Yupeng Hu

Zixu Li, Yupeng Hu, Zhiwei Chen et al.

Composed Image Retrieval (CIR) represents a challenging retrieval task that targets locating specific images through multimodal inputs. Despite recent progress in CIR techniques, prior approaches often overlook cases where images appear visually alike yet differ in attributes, potentially undermining both multimodal feature fusion and similarity modeling. To mitigate this limitation, we design a unified representation of cross-modal features based on attribute prototypes. Nevertheless, the task is far from straightforward, owing to three core issues: (1) entanglement in attribute-level semantics, (2) inconsistency across modalities, and (3) supervised signal missing. To tackle the above obstacles, we introduce a COMposed image retrieval network guided By attrIbute-based NEighbor Relations (COMBINER). Specifically, we first design an Adaptive Semantic Disentanglement module, which is capable of disentangling attribute features based on multimodal primitive features. Secondly, we propose a Unified Prototype-based Composition module, which can construct cross-modal unified prototypes (CUP) and facilitate multimodal feature composition. Finally, we introduce a Dual Relations Modeling module, which can mine pairwise and neighbor relations based on attribute similarity. Compared to traditional neighbor relations modeling CIR methods, COMBINER represents the first study addressing the phenomenon of visually similar but attribute-unrelated samples. It achieves a more accurate understanding of the semantic relations among samples by employing an attribute prototype-based similarity metric. Comprehensive experiments conducted on three benchmark datasets confirm the effectiveness of our proposed COMBINER. The implementation of our method will be accessed at https://github.com/Lee-zixu/COMBINER

Andrey Moskalenko, Alexey Bryncev, Ivan Kosmynin et al.

This paper presents an overview of the NTIRE 2026 Challenge on Video Saliency Prediction. The goal of the challenge participants was to develop automatic saliency map prediction methods for the provided video sequences. The novel dataset of 2,000 diverse videos with an open license was prepared for this challenge. The fixations and corresponding saliency maps were collected using crowdsourced mouse tracking and contain viewing data from over 5,000 assessors. Evaluation was performed on a subset of 800 test videos using generally accepted quality metrics. The challenge attracted over 20 teams making submissions, and 7 teams passed the final phase with code review. All data used in this challenge is made publicly available - https://github.com/msu-video-group/NTIRE26_Saliency_Prediction.

Zixu Li, Yupeng Hu, Zhiheng Fu et al.

The CoVR-R challenge evaluates composed video retrieval, where a system must retrieve a target video from a large gallery given a reference video and a textual edit instruction. This setting is not a standard video-text retrieval problem: the query is defined by both the visual evidence in the source video and the transformation implied by the edit. A strong embedding model can provide scalable candidate recall, but it may under-express target-side consequences such as state changes, action replacement, object preservation, or temporal consistency. A pairwise multimodal reranker can verify such details more directly, but exhaustive reranking over the full gallery is computationally infeasible. We present $\mathbb{R}^3$, a zero-shot composed video retrieval pipeline built around Reasoning-guided Recalling and Reranking. The core idea is to turn the source-edit query into a reasoning-grounded retrieval program rather than treating the edit text as a short caption. First, the model generates a reasoning trace that describes the expected target video after applying the edit. Then the trace is encoded together with the source video as a reasoning-augmented query, and its retrieval score is fused with the base composed query through an agreement-gated residual rule. At last, a re-ranker verifies the recalled candidates with direct source-candidate comparison. Experiments have demonstrated the effectiveness of our method in addressing this challenge. Codes are available on https://github.com/Lee-zixu/R-3.

Zixu Li, Yupeng Hu, Zhiwei Chen et al.

With the rapid growth of video data, Composed Video Retrieval (CVR) has emerged as a novel paradigm in video retrieval and is receiving increasing attention from researchers. Unlike unimodal video retrieval methods, the CVR task takes a multi-modal query consisting of a reference video and a piece of modification text as input. The modification text conveys the user's intended alterations to the reference video. Based on this input, the model aims to retrieve the most relevant target video. In the CVR task, there exists a substantial discrepancy in information density between video and text modalities. Traditional composition methods tend to bias the composed feature toward the reference video, which leads to suboptimal retrieval performance. This limitation is significant due to the presence of three core challenges: (1) modal contribution entanglement, (2) explicit optimization of composed features, and (3) retrieval uncertainty. To address these challenges, we propose the evidence-dRivRn dual-sTream diRectionAl anChor calibration networK (ReTrack). ReTrack is the first CVR framework that improves multi-modal query understanding by calibrating directional bias in composed features. It consists of three key modules: Semantic Contribution Disentanglement, Composition Geometry Calibration, and Reliable Evidence-driven Alignment. Specifically, ReTrack estimates the semantic contribution of each modality to calibrate the directional bias of the composed feature. It then uses the calibrated directional anchors to compute bidirectional evidence that drives reliable composed-to-target similarity estimation. Moreover, ReTrack exhibits strong generalization to the Composed Image Retrieval (CIR) task, achieving SOTA performance across three benchmark datasets in both CVR and CIR scenarios. Codes are available at https://github.com/Lee-zixu/ReTrack

Zixu Li, Yupeng Hu, Zhiwei Chen et al.

