Yingjian Zhu

Yingjian Zhu, Xinming Wang, Kun Ding et al.

Multi-modal Retrieval-Augmented Generation (RAG) has emerged as a highly effective paradigm for Knowledge-Based Visual Question Answering (KB-VQA). Despite recent advancements, prevailing methods still primarily depend on images as the retrieval key, and often overlook or misplace the role of Vision-Language Models (VLMs), thereby failing to leverage their potential fully. In this paper, we introduce WikiSeeker, a novel multi-modal RAG framework that bridges these gaps by proposing a multi-modal retriever and redefining the role of VLMs. Rather than serving merely as answer generators, we assign VLMs two specialized agents: a Refiner and an Inspector. The Refiner utilizes the capability of VLMs to rewrite the textual query according to the input image, significantly improving the performance of the multimodal retriever. The Inspector facilitates a decoupled generation strategy by selectively routing reliable retrieved context to another LLM for answer generation, while relying on the VLM's internal knowledge when retrieval is unreliable. Extensive experiments on EVQA, InfoSeek, and M2KR demonstrate that WikiSeeker achieves state-of-the-art performance, with substantial improvements in both retrieval accuracy and answer quality. Our code will be released on https://github.com/zhuyjan/WikiSeeker.

Jun Xie, Yingjian Zhu, Feng Chen et al.

In this paper, we present our solution for the semi-supervised learning track (MER-SEMI) in MER2025. We propose a comprehensive framework, grounded in the principle that "more is better," to construct a robust Mixture of Experts (MoE) emotion recognition system. Our approach integrates a diverse range of input modalities as independent experts, including novel signals such as knowledge from large Vision-Language Models (VLMs) and temporal Action Unit (AU) information. To effectively utilize unlabeled data, we introduce a consensus-based pseudo-labeling strategy, generating high-quality labels from the agreement between a baseline model and Gemini, which are then used in a two-stage training paradigm. Finally, we employ a multi-expert voting ensemble combined with a rule-based re-ranking process to correct prediction bias and better align the outputs with human preferences. Evaluated on the MER2025-SEMI challenge dataset, our method achieves an F1-score of 0.8772 on the test set, ranking 2nd in the track. Our code is available at https://github.com/zhuyjan/MER2025-MRAC25.

Jun Xie, Xiongjun Guan, Yingjian Zhu et al.

In this paper, we present the runner-up solution for the Ego4D EgoSchema Challenge at CVPR 2025 (Confirmed on May 20, 2025). Inspired by the success of large models, we evaluate and leverage leading accessible multimodal large models and adapt them to video understanding tasks via few-shot learning and model ensemble strategies. Specifically, diversified prompt styles and process paradigms are systematically explored and evaluated to effectively guide the attention of large models, fully unleashing their powerful generalization and adaptability abilities. Experimental results demonstrate that, with our carefully designed approach, directly utilizing an individual multimodal model already outperforms the previous state-of-the-art (SOTA) method which includes several additional processes. Besides, an additional stage is further introduced that facilitates the cooperation and ensemble of periodic results, which achieves impressive performance improvements. We hope this work serves as a valuable reference for the practical application of large models and inspires future research in the field. Our Code is available at https://github.com/XiongjunGuan/EgoSchema-CVPR25.

Yingjian Zhu, Ying Wang, Yuyang Hong et al.

Recently, an audio-visual instance segmentation (AVIS) task has been introduced, aiming to identify, segment and track individual sounding instances in videos. However, prevailing methods primarily adopt the offline paradigm, that cannot associate detected instances across consecutive clips, making them unsuitable for real-world scenarios that involve continuous video streams. To address this limitation, we introduce SeaVIS, the first online framework designed for audio-visual instance segmentation. SeaVIS leverages the Causal Cross Attention Fusion (CCAF) module to enable efficient online processing, which integrates visual features from the current frame with the entire audio history under strict causal constraints. A major challenge for conventional VIS methods is that appearance-based instance association fails to distinguish between an object's sounding and silent states, resulting in the incorrect segmentation of silent objects. To tackle this, we employ an Audio-Guided Contrastive Learning (AGCL) strategy to generate instance prototypes that encode not only visual appearance but also sounding activity. In this way, instances preserved during per-frame prediction that do not emit sound can be effectively suppressed during instance association process, thereby significantly enhancing the audio-following capability of SeaVIS. Extensive experiments conducted on the AVISeg dataset demonstrate that SeaVIS surpasses existing state-of-the-art models across multiple evaluation metrics while maintaining a competitive inference speed suitable for real-time processing.

