Visual AutoRegressive (VAR) models based on next-scale prediction enable efficient hierarchical generation, yet the inference cost grows quadratically at high resolutions. We observe that the computationally intensive later scales predominantly refine high-frequency textures and exhibit substantial spatial redundancy, in contrast to earlier scales that determine the global structural layout. Existing pruning methods primarily focus on high-frequency detection for token selection, often overlooking structural coherence and consequently degrading global semantics. To address this limitation, we propose StepVAR, a training-free token pruning framework that accelerates VAR inference by jointly considering structural and textural importance. Specifically, we employ a lightweight high-pass filter to capture local texture details, while leveraging Principal Component Analysis (PCA) to preserve global structural information. This dual-criterion design enables the model to retain tokens critical for both fine-grained fidelity and overall composition. To maintain valid next-scale prediction under sparse tokens, we further introduce a nearest neighbor feature propagation strategy to reconstruct dense feature maps from pruned representations. Extensive experiments on state-of-the-art text-to-image and text-to-video VAR models demonstrate that StepVAR achieves substantial inference speedups while maintaining generation quality. Quantitative and qualitative evaluations consistently show that our method outperforms existing acceleration approaches, validating its effectiveness and general applicability across diverse VAR architectures.

DNA sequence classification is pivotal in genomics and bioinformatics for elucidating biological functions and diseases. Traditional sequence alignment methods, while precise, face significant challenges when applied to extensive, diverse datasets due to their computational intensity and limitations in scalability. To this end, digital encoding techniques transform DNA into vectors suitable for machine learning. However, these approaches often lose essential sequential or structural information, affecting the classification accuracy. In this work, we propose a novel approach, Single-Source Dual-stream representation learning (SSD), to enhance DNA sequence classification. SSD achieves this by extracting two pseudo-modalities from single-source data and integrating them into a dual-stream representation. Specifically, SSD regards DNA sequence as text and its Frequency Chaos Game Representation (FCGR) as image, effectively reframing DNA classification as a multi-modal learning task to capture diverse feature perspectives. We use BERT for DNA sequence text and Vision Transformer (ViT) for FCGR image encoding, with pre-training to capture information from both scales and obtain more generalized representations. Subsequently, an adaptive fusion module is designed to fuse the dual-stream representations before hierarchical classification to fully exploit the strengths of both modalities. Extensive experiments on three datasets reveal that SSD outperforms existing methods, highlighting its robust generalization and potential for novel genomic discoveries. Code is available at https://github.com/jiaruizhou/SSD.

Pre-trained vision-language models (VLMs) have shown remarkable generalization capabilities via prompting, which leverages VLMs as knowledge bases to extract information beneficial for downstream tasks. However, existing methods primarily employ uni-modal prompting, which only engages a uni-modal branch, failing to simultaneously adjust vision-language (V-L) features. Additionally, the one-pass forward pipeline in VLM encoding struggles to align V-L features that have a huge gap. Confronting these challenges, we propose a novel method, Progressive Multi-modal conditional Prompt Tuning (ProMPT). ProMPT exploits a recurrent structure, optimizing and aligning V-L features by iteratively utilizing image and current encoding information. It comprises an initialization and a multi-modal iterative evolution (MIE) module. Initialization is responsible for encoding images and text using a VLM, followed by a feature filter that selects text features similar to image. MIE then facilitates multi-modal prompting through class-conditional vision prompting, instance-conditional text prompting, and feature filtering. In each MIE iteration, vision prompts are obtained from filtered text features via a vision generator, promoting image features to focus more on target object during vision prompting. The encoded image features are fed into a text generator to produce text prompts that are more robust to class shifts. Thus, V-L features are progressively aligned, enabling advance from coarse to exact prediction. Extensive experiments are conducted in three settings to evaluate the efficacy of ProMPT. The results indicate that ProMPT outperforms existing methods on average across all settings, demonstrating its superior generalization and robustness. Code is available at https://github.com/qiuxiaoyu9954/ProMPT.

