Qiang Zhang

Benyu Zhang, Qiang Zhang, Jianpeng Cheng et al.

Large Language Models (LLMs) represent a promising frontier for recommender systems, yet their development has been impeded by the absence of predictable scaling laws, which are crucial for guiding research and optimizing resource allocation. We hypothesize that this may be attributed to the inherent noise, bias, and incompleteness of raw user interaction data in prior continual pre-training (CPT) efforts. This paper introduces a novel, layered framework for generating high-quality synthetic data that circumvents such issues by creating a curated, pedagogical curriculum for the LLM. We provide powerful, direct evidence for the utility of our curriculum by showing that standard sequential models trained on our principled synthetic data significantly outperform ($+130\%$ on recall@100 for SasRec) models trained on real data in downstream ranking tasks, demonstrating its superiority for learning generalizable user preference patterns. Building on this, we empirically demonstrate, for the first time, robust power-law scaling for an LLM that is continually pre-trained on our high-quality, recommendation-specific data. Our experiments reveal consistent and predictable perplexity reduction across multiple synthetic data modalities. These findings establish a foundational methodology for reliable scaling LLM capabilities in the recommendation domain, thereby shifting the research focus from mitigating data deficiencies to leveraging high-quality, structured information.

Zixuan Ding, Ao Wang, Hui Chen et al.

Multi-label recognition (MLR) with incomplete labels is very challenging. Recent works strive to explore the image-to-label correspondence in the vision-language model, \ie, CLIP, to compensate for insufficient annotations. In spite of promising performance, they generally overlook the valuable prior about the label-to-label correspondence. In this paper, we advocate remedying the deficiency of label supervision for the MLR with incomplete labels by deriving a structured semantic prior about the label-to-label correspondence via a semantic prior prompter. We then present a novel Semantic Correspondence Prompt Network (SCPNet), which can thoroughly explore the structured semantic prior. A Prior-Enhanced Self-Supervised Learning method is further introduced to enhance the use of the prior. Comprehensive experiments and analyses on several widely used benchmark datasets show that our method significantly outperforms existing methods on all datasets, well demonstrating the effectiveness and the superiority of our method. Our code will be available at https://github.com/jameslahm/SCPNet.

Ruixue Ding, Boli Chen, Pengjun Xie et al.

As a core task in location-based services (LBS) (e.g., navigation maps), query and point of interest (POI) matching connects users' intent with real-world geographic information. Recently, pre-trained models (PTMs) have made advancements in many natural language processing (NLP) tasks. Generic text-based PTMs do not have enough geographic knowledge for query-POI matching. To overcome this limitation, related literature attempts to employ domain-adaptive pre-training based on geo-related corpus. However, a query generally contains mentions of multiple geographic objects, such as nearby roads and regions of interest (ROIs). The geographic context (GC), i.e., these diverse geographic objects and their relationships, is therefore pivotal to retrieving the most relevant POI. Single-modal PTMs can barely make use of the important GC and therefore have limited performance. In this work, we propose a novel query-POI matching method Multi-modal Geographic language model (MGeo), which comprises a geographic encoder and a multi-modal interaction module. MGeo represents GC as a new modality and is able to fully extract multi-modal correlations for accurate query-POI matching. Besides, there is no publicly available benchmark for this topic. In order to facilitate further research, we build a new open-source large-scale benchmark Geographic TExtual Similarity (GeoTES). The POIs come from an open-source geographic information system (GIS). The queries are manually generated by annotators to prevent privacy issues. Compared with several strong baselines, the extensive experiment results and detailed ablation analyses on GeoTES demonstrate that our proposed multi-modal pre-training method can significantly improve the query-POI matching capability of generic PTMs, even when the queries' GC is not provided. Our code and dataset are publicly available at https://github.com/PhantomGrapes/MGeo.

Yuancheng Wang, Haoyue Zhan, Liwei Liu et al.

The recent large-scale text-to-speech (TTS) systems are usually grouped as autoregressive and non-autoregressive systems. The autoregressive systems implicitly model duration but exhibit certain deficiencies in robustness and lack of duration controllability. Non-autoregressive systems require explicit alignment information between text and speech during training and predict durations for linguistic units (e.g. phone), which may compromise their naturalness. In this paper, we introduce Masked Generative Codec Transformer (MaskGCT), a fully non-autoregressive TTS model that eliminates the need for explicit alignment information between text and speech supervision, as well as phone-level duration prediction. MaskGCT is a two-stage model: in the first stage, the model uses text to predict semantic tokens extracted from a speech self-supervised learning (SSL) model, and in the second stage, the model predicts acoustic tokens conditioned on these semantic tokens. MaskGCT follows the mask-and-predict learning paradigm. During training, MaskGCT learns to predict masked semantic or acoustic tokens based on given conditions and prompts. During inference, the model generates tokens of a specified length in a parallel manner. Experiments with 100K hours of in-the-wild speech demonstrate that MaskGCT outperforms the current state-of-the-art zero-shot TTS systems in terms of quality, similarity, and intelligibility. Audio samples are available at https://maskgct.github.io/. We release our code and model checkpoints at https://github.com/open-mmlab/Amphion/blob/main/models/tts/maskgct.

Qiang Zhang, Seung-Hwan Baek, Szymon Rusinkiewicz et al.

We propose a differentiable rendering algorithm for efficient novel view synthesis. By departing from volume-based representations in favor of a learned point representation, we improve on existing methods more than an order of magnitude in memory and runtime, both in training and inference. The method begins with a uniformly-sampled random point cloud and learns per-point position and view-dependent appearance, using a differentiable splat-based renderer to evolve the model to match a set of input images. Our method is up to 300x faster than NeRF in both training and inference, with only a marginal sacrifice in quality, while using less than 10~MB of memory for a static scene. For dynamic scenes, our method trains two orders of magnitude faster than STNeRF and renders at near interactive rate, while maintaining high image quality and temporal coherence even without imposing any temporal-coherency regularizers.

Haijin Wang, Qiang Zhang, Shiping Wang et al.

In this paper we discuss the local discontinuous Galerkin methods coupled with two specific explicit-implicit-null time discretizations for solving one-dimensional nonlinear diffusion problems $U_t=(a(U)U_x)_x$. The basic idea is to add and subtract two equal terms $a_0 U_{xx}$ on the right hand side of the partial differential equation, then to treat the term $a_0 U_{xx}$ implicitly and the other terms $(a(U)U_x)_x-a_0 U_{xx}$ explicitly. We give stability analysis for the method on a simplified model by the aid of energy analysis, which gives a guidance for the choice of $a_0$, i.e, $a_0 \ge \max\{a(u)\}/2$ to ensure the unconditional stability of the first order and second order schemes. The optimal error estimate is also derived for the simplified model, and numerical experiments are given to demonstrate the stability, accuracy and performance of the schemes for nonlinear diffusion equations.

Xiang Zhuang, Qiang Zhang, Bin Wu et al.

