluation of translation quality.

Hermes the Polyglot: A Unified Framework to Enhance Expressiveness for Multimodal Interlingual Subtitling

Interlingual subtitling, which translates subtitles of visual media into a target language, is essential for entertainment localization but has not yet been explored in machine translation. Although Large Language Models (LLMs) have significantly advanced the general capabilities of machine translation, the distinctive characteristics of subtitle texts pose persistent challenges in interlingual subtitling, particularly regarding semantic coherence, pronoun and terminology translation, and translation expressiveness. To address these issues, we present Hermes, an LLM-based automated subtitling framework. Hermes integrates three modules: Speaker Diarization, Terminology Identification, and Expressiveness Enhancement, which effectively tackle the above challenges. Experiments demonstrate that Hermes achieves state-of-the-art diarization performance and generates expressive, contextually coherent translations, thereby advancing research in interlingual subtitling.

Agentic Reward Modeling: Verifying GUI Agent via Online Proactive Interaction

Reinforcement learning with verifiable rewards (RLVR) is pivotal for the continuous evolution of GUI agents, yet existing evaluation paradigms face significant limitations. Rule-based methods suffer from poor scalability and cannot handle open-ended tasks, while LLM-as-a-Judge approaches rely on passive visual observation, often failing to capture latent system states due to partial state observability. To address these challenges, we advocate for a paradigm shift from passive evaluation to Agentic Interactive Verification. We introduce VAGEN, a framework that employs a verifier agent equipped with interaction tools to autonomously plan verification strategies and proactively probe the environment for evidence of task completion. Leveraging the insight that GUI tasks are typically "easy to verify but hard to solve", VAGEN overcomes the bottlenecks of visual limitations. Experimental results on OSWorld-Verified and AndroidWorld benchmarks demonstrate that VAGEN significantly improves evaluation accuracy compared to LLM-as-a-Judge baselines and further enhances performance through test-time scaling strategies.

VL4Gaze: Unleashing Vision-Language Models for Gaze Following

Human gaze provides essential cues for interpreting attention, intention, and social interaction in visual scenes, yet gaze understanding remains largely unexplored in current vision-language models (VLMs). While recent VLMs achieve strong scene-level reasoning across a range of visual tasks, there exists no benchmark that systematically evaluates or trains them for gaze interpretation, leaving open the question of whether gaze understanding can emerge from general-purpose vision-language pre-training. To address this gap, we introduce VL4Gaze, the first large-scale benchmark designed to investigate, evaluate, and unlock the potential of VLMs for gaze understanding. VL4Gaze contains 489K automatically generated question-answer pairs across 124K images and formulates gaze understanding as a unified VQA problem through four complementary tasks: (1) gaze object description, (2) gaze direction description, (3) gaze point location, and (4) ambiguous question recognition. We comprehensively evaluate both commercial and open-source VLMs under in-context learning and fine-tuning settings. The results show that even large-scale VLMs struggle to reliably infer gaze semantics and spatial localization without task-specific supervision. In contrast, training on VL4Gaze brings substantial and consistent improvements across all tasks, highlighting the importance of targeted multi-task supervision for developing gaze understanding capabilities in VLMs. We will release the dataset and code to support further research and development in this direction.

Fine-grained Video Dubbing Duration Alignment with Segment Supervised Preference Optimization

Video dubbing aims to translate original speech in visual media programs from the source language to the target language, relying on neural machine translation and text-to-speech technologies. Due to varying information densities across languages, target speech often mismatches the source speech duration, causing audio-video synchronization issues that significantly impact viewer experience. In this study, we approach duration alignment in LLM-based video dubbing machine translation as a preference optimization problem. We propose the Segment Supervised Preference Optimization (SSPO) method, which employs a segment-wise sampling strategy and fine-grained loss to mitigate duration mismatches between source and target lines. Experimental results demonstrate that SSPO achieves superior performance in duration alignment tasks.

Towards Real-World Rumor Detection: Anomaly Detection Framework with Graph Supervised Contrastive Learning

Current rumor detection methods based on propagation structure learning predominately treat rumor detection as a class-balanced classification task on limited labeled data. However, real-world social media data exhibits an imbalanced distribution with a minority of rumors among massive regular posts. To address the data scarcity and imbalance issues, we construct two large-scale conversation datasets from Weibo and Twitter and analyze the domain distributions. We find obvious differences between rumor and non-rumor distributions, with non-rumors mostly in entertainment domains while rumors concentrate in news, indicating the conformity of rumor detection to an anomaly detection paradigm. Correspondingly, we propose the Anomaly Detection framework with Graph Supervised Contrastive Learning (AD-GSCL). It heuristically treats unlabeled data as non-rumors and adapts graph contrastive learning for rumor detection. Extensive experiments demonstrate AD-GSCL's superiority under class-balanced, imbalanced, and few-shot conditions. Our findings provide valuable insights for real-world rumor detection featuring imbalanced data distributions.

Propagation Tree Is Not Deep: Adaptive Graph Contrastive Learning Approach for Rumor Detection

Rumor detection on social media has become increasingly important. Most existing graph-based models presume rumor propagation trees (RPTs) have deep structures and learn sequential stance features along branches. However, through statistical analysis on real-world datasets, we find RPTs exhibit wide structures, with most nodes being shallow 1-level replies. To focus learning on intensive substructures, we propose Rumor Adaptive Graph Contrastive Learning (RAGCL) method with adaptive view augmentation guided by node centralities. We summarize three principles for RPT augmentation: 1) exempt root nodes, 2) retain deep reply nodes, 3) preserve lower-level nodes in deep sections. We employ node dropping, attribute masking and edge dropping with probabilities from centrality-based importance scores to generate views. A graph contrastive objective then learns robust rumor representations. Extensive experiments on four benchmark datasets demonstrate RAGCL outperforms state-of-the-art methods. Our work reveals the wide-structure nature of RPTs and contributes an effective graph contrastive learning approach tailored for rumor detection through principled adaptive augmentation. The proposed principles and augmentation techniques can potentially benefit other applications involving tree-structured graphs.