Composed Image Retrieval (CIR) is a flexible image retrieval paradigm that enables users to accurately locate the target image through a multimodal query composed of a reference image and modification text. Although this task has demonstrated promising applications in personalized search and recommendation systems, it encounters a severe challenge in practical scenarios known as the Noise Triplet Correspondence (NTC) problem. This issue primarily arises from the high cost and subjectivity involved in annotating triplet data. To address this problem, we identify two central challenges: the precise estimation of composed semantic discrepancy and the insufficient progressive adaptation to modification discrepancy. To tackle these challenges, we propose a cHrono-synergiA roBust progressIve learning framework for composed image reTrieval (HABIT), which consists of two core modules. First, the Mutual Knowledge Estimation Module quantifies sample cleanliness by calculating the Transition Rate of mutual information between the composed feature and the target image, thereby effectively identifying clean samples that align with the intended modification semantics. Second, the Dual-consistency Progressive Learning Module introduces a collaborative mechanism between the historical and current models, simulating human habit formation to retain good habits and calibrate bad habits, ultimately enabling robust learning under the presence of NTC. Extensive experiments conducted on two standard CIR datasets demonstrate that HABIT significantly outperforms most methods under various noise ratios, exhibiting superior robustness and retrieval performance. Codes are available at https://github.com/Lee-zixu/HABIT

Zixu Li, Zhiwei Chen, Zhiheng Fu et al.

The 1st Cross-Domain EgoCross Challenge at EgoVis, CVPR 2026 evaluates whether multimodal large language models can reason over egocentric videos across surgery, industry, extreme sports, and animal perspective. We achieved second place in both the Source-Limited and Open-Source tracks. In this report, we formulate EgoCross as a robust cross-domain embodied video reasoning problem rather than a simple multiple-choice visual question answering task. We identify three key challenges: (C1) temporal boundary ambiguity, where critical state transitions are sparsely sampled and often occur between frames; (C2) cross-domain semantic granularity mismatch, where the same capability requires different domain-specific visual grammar; and (C3) decision instability under close options, where long multimodal reasoning can select unsupported distractors or produce malformed outputs. To address them, we propose OmniEgo-R$^2$ (Omnidomain Egocentric Routed Reasoning), a unified routed reasoning pipeline consisting of temporal-evidence normalization, domain-agnostic capability routing, structured perception--dynamics--decision reasoning, boundary-aware option verification, and defensive answer calibration. OmniEgo-R$^2$ uses the Qwen3-VL-4B-SFT checkpoints on each EgoCross domain as the visual-language backbone, and wraps them with lightweight test-time reasoning and parsing programs. Our final submissions obtain 66.35% overall accuracy in the Source-Limited track and 66.77% in the Open-Source track, ranking second in both leaderboards.

Mingyu Zhang, Zixu Li, Zhiwei Chen et al.

Composed Image Retrieval (CIR) is a challenging image retrieval paradigm. It aims to retrieve target images from large-scale image databases that are consistent with the modification semantics, based on a multimodal query composed of a reference image and modification text. Although existing methods have made significant progress in cross-modal alignment and feature fusion, a key flaw remains: the neglect of contextual information in discriminating matching samples. However, addressing this limitation is not an easy task due to two challenges: 1) implicit dependencies and 2) the lack of a differential amplification mechanism. To address these challenges, we propose a dual-patH composItional coNtextualized neTwork (HINT), which can perform contextualized encoding and amplify the similarity differences between matching and non-matching samples, thus improving the upper performance of CIR models in complex scenarios. Our HINT model achieves optimal performance on all metrics across two CIR benchmark datasets, demonstrating the superiority of our HINT model. Codes are available at https://github.com/zh-mingyu/HINT.

Guozhi Qiu, Zhiwei Chen, Zixu Li et al.

Composed Image Retrieval (CIR) uses a reference image and a modification text as a query to retrieve a target image satisfying the requirement of ``modifying the reference image according to the text instructions''. However, existing CIR methods face two limitations: (1) frequency bias leading to ``Rare Sample Neglect'', and (2) susceptibility of similarity scores to interference from hard negative samples and noise. To address these limitations, we confront two key challenges: asymmetric rare semantic localization and robust similarity estimation under hard negative samples. To solve these challenges, we propose the Modification frEquentation-rarity baLance neTwork MELT. MELT assigns increased attention to rare modification semantics in multimodal contexts while applying diffusion-based denoising to hard negative samples with high similarity scores, enhancing multimodal fusion and matching. Extensive experiments on two CIR benchmarks validate the superior performance of MELT. Codes are available at https://github.com/luckylittlezhi/MELT.

Qilang Ye, Wei Zeng, Meng Liu et al.

Can Multimodal Large Language Models (MLLMs) discern confused objects that are visually present but audio-absent? To study this, we introduce a new benchmark, AV-ConfuseBench, which simulates an ``Audio-Visual Confusion'' scene by modifying the corresponding sound of an object in the video, e.g., mute the sounding object and ask MLLMs Is there a/an muted-object sound''. Experimental results reveal that MLLMs, such as Qwen2.5-Omni and Gemini 2.5, struggle to discriminate non-existent audio due to visually dominated reasoning. Motivated by this observation, we introduce RL-CoMM, a Reinforcement Learning-based Collaborative Multi-MLLM that is built upon the Qwen2.5-Omni foundation. RL-CoMM includes two stages: 1) To alleviate visually dominated ambiguities, we introduce an external model, a Large Audio Language Model (LALM), as the reference model to generate audio-only reasoning. Then, we design a Step-wise Reasoning Reward function that enables MLLMs to self-improve audio-visual reasoning with the audio-only reference. 2) To ensure an accurate answer prediction, we introduce Answer-centered Confidence Optimization to reduce the uncertainty of potential heterogeneous reasoning differences. Extensive experiments on audio-visual question answering and audio-visual hallucination show that RL-CoMM improves the accuracy by 10~30\% over the baseline model with limited training data. Follow: https://github.com/rikeilong/AVConfusion.

Zhiwei Chen, Yupeng Hu, Zhiheng Fu et al.