Molecular property is usually observed with a limited number of samples, and researchers have considered property prediction as a few-shot problem. One important fact that has been ignored by prior works is that each molecule can be recorded with several different properties simultaneously. To effectively utilize many-to-many correlations of molecules and properties, we propose a Graph Sampling-based Meta-learning (GS-Meta) framework for few-shot molecular property prediction. First, we construct a Molecule-Property relation Graph (MPG): molecule and properties are nodes, while property labels decide edges. Then, to utilize the topological information of MPG, we reformulate an episode in meta-learning as a subgraph of the MPG, containing a target property node, molecule nodes, and auxiliary property nodes. Third, as episodes in the form of subgraphs are no longer independent of each other, we propose to schedule the subgraph sampling process with a contrastive loss function, which considers the consistency and discrimination of subgraphs. Extensive experiments on 5 commonly-used benchmarks show GS-Meta consistently outperforms state-of-the-art methods by 5.71%-6.93% in ROC-AUC and verify the effectiveness of each proposed module. Our code is available at https://github.com/HICAI-ZJU/GS-Meta.

Lingfeng Zhang, Xiaoshuai Hao, Qinwen Xu et al.

Vision-and-language navigation (VLN) is a key task in Embodied AI, requiring agents to navigate diverse and unseen environments while following natural language instructions. Traditional approaches rely heavily on historical observations as spatio-temporal contexts for decision making, leading to significant storage and computational overhead. In this paper, we introduce MapNav, a novel end-to-end VLN model that leverages Annotated Semantic Map (ASM) to replace historical frames. Specifically, our approach constructs a top-down semantic map at the start of each episode and update it at each timestep, allowing for precise object mapping and structured navigation information. Then, we enhance this map with explicit textual labels for key regions, transforming abstract semantics into clear navigation cues and generate our ASM. MapNav agent using the constructed ASM as input, and use the powerful end-to-end capabilities of VLM to empower VLN. Extensive experiments demonstrate that MapNav achieves state-of-the-art (SOTA) performance in both simulated and real-world environments, validating the effectiveness of our method. Moreover, we will release our ASM generation source code and dataset to ensure reproducibility, contributing valuable resources to the field. We believe that our proposed MapNav can be used as a new memory representation method in VLN, paving the way for future research in this field.

Fulong Ma, Daojie Peng, Wenjun Yue et al.

Recent World Action Models (WAMs) have demonstrated impressive capabilities in embodied decision-making. However, whether their effectiveness stems from explicit future imagination during inference or representation learning induced by predictive training remains an open question. Emerging evidence suggests the primary advantage lies in learning robust latent representations rather than generating future observations at test time. Nevertheless, existing WAMs mainly rely on RGB-based future prediction, which provides limited structural and spatial understanding of complex environments. To address this, we propose a structured world modeling framework that enhances latent representations through geometric and semantic supervision. Alongside future RGB prediction, our model introduces two auxiliary prediction branches for future geometry and semantic representations, enabling it to jointly capture scene dynamics, spatial geometry, and semantic context within a unified latent space. Crucially, our approach preserves efficient inference by avoiding explicit future rollout or video generation at test time. Extensive experiments show that incorporating structured world supervision consistently improves action prediction accuracy, scene understanding, and robustness under challenging embodied scenarios, highlighting its potential for advancing scalable and efficient WAMs.

De Cheng, Gerong Wang, Bo Wang et al.

Zero-shot learning (ZSL) aims to learn models that can recognize unseen image semantics based on the training of data with seen semantics. Recent studies either leverage the global image features or mine discriminative local patch features to associate the extracted visual features to the semantic attributes. However, due to the lack of the necessary top-down guidance and semantic alignment for ensuring the model attending to the real attribute-correlation regions, these methods still encounter a significant semantic gap between the visual modality and the attribute modality, which makes their prediction on unseen semantics unreliable. To solve this problem, this paper establishes a novel transformer encoder-decoder model, called hybrid routing transformer (HRT). In HRT encoder, we embed an active attention, which is constructed by both the bottom-up and the top-down dynamic routing pathways to generate the attribute-aligned visual feature. While in HRT decoder, we use static routing to calculate the correlation among the attribute-aligned visual features, the corresponding attribute semantics, and the class attribute vectors to generate the final class label predictions. This design makes the presented transformer model a hybrid of 1) top-down and bottom-up attention pathways and 2) dynamic and static routing pathways. Comprehensive experiments on three widely-used benchmark datasets, namely CUB, SUN, and AWA2, are conducted. The obtained experimental results demonstrate the effectiveness of the proposed method.

Xiang Zhuang, Qiang Zhang, Keyan Ding et al.

Molecular representation learning lays the foundation for drug discovery. However, existing methods suffer from poor out-of-distribution (OOD) generalization, particularly when data for training and testing originate from different environments. To address this issue, we propose a new framework for learning molecular representations that exhibit invariance and robustness against distribution shifts. Specifically, we propose a strategy called ``first-encoding-then-separation'' to identify invariant molecule features in the latent space, which deviates from conventional practices. Prior to the separation step, we introduce a residual vector quantization module that mitigates the over-fitting to training data distributions while preserving the expressivity of encoders. Furthermore, we design a task-agnostic self-supervised learning objective to encourage precise invariance identification, which enables our method widely applicable to a variety of tasks, such as regression and multi-label classification. Extensive experiments on 18 real-world molecular datasets demonstrate that our model achieves stronger generalization against state-of-the-art baselines in the presence of various distribution shifts. Our code is available at https://github.com/HICAI-ZJU/iMoLD.

Jiahang Cao, Ziqing Wang, Hanzhong Guo et al.

Spiking neural networks (SNNs) have ultra-low energy consumption and high biological plausibility due to their binary and bio-driven nature compared with artificial neural networks (ANNs). While previous research has primarily focused on enhancing the performance of SNNs in classification tasks, the generative potential of SNNs remains relatively unexplored. In our paper, we put forward Spiking Denoising Diffusion Probabilistic Models (SDDPM), a new class of SNN-based generative models that achieve high sample quality. To fully exploit the energy efficiency of SNNs, we propose a purely Spiking U-Net architecture, which achieves comparable performance to its ANN counterpart using only 4 time steps, resulting in significantly reduced energy consumption. Extensive experimental results reveal that our approach achieves state-of-the-art on the generative tasks and substantially outperforms other SNN-based generative models, achieving up to 12x and 6x improvement on the CIFAR-10 and the CelebA datasets, respectively. Moreover, we propose a threshold-guided strategy that can further improve the performances by 2.69% in a training-free manner. The SDDPM symbolizes a significant advancement in the field of SNN generation, injecting new perspectives and potential avenues of exploration. Our code is available at https://github.com/AndyCao1125/SDDPM.

Jiahang Cao, Qiang Zhang, Jingkai Sun et al.

