Yiran Zhu

Zhengxuan Wei, Xu Guo, Xinghui Li et al.

Video world models aim to simulate controllable visual environments, but long-horizon rollouts depend on what the model remembers after observations leave its native context window. Explicit memories retain frames or online 3D reconstructions, which can suffer from heuristic retrieval errors, redundant appearance storage, or reconstruction artifacts. Implicit memories compress history into a compact state, but existing designs are not explicitly constrained to encode cross-view scene geometry. We propose GIM-World, a geometry-aware implicit memory framework for video world models. A lightweight transformer encoder compresses variable-length history into fixed-size memory tokens, a camera-queryable geometry head distills 3D scene structure from a frozen foundation model into the memory during training, and an information-guided pruning rule keeps encoding cost bounded as history grows. The geometry teacher is discarded at inference, leaving a lightweight memory module. Experiments on MIND show that GIM-World better preserves long-horizon geometric and visual consistency than both explicit- and implicit-memory baselines.

Yiran Zhu, Changxi Chi, Hongxin Xiang et al.

Protein inverse folding aims to design an amino acid sequence that will fold into a given backbone structure, serving as a central task in protein design. Two main paradigms have been widely explored. Template-based methods exploit database-derived structural priors and can achieve high local precision when close structural neighbors are available, but their dependence on database coverage and match quality often degrades performance on out-of-distribution (OOD) targets. Deep learning approaches, in contrast, learn general structure-to-sequence regularities and usually generalize better to new backbones. However, they struggle to capture fine-grained local structure, which can cause uncertain residue predictions and missed local motifs in ambiguous regions. We introduce Refold, a novel framework that synergistically integrates the strengths of database-derived structural priors and deep learning prediction to enhance inverse folding. Refold obtains structural priors from matched neighbors and fuses them with model predictions to refine residue probabilities. In practice, low-quality neighbors can introduce noise, potentially degrading model performance. We address this issue with a Dynamic Utility Gate that controls prior injection and falls back to the base prediction when the priors are untrustworthy. Comprehensive evaluations on standard benchmarks demonstrate that Refold achieves state-of-the-art native sequence recovery of 0.63 on both CATH 4.2 and CATH 4.3. Also, analysis indicates that Refold delivers larger gains on high-uncertainty regions, reflecting the complementarity between structural priors and deep learning predictions.

Litong Gong, Yiran Zhu, Weijie Li et al.

Recently, video generation has achieved significant rapid development based on superior text-to-image generation techniques. In this work, we propose a high fidelity framework for image-to-video generation, named AtomoVideo. Based on multi-granularity image injection, we achieve higher fidelity of the generated video to the given image. In addition, thanks to high quality datasets and training strategies, we achieve greater motion intensity while maintaining superior temporal consistency and stability. Our architecture extends flexibly to the video frame prediction task, enabling long sequence prediction through iterative generation. Furthermore, due to the design of adapter training, our approach can be well combined with existing personalized models and controllable modules. By quantitatively and qualitatively evaluation, AtomoVideo achieves superior results compared to popular methods, more examples can be found on our project website: https://atomo-video.github.io/.

Weijie Li, Litong Gong, Yiran Zhu et al.

Image-to-video (I2V) generation tasks always suffer from keeping high fidelity in the open domains. Traditional image animation techniques primarily focus on specific domains such as faces or human poses, making them difficult to generalize to open domains. Several recent I2V frameworks based on diffusion models can generate dynamic content for open domain images but fail to maintain fidelity. We found that two main factors of low fidelity are the loss of image details and the noise prediction biases during the denoising process. To this end, we propose an effective method that can be applied to mainstream video diffusion models. This method achieves high fidelity based on supplementing more precise image information and noise rectification. Specifically, given a specified image, our method first adds noise to the input image latent to keep more details, then denoises the noisy latent with proper rectification to alleviate the noise prediction biases. Our method is tuning-free and plug-and-play. The experimental results demonstrate the effectiveness of our approach in improving the fidelity of generated videos. For more image-to-video generated results, please refer to the project website: https://noise-rectification.github.io.

Liao Shen, Wentao Jiang, Yiran Zhu et al.

Recent advances in image-to-video (I2V) generation have achieved remarkable progress in synthesizing high-quality, temporally coherent videos from static images. Among all the applications of I2V, human-centric video generation includes a large portion. However, existing I2V models encounter difficulties in maintaining identity consistency between the input human image and the generated video, especially when the person in the video exhibits significant expression changes and movements. This issue becomes critical when the human face occupies merely a small fraction of the image. Since humans are highly sensitive to identity variations, this poses a critical yet under-explored challenge in I2V generation. In this paper, we propose Identity-Preserving Reward-guided Optimization (IPRO), a novel video diffusion framework based on reinforcement learning to enhance identity preservation. Instead of introducing auxiliary modules or altering model architectures, our approach introduces a direct and effective tuning algorithm that optimizes diffusion models using a face identity scorer. To improve performance and accelerate convergence, our method backpropagates the reward signal through the last steps of the sampling chain, enabling richer gradient feedback. We also propose a novel facial scoring mechanism that treats faces in ground-truth videos as facial feature pools, providing multi-angle facial information to enhance generalization. A KL-divergence regularization is further incorporated to stabilize training and prevent overfitting to the reward signal. Extensive experiments on Wan 2.2 I2V model and our in-house I2V model demonstrate the effectiveness of our method. Our project and code are available at https://ipro-alimama.github.io/.

Wei Yang, Yiran Zhu, Zilin Li et al.