Composed Image Retrieval (CIR) is a challenging image retrieval paradigm that enables to retrieve target images based on multimodal queries consisting of reference images and modification texts. Although substantial progress has been made in recent years, existing methods assume that all samples are correctly matched. However, in real-world scenarios, due to high triplet annotation costs, CIR datasets inevitably contain annotation errors, resulting in incorrectly matched triplets. To address this issue, the problem of Noisy Triplet Correspondence (NTC) has attracted growing attention. We argue that noise in CIR can be categorized into two types: cross-modal correspondence noise and modality-inherent noise. The former arises from mismatches across modalities, whereas the latter originates from intra-modal background interference or visual factors irrelevant to the coarse-grained modification annotations. However, modality-inherent noise is often overlooked, and research on cross-modal correspondence noise remains nascent. To tackle above issues, we propose the Invariance and discrimiNaTion-awarE Noise neTwork (INTENT), comprising two components: Visual Invariant Composition and Bi-Objective Discriminative Learning, specifically designed to handle the two-aspect noise. The former applies causal intervention on the visual side via Fast Fourier Transform (FFT) to generate intervened composed features, enforcing visual invariance and enabling the model to ignore modality-inherent noise during composition. The latter adopts collaborative optimization with both positive and negative samples, and constructs a scalable decision boundary that dynamically adjusts decisions based on the loyalty degree, enabling robust correspondence discrimination. Extensive experiments on two widely used benchmark datasets demonstrate the superiority and robustness of INTENT.

Qianyun Yang, Zhiwei Chen, Yupeng Hu et al.

Hybrid Approximate Nearest Neighbor Search (Hybrid ANNS) is a foundational search technology for large-scale heterogeneous data and has gained significant attention in both academia and industry. However, current approaches overlook the heterogeneity in data distribution, thus ignoring two major challenges: the Compatibility Barrier for Similarity Magnitude Heterogeneity and the Tolerance Bottleneck to Attribute Cardinality. To overcome these issues, we propose the robuSt heTerogeneity-Aware hyBrid retrievaL framEwork, STABLE, designed for accurate, efficient, and robust hybrid ANNS under datasets with various distributions. Specifically, we introduce an enhAnced heterogeneoUs semanTic perceptiOn (AUTO) metric to achieve a joint measurement of feature similarity and attribute consistency, addressing similarity magnitude heterogeneity and improving robustness to datasets with various attribute cardinalities. Thereafter, we construct our Heterogeneous sEmantic reLation graPh (HELP) index based on AUTO to organize heterogeneous semantic relations. Finally, we employ a novel Dynamic Heterogeneity Routing method to ensure an efficient search. Extensive experiments on five feature vector benchmarks with various attribute cardinalities demonstrate the superior performance of STABLE.

Zixu Li, Yupeng Hu, Zhiwei Chen et al.

The Composed Image Retrieval (CIR) task provides a flexible retrieval paradigm via a reference image and modification text, but it heavily relies on expensive and error-prone triplet annotations. This paper systematically investigates the Noisy Triplet Correspondence (NTC) problem introduced by annotations. We find that NTC noise, particularly ``hard noise'' (i.e., the reference and target images are highly similar but the modification text is incorrect), poses a unique challenge to existing Noise Correspondence Learning (NCL) methods because it breaks the traditional ``small loss hypothesis''. We identify and elucidate three key, yet overlooked, challenges in the NTC task, namely (C1) Modality Suppression, (C2) Negative Anchor Deficiency, and (C3) Unlearning Backlash. To address these challenges, we propose a Cone-based robuSt noisE-unlearning comPositional network (ConeSep). Specifically, we first propose Geometric Fidelity Quantization, theoretically establishing and practically estimating a noise boundary to precisely locate noisy correspondence. Next, we introduce Negative Boundary Learning, which learns a ``diagonal negative combination'' for each query as its explicit semantic opposite-anchor in the embedding space. Finally, we design Boundary-based Targeted Unlearning, which models the noisy correction process as an optimal transport problem, elegantly avoiding Unlearning Backlash. Extensive experiments on benchmark datasets (FashionIQ and CIRR) demonstrate that ConeSep significantly outperforms current state-of-the-art methods, which fully demonstrates the effectiveness and robustness of our method.

Zhiheng Fu, Zixu Li, Zhiwei Chen et al.

The EPIC-KITCHENS-100 Action Detection challenge evaluates whether a model can localize the start and end of each action in long untrimmed egocentric videos and assign the corresponding verb--noun action label. In this report, we formulate our submission as EgoAction (Egocentric Action Composition with Reliability-Aware Temporal Fusion), a unified decoupled detection and fusion pipeline. The pipeline uses EPIC-finetuned VideoMAE-L features, trains separate noun and verb temporal detectors with causal temporal modeling, composes action hypotheses from top noun--verb pairs, and introduces a confidence-adaptive boundary fusion rule at post-processing time. The key observation is that verb and noun streams often fail differently: verb scores are sensitive to motion transitions, whereas noun scores are sensitive to hand-object visibility and object clutter. A fixed arithmetic mean of their predicted boundaries can therefore amplify localization errors when one stream degenerates. We replace this hard-coded mean with Dynamic Weighted Fusion (DWF), which normalizes the maximum noun and verb classification confidences into proposal-wise boundary weights and linearly combines the two intervals. This lightweight tensor-only operator shifts boundary authority toward the more reliable stream while preserving the decoupled action scoring mechanism. Together with sliding-window inference, top-K noun--verb action composition, and class-wise Soft-NMS, EgoAction provides a compact and reproducible system for egocentric temporal action detection.

Zhiwei Chen, Yupeng Hu, Zixu Li et al.

This technical report presents our solution, EgoAdapt (Egocentric Adaptation via Category, Calibration, and Consistency), to the CVPR 2026 HD-EPIC VQA challenge. HD-EPIC evaluates whether a vision-language model can reason over realistic first-person kitchen videos, where the evidence for an answer may be a short hand-object interaction, a long recipe trajectory, a spatial relation to a fixture, or a subtle gaze cue. The benchmark contains 26K multiple-choice questions across seven macro-categories: recipe, ingredient, nutrition, fine-grained action, 3D perception, object motion, and gaze. We observe that the main difficulty is not only model capacity, but also the mismatch between a single generic inference recipe and the heterogeneous temporal, spatial, and semantic structure of the benchmark. Our method, EgoAdapt, introduces three inference-time components: (1) category-conditioned routing with per-category prompts, frame budgets, and sampling rates; (2) calibrated option scoring that evaluates all candidate answers with letter-token likelihoods and generation agreement instead of relying only on direct generation; and (3) test-time consistency adaptation that aggregates predictions across option permutations and verification-style prompts for ambiguous cases. This design substantially improves over the available HD-EPIC baselines.