Diffusion models have been widely employed in the field of 3D manipulation due to their efficient capability to learn distributions, allowing for precise prediction of action trajectories. However, diffusion models typically rely on large parameter UNet backbones as policy networks, which can be challenging to deploy on resource-constrained devices. Recently, the Mamba model has emerged as a promising solution for efficient modeling, offering low computational complexity and strong performance in sequence modeling. In this work, we propose the Mamba Policy, a lighter but stronger policy that reduces the parameter count by over 80% compared to the original policy network while achieving superior performance. Specifically, we introduce the XMamba Block, which effectively integrates input information with conditional features and leverages a combination of Mamba and Attention mechanisms for deep feature extraction. Extensive experiments demonstrate that the Mamba Policy excels on the Adroit, Dexart, and MetaWorld datasets, requiring significantly fewer computational resources. Additionally, we highlight the Mamba Policy's enhanced robustness in long-horizon scenarios compared to baseline methods and explore the performance of various Mamba variants within the Mamba Policy framework. Real-world experiments are also conducted to further validate its effectiveness. Our open-source project page can be found at https://andycao1125.github.io/mamba_policy/.

Deyu An, Qiang Zhang, Jianshu Chao et al.

Unmanned aerial vehicles (UAVs) are frequently used for inspecting power lines and capturing high-resolution aerial images. However, detecting power lines in aerial images is difficult,as the foreground data(i.e, power lines) is small and the background information is abundant.To tackle this problem, we introduce DUFormer, a semantic segmentation algorithm explicitly designed to detect power lines in aerial images. We presuppose that it is advantageous to train an efficient Transformer model with sufficient feature extraction using a convolutional neural network(CNN) with a strong inductive bias.With this goal in mind, we introduce a heavy token encoder that performs overlapping feature remodeling and tokenization. The encoder comprises a pyramid CNN feature extraction module and a power line feature enhancement module.After successful local feature extraction for power lines, feature fusion is conducted.Then,the Transformer block is used for global modeling. The final segmentation result is achieved by amalgamating local and global features in the decode head.Moreover, we demonstrate the importance of the joint multi-weight loss function in power line segmentation. Our experimental results show that our proposed method outperforms all state-of-the-art methods in power line segmentation on the publicly accessible TTPLA dataset.

Lingfeng Zhang, Xiaoshuai Hao, Yingbo Tang et al.

Navigation and manipulation are fundamental capabilities of embodied intelligence, enabling robots to interpret natural language commands and interact physically with their surroundings. However, current Vision-Language-Action (VLA) models remain constrained by task-specific architectures, specializing in either navigation or manipulation, which hinders the development of general-purpose robotic agents. To bridge this gap, we introduce OneVLA, a unified architecture that integrates these distinct tasks into a single, cohesive framework. Specifically, we design a unified action head capable of generating both navigation and manipulation actions without requiring task-specific variants. Furthermore, we propose a multi stage progressive training strategy-incorporating curated data construction and Chain-of-Thought (CoT) fine-tuning that facilitates strong positive transfer and mutual reinforcement between the two domains. Extensive experiments in both simulated and real-world environments demonstrate that OneVLA achieves state-of-the-art performance, significantly outperforming both specialized single-task and existing cross-task models. By unifying these core capabilities, OneVLA paves the way for truly general-purpose robotic systems. The model and source code will be publicly released.

Jiarui Feng, Hanqing Zeng, Karish Grover et al.

Mixture-of-Experts (MoE) models have become a leading approach for decoupling parameter count from computational cost in large language models, yet effectively scaling MoE performance remains a challenge. Prior work shows that fine-grained experts enlarge the space of expert combinations and improve flexibility, but they also impose substantial routing overhead, creating a new scalability bottleneck. In this paper, we explore a complementary axis for scaling -- how expert outputs are aggregated. We theoretically show that replacing the standard weighted-summation aggregation with structural aggregation expands the expert-combination space without altering the experts or router, and enables possible multi-step reasoning within a single MoE layer. To this end, we propose DAG-MoE, a sparse MoE framework that employs a lightweight module to automatically learn the optimal aggregation structure among the selected experts. Extensive experiments under standard language modeling settings show that DAG-MoE consistently improves performance in both pretraining and fine-tuning, surpassing traditional MoE baselines.

Haiyang Mei, Xin Yang, Letian Yu et al.

Glass is very common in our daily life. Existing computer vision systems neglect it and thus may have severe consequences, e.g., a robot may crash into a glass wall. However, sensing the presence of glass is not straightforward. The key challenge is that arbitrary objects/scenes can appear behind the glass. In this paper, we propose an important problem of detecting glass surfaces from a single RGB image. To address this problem, we construct the first large-scale glass detection dataset (GDD) and propose a novel glass detection network, called GDNet-B, which explores abundant contextual cues in a large field-of-view via a novel large-field contextual feature integration (LCFI) module and integrates both high-level and low-level boundary features with a boundary feature enhancement (BFE) module. Extensive experiments demonstrate that our GDNet-B achieves satisfying glass detection results on the images within and beyond the GDD testing set. We further validate the effectiveness and generalization capability of our proposed GDNet-B by applying it to other vision tasks, including mirror segmentation and salient object detection. Finally, we show the potential applications of glass detection and discuss possible future research directions.

Yongle Luo, Yuxin Wang, Kun Dong et al.

Exploration with sparse rewards remains a challenging research problem in reinforcement learning (RL). Especially for sequential object manipulation tasks, the RL agent always receives negative rewards until completing all sub-tasks, which results in low exploration efficiency. To solve these tasks efficiently, we propose a novel self-guided continual RL framework, RelayHER (RHER). RHER first decomposes a sequential task into new sub-tasks with increasing complexity and ensures that the simplest sub-task can be learned quickly by utilizing Hindsight Experience Replay (HER). Secondly, we design a multi-goal & multi-task network to learn these sub-tasks simultaneously. Finally, we propose a Self-Guided Exploration Strategy (SGES). With SGES, the learned sub-task policy will guide the agent to the states that are helpful to learn more complex sub-task with HER. By this self-guided exploration and relay policy learning, RHER can solve these sequential tasks efficiently stage by stage. The experimental results show that RHER significantly outperforms vanilla-HER in sample-efficiency on five singleobject and five complex multi-object manipulation tasks (e.g., Push, Insert, ObstaclePush, Stack, TStack, etc.). The proposed RHER has also been applied to learn a contact-rich push task on a physical robot from scratch, and the success rate reached 10/10 with only 250 episodes.

Yue Feng, Aldo Lipani, Fanghua Ye et al.

Dialogue State Tracking (DST) aims to keep track of users' intentions during the course of a conversation. In DST, modelling the relations among domains and slots is still an under-studied problem. Existing approaches that have considered such relations generally fall short in: (1) fusing prior slot-domain membership relations and dialogue-aware dynamic slot relations explicitly, and (2) generalizing to unseen domains. To address these issues, we propose a novel \textbf{D}ynamic \textbf{S}chema \textbf{G}raph \textbf{F}usion \textbf{Net}work (\textbf{DSGFNet}), which generates a dynamic schema graph to explicitly fuse the prior slot-domain membership relations and dialogue-aware dynamic slot relations. It also uses the schemata to facilitate knowledge transfer to new domains. DSGFNet consists of a dialogue utterance encoder, a schema graph encoder, a dialogue-aware schema graph evolving network, and a schema graph enhanced dialogue state decoder. Empirical results on benchmark datasets (i.e., SGD, MultiWOZ2.1, and MultiWOZ2.2), show that DSGFNet outperforms existing methods.

Jiahang Cao, Hanzhong Guo, Ziqing Wang et al.

