48 accepted papers
Text-to-Audio-Video (T2AV) generation is rapidly becoming a core interface for media creation, yet its evaluation remains fragmented. Existing benchmarks largely assess audio and video in isolation or rely on coarse embedding similarity, failing to capture fine-grained joint correctness required by …
While on-policy distillation offers dense supervision for training small reasoning models, its optimization dynamics in the multimodal domain remain under-explored. In this work, we challenge the standard monolithic view of Vision-Language Model (VLM) distillation by mathematically decomposing the l…
Recent advances in trajectory-controllable video generation have achieved remarkable progress. Previous methods mainly use adapter-based architectures for precise motion control along predefined trajectories.However, all these methods rely on a multi-step denoising process, leading to substantial ti
Current diffusion-based acceleration methods for long-portrait animation struggle to ensure identity (ID) consistency. This paper presents FlashPortrait, an end-to-end video diffusion transformer capable of synthesizing ID-preserving, infinite-length videos while achieving up to 6xacceleration in in
Text-to-video generation poses significant challenges due to the inherent complexity of video data, which spans both temporal and spatial dimensions. It introduces additional redundancy, abrupt variations, and a domain gap between language and vision tokens while generation. Addressing these challen
CLIP is a seminal multimodal model that maps images and text into a shared representation space by contrastive learning on billions of image–caption pairs. Inspired by the rapid progress of large language models (LLMs), we investigate how the superior linguistic understanding and broad world knowled
Despite recent progress, video diffusion models still struggle to synthesize realistic videos involving highly dynamic motions or requiring fine-grained motion controllability. A central limitation lies in the scarcity of such examples in commonly used training datasets. To address this, we introduc
Reinforcement Learning with Verifiable Rewards (RLVR) traditionally relies on a sparse, outcome-based signal. Recent work shows that providing a fine-grained, model-intrinsic signal--rewarding the confidence growth in the ground-truth answer--effectively improves language reasoning training by provi
LLM-based deep research agents are largely built on the ReAct framework. This linear design makes it difficult to revisit earlier states, branch into alternative search directions, or maintain global awareness under long contexts, often leading to local optima, redundant exploration, and inefficient…
Latent Diffusion Models (LDMs) inherently follow a coarse-to-fine generation process, where high-level semantic structure is generated slightly earlier than fine-grained texture. This indicates the preceding semantics potentially benefit the texture generation by providing a semantic anchor. Recent
Supervised fine-tuning (SFT) is computationally efficient but often yields inferior generalization compared to reinforcement learning (RL). This gap is primarily driven by RL’s use of on-policy data. We propose a framework to bridge this chasm by enabling On-Policy SFT. We first present ***Distribut…
We present $\textit{Video-in-the-Loop}$ (ViTL), a two-stage long-video QA framework that preserves a fixed token budget by first $\textit{localizing}$ question-relevant interval(s) with a low-fps skim and then $\textit{answering}$ via span-aware reallocation of visual tokens at higher effective fram…
Text-guided video prediction (TVP) involves predicting the motion of future frames from the initial frame according to an instruction, which has wide applications in virtual reality, robotics, and content creation. Previous TVP methods make significant breakthroughs by adapting Stable Diffusion for…
Recent advances in diffusion-based generative models have demonstrated superior performance in subject-driven image generation. Identity (ID) preserving image generation, as a subtask of subject-driven image generation, aims to generate customized images for specific human identity and has broad app…
Estimating frequencies of damped sinusoids is the underlying problem of many practical applications. Existing algorithms are often inaccurate for estimating frequencies from damped sinusoids since many of them are designed for undamped signals. In this paper we propose an algorithm to estimate frequ…
We present FloVD, a novel video diffusion model for camera-controllable video generation. FloVD leverages optical flow to represent the motions of the camera and moving objects. This approach offers two key benefits. Since optical flow can be directly estimated from videos, our approach allows for t…
In this paper, we present HomoGen, an enhanced video inpainting method based on homography propagation and diffusion models. HomoGen leverages homography registration to propagate contextual pixels as priors for generating missing content in corrupted videos. Unlike previous flow-based propagation m…
We present JointDiT, a diffusion transformer that models the joint distribution of RGB and depth. By leveraging the architectural benefit and outstanding image prior of the state-of-the-art diffusion transformer, JointDiT not only generates high-fidelity images but also produces geometrically plausi…
Recent advances in video generation have led to remarkable improvements in visual quality and temporal coherence. Upon this, trajectory-controllable video generation has emerged to enable precise object motion control through explicitly defined spatial paths.However, existing methods struggle with c…
Despite impressive advancements in diffusion-based video editing models in altering video attributes, there has been limited exploration into modifying motion information while preserving the original protagonist's appearance and background. In this paper, we propose MotionFollower, a score-guided d…
Commercial video generation models have exhibited realistic, high-fidelity results but are still restricted to limited access.One crucial obstacle for large-scale applications is the expensive training and inference cost.In this paper, we argue that videos contain significantly more redundant inform…
Current diffusion models for human image animation struggle to ensure identity (ID) consistency. This paper presents StableAnimator, the first end-to-end ID-preserving video diffusion framework, which synthesizes high-quality videos without any post-processing, conditioned on a reference image and a…
Modern vision models are trained on very large noisy datasets. While these models acquire strong capabilities, they may not follow the user's intent to output the desired results in certain aspects, e.g., visual aesthetic, preferred style, and responsibility. In this paper, we target the realm of vi…
Graph Convolutional Networks (GCNs) have long set the state-of-the-art in skeleton-based action recognition leveraging their ability to unravel the complex dynamics of human joint topology through the graph's adjacency matrix. However an inherent flaw has come to light in these cutting-edge models:…