Zixu Li, Yupeng Hu, Zhiwei Chen et al.

Video-text retrieval has witnessed remarkable progress driven by large-scale vision-language pretraining, yet most existing approaches inherit an implicit assumption from image-text retrieval: that visual semantics can be captured frame-by-frame. This assumption overlooks the temporal dynamics of egocentric videos. The EPIC-KITCHENS-100 Multi-Instance Retrieval (MIR) challenge further raises the bar by providing soft-label relevance matrices rather than binary labels, demanding models that can resolve graded semantic correspondences across modalities. In this report, we present our solution, termed TempRet, to the CVPR 2026 EPIC-KITCHENS-100 MIR challenge. Our approach builds upon a CLIP-based dual-encoder backbone and introduces two key components to address the temporal and cross-modal challenges. First, a temporal transformer operates exclusively on the video side, modeling inter-frame dependencies through learnable positional encodings and multi-head self-attention over frame-level CLIP features. Second, a two-stage reranking pipeline first retrieves Top-K candidates via the dual-encoder, then refines their scores using a cross-encoder equipped with an Image-Text Matching (ITM) head. The entire system is trained with Symmetric Multi-Similarity Loss to exploit the soft-label relevance matrices provided by the challenge. Our method achieves 67.97% average mAP and 82.92% average nDCG on the EK-100 MIR benchmark, demonstrating the effectiveness of temporal modeling and cross-modal refinement for egocentric video retrieval.

Zixu Li, Yupeng Hu, Zhiheng Fu et al.

Composed Image Retrieval (CIR) is an important image retrieval paradigm that enables users to retrieve a target image using a multimodal query that consists of a reference image and modification text. Although research on CIR has made significant progress, prevailing setups still rely simple modification texts that typically cover only a limited range of salient changes, which induces two limitations highly relevant to practical applications, namely Insufficient Entity Coverage and Clause-Entity Misalignment. In order to address these issues and bring CIR closer to real-world use, we construct two instruction-rich multi-modification datasets, M-FashionIQ and M-CIRR. In addition, we propose TEMA, the Text-oriented Entity Mapping Architecture, which is the first CIR framework designed for multi-modification while also accommodating simple modifications. Extensive experiments on four benchmark datasets demonstrate that TEMA's superiority in both original and multi-modification scenarios, while maintaining an optimal balance between retrieval accuracy and computational efficiency. Our codes and constructed multi-modification dataset (M-FashionIQ and M-CIRR) are available at https://github.com/lee-zixu/ACL26-TEMA/.

Zhiwei Chen, Yupeng Hu, Zixu Li et al.

Composed Video Retrieval (CVR) is a challenging video retrieval task that utilizes multi-modal queries, consisting of a reference video and modification text, to retrieve the desired target video. The core of this task lies in understanding the multi-modal composed query and achieving accurate composed feature learning. Within multi-modal queries, the video modality typically carries richer semantic content compared to the textual modality. However, previous works have largely overlooked the disparity in information density between these two modalities. This limitation can lead to two critical issues: 1) modification subject referring ambiguity and 2) limited detailed semantic focus, both of which degrade the performance of CVR models. To address the aforementioned issues, we propose a novel CVR framework, namely the Hierarchical Uncertainty-aware Disambiguation network (HUD). HUD is the first framework that leverages the disparity in information density between video and text to enhance multi-modal query understanding. It comprises three key components: (a) Holistic Pronoun Disambiguation, (b) Atomistic Uncertainty Modeling, and (c) Holistic-to-Atomistic Alignment. By exploiting overlapping semantics through holistic cross-modal interaction and fine-grained semantic alignment via atomistic-level cross-modal interaction, HUD enables effective object disambiguation and enhances the focus on detailed semantics, thereby achieving precise composed feature learning. Moreover, our proposed HUD is also applicable to the Composed Image Retrieval (CIR) task and achieves state-of-the-art performance across three benchmark datasets for both CVR and CIR tasks. The codes are available on https://zivchen-ty.github.io/HUD.github.io/.

Kun Wang, Yupeng Hu, Zhiran Li et al.

In this report, we present our champion solution for the NTIRE 2026 Challenge on Video Saliency Prediction held in conjunction with CVPR 2026. To exploit complementary inductive biases for video saliency, we propose Video Saliency with Adaptive Gated Experts (ViSAGE), a multi-expert ensemble framework. Each specialized decoder performs adaptive gating and modulation to refine spatio-temporal features. The complementary predictions from different experts are then fused at inference. ViSAGE thereby aggregates diverse inductive biases to capture complex spatio-temporal saliency cues in videos. On the Private Test set, ViSAGE ranked first on two out of four evaluation metrics, and outperformed most competing solutions on the other two metrics, demonstrating its effectiveness and generalization ability. Our code has been released at https://github.com/iLearn-Lab/CVPRW26-ViSAGE.

Zixu Li, Zhiheng Fu, Yupeng Hu et al.