Recent years have witnessed Spiking Neural Networks (SNNs) gaining attention for their ultra-low energy consumption and high biological plausibility compared with traditional Artificial Neural Networks (ANNs). Despite their distinguished properties, the application of SNNs in the computationally intensive field of image generation is still under exploration. In this paper, we propose the Spiking Diffusion Models (SDMs), an innovative family of SNN-based generative models that excel in producing high-quality samples with significantly reduced energy consumption. In particular, we propose a Temporal-wise Spiking Mechanism (TSM) that allows SNNs to capture more temporal features from a bio-plasticity perspective. In addition, we propose a threshold-guided strategy that can further improve the performances by up to 16.7% without any additional training. We also make the first attempt to use the ANN-SNN approach for SNN-based generation tasks. Extensive experimental results reveal that our approach not only exhibits comparable performance to its ANN counterpart with few spiking time steps, but also outperforms previous SNN-based generative models by a large margin. Moreover, we also demonstrate the high-quality generation ability of SDM on large-scale datasets, e.g., LSUN bedroom. This development marks a pivotal advancement in the capabilities of SNN-based generation, paving the way for future research avenues to realize low-energy and low-latency generative applications. Our code is available at https://github.com/AndyCao1125/SDM.

Zhengxiang Shi, Qiang Zhang, Aldo Lipani

Inferring spatial relations in natural language is a crucial ability an intelligent system should possess. The bAbI dataset tries to capture tasks relevant to this domain (task 17 and 19). However, these tasks have several limitations. Most importantly, they are limited to fixed expressions, they are limited in the number of reasoning steps required to solve them, and they fail to test the robustness of models to input that contains irrelevant or redundant information. In this paper, we present a new Question-Answering dataset called StepGame for robust multi-hop spatial reasoning in texts. Our experiments demonstrate that state-of-the-art models on the bAbI dataset struggle on the StepGame dataset. Moreover, we propose a Tensor-Product based Memory-Augmented Neural Network (TP-MANN) specialized for spatial reasoning tasks. Experimental results on both datasets show that our model outperforms all the baselines with superior generalization and robustness performance.

Yuanyuan Liu, Chengjiang Long, Zhaoxuan Zhang et al.

3D scene graph generation (SGG) has been of high interest in computer vision. Although the accuracy of 3D SGG on coarse classification and single relation label has been gradually improved, the performance of existing works is still far from being perfect for fine-grained and multi-label situations. In this paper, we propose a framework fully exploring contextual information for the 3D SGG task, which attempts to satisfy the requirements of fine-grained entity class, multiple relation labels, and high accuracy simultaneously. Our proposed approach is composed of a Graph Feature Extraction module and a Graph Contextual Reasoning module, achieving appropriate information-redundancy feature extraction, structured organization, and hierarchical inferring. Our approach achieves superior or competitive performance over previous methods on the 3DSSG dataset, especially on the relationship prediction sub-task.

Chang-Bin Zhang, Yujie Zhong, Qiang Zhang et al.

While visually grounded Chain-of-Thought (CoT) has emerged as a promising paradigm to enhance fine-grained perception in multimodal large language models (MLLMs), its efficacy during the inference phase remains underexplored. In this work, we empirically find that mandating explicit object boxes in visually grounded CoT during inference often degrades performance compared to standard textual CoT, which reasons without explicit visual grounding. We hypothesize that the visual localization capability can be internalized into the textual CoT and that the mandatory explicit grounding introduces unnecessary interference with the model's primary objective of answer prediction. To address this problem, we propose Internalizing Visually Grounded Reasoning (\textbf{iVGR}), a novel reinforcement learning framework that transfers localization capabilities into the textual reasoning process. We employ a dual-stream training strategy, where a textual stream is aligned with a high-quality visually grounded stream via a proposed consistency reward, enabling the model to localize accurately without explicit grounding during inference. Extensive experiments demonstrate that our method significantly outperforms existing baselines on fine-grained benchmarks, while maintaining the flexibility to support tool-assisted inference workflows.

Jiawei Liu, Jingyi Xie, Fanrui Zhang et al.

The explosive growth of rumors with text and images on social media platforms has drawn great attention. Existing studies have made significant contributions to cross-modal information interaction and fusion, but they fail to fully explore hierarchical and complex semantic correlation across different modality content, severely limiting their performance on detecting multi-modal rumor. In this work, we propose a novel knowledge-enhanced hierarchical information correlation learning approach (KhiCL) for multi-modal rumor detection by jointly modeling the basic semantic correlation and high-order knowledge-enhanced entity correlation. Specifically, KhiCL exploits cross-modal joint dictionary to transfer the heterogeneous unimodality features into the common feature space and captures the basic cross-modal semantic consistency and inconsistency by a cross-modal fusion layer. Moreover, considering the description of multi-modal content is narrated around entities, KhiCL extracts visual and textual entities from images and text, and designs a knowledge relevance reasoning strategy to find the shortest semantic relevant path between each pair of entities in external knowledge graph, and absorbs all complementary contextual knowledge of other connected entities in this path for learning knowledge-enhanced entity representations. Furthermore, KhiCL utilizes a signed attention mechanism to model the knowledge-enhanced entity consistency and inconsistency of intra-modality and inter-modality entity pairs by measuring their corresponding semantic relevant distance. Extensive experiments have demonstrated the effectiveness of the proposed method.

Dongting Li, Xingyu Chen, Qianyang Wu et al.

Humanoid robots show promise for complex whole-body tasks in unstructured environments. Although Human-Object Interaction (HOI) has advanced, most methods focus on fully actuated objects rigidly coupled to the robot, ignoring underactuated objects with independent dynamics and non-holonomic constraints. These introduce control challenges from coupling forces and occlusions. We present HAIC, a unified framework for robust interaction across diverse object dynamics without external state estimation. Our key contribution is a dynamics predictor that estimates high-order object states (velocity, acceleration) solely from proprioceptive history. These predictions are projected onto static geometric priors to form a spatially grounded dynamic occupancy map, enabling the policy to infer collision boundaries and contact affordances in blind spots. We use asymmetric fine-tuning, where a world model continuously adapts to the student policy's exploration, ensuring robust state estimation under distribution shifts. Experiments on a humanoid robot show HAIC achieves high success rates in agile tasks (skateboarding, cart pushing/pulling under various loads) by proactively compensating for inertial perturbations, and also masters multi-object long-horizon tasks like carrying a box across varied terrain by predicting the dynamics of multiple objects.

Lingbing Guo, Yuqiang Han, Qiang Zhang et al.

Embedding-based methods have attracted increasing attention in recent entity alignment (EA) studies. Although great promise they can offer, there are still several limitations. The most notable is that they identify the aligned entities based on cosine similarity, ignoring the semantics underlying the embeddings themselves. Furthermore, these methods are shortsighted, heuristically selecting the closest entity as the target and allowing multiple entities to match the same candidate. To address these limitations, we model entity alignment as a sequential decision-making task, in which an agent sequentially decides whether two entities are matched or mismatched based on their representation vectors. The proposed reinforcement learning (RL)-based entity alignment framework can be flexibly adapted to most embedding-based EA methods. The experimental results demonstrate that it consistently advances the performance of several state-of-the-art methods, with a maximum improvement of 31.1% on Hits@1.