Knowledge graph embedding (KGE) is an efficient and scalable method for knowledge graph completion tasks. Existing KGE models typically map entities and relations into a unified continuous vector space and define a score function to capture the connectivity patterns among the elements (entities and relations) of facts. The score on a fact measures its plausibility in a knowledge graph (KG). However, since the connectivity patterns are very complex in a real knowledge graph, it is difficult to define an explicit and efficient score function to capture them, which also limits their performance. This paper argues that plausible facts in a knowledge graph come from a distribution in the low-dimensional fact space. Inspired by this insight, this paper proposes a novel framework called Fact Embedding through Diffusion Model (FDM) to address the knowledge graph completion task. Instead of defining a score function to measure the plausibility of facts in a knowledge graph, this framework directly learns the distribution of plausible facts from the known knowledge graph and casts the entity prediction task into the conditional fact generation task. Specifically, we concatenate the elements embedding in a fact as a whole and take it as input. Then, we introduce a Conditional Fact Denoiser to learn the reverse denoising diffusion process and generate the target fact embedding from noised data. Extensive experiments demonstrate that FDM significantly outperforms existing state-of-the-art methods in three benchmark datasets.

Molecular pre-training, which is about to learn an effective representation for molecules on large amount of data, has attracted substantial attention in cheminformatics and bioinformatics. A molecule can be viewed as either a graph (where atoms are connected by bonds) or a SMILES sequence (where depth-first-search is applied to the molecular graph with specific rules). The Transformer and graph neural networks (GNN) are two representative methods to deal with the sequential data and the graphic data, which can globally and locally model the molecules respectively and are supposed to be complementary. In this work, we propose to leverage both representations and design a new pre-training algorithm, dual-view molecule pre-training (briefly, DVMP), that can effectively combine the strengths of both types of molecule representations. DVMP has a Transformer branch and a GNN branch, and the two branches are pre-trained to maintain the semantic consistency of molecules. After pre-training, we can use either the Transformer branch (this one is recommended according to empirical results), the GNN branch, or both for downstream tasks. DVMP is tested on 11 molecular property prediction tasks and outperforms strong baselines. Furthermore, we test DVMP on three retrosynthesis tasks and it achieves state-of-the-art results. Our code is released at https://github.com/microsoft/DVMP.

The increased integration of renewable energy poses a slew of technical challenges for the operation of power distribution networks. Among them, voltage fluctuations caused by the instability of renewable energy are receiving increasing attention. Utilizing MARL algorithms to coordinate multiple control units in the grid, which is able to handle rapid changes of power systems, has been widely studied in active voltage control task recently. However, existing approaches based on MARL ignore the unique nature of the grid and achieve limited performance. In this paper, we introduce the transformer architecture to extract representations adapting to power network problems and propose a Transformer-based Multi-Agent Actor-Critic framework (T-MAAC) to stabilize voltage in power distribution networks. In addition, we adopt a novel auxiliary-task training process tailored to the voltage control task, which improves the sample efficiency and facilitating the representation learning of the transformer-based model. We couple T-MAAC with different multi-agent actor-critic algorithms, and the consistent improvements on the active voltage control task demonstrate the effectiveness of the proposed method.

Molecular representation learning has attracted much attention recently. A molecule can be viewed as a 2D graph with nodes/atoms connected by edges/bonds, and can also be represented by a 3D conformation with 3-dimensional coordinates of all atoms. We note that most previous work handles 2D and 3D information separately, while jointly leveraging these two sources may foster a more informative representation. In this work, we explore this appealing idea and propose a new representation learning method based on a unified 2D and 3D pre-training. Atom coordinates and interatomic distances are encoded and then fused with atomic representations through graph neural networks. The model is pre-trained on three tasks: reconstruction of masked atoms and coordinates, 3D conformation generation conditioned on 2D graph, and 2D graph generation conditioned on 3D conformation. We evaluate our method on 11 downstream molecular property prediction tasks: 7 with 2D information only and 4 with both 2D and 3D information. Our method achieves state-of-the-art results on 10 tasks, and the average improvement on 2D-only tasks is 8.3%. Our method also achieves significant improvement on two 3D conformation generation tasks.