Vision-language models (VLMs) possess rich knowledge but often fail on hierarchical understanding tasks, where the goal is to predict a coarse-to-fine taxonomy path that remains consistent across all levels. We compare three inference paradigms for hierarchical VQA and find that stepwise reasoning, when conditioned on prior answers, significantly outperforms single-pass prompting. Further analysis indicates that the main limitation of current VLMs is their inability to maintain cross-level state, rather than a lack of taxonomic knowledge. Motivated by this diagnosis, we propose Self-Elicited Knowledge Distillation (SEKD), which requires no human labels or external tools: the same VLM is prompted to reason step by step and act as a teacher by exposing its hard labels, soft distributions, and decoder hidden states, while a single-pass student distills these signals. The student VLM remains efficient while approaching the accuracy of its multi-step teacher. It improves in-domain path consistency (HCA) by up to +29.50 percentage points, raises zero-shot HCA on an unseen taxonomy from 4.15% to 42.26%, and yields gains on challenging mathematical benchmarks. Because all supervision is self-elicited, SEKD scales to new taxonomies and datasets without annotation cost, providing a practical route to imbue compact VLMs with dependency-aware multi-step reasoning.

Zilin Li, Weiwei Xu, Xuanqi Zhao et al.

Facial emotion recognition (FER) models trained only on pixels often fail to generalize across datasets because facial appearance is an indirect and biased proxy for underlying affect. We present NeuroGaze-Distill, a cross-modal distillation framework that transfers brain-informed priors into an image-only FER student via static Valence/Arousal (V/A) prototypes and a depression-inspired geometric prior (D-Geo). A teacher trained on EEG topographic maps from DREAMER (with MAHNOB-HCI as unlabeled support) produces a consolidated 5x5 V/A prototype grid that is frozen and reused; no EEG-face pairing and no non-visual signals at deployment are required. The student (ResNet-18/50) is trained on FERPlus with conventional CE/KD and two lightweight regularizers: (i) Proto-KD (cosine) aligns student features to the static prototypes; (ii) D-Geo softly shapes the embedding geometry in line with affective findings often reported in depression research (e.g., anhedonia-like contraction in high-valence regions). We evaluate both within-domain (FERPlus validation) and cross-dataset protocols (AffectNet-mini; optional CK+), reporting standard 8-way scores alongside present-only Macro-F1 and balanced accuracy to fairly handle label-set mismatch. Ablations attribute consistent gains to prototypes and D-Geo, and favor 5x5 over denser grids for stability. The method is simple, deployable, and improves robustness without architectural complexity.

Yiran Zhu, Wei Yang, Yan su et al.

We propose a multimodal spatiotemporal graph neural network (STG) framework to predict colorectal cancer liver metastasis (CRLM) progression. Current clinical models do not effectively integrate the tumor's spatial heterogeneity, dynamic evolution, and complex multimodal data relationships, limiting their predictive accuracy. Our STG framework combines preoperative CT imaging and clinical data into a heterogeneous graph structure, enabling joint modeling of tumor distribution and temporal evolution through spatial topology and cross-modal edges. The framework uses GraphSAGE to aggregate spatiotemporal neighborhood information and leverages supervised and contrastive learning strategies to enhance the model's ability to capture temporal features and improve robustness. A lightweight version of the model reduces parameter count by 78.55%, maintaining near-state-of-the-art performance. The model jointly optimizes recurrence risk regression and survival analysis tasks, with contrastive loss improving feature representational discriminability and cross-modal consistency. Experimental results on the MSKCC CRLM dataset show a time-adjacent accuracy of 85% and a mean absolute error of 1.1005, significantly outperforming existing methods. The innovative heterogeneous graph construction and spatiotemporal decoupling mechanism effectively uncover the associations between dynamic tumor microenvironment changes and prognosis, providing reliable quantitative support for personalized treatment decisions.

Jie Qin, Wei Yang, Yan Su et al.

In breast cancer HER2 assessment, clinical evaluation relies on combined H&E and IHC images, yet acquiring both modalities is often hindered by clinical constraints and cost. We propose an adaptive bimodal prediction framework that flexibly supports single- or dual-modality inputs through two core innovations: a dynamic branch selector activating modality completion or joint inference based on input availability, and a cross-modal GAN (CM-GAN) enabling feature-space reconstruction of missing modalities. This design dramatically improves H&E-only accuracy from 71.44% to 94.25%, achieves 95.09% with full dual-modality inputs, and maintains 90.28% reliability under single-modality conditions. The "dual-modality preferred, single-modality compatible" architecture delivers near-dual-modality accuracy without mandatory synchronized acquisition, offering a cost-effective solution for resource-limited regions and significantly improving HER2 assessment accessibility.

Wei Yang, Yiran Zhu, Jiayu Shen et al.

Diabetic Macular Edema (DME), a prevalent complication among diabetic patients, constitutes a major cause of visual impairment and blindness. Although deep learning has achieved remarkable progress in medical image analysis, traditional DME diagnosis still relies on extensive annotated data and subjective ophthalmologist assessments, limiting practical applications. To address this, we present RURANET++, an unsupervised learning-based automated DME diagnostic system. This framework incorporates an optimized U-Net architecture with embedded Spatial and Channel Squeeze & Excitation (SCSE) attention mechanisms to enhance lesion feature extraction. During feature processing, a pre-trained GoogLeNet model extracts deep features from retinal images, followed by PCA-based dimensionality reduction to 50 dimensions for computational efficiency. Notably, we introduce a novel clustering algorithm employing multi-projection heads to explicitly control cluster diversity while dynamically adjusting similarity thresholds, thereby optimizing intra-class consistency and inter-class discrimination. Experimental results demonstrate superior performance across multiple metrics, achieving maximum accuracy (0.8411), precision (0.8593), recall (0.8411), and F1-score (0.8390), with exceptional clustering quality. This work provides an efficient unsupervised solution for DME diagnosis with significant clinical implications.