Wenxuan Zhu, Chao Yu, Qiang Zhang

Deep reinforcement learning (DRL) requires the collection of interventional data, which is sometimes expensive and even unethical in the real world, such as in the autonomous driving and the medical field. Offline reinforcement learning promises to alleviate this issue by exploiting the vast amount of observational data available in the real world. However, observational data may mislead the learning agent to undesirable outcomes if the behavior policy that generates the data depends on unobserved random variables (i.e., confounders). In this paper, we propose two deconfounding methods in DRL to address this problem. The methods first calculate the importance degree of different samples based on the causal inference technique, and then adjust the impact of different samples on the loss function by reweighting or resampling the offline dataset to ensure its unbiasedness. These deconfounding methods can be flexibly combined with existing model-free DRL algorithms such as soft actor-critic and deep Q-learning, provided that a weak condition can be satisfied by the loss functions of these algorithms. We prove the effectiveness of our deconfounding methods and validate them experimentally.

Ikboljon Sobirov, Cheng Xie, Muhammad Siddique et al.

Since the emergence of convolutional neural networks (CNNs) and, later, vision transformers (ViTs), deep learning architectures have predominantly relied on identical block types with varying hyperparameters. We propose a novel block alternation strategy to leverage the complementary strengths of different architectural designs, assembling structurally distinct components similar to Lego blocks. We introduce LegoNet, a deep learning framework that alternates CNN-based and SwinViT-based blocks to enhance feature learning for medical image segmentation. We investigate three variations of LegoNet and apply this concept to a previously unexplored clinical problem: the segmentation of the internal mammary artery (IMA), aorta, and perivascular adipose tissue (PVAT) from computed tomography angiography (CTA) scans. These PVAT regions have been shown to possess prognostic value in assessing cardiovascular risk and primary clinical outcomes. We evaluate LegoNet on large datasets, achieving superior performance to other leading architectures. Furthermore, we assess the model's generalizability on external testing cohorts, where an expert clinician corrects the model's segmentations, achieving DSC > 0.90 across various external, international, and public cohorts. To further validate the model's clinical reliability, we perform intra- and inter-observer variability analysis, demonstrating strong agreement with human annotations. The proposed methodology has significant implications for diagnostic cardiovascular management and early prognosis, offering a robust, automated solution for vascular and perivascular segmentation and risk assessment in clinical practice, paving the way for personalised medicine.

Chen Chen, Yuchen Hu, Qiang Zhang et al.

Audio-visual speech recognition (AVSR) has gained remarkable success for ameliorating the noise-robustness of speech recognition. Mainstream methods focus on fusing audio and visual inputs to obtain modality-invariant representations. However, such representations are prone to over-reliance on audio modality as it is much easier to recognize than video modality in clean conditions. As a result, the AVSR model underestimates the importance of visual stream in face of noise corruption. To this end, we leverage visual modality-specific representations to provide stable complementary information for the AVSR task. Specifically, we propose a reinforcement learning (RL) based framework called MSRL, where the agent dynamically harmonizes modality-invariant and modality-specific representations in the auto-regressive decoding process. We customize a reward function directly related to task-specific metrics (i.e., word error rate), which encourages the MSRL to effectively explore the optimal integration strategy. Experimental results on the LRS3 dataset show that the proposed method achieves state-of-the-art in both clean and various noisy conditions. Furthermore, we demonstrate the better generality of MSRL system than other baselines when test set contains unseen noises.

Qiuchen Wang, Shihang Wang, Yu Zeng et al.

Effectively retrieving, reasoning, and understanding multimodal information remains a critical challenge for agentic systems. Traditional Retrieval-augmented Generation (RAG) methods rely on linear interaction histories, which struggle to handle long-context tasks, especially those involving information-sparse yet token-heavy visual data in iterative reasoning scenarios. To bridge this gap, we introduce VimRAG, a framework tailored for multimodal Retrieval-augmented Reasoning across text, images, and videos. Inspired by our systematic study, we model the reasoning process as a dynamic directed acyclic graph that structures the agent states and retrieved multimodal evidence. Building upon this structured memory, we introduce a Graph-Modulated Visual Memory Encoding mechanism, with which the significance of memory nodes is evaluated via their topological position, allowing the model to dynamically allocate high-resolution tokens to pivotal evidence while compressing or discarding trivial clues. To implement this paradigm, we propose a Graph-Guided Policy Optimization strategy. This strategy disentangles step-wise validity from trajectory-level rewards by pruning memory nodes associated with redundant actions, thereby facilitating fine-grained credit assignment. Extensive experiments demonstrate that VimRAG consistently achieves state-of-the-art performance on diverse multimodal RAG benchmarks. The code is available at https://github.com/Alibaba-NLP/VRAG.

Huakang Chen, Jingbin Hu, Liumeng Xue et al.

Instruction-following text-to-speech (TTS) has emerged as an important capability for controllable and expressive speech generation, yet its evaluation remains underdeveloped due to limited benchmark coverage, weak diagnostic granularity, and insufficient multilingual support. We present \textbf{MINT-Bench}, a comprehensive multilingual benchmark for instruction-following TTS. MINT-Bench is built upon a hierarchical multi-axis taxonomy, a scalable multi-stage data construction pipeline, and a hierarchical hybrid evaluation protocol that jointly assesses content consistency, instruction following, and perceptual quality. Experiments across ten languages show that current systems remain far from solved: frontier commercial systems lead overall, while leading open-source models become highly competitive and can even outperform commercial counterparts in localized settings such as Chinese. The benchmark further reveals that harder compositional and paralinguistic controls remain major bottlenecks for current systems. We release MINT-Bench together with the data construction and evaluation toolkit to support future research on controllable, multilingual, and diagnostically grounded TTS evaluation. The leaderboard and demo are available at https://longwaytog0.github.io/MINT-Bench/

Qiang Zhang, Jason Naradowsky, Yusuke Miyao

We introduce the task of implicit offensive text detection in dialogues, where a statement may have either an offensive or non-offensive interpretation, depending on the listener and context. We argue that reasoning is crucial for understanding this broader class of offensive utterances and release SLIGHT, a dataset to support research on this task. Experiments using the data show that state-of-the-art methods of offense detection perform poorly when asked to detect implicitly offensive statements, achieving only ${\sim} 11\%$ accuracy. In contrast to existing offensive text detection datasets, SLIGHT features human-annotated chains of reasoning which describe the mental process by which an offensive interpretation can be reached from each ambiguous statement. We explore the potential for a multi-hop reasoning approach by utilizing existing entailment models to score the probability of these chains and show that even naive reasoning models can yield improved performance in most situations. Furthermore, analysis of the chains provides insight into the human interpretation process and emphasizes the importance of incorporating additional commonsense knowledge.

Hua Yu, Yaqing Hou, Wenbin Pei et al.