Composed Image Retrieval (CIR) facilitates image retrieval through a multimodal query consisting of a reference image and modification text. The reference image defines the retrieval context, while the modification text specifies desired alterations. However, existing CIR datasets predominantly employ coarse-grained modification text (CoarseMT), which inadequately captures fine-grained retrieval intents. This limitation introduces two key challenges: (1) ignoring detailed differences leads to imprecise positive samples, and (2) greater ambiguity arises when retrieving visually similar images. These issues degrade retrieval accuracy, necessitating manual result filtering or repeated queries. To address these limitations, we develop a robust fine-grained CIR data annotation pipeline that minimizes imprecise positive samples and enhances CIR systems' ability to discern modification intents accurately. Using this pipeline, we refine the FashionIQ and CIRR datasets to create two fine-grained CIR datasets: Fine-FashionIQ and Fine-CIRR. Furthermore, we introduce FineCIR, the first CIR framework explicitly designed to parse the modification text. FineCIR effectively captures fine-grained modification semantics and aligns them with ambiguous visual entities, enhancing retrieval precision. Extensive experiments demonstrate that FineCIR consistently outperforms state-of-the-art CIR baselines on both fine-grained and traditional CIR benchmark datasets. Our FineCIR code and fine-grained CIR datasets are available at https://github.com/SDU-L/FineCIR.git.

Dongjie Cheng, Yongqi Li, Zhixin Ma et al.

Multimodal Large Language Models (MLLMs) are making significant progress in multimodal reasoning. Early approaches focus on pure text-based reasoning. More recent studies have incorporated multimodal information into the reasoning steps; however, they often follow a single task-specific reasoning pattern, which limits their generalizability across various multimodal tasks. In fact, there are numerous multimodal tasks requiring diverse reasoning skills, such as zooming in on a specific region or marking an object within an image. To address this, we propose unified generative multimodal reasoning, which unifies diverse multimodal reasoning skills by generating intermediate images during the reasoning process. We instantiate this paradigm with Omni-R1, a two-stage SFT+RL framework featuring perception alignment loss and perception reward, thereby enabling functional image generation. Additionally, we introduce Omni-R1-Zero, which eliminates the need for multimodal annotations by bootstrapping step-wise visualizations from text-only reasoning data. Empirical results show that Omni-R1 achieves unified generative reasoning across a wide range of multimodal tasks, and Omni-R1-Zero can match or even surpass Omni-R1 on average, suggesting a promising direction for generative multimodal reasoning.

Shaokun Wang, Weili Guan, Jizhou Han et al.

Continual Text-to-Video Retrieval (CTVR) is a challenging multimodal continual learning setting, where models must incrementally learn new semantic categories while maintaining accurate text-video alignment for previously learned ones, thus making it particularly prone to catastrophic forgetting. A key challenge in CTVR is feature drift, which manifests in two forms: intra-modal feature drift caused by continual learning within each modality, and non-cooperative feature drift across modalities that leads to modality misalignment. To mitigate these issues, we propose StructAlign, a structured cross-modal alignment method for CTVR. First, StructAlign introduces a simplex Equiangular Tight Frame (ETF) geometry as a unified geometric prior to mitigate modality misalignment. Building upon this geometric prior, we design a cross-modal ETF alignment loss that aligns text and video features with category-level ETF prototypes, encouraging the learned representations to form an approximate simplex ETF geometry. In addition, to suppress intra-modal feature drift, we design a Cross-modal Relation Preserving loss, which leverages complementary modalities to preserve cross-modal similarity relations, providing stable relational supervision for feature updates. By jointly addressing non-cooperative feature drift across modalities and intra-modal feature drift, StructAlign effectively alleviates catastrophic forgetting in CTVR. Extensive experiments on benchmark datasets demonstrate that our method consistently outperforms state-of-the-art continual retrieval approaches.

Chao Chen, Zhixin Ma, Yongqi Li et al.

Multimodal reasoning aims to enhance the capabilities of MLLMs by incorporating intermediate reasoning steps before reaching the final answer. It has evolved from text-only reasoning to the integration of visual information, enabling the thought process to be conveyed through both images and text. Despite its effectiveness, current multimodal reasoning methods depend on explicit reasoning steps that require labor-intensive vision-text annotations and inherently introduce significant inference latency. To address these issues, we introduce multimodal latent reasoning with the advantages of multimodal representation, reduced annotation, and inference efficiency. To facilicate it, we propose Interleaved Vision-Text Latent Reasoning (IVT-LR), which injects both visual and textual information in the reasoning process within the latent space. Specifically, IVT-LR represents each reasoning step by combining two implicit parts: latent text (the hidden states from the previous step) and latent vision (a set of selected image embeddings). We further introduce a progressive multi-stage training strategy to enable MLLMs to perform the above multimodal latent reasoning steps. Experiments on M3CoT and ScienceQA demonstrate that our IVT-LR method achieves an average performance increase of 5.45% in accuracy, while simultaneously achieving a speed increase of over 5 times compared to existing approaches. Code available at https://github.com/FYYDCC/IVT-LR.

Yupeng Hu, Zhe Jin, Wenjia Li et al.

In this paper, we present the design and implementation of a Systematic Inter-Component Communication Analysis Technology (SIAT) consisting of two key modules: \emph{Monitor} and \emph{Analyzer}. As an extension to the Android operating system at framework layer, the \emph{Monitor} makes the first attempt to revise the taint tag approach named TaintDroid both at method-level and file-level, to migrate it to the app-pair ICC paths identification through systemwide tracing and analysis of taint in intent both at the data flow and control flow. By taking over the taint logs offered by the \emph{Monitor}, the \emph{Analyzer} can build the accurate and integrated ICC models adopted to identify the specific threat models with the detection algorithms and predefined rules. Meanwhile, we employ the models' deflation technology to improve the efficiency of the \emph{Analyzer}. We implement the SIAT with Android Open Source Project and evaluate its performance through extensive experiments on well-known datasets and real-world apps. The experimental results show that, compared to state-of-the-art approaches, the SIAT can achieve about 25\%$\sim$200\% accuracy improvements with 1.0 precision and 0.98 recall at the cost of negligible runtime overhead. Moreover, the SIAT can identify two undisclosed cases of bypassing that prior technologies cannot detect and quite a few malicious ICC threats in real-world apps with lots of downloads on the Google Play market.

