相关论文: Text-Driven Reasoning Video Editing via Reinforcem…

Effectiveness and interpretability are two essential properties for trustworthy AI systems. Most recent studies in visual reasoning are dedicated to improving the accuracy of predicted answers, and less attention is paid to explaining the…

Generative models have substantially expanded video generation capabilities, yet practical thought-to-video creation remains a multi-stage, multi-modal, and decision-intensive process. However, existing tools either hide intermediate…

Decomposing a video into a layer-based representation is crucial for easy video editing for the creative industries, as it enables independent editing of specific layers. Existing video-layer decomposition models rely on implicit neural…

Text-driven video editing is rapidly advancing, yet its rigorous evaluation remains challenging due to the absence of dedicated video quality assessment (VQA) models capable of discerning the nuances of editing quality. To address this…

Learning general-purpose reasoning capabilities has long been a challenging problem in AI. Recent research in large language models (LLMs), such as DeepSeek-R1, has shown that reinforcement learning techniques like GRPO can enable…

Video grounding aims to localize a moment from an untrimmed video for a given textual query. Existing approaches focus more on the alignment of visual and language stimuli with various likelihood-based matching or regression strategies,…

Retrieving events from videos using text queries has become increasingly challenging due to the rapid growth of multimedia content. Existing methods for text-based video event retrieval often focus heavily on object-level descriptions,…

Existing dense or paragraph video captioning approaches rely on holistic representations of videos, possibly coupled with learned object/action representations, to condition hierarchical language decoders. However, they fundamentally lack…

Reinforcement learning (RL) has emerged as a promising approach for eliciting reasoning chains before generating final answers. However, multimodal large language models (MLLMs) generate reasoning that lacks integration of visual…

Assessing the quality of outputs generated by generative models, such as large language models and vision language models, presents notable challenges. Traditional methods for evaluation typically rely on either human assessments, which are…

Raven's Progressive Matrices (RPMs) are frequently used in evaluating human's visual reasoning ability. Researchers have made considerable efforts in developing systems to automatically solve the RPM problem, often through a black-box…

While Reinforcement Learning with Verifiable Rewards (RLVR) is effective for deterministically checkable tasks, many vision-language tasks are partially verifiable, demanding multi-criteria supervision (e.g., perceptual details, reasoning…

Despite the fact that text-to-video (TTV) model has recently achieved remarkable success, there have been few approaches on TTV for its extension to video editing. Motivated by approaches on TTV models adapting from diffusion-based…

Video understanding is inherently intention-driven-humans naturally focus on relevant frames based on their goals. Recent advancements in multimodal large language models (MLLMs) have enabled flexible query-driven reasoning; however,…

Recent advances in foundation models highlight a clear trend toward unification and scaling, showing emergent capabilities across diverse domains. While image generation and editing have rapidly transitioned from task-specific to unified…

The recent success in deep learning has lead to various effective representation learning methods for videos. However, the current approaches for video representation require large amount of human labeled datasets for effective learning. We…

Text-to-Video (T2V) retrieval aims to identify the most relevant item from a gallery of videos based on a user's text query. Traditional methods rely solely on aligning video and text modalities to compute the similarity and retrieve…

Text revision refers to a family of natural language generation tasks, where the source and target sequences share moderate resemblance in surface form but differentiate in attributes, such as text formality and simplicity. Current…

While Large Language Models (LLMs) excel at reasoning on text and Vision-Language Models (VLMs) are highly effective for visual perception, applying those models for visual instruction-based planning remains a widely open problem. In this…

In light of recent progress in video editing, deep learning models focusing on both spatial and temporal dependencies have emerged as the primary method. However, these models suffer from the quadratic computational complexity of…