Diverse human motion prediction (HMP) aims to predict multiple plausible future motions given an observed human motion sequence. It is a challenging task due to the diversity of potential human motions while ensuring an accurate description of future human motions. Current solutions are either low-diversity or limited in expressiveness. Recent denoising diffusion models (DDPM) hold potential generative capabilities in generative tasks. However, introducing DDPM directly into diverse HMP incurs some issues. Although DDPM can increase the diversity of the potential patterns of human motions, the predicted human motions become implausible over time because of the significant noise disturbances in the forward process of DDPM. This phenomenon leads to the predicted human motions being hard to control, seriously impacting the quality of predicted motions and restricting their practical applicability in real-world scenarios. To alleviate this, we propose a novel conditional diffusion-based generative model, called DivDiff, to predict more diverse and realistic human motions. Specifically, the DivDiff employs DDPM as our backbone and incorporates Discrete Cosine Transform (DCT) and transformer mechanisms to encode the observed human motion sequence as a condition to instruct the reverse process of DDPM. More importantly, we design a diversified reinforcement sampling function (DRSF) to enforce human skeletal constraints on the predicted human motions. DRSF utilizes the acquired information from human skeletal as prior knowledge, thereby reducing significant disturbances introduced during the forward process. Extensive results received in the experiments on two widely-used datasets (Human3.6M and HumanEva-I) demonstrate that our model obtains competitive performance on both diversity and accuracy.

Yu Qiao, Ziqi Wei, Yuhao Liu et al.

This paper reviews recent deep-learning-based matting research and conceives our wider and higher motivation for image matting. Many approaches achieve alpha mattes with complex encoders to extract robust semantics, then resort to the U-net-like decoder to concatenate or fuse encoder features. However, image matting is essentially a pixel-wise regression, and the ideal situation is to perceive the maximum opacity correspondence from the input image. In this paper, we argue that the high-resolution feature representation, perception and communication are more crucial for matting accuracy. Therefore, we propose an Intensive Integration and Global Foreground Perception network (I2GFP) to integrate wider and higher feature streams. Wider means we combine intensive features in each decoder stage, while higher suggests we retain high-resolution intermediate features and perceive large-scale foreground appearance. Our motivation sacrifices model depth for a significant performance promotion. We perform extensive experiments to prove the proposed I2GFP model, and state-of-the-art results can be achieved on different public datasets.

Zeyuan Wang, Qiang Zhang, Keyan Ding et al.

Large Language Models (LLMs) have revolutionized the field of natural language processing, but they fall short in comprehending biological sequences such as proteins. To address this challenge, we propose InstructProtein, an innovative LLM that possesses bidirectional generation capabilities in both human and protein languages: (i) taking a protein sequence as input to predict its textual function description and (ii) using natural language to prompt protein sequence generation. To achieve this, we first pre-train an LLM on both protein and natural language corpora, enabling it to comprehend individual languages. Then supervised instruction tuning is employed to facilitate the alignment of these two distinct languages. Herein, we introduce a knowledge graph-based instruction generation framework to construct a high-quality instruction dataset, addressing annotation imbalance and instruction deficits in existing protein-text corpus. In particular, the instructions inherit the structural relations between proteins and function annotations in knowledge graphs, which empowers our model to engage in the causal modeling of protein functions, akin to the chain-of-thought processes in natural languages. Extensive experiments on bidirectional protein-text generation tasks show that InstructProtein outperforms state-of-the-art LLMs by large margins. Moreover, InstructProtein serves as a pioneering step towards text-based protein function prediction and sequence design, effectively bridging the gap between protein and human language understanding.

Qiang Zhang, Jason Naradowsky, Yusuke Miyao

Knowing how to end and resume conversations over time is a natural part of communication, allowing for discussions to span weeks, months, or years. The duration of gaps between conversations dictates which topics are relevant and which questions to ask, and dialogue systems which do not explicitly model time may generate responses that are unnatural. In this work we explore the idea of making dialogue models aware of time, and present GapChat, a multi-session dialogue dataset in which the time between each session varies. While the dataset is constructed in real-time, progress on events in speakers' lives is simulated in order to create realistic dialogues occurring across a long timespan. We expose time information to the model and compare different representations of time and event progress. In human evaluation we show that time-aware models perform better in metrics that judge the relevance of the chosen topics and the information gained from the conversation.

Qiang Zhang, Hanchao Yu, Ivan Ji et al.

Recent years have witnessed success of sequential modeling, generative recommender, and large language model for recommendation. Though the scaling law has been validated for sequential models, it showed inefficiency in computational capacity when considering real-world applications like recommendation, due to the non-linear(quadratic) increasing nature of the transformer model. To improve the efficiency of the sequential model, we introduced a novel approach to sequential recommendation that leverages personalization techniques to enhance efficiency and performance. Our method compresses long user interaction histories into learnable tokens, which are then combined with recent interactions to generate recommendations. This approach significantly reduces computational costs while maintaining high recommendation accuracy. Our method could be applied to existing transformer based recommendation models, e.g., HSTU and HLLM. Extensive experiments on multiple sequential models demonstrate its versatility and effectiveness. Source code is available at \href{https://github.com/facebookresearch/PerSRec}{https://github.com/facebookresearch/PerSRec}.

Yi Xiao, Qiangqiang Yuan, Kui Jiang et al.

Recent progress in remote sensing image (RSI) super-resolution (SR) has exhibited remarkable performance using deep neural networks, e.g., Convolutional Neural Networks and Transformers. However, existing SR methods often suffer from either a limited receptive field or quadratic computational overhead, resulting in sub-optimal global representation and unacceptable computational costs in large-scale RSI. To alleviate these issues, we develop the first attempt to integrate the Vision State Space Model (Mamba) for RSI-SR, which specializes in processing large-scale RSI by capturing long-range dependency with linear complexity. To achieve better SR reconstruction, building upon Mamba, we devise a Frequency-assisted Mamba framework, dubbed FMSR, to explore the spatial and frequent correlations. In particular, our FMSR features a multi-level fusion architecture equipped with the Frequency Selection Module (FSM), Vision State Space Module (VSSM), and Hybrid Gate Module (HGM) to grasp their merits for effective spatial-frequency fusion. Considering that global and local dependencies are complementary and both beneficial for SR, we further recalibrate these multi-level features for accurate feature fusion via learnable scaling adaptors. Extensive experiments on AID, DOTA, and DIOR benchmarks demonstrate that our FMSR outperforms state-of-the-art Transformer-based methods HAT-L in terms of PSNR by 0.11 dB on average, while consuming only 28.05% and 19.08% of its memory consumption and complexity, respectively. Code will be available at https://github.com/XY-boy/FreMamba

Qiang Zhang, Jason Naradowsky, Yusuke Miyao

When engaging in conversations, dialogue agents in a virtual simulation environment may exhibit their own emotional states that are unrelated to the immediate conversational context, a phenomenon known as self-emotion. This study explores how such self-emotion affects the agents' behaviors in dialogue strategies and decision-making within a large language model (LLM)-driven simulation framework. In a dialogue strategy prediction experiment, we analyze the dialogue strategy choices employed by agents both with and without self-emotion, comparing them to those of humans. The results show that incorporating self-emotion helps agents exhibit more human-like dialogue strategies. In an independent experiment comparing the performance of models fine-tuned on GPT-4 generated dialogue datasets, we demonstrate that self-emotion can lead to better overall naturalness and humanness. Finally, in a virtual simulation environment where agents have discussions on multiple topics, we show that self-emotion of agents can significantly influence the decision-making process of the agents, leading to approximately a 50% change in decisions.