Haoliang Sun, Qi Wei, Lei Feng et al.

Label noise has been broadly observed in real-world datasets. To mitigate the negative impact of overfitting to label noise for deep models, effective strategies (\textit{e.g.}, re-weighting, or loss rectification) have been broadly applied in prevailing approaches, which have been generally learned under the meta-learning scenario. Despite the robustness of noise achieved by the probabilistic meta-learning models, they usually suffer from model collapse that degenerates generalization performance. In this paper, we propose variational rectification inference (VRI) to formulate the adaptive rectification for loss functions as an amortized variational inference problem and derive the evidence lower bound under the meta-learning framework. Specifically, VRI is constructed as a hierarchical Bayes by treating the rectifying vector as a latent variable, which can rectify the loss of the noisy sample with the extra randomness regularization and is, therefore, more robust to label noise. To achieve the inference of the rectifying vector, we approximate its conditional posterior with an amortization meta-network. By introducing the variational term in VRI, the conditional posterior is estimated accurately and avoids collapsing to a Dirac delta function, which can significantly improve the generalization performance. The elaborated meta-network and prior network adhere to the smoothness assumption, enabling the generation of reliable rectification vectors. Given a set of clean meta-data, VRI can be efficiently meta-learned within the bi-level optimization programming. Besides, theoretical analysis guarantees that the meta-network can be efficiently learned with our algorithm. Comprehensive comparison experiments and analyses validate its effectiveness for robust learning with noisy labels, particularly in the presence of open-set noise.

Zhiheng Fu, Yupeng Hu, Qianyun Yang et al.

Composed Image Retrieval (CIR) has attracted significant attention due to its flexible multimodal query method, yet its development is severely constrained by the Noisy Triplet Correspondence (NTC) problem. Most existing robust learning methods rely on the "small loss hypothesis", but the unique semantic ambiguity in NTC, such as "partial matching", invalidates this assumption, leading to unreliable noise identification. This entraps the model in a self dependent vicious cycle where the learner is intertwined with the arbiter, ultimately causing catastrophic "representation pollution". To address this critical challenge, we propose a novel "Expert-Proxy-Diversion" decoupling paradigm, named Air-Know (ArbIteR calibrated Knowledge iNternalizing rObust netWork). Air-Know incorporates three core modules: (1) External Prior Arbitration (EPA), which utilizes Multimodal Large Language Models (MLLMs) as an offline expert to construct a high precision anchor dataset; (2) Expert Knowledge Internalization (EKI), which efficiently guides a lightweight proxy "arbiter" to internalize the expert's discriminative logic; (3) Dual Stream Reconciliation (DSR), which leverages the EKI's matching confidence to divert the training data, achieving a clean alignment stream and a representation feedback reconciliation stream. Extensive experiments on multiple CIR benchmark datasets demonstrate that Air-Know significantly outperforms existing SOTA methods under the NTC setting, while also showing strong competitiveness in traditional CIR.

Haoqiang Lin, Haokun Wen, Xuemeng Song et al.

Composed Image Retrieval (CIR) allows users to search target images with a multimodal query, comprising a reference image and a modification text that describes the user's modification demand over the reference image. Nevertheless, due to the expensive labor cost of training data annotation, recent researchers have shifted to the challenging task of zero-shot CIR (ZS-CIR), which targets fulfilling CIR without annotated triplets. The pioneer ZS-CIR studies focus on converting the CIR task into a standard text-to-image retrieval task by pre-training a textual inversion network that can map a given image into a single pseudo-word token. Despite their significant progress, their coarse-grained textual inversion may be insufficient to capture the full content of the image accurately. To overcome this issue, in this work, we propose a novel Fine-grained Textual Inversion Network for ZS-CIR, named FTI4CIR. In particular, FTI4CIR comprises two main components: fine-grained pseudo-word token mapping and tri-wise caption-based semantic regularization. The former maps the image into a subject-oriented pseudo-word token and several attribute-oriented pseudo-word tokens to comprehensively express the image in the textual form, while the latter works on jointly aligning the fine-grained pseudo-word tokens to the real-word token embedding space based on a BLIP-generated image caption template. Extensive experiments conducted on three benchmark datasets demonstrate the superiority of our proposed method.

Zhiwei Chen, Yupeng Hu, Zixu Li et al.

Composed Image Retrieval (CIR) represents a novel retrieval paradigm that is capable of expressing users' intricate retrieval requirements flexibly. It enables the user to give a multimodal query, comprising a reference image and a modification text, and subsequently retrieve the target image. Notwithstanding the considerable advances made by prevailing methodologies, CIR remains in its nascent stages due to two limitations: 1) inhomogeneity between dominant and noisy portions in visual data is ignored, leading to query feature degradation, and 2) the priority of textual data in the image modification process is overlooked, which leads to a visual focus bias. To address these two limitations, this work presents a focus mapping-based feature extractor, which consists of two modules: dominant portion segmentation and dual focus mapping. It is designed to identify significant dominant portions in images and guide the extraction of visual and textual data features, thereby reducing the impact of noise interference. Subsequently, we propose a textually guided focus revision module, which can utilize the modification requirements implied in the text to perform adaptive focus revision on the reference image, thereby enhancing the perception of the modification focus on the composed features. The aforementioned modules collectively constitute the segmentatiOn-based Focus shiFt reviSion nETwork (\mbox{OFFSET}), and comprehensive experiments on four benchmark datasets substantiate the superiority of our proposed method. The codes and data are available on https://zivchen-ty.github.io/OFFSET.github.io/

Kun Ouyang, Liqiang Jing, Xuemeng Song et al.