Lin Chen, Yingjian Zhu, Qi Yang et al.

Open-vocabulary semantic segmentation (OVSS) aims to segment and recognize objects universally. Trained on extensive high-quality segmentation data, the segment anything model (SAM) has demonstrated remarkable universal segmentation capabilities, offering valuable support for OVSS. Although previous methods have made progress in leveraging SAM for OVSS, there are still some challenges: (1) SAM's tendency to over-segment and (2) hard combinations between fixed masks and labels. This paper introduces a novel mask-injected framework, SAM-MI, which effectively integrates SAM with OVSS models to address these challenges. Initially, SAM-MI employs a Text-guided Sparse Point Prompter to sample sparse prompts for SAM instead of previous dense grid-like prompts, thus significantly accelerating the mask generation process. The framework then introduces Shallow Mask Aggregation (SMAgg) to merge partial masks to mitigate the SAM's over-segmentation issue. Finally, Decoupled Mask Injection (DMI) incorporates SAM-generated masks for guidance at low-frequency and high-frequency separately, rather than directly combining them with labels. Extensive experiments on multiple benchmarks validate the superiority of SAM-MI. Notably, the proposed method achieves a 16.7% relative improvement in mIoU over Grounded-SAM on the MESS benchmark, along with a 1.6$\times$ speedup. We hope SAM-MI can serve as an alternative methodology to effectively equip the OVSS model with SAM.

Xinming Wang, Jian Xu, Bin Yu et al.

Large reasoning models (LRMs) show strong capabilities in complex reasoning, yet their marginal gains on evidence-dependent factual questions are limited. We find this limitation is partially attributable to a reasoning-answer hit gap, where the model identifies the correct facts during reasoning but fails to incorporate them into the final response, thereby reducing factual fidelity. To address this issue, we propose MR-ALIGN, a Meta-Reasoning informed alignment framework that enhances factuality without relying on external verifiers. MR-ALIGN quantifies state transition probabilities along the model's thinking process and constructs a transition-aware implicit reward that reinforces beneficial reasoning patterns while suppressing defective ones at the atomic thinking segments. This re-weighting reshapes token-level signals into probability-aware segment scores, encouraging coherent reasoning trajectories that are more conducive to factual correctness. Empirical evaluations across four factual QA datasets and one long-form factuality benchmark show that MR-ALIGN consistently improves accuracy and truthfulness while reducing misleading reasoning. These results highlight that aligning the reasoning process itself, rather than merely the outputs, is pivotal for advancing factuality in LRMs.

Zhepeng Wang, Yingjian Zhu, Guanghao Dong et al.

This study investigates the integration of trustworthy prior reasoning knowledge from MLLMs into multimodal emotion recognition. We employ Gemini to generate fine-grained, modality-separable reasoning traces, which are injected as priors during the fusion stage to enrich cross-modal interactions. To mitigate the pronounced class-imbalance in multimodal emotion recognition, we introduce Balanced Dual-Contrastive Learning, a loss formulation that jointly balances inter-class and intra-class distributions. Applied to the MER2024 benchmark, our prior-enhanced framework yields substantial performance gains, demonstrating that the reliability of MLLM-derived reasoning can be synergistically combined with the domain adaptability of lightweight fusion networks for robust, scalable emotion recognition.

Jun Xie, Zhaoran Zhao, Xiongjun Guan et al.

We propose a novel framework for open-ended video question answering that enhances reasoning depth and robustness in complex real-world scenarios, as benchmarked on the CVRR-ES dataset. Existing Video-Large Multimodal Models (Video-LMMs) often exhibit limited contextual understanding, weak temporal modeling, and poor generalization to ambiguous or compositional queries. To address these challenges, we introduce a prompting-and-response integration mechanism that coordinates multiple heterogeneous Video-Language Models (VLMs) via structured chains of thought, each tailored to distinct reasoning pathways. An external Large Language Model (LLM) serves as an evaluator and integrator, selecting and fusing the most reliable responses. Extensive experiments demonstrate that our method significantly outperforms existing baselines across all evaluation metrics, showcasing superior generalization and robustness. Our approach offers a lightweight, extensible strategy for advancing multimodal reasoning without requiring model retraining, setting a strong foundation for future Video-LMM development.