Hao Cheng, Erjia Xiao, Yichi Wang et al.

Recently, driven by advancements in Multimodal Large Language Models (MLLMs), Vision Language Action Models (VLAMs) are being proposed to achieve better performance in open-vocabulary scenarios for robotic manipulation tasks. Since manipulation tasks involve direct interaction with the physical world, ensuring robustness and safety during the execution of this task is always a very critical issue. In this paper, by synthesizing current safety research on MLLMs and the specific application scenarios of the manipulation task in the physical world, we comprehensively evaluate VLAMs in the face of potential physical threats. Specifically, we propose the Physical Vulnerability Evaluating Pipeline (PVEP) that can incorporate as many visual modal physical threats as possible for evaluating the physical robustness of VLAMs. The physical threats in PVEP specifically include Out-of-Distribution, Typography-based Visual Prompt, and Adversarial Patch Attacks. By comparing the performance fluctuations of VLAMs before and after being attacked, we provide generalizable \textbf{\textit{Analyses}} of how VLAMs respond to different physical threats.

Xiaoyang Jiang, Qiang Zhang, Jingkai Sun et al.

Recent advancements in legged robots using deep reinforcement learning have led to significant progress. Quadruped robots can perform complex tasks in challenging environments, while bipedal and humanoid robots have also achieved breakthroughs. Current reinforcement learning methods leverage diverse robot bodies and historical information to perform actions, but previous research has not emphasized the speed and energy consumption of network inference and the biological significance of neural networks. Most networks are traditional artificial neural networks that utilize multilayer perceptrons (MLP). This paper presents a novel Spiking Neural Network (SNN) for legged robots, showing exceptional performance in various simulated terrains. SNNs provide natural advantages in inference speed and energy consumption, and their pulse-form processing enhances biological interpretability. This study presents a highly efficient SNN for legged robots that can be seamless integrated into other learning models.

Zelin Tao, Zeran Su, Peiran Liu et al.

Achieving general-purpose humanoid control requires a delicate balance between the precise execution of commanded motions and the flexible, anthropomorphic adaptability needed to recover from unpredictable environmental perturbations. Current general controllers predominantly formulate motion control as a rigid reference-tracking problem. While effective in nominal conditions, these trackers often exhibit brittle, non-anthropomorphic failure modes under severe disturbances, lacking the generative adaptability inherent to human motor control. To overcome this limitation, we propose Heracles, a novel state-conditioned diffusion middleware that bridges precise motion tracking and generative synthesis. Rather than relying on rigid tracking paradigms or complex explicit mode-switching, Heracles operates as an intermediary layer between high-level reference motions and low-level physics trackers. By conditioning on the robot's real-time state, the diffusion model implicitly adapts its behavior: it approximates an identity map when the state closely aligns with the reference, preserving zero-shot tracking fidelity. Conversely, when encountering significant state deviations, it seamlessly transitions into a generative synthesizer to produce natural, anthropomorphic recovery trajectories. Our framework demonstrates that integrating generative priors into the control loop not only significantly enhances robustness against extreme perturbations but also elevates humanoid control from a rigid tracking paradigm to an open-ended, generative general-purpose architecture.

Panfeng Cao, Ye Wang, Qiang Zhang et al.

Key information extraction (KIE) from scanned documents has gained increasing attention because of its applications in various domains. Although promising results have been achieved by some recent KIE approaches, they are usually built based on discriminative models, which lack the ability to handle optical character recognition (OCR) errors and require laborious token-level labelling. In this paper, we propose a novel generative end-to-end model, named GenKIE, to address the KIE task. GenKIE is a sequence-to-sequence multimodal generative model that utilizes multimodal encoders to embed visual, layout and textual features and a decoder to generate the desired output. Well-designed prompts are leveraged to incorporate the label semantics as the weakly supervised signals and entice the generation of the key information. One notable advantage of the generative model is that it enables automatic correction of OCR errors. Besides, token-level granular annotation is not required. Extensive experiments on multiple public real-world datasets show that GenKIE effectively generalizes over different types of documents and achieves state-of-the-art results. Our experiments also validate the model's robustness against OCR errors, making GenKIE highly applicable in real-world scenarios.

Pratyaksh Prabhav Rao, Feng Qiao, Weide Zhang et al.

Accurate segmentation of power lines in aerial images is essential to ensure the flight safety of aerial vehicles. Acquiring high-quality ground truth annotations for training a deep learning model is a laborious process. Therefore, developing algorithms that can leverage knowledge from labelled synthetic data to unlabelled real images is highly demanded. This process is studied in Unsupervised domain adaptation (UDA). Recent approaches to self-training have achieved remarkable performance in UDA for semantic segmentation, which trains a model with pseudo labels on the target domain. However, the pseudo labels are noisy due to a discrepancy in the two data distributions. We identify that context dependency is important for bridging this domain gap. Motivated by this, we propose QuadFormer, a novel framework designed for domain adaptive semantic segmentation. The hierarchical quadruple transformer combines cross-attention and self-attention mechanisms to adapt transferable context. Based on cross-attentive and self-attentive feature representations, we introduce a pseudo label correction scheme to online denoise the pseudo labels and reduce the domain gap. Additionally, we present two datasets - ARPLSyn and ARPLReal to further advance research in unsupervised domain adaptive powerline segmentation. Finally, experimental results indicate that our method achieves state-of-the-art performance for the domain adaptive power line segmentation on ARPLSyn$\rightarrow$TTTPLA and ARPLSyn$\rightarrow$ARPLReal.

Qiang Zhang, Zhongnian Li

Binary decompilation is a critical reverse engineering task aimed at reconstructing high-level source code from stripped executables. Although Large Language Models (LLMs) have recently shown promise, they often suffer from "logical hallucinations" and "semantic misalignment" due to the irreversible semantic loss during compilation, resulting in generated code that fails to re-execute. In this study, we propose Cognitive Decompiler Refinement with Robustness (CoDe-R), a lightweight two-stage code refinement framework. The first stage introduces Semantic Cognitive Enhancement (SCE), a Rationale-Guided Semantic Injection strategy that trains the model to recover high-level algorithmic intent alongside code. The second stage introduces a Dynamic Dual-Path Fallback (DDPF) mechanism during inference, which adaptively balances semantic recovery and syntactic stability via a hybrid verification strategy. Evaluation on the HumanEval-Decompile benchmark demonstrates that CoDe-R (using a 1.3B backbone) establishes a new State-of-the-Art (SOTA) in the lightweight regime. Notably, it is the first 1.3B model to exceed an Average Re-executability Rate of 50.00%, significantly outperforming the baseline and effectively bridging the gap between efficient models and expert-level performance. Our code is available at https://github.com/Theaoi/CoDe-R.

Yi Xiao, Qiangqiang Yuan, Qiang Zhang et al.