Sarcasm Explanation in Dialogue (SED) is a new yet challenging task, which aims to generate a natural language explanation for the given sarcastic dialogue that involves multiple modalities (\ie utterance, video, and audio). Although existing studies have achieved great success based on the generative pretrained language model BART, they overlook exploiting the sentiments residing in the utterance, video and audio, which play important roles in reflecting sarcasm that essentially involves subtle sentiment contrasts. Nevertheless, it is non-trivial to incorporate sentiments for boosting SED performance, due to three main challenges: 1) diverse effects of utterance tokens on sentiments; 2) gap between video-audio sentiment signals and the embedding space of BART; and 3) various relations among utterances, utterance sentiments, and video-audio sentiments. To tackle these challenges, we propose a novel sEntiment-enhanceD Graph-based multimodal sarcasm Explanation framework, named EDGE. In particular, we first propose a lexicon-guided utterance sentiment inference module, where a heuristic utterance sentiment refinement strategy is devised. We then develop a module named Joint Cross Attention-based Sentiment Inference (JCA-SI) by extending the multimodal sentiment analysis model JCA to derive the joint sentiment label for each video-audio clip. Thereafter, we devise a context-sentiment graph to comprehensively model the semantic relations among the utterances, utterance sentiments, and video-audio sentiments, to facilitate sarcasm explanation generation. Extensive experiments on the publicly released dataset WITS verify the superiority of our model over cutting-edge methods.

Yang Tian, Fan Liu, Jingyuan Zhang et al.

Multimodal Retrieval-Augmented Generation (MMRAG) has been introduced to enhance Multimodal Large Language Models by incorporating externally retrieved multimodal knowledge, but it introduces two challenges: Parametric-Retrieved Knowledge Inconsistency (PRKI), where discrepancies between parametric and retrieved knowledge create uncertainty in determining reliability, and Visual-Textual Knowledge Inconsistency (VTKI), where misalignment between visual and textual sources disrupts entity representation. To address these challenges, we propose Cross-source knowledge \textbf{Re}conciliation for Multimodal RAG (CoRe-MMRAG), a novel end-to-end framework that effectively reconciles inconsistencies across knowledge sources. CoRe-MMRAG follows a four-stage pipeline: it first generates an internal response from parametric knowledge, then selects the most relevant multimodal evidence via joint similarity assessment, generates an external response, and finally integrates both to produce a reliable answer. Additionally, a specialized training paradigm enhances knowledge source discrimination, multimodal integration, and unified answer generation. Experiments on KB-VQA benchmarks show that CoRe-MMRAG achieves substantial improvements over baseline methods, achieving 5.6% and 9.3% performance gains on InfoSeek and Encyclopedic-VQA, respectively.

Yudong Han, Haocong Wang, Yupeng Hu et al.

Due to the superior ability of global dependency, transformer and its variants have become the primary choice in Masked Time-series Modeling (MTM) towards time-series classification task. In this paper, we experimentally analyze that existing transformer-based MTM methods encounter with two under-explored issues when dealing with time series data: (1) they encode features by performing long-dependency ensemble averaging, which easily results in rank collapse and feature homogenization as the layer goes deeper; (2) they exhibit distinct priorities in fitting different frequency components contained in the time-series, inevitably leading to spectrum energy imbalance of encoded feature. To tackle these issues, we propose an auxiliary content-aware balanced decoder (CBD) to optimize the encoding quality in the spectrum space within masked modeling scheme. Specifically, the CBD iterates on a series of fundamental blocks, and thanks to two tailored units, each block could progressively refine the masked representation via adjusting the interaction pattern based on local content variations of time-series and learning to recalibrate the energy distribution across different frequency components. Moreover, a dual-constraint loss is devised to enhance the mutual optimization of vanilla decoder and our CBD. Extensive experimental results on ten time-series classification datasets show that our method nearly surpasses a bunch of baselines. Meanwhile, a series of explanatory results are showcased to sufficiently demystify the behaviors of our method.

Yang Tian, Fan Liu, Jingyuan Zhang et al.

Large Multimodal Models (LMMs) have achieved remarkable progress in generating photorealistic and prompt-aligned images, but they often produce outputs that contradict verifiable knowledge, especially when prompts involve fine-grained attributes or time-sensitive events. Conventional retrieval-augmented approaches attempt to address this issue by introducing external information, yet they are fundamentally incapable of grounding generation in accurate and evolving knowledge due to their reliance on static sources and shallow evidence integration. To bridge this gap, we introduce ORIG, an agentic open multimodal retrieval-augmented framework for Factual Image Generation (FIG), a new task that requires both visual realism and factual grounding. ORIG iteratively retrieves and filters multimodal evidence from the web and incrementally integrates the refined knowledge into enriched prompts to guide generation. To support systematic evaluation, we build FIG-Eval, a benchmark spanning ten categories across perceptual, compositional, and temporal dimensions. Experiments demonstrate that ORIG substantially improves factual consistency and overall image quality over strong baselines, highlighting the potential of open multimodal retrieval for factual image generation.

Yupeng Hu, Changxing Ding, Chang Sun et al.

Open vocabulary Human-Object Interaction (HOI) detection is a challenging task that detects all <human, verb, object> triplets of interest in an image, even those that are not pre-defined in the training set. Existing approaches typically rely on output features generated by large Vision-Language Models (VLMs) to enhance the generalization ability of interaction representations. However, the visual features produced by VLMs are holistic and coarse-grained, which contradicts the nature of detection tasks. To address this issue, we propose a novel Bilateral Collaboration framework for open vocabulary HOI detection (BC-HOI). This framework includes an Attention Bias Guidance (ABG) component, which guides the VLM to produce fine-grained instance-level interaction features according to the attention bias provided by the HOI detector. It also includes a Large Language Model (LLM)-based Supervision Guidance (LSG) component, which provides fine-grained token-level supervision for the HOI detector by the LLM component of the VLM. LSG enhances the ability of ABG to generate high-quality attention bias. We conduct extensive experiments on two popular benchmarks: HICO-DET and V-COCO, consistently achieving superior performance in the open vocabulary and closed settings. The code will be released in Github.