Rate adaption is one of the decisive factors for the applications of video compression. However, previous deep video compression methods are usually optimized for a single fixed rate-distortion (R-D) tradeoff. While they can achieve multiple bitrates by training multiple independent models, the realized bitrates are limited to several discrete points on the R-D curve and the storage cost increases proportionally to the number of models. In this paper, we propose a variable-rate scheme for deep video compression, which can achieve continuously variable rate by a single model, i.e., it can reach any point on the R-D curve. In our scheme, two deep auto-encoders are used to compress the residual and the motion vector field respectively, which directly generate the final bitstream. The basic rate adaptation can be achieved by using the R-D tradeoff parameter to deeply modulate all the internal feature maps of the auto-encoders. However, other modules in our scheme, notably motion estimation and motion compensation, also affect the final bitrate indirectly. We further use the R-D tradeoff parameter to modulate them via a conditional map, which effectively improves the compression efficiency. We use a multi-rate-distortion loss function together with a step-by-step training strategy to optimize the entire scheme. Our experiments show that the proposed scheme achieves continuously variable rate by a single model with almost the same compression efficiency as multiple fixed-rate models. The additional parameters and computation of our model are negligible when compared with a single fixed-rate model.

The micro-video recommendation system becomes an essential part of the e-commerce platform, which helps disseminate micro-videos to potentially interested users. Existing micro-video recommendation methods only focus on users' browsing behaviors on micro-videos, but ignore their purchasing intentions in the e-commerce environment. Thus, they usually achieve unsatisfied e-commerce micro-video recommendation performances. To address this problem, we design a sequential multi-modal information transfer network (SEMI), which utilizes product-domain user behaviors to assist micro-video recommendations. SEMI effectively selects relevant items (i.e., micro-videos and products) with multi-modal features in the micro-video domain and product domain to characterize users' preferences. Moreover, we also propose a cross-domain contrastive learning (CCL) algorithm to pre-train sequence encoders for modeling users' sequential behaviors in these two domains. The objective of CCL is to maximize a lower bound of the mutual information between different domains. We have performed extensive experiments on a large-scale dataset collected from Taobao, a world-leading e-commerce platform. Experimental results show that the proposed method achieves significant improvements over state-of-the-art recommendation methods. Moreover, the proposed method has also been deployed on Taobao, and the online A/B testing results further demonstrate its practical value.

In this paper, we first extend the video-based point cloud compression (V-PCC) to support the plenoptic point cloud compression by generating multiple attribute videos. Then based on the observation that these videos from multiple views have very high correlations, we propose encoding them using multiview high efficiency video coding. We further propose a block-based padding method that unifies the unoccupied attribute pixels from different views to reduce their bit cost.

In this paper, we present a novel pseudo sequence based 2-D hierarchical reference structure for light-field image compression. In the proposed scheme, we first decompose the light-field image into multiple views and organize them into a 2-D coding structure according to the spatial coordinates of the corresponding microlens. Then we mainly develop three technologies to optimize the 2-D coding structure. First, we divide all the views into four quadrants, and all the views are encoded one quadrant after another to reduce the reference buffer size as much as possible. Inside each quadrant, all the views are encoded hierarchically to fully exploit the correlations between different views. Second, we propose to use the distance between the current view and its reference views as the criteria for selecting better reference frames for each inter view. Third, we propose to use the spatial relative positions between different views to achieve more accurate motion vector scaling. The whole scheme is implemented in the reference software of High Efficiency Video Coding. The experimental results demonstrate that the proposed novel pseudo-sequence based 2-D hierarchical structure can achieve maximum 14.2% bit-rate savings compared with the state-of-the-art light-field image compression method.

We demonstrate a video captioning bot, named Seeing Bot, which can generate a natural language description about what it is seeing in near real time. Specifically, given a live streaming video, Seeing Bot runs two pre-learned and complementary captioning modules in parallel - one for generating image-level caption for each sampled frame, and the other for generating video-level caption for each sampled video clip. In particular, both the image and video captioning modules are boosted by incorporating semantic attributes which can enrich the generated descriptions, leading to human-level caption generation. A visual-semantic embedding model is then exploited to rank and select the final caption from the two parallel modules by considering the semantic relevance between video content and the generated captions. The Seeing Bot finally converts the generated description to speech and sends the speech to an end user via an earphone. Our demonstration is conducted on any videos in the wild and supports live video captioning.