Recent efforts have witnessed remarkable progress in Satellite Video Super-Resolution (SVSR). However, most SVSR methods usually assume the degradation is fixed and known, e.g., bicubic downsampling, which makes them vulnerable in real-world scenes with multiple and unknown degradations. To alleviate this issue, blind SR has thus become a research hotspot. Nevertheless, existing approaches are mainly engaged in blur kernel estimation while losing sight of another critical aspect for VSR tasks: temporal compensation, especially compensating for blurry and smooth pixels with vital sharpness from severely degraded satellite videos. Therefore, this paper proposes a practical Blind SVSR algorithm (BSVSR) to explore more sharp cues by considering the pixel-wise blur levels in a coarse-to-fine manner. Specifically, we employed multi-scale deformable convolution to coarsely aggregate the temporal redundancy into adjacent frames by window-slid progressive fusion. Then the adjacent features are finely merged into mid-feature using deformable attention, which measures the blur levels of pixels and assigns more weights to the informative pixels, thus inspiring the representation of sharpness. Moreover, we devise a pyramid spatial transformation module to adjust the solution space of sharp mid-feature, resulting in flexible feature adaptation in multi-level domains. Quantitative and qualitative evaluations on both simulated and real-world satellite videos demonstrate that our BSVSR performs favorably against state-of-the-art non-blind and blind SR models. Code will be available at https://github.com/XY-boy/Blind-Satellite-VSR

Jiahao Ma, Qiang Zhang, Peiran Liu et al.

Surround-view perception is increasingly important for robotic navigation and loco-manipulation, especially in human-in-the-loop settings such as teleoperation, data collection, and emergency takeover. However, current robotic visual interfaces are often limited to narrow forward-facing views, or, when multiple on-board cameras are available, require cumbersome manual switching that interrupts the operator's workflow. Both configurations suffer from motion-induced jitter that causes simulator sickness in head-mounted displays. We introduce a surround-view robotic vision system that combines six cameras with LiDAR to provide full 360$^\circ$ visual coverage, while meeting the geometric and real-time constraints of embodied deployment. We further present \textsc{RobotPan}, a feed-forward framework that predicts \emph{metric-scaled} and \emph{compact} 3D Gaussians from calibrated sparse-view inputs for real-time rendering, reconstruction, and streaming. \textsc{RobotPan} lifts multi-view features into a unified spherical coordinate representation and decodes Gaussians using hierarchical spherical voxel priors, allocating fine resolution near the robot and coarser resolution at larger radii to reduce computational redundancy without sacrificing fidelity. To support long sequences, our online fusion updates dynamic content while preventing unbounded growth in static regions by selectively updating appearance. Finally, we release a multi-sensor dataset tailored to 360$^\circ$ novel view synthesis and metric 3D reconstruction for robotics, covering navigation, manipulation, and locomotion on real platforms. Experiments show that \textsc{RobotPan} achieves competitive quality against prior feed-forward reconstruction and view-synthesis methods while producing substantially fewer Gaussians, enabling practical real-time embodied deployment. Project website: https://robotpan.github.io/

Jiaxu Wang, Junhao He, Jingkai Sun et al.

Learning real-world dynamics from visual observations is crucial for various domains. A common strategy is to calibrate simulators by estimating physical parameters, yet accuracy is ultimately bounded by the underlying physical models, which often assume materials are homogeneous and isotropic. Even if reasonable, real-world objects typically exhibit mild anisotropy and heterogeneity. After the near-isotropic backbone is well calibrated, these residual effects become the key bottleneck for further closing the real-to-sim gap. Although neural networks can fit dynamics end-to-end, such black-box modeling discards strong physical priors, leading to poor data efficiency and overfitting. Therefore, we propose MoSA, a motion-constrained stress adaptation framework that targets these residual effects to further improve real-to-sim dynamics learning. MoSA uses an isotropic model as a physics prior and learns residual stress operators to capture mild anisotropy and heterogeneity. It progressively adapts stresses via microplane-constrained redistribution in a physics-informed cascaded network. We further impose motion constraints by supervising temporal and spatial derivatives of the deformation field. Experimentally, our learned dynamics achieves superior accuracy, generalization, and robustness, while learning physically meaningful residual anisotropy. Finally, we validate MoSA in a robot manipulation setting, showing that better real-to-sim dynamics modeling translates into more reliable sim-to-real transfer. Project Page is available at https://mercerai.github.io/MoSA/.

Yuan Xu, Jiabing Yang, Xiaofeng Wang et al.

Imitation learning based visuomotor policies have achieved strong performance in robotic manipulation, yet they often remain sensitive to egocentric viewpoint shifts. Unlike third-person viewpoint changes that only move the camera, egocentric shifts simultaneously alter both the camera pose and the robot action coordinate frame, making it necessary to jointly transfer action trajectories and synthesize corresponding observations under novel egocentric viewpoints. To address this challenge, we present EgoDemoGen, a framework that generates paired observation--action demonstrations under novel egocentric viewpoints through two key components: 1{)} EgoTrajTransfer, which transfers robot trajectories to the novel egocentric coordinate frame through motion-skill segmentation, geometry-aware transformation, and inverse kinematics filtering; and 2{)} EgoViewTransfer, a conditional video generation model that fuses a novel-viewpoint reprojected scene video and a robot motion video rendered from the transferred trajectory to synthesize photorealistic observations, trained with a self-supervised double reprojection strategy without requiring multi-viewpoint data. Experiments in simulation and real-world settings show that EgoDemoGen consistently improves policy success rates under both standard and novel egocentric viewpoints, with absolute gains of +24.6\% and +16.9\% in simulation and +16.0\% and +23.0\% on the real robot. Moreover, EgoViewTransfer achieves superior video generation quality for novel egocentric observations.

Shuofei Qiao, Yunxiang Wei, Jiazheng Fan et al.

The exponential growth of global academic output has confronted researchers and AI agents with an unprecedented ``information explosion,'' where fragmented and unstructured knowledge organization impedes deep interdisciplinary integration. Current academic retrieval tools predominantly rely on superficial keyword matching or vector-space semantic retrieval, which lack the topological reasoning capabilities required to navigate complex logical connections. Agentic deep-research-based frameworks are often prone to logical hallucinations and consuming high inference costs. To bridge this gap, in this report, we introduce SciAtlas, a large-scale, multi-disciplinary, heterogeneous academic resource knowledge graph designed as a panoramic scientific evolution network. By integrating over 43M papers from 26 disciplines, and a total of 157M entities and 3B triplets, SciAtlas provides a structured topological cognitive substrate that dismantles disciplinary barriers and furnishes AI agents with a global perspective. Furthermore, we develop a neuro-symbolic retrieval algorithm featuring tri-path collaborative recall and graph reranking, achieving a seamless transition from simple semantic matching to deterministic association discovery. We also present key application directions of SciAtlas, including literature review, automated research trend synthesis, idea positioning, and academic trajectory exploration, to demonstrate that SciAtlas can serve as an effective ``cognitive map'' to empower the full loop of automated scientific research while significantly reducing reasoning costs. We have released the interfaces for KG retrieval and various downstream tasks in our GitHub repo.