Yanlin Li, Hao Liu, Huimin Liu et al.

Theory of Mind (ToM) in Large Language Models (LLMs) refers to their capacity for reasoning about mental states, yet failures in this capacity often manifest as systematic implicit bias. Evaluating this bias is challenging, as conventional direct-query methods are susceptible to social desirability effects and fail to capture its subtle, multi-dimensional nature. To this end, we propose an evaluation framework that leverages the Stereotype Content Model (SCM) to reconceptualize bias as a multi-dimensional failure in ToM across Competence, Sociability, and Morality. The framework introduces two indirect tasks: the Word Association Bias Test (WABT) to assess implicit lexical associations and the Affective Attribution Test (AAT) to measure covert affective leanings, both designed to probe latent stereotypes without triggering model avoidance. Extensive experiments on 8 State-of-the-Art LLMs demonstrate our framework's capacity to reveal complex bias structures, including pervasive sociability bias, multi-dimensional divergence, and asymmetric stereotype amplification, thereby providing a more robust methodology for identifying the structural nature of implicit bias.

Wenliang Zhong, Haoyu Tang, Qinghai Zheng et al.

The rapid evolution of deep learning and large language models has led to an exponential growth in the demand for training data, prompting the development of Dataset Distillation methods to address the challenges of managing large datasets. Among these, Matching Training Trajectories (MTT) has been a prominent approach, which replicates the training trajectory of an expert network on real data with a synthetic dataset. However, our investigation found that this method suffers from three significant limitations: 1. Instability of expert trajectory generated by Stochastic Gradient Descent (SGD); 2. Low convergence speed of the distillation process; 3. High storage consumption of the expert trajectory. To address these issues, we offer a new perspective on understanding the essence of Dataset Distillation and MTT through a simple transformation of the objective function, and introduce a novel method called Matching Convexified Trajectory (MCT), which aims to provide better guidance for the student trajectory. MCT leverages insights from the linearized dynamics of Neural Tangent Kernel methods to create a convex combination of expert trajectories, guiding the student network to converge rapidly and stably. This trajectory is not only easier to store, but also enables a continuous sampling strategy during distillation, ensuring thorough learning and fitting of the entire expert trajectory. Comprehensive experiments across three public datasets validate the superiority of MCT over traditional MTT methods.

Yupeng Hu, Han Jiang, Hao Liu et al.

Recently, temporal action localization (TAL) has garnered significant interest in information retrieval community. However, existing supervised/weakly supervised methods are heavily dependent on extensive labeled temporal boundaries and action categories, which is labor-intensive and time-consuming. Although some unsupervised methods have utilized the ``iteratively clustering and localization'' paradigm for TAL, they still suffer from two pivotal impediments: 1) unsatisfactory video clustering confidence, and 2) unreliable video pseudolabels for model training. To address these limitations, we present a novel self-paced iterative learning model to enhance clustering and localization training simultaneously, thereby facilitating more effective unsupervised TAL. Concretely, we improve the clustering confidence through exploring the contextual feature-robust visual information. Thereafter, we design two (constant- and variable- speed) incremental instance learning strategies for easy-to-hard model training, thus ensuring the reliability of these video pseudolabels and further improving overall localization performance. Extensive experiments on two public datasets have substantiated the superiority of our model over several state-of-the-art competitors.

Xubin Zhong, Changxing Ding, Yupeng Hu et al.

Human-Object Interaction (HOI) detection is a core task for human-centric image understanding. Recent one-stage methods adopt a transformer decoder to collect image-wide cues that are useful for interaction prediction; however, the interaction representations obtained using this method are entangled and lack interpretability. In contrast, traditional two-stage methods benefit significantly from their ability to compose interaction features in a disentangled and explainable manner. In this paper, we improve the performance of one-stage methods by enabling them to extract disentangled interaction representations. First, we propose Shunted Cross-Attention (SCA) to extract human appearance, object appearance, and global context features using different cross-attention heads. This is achieved by imposing different masks on the cross-attention maps produced by the different heads. Second, we introduce the Interaction-aware Pose Estimation (IPE) task to learn interaction-relevant human pose features using a disentangled decoder. This is achieved with a novel attention module that accurately captures the human keypoints relevant to the current interaction category. Finally, our approach fuses the appearance feature and pose feature via element-wise addition to form the interaction representation. Experimental results show that our approach can be readily applied to existing one-stage HOI detectors. Moreover, we achieve state-of-the-art performance on two benchmarks: HICO-DET and V-COCO.

Haoyu Tang, Yunxiao Wang, Jihua Zhu et al.

With the development of internet of things technologies, tremendous sensor audio data has been produced, which poses great challenges to audio-based event detection in smart cities. In this paper, we target a challenging audio-based event detection task, namely, text-to-audio grounding. In addition to precisely localizing all of the desired on- and off-sets in the untrimmed audio, this challenging new task requires extensive acoustic and linguistic comprehension as well as the reasoning for the crossmodal matching relations between the audio and query. The current approaches often treat the query as an entire one through a global query representation in order to address those issues. We contend that this strategy has several drawbacks. Firstly, the interactions between the query and the audio are not fully utilized. Secondly, it has not distinguished the importance of different keywords in a query. In addition, since the audio clips are of arbitrary lengths, there exist many segments which are irrelevant to the query but have not been filtered out in the approach. This further hinders the effective grounding of desired segments. Motivated by the above concerns, a novel Cross-modal Graph Interaction (CGI) model is proposed to comprehensively model the relations between the words in a query through a novel language graph. To capture the fine-grained relevances between the audio and query, a cross-modal attention module is introduced to generate snippet-specific query representations and automatically assign higher weights to keywords with more important semantics. Furthermore, we develop a cross-gating module for the audio and query to weaken irrelevant parts and emphasize the important ones.