Similarity search is one of the fundamental problems for large scale multimedia applications. Hashing techniques, as one popular strategy, have been intensively investigated owing to the speed and memory efficiency. Recent research has shown that leveraging supervised information can lead to high quality hashing. However, most existing supervised methods learn hashing function by treating each training example equally while ignoring the different semantic degree related to the label, i.e. semantic confidence, of different examples. In this paper, we propose a novel semi-supervised hashing framework by leveraging semantic confidence. Specifically, a confidence factor is first assigned to each example by neighbor voting and click count in the scenarios with label and click-through data, respectively. Then, the factor is incorporated into the pairwise and triplet relationship learning for hashing. Furthermore, the two learnt relationships are seamlessly encoded into semi-supervised hashing methods with pairwise and listwise supervision respectively, which are formulated as minimizing empirical error on the labeled data while maximizing the variance of hash bits or minimizing quantization loss over both the labeled and unlabeled data. In addition, the kernelized variant of semi-supervised hashing is also presented. We have conducted experiments on both CIFAR-10 (with label) and Clickture (with click data) image benchmarks (up to one million image examples), demonstrating that our approaches outperform the state-of-the-art hashing techniques.

Hand posture recognition (HPR) is quite a challenging task, due to both the difficulty in detecting and tracking hands with normal cameras and the limitations of traditional manually selected features. In this article, we propose a two-stage HPR system for Sign Language Recognition using a Kinect sensor. In the first stage, we propose an effective algorithm to implement hand detection and tracking. The algorithm incorporates both color and depth information, without specific requirements on uniform-colored or stable background. It can handle the situations in which hands are very close to other parts of the body or hands are not the nearest objects to the camera and allows for occlusion of hands caused by faces or other hands. In the second stage, we apply deep neural networks (DNNs) to automatically learn features from hand posture images that are insensitive to movement, scaling, and rotation. Experiments verify that the proposed system works quickly and accurately and achieves a recognition accuracy as high as 98.12%.

One of the fundamental problems in image search is to rank image documents according to a given textual query. Existing search engines highly depend on surrounding texts for ranking images, or leverage the query-image pairs annotated by human labelers to train a series of ranking functions. However, there are two major limitations: 1) the surrounding texts are often noisy or too few to accurately describe the image content, and 2) the human annotations are resourcefully expensive and thus cannot be scaled up. We demonstrate in this paper that the above two fundamental challenges can be mitigated by jointly exploring the cross-view learning and the use of click-through data. The former aims to create a latent subspace with the ability in comparing information from the original incomparable views (i.e., textual and visual views), while the latter explores the largely available and freely accessible click-through data (i.e., ``crowdsourced" human intelligence) for understanding query. Specifically, we propose a novel cross-view learning method for image search, named Click-through-based Cross-view Learning (CCL), by jointly minimizing the distance between the mappings of query and image in the latent subspace and preserving the inherent structure in each original space. On a large-scale click-based image dataset, CCL achieves the improvement over Support Vector Machine-based method by 4.0\% in terms of relevance, while reducing the feature dimension by several orders of magnitude (e.g., from thousands to tens). Moreover, the experiments also demonstrate the superior performance of CCL to several state-of-the-art subspace learning techniques.

We propose a novel low bit-rate compression scheme with sub pixel-based down-sampling and reconstruction (SPDR) for full color images. In the encoder stage, a decoder-dependent multi-channel sub pixel-based down-sampling is proposed, which is more effective in retaining high frequency detail than conventional pixel-based process. The decoder first decompresses the low-resolution image and then up-converts it to the original resolution using encoder dependent sub pixel-based reconstruction scheme by jointly considering the sub pixel-based down-sampling effect and the compression degradation. Compared to existing algorithms with comparable encoder and decoder complexity, the proposed SPDR offers complete standard compliance, competitive rate-distortion performance, and superior subjective quality.