Vision-and-Language Navigation (VLN) aims to develop embodied agents that navigate based on human instructions. However, current VLN frameworks often rely on static environments and optimal expert supervision, limiting their real-world applicability. To address this, we introduce Human-Aware Vision-…
We present MicroCinema a straightforward yet effective framework for high-quality and coherent text-to-video generation. Unlike existing approaches that align text prompts with video directly MicroCinema introduces a Divide-and-Conquer strategy which divides the text-to-video into a two-stage proces…
Existing diffusion-based video editing models have made gorgeous advances for editing attributes of a source video over time but struggle to manipulate the motion information while preserving the original protagonist's appearance and background. To address this we propose MotionEditor the first diff…
The recent wave of AI-generated content has witnessed the great development and success of Text-to-Image (T2I) technologies. By contrast Text-to-Video (T2V) still falls short of expectations though attracting increasing interest. Existing works either train from scratch or adapt large T2I model to v…
We introduce AiT, a unified output representation for various vision tasks, which is a crucial step towards general-purpose vision task solvers. Despite the challenges posed by the high-dimensional and task-specific outputs, we showcase the potential of using discrete representation (VQ-VAE) to mode…
Charts are a powerful tool for visually conveying complex data, but their comprehension poses a challenge due to the diverse chart types and intricate components. Existing chart comprehension methods suffer from either heuristic rules or an over-reliance on OCR systems, resulting in suboptimal perfo…
There has been a debate on the choice of plain vs. hierarchical vision transformers, where researchers often believe that the former (e.g., ViT) has a simpler design but the latter (e.g., Swin) enjoys higher recognition accuracy. Recently, the emerge of masked image modeling (MIM), a self-supervised…
Contrastive language-image pretraining (CLIP) has demonstrated remarkable success in various image tasks. However, how to extend CLIP with effective temporal modeling is still an open and crucial problem. Existing factorized or joint spatial-temporal modeling trades off between the efficiency and pe…
Scaling properties have been one of the central issues in self-supervised pre-training, especially the data scalability, which has successfully motivated the large-scale self-supervised pre-trained language models and endowed them with significant modeling capabilities. However, scaling properties s…
In order to reveal the rationale behind model predictions, many works have exploited providing explanations in various forms. Recently, to further guarantee readability, more and more works turn to generate sentence-level human language explanations. However, current works pursuing sentence- level e…
Vision Transformers (ViTs) have achieved overwhelming success, yet they suffer from vulnerable resolution scalability, i.e., the performance drops drastically when presented with input resolutions that are unseen during training. We introduce, ResFormer, a framework that is built upon the seminal id…
Semi-supervised action recognition is a challenging but critical task due to the high cost of video annotations. Existing approaches mainly use convolutional neural networks, yet current revolutionary vision transformer models have been less explored. In this paper, we investigate the use of transfo…
Unit-modulus constrained optimization is frequently encountered in many engineering problems. In our recent study for massive MIMO precoding, we devised a penalty method for unit-modulus optimization. In this paper, we revisit this penalty method in several other unit-modulus applications in signal…
In order to better understand the rationale behind model behavior, recent works have exploited providing interpretation to support the inference prediction. However, existing methods tend to provide human-unfriendly interpretation, and are prone to sub-optimal performance due to one-side promotion,…
Vision Transformer (ViT) attains state-of-the-art performance in visual recognition, and the variant, Local Vision Transformer, makes further improvements. The major component in Local Vision Transformer, local attention, performs the attention separately over small local windows. We rephrase local…
Previous work generally believes that improving the spatial invariance of convolutional networks is the key to object counting. However, after verifying several mainstream counting networks, we surprisingly found too strict pixel-level spatial invariance would cause overfit noise in the density map…
This paper presents SimMIM, a simple framework for masked image modeling. We have simplified recently proposed relevant approaches, without the need for special designs, such as block-wise masking and tokenization via discrete VAE or clustering. To investigate what makes a masked image modeling task…
Consistent in-focus input imagery is an essential precondition for machine vision systems to perceive the dynamic environment. A de-focus blur severely degrades the performance of vision systems. To tackle this problem, we propose a deep-learning-based framework estimating the kernel scale and orien…
Training temporal action detection in videos requires large amounts of labeled data, yet such annotation is expensive to collect. Incorporating unlabeled or weakly-labeled data to train action detection model could help reduce annotation cost. In this work, we first introduce the Semi-supervised Act…
Convolutional Neural Networks (CNNs) are known to rely more on local texture rather than global shape when making decisions. Recent work also indicates a close relationship between CNN’s texture-bias and its robustness against distribution shift, adversarial perturbation, random corruption, etc. In…
Weakly-supervised temporal action localization is a problem of learning an action localization model with only video-level action labeling available. The general framework largely relies on the classification activation, which employs an attention model to identify the action-related frames and then…
Hashing has shown great potential in large-scale image retrieval due to its storage and computation efficiency, especially the recent deep supervised hashing methods. To achieve promising performance, deep supervised hashing methods require a large amount of training data from different classes. How…
The aim of crowd counting is to estimate the number of people in images by leveraging the annotation of center positions for pedestrians' heads. Promising progresses have been made with the prevalence of deep Convolutional Neural Networks. Existing methods widely employ the Euclidean distance (i.e.,…
Detecting actions in videos is a challenging task as video is an information intensive media with complex variations. Existing approaches predominantly generate action proposals for each individual frame or fixed-length clip independently, while overlooking temporal context across them. Such tempora…