Related papers: VISTA: A Test-Time Self-Improving Video Generation…

Knowledge-based visual question answering (KB-VQA) requires vision-language models to understand images and use external knowledge, especially for rare entities and long-tail facts. Most existing retrieval-augmented generation (RAG) methods…

Text-to-image models are powerful for producing high-quality images based on given text prompts, but crafting these prompts often requires specialized vocabulary. To address this, existing methods train rewriting models with supervision…

We present VISTA (Visualization of Internal States and Their Associations), a novel pipeline for visually exploring and interpreting neural network representations. VISTA addresses the challenge of analyzing vast multidimensional spaces in…

Answering complex natural language questions often necessitates multi-step reasoning and integrating external information. Several systems have combined knowledge retrieval with a large language model (LLM) to answer such questions. These…

Many video workflows benefit from a mixture of user controls with varying granularity, from exact 4D object trajectories and camera paths to coarse text prompts, while existing video generative models are typically trained for fixed input…

We present PresentAgent, a multimodal agent that transforms long-form documents into narrated presentation videos. While existing approaches are limited to generating static slides or text summaries, our method advances beyond these…

The vision and language generative models have been overgrown in recent years. For video generation, various open-sourced models and public-available services have been developed to generate high-quality videos. However, these methods often…

Long-form video understanding represents a significant challenge within computer vision, demanding a model capable of reasoning over long multi-modal sequences. Motivated by the human cognitive process for long-form video understanding, we…

Video question answering (VideoQA) is a challenging task that requires integrating spatial, temporal, and semantic information to capture the complex dynamics of video sequences. Although recent advances have introduced various approaches…

Text-to-video generation has made significant strides, but replicating the capabilities of advanced systems like OpenAI Sora remains challenging due to their closed-source nature. Existing open-source methods struggle to achieve comparable…

While image manipulation achieves tremendous breakthroughs (e.g., generating realistic faces) in recent years, video generation is much less explored and harder to control, which limits its applications in the real world. For instance,…

Vision-language models (VLMs) have made significant progress in image classification by training with large-scale paired image-text data. Their performances largely depend on the prompt quality. While recent methods show that visual…

Visual Retrieval-Augmented Generation (VRAG) empowers Vision-Language Models to retrieve and reason over visually rich documents. To tackle complex queries requiring multi-step reasoning, agentic VRAG systems interleave reasoning with…

Recent advances in AI-generated content (AIGC) have led to the emergence of powerful text-to-video generation models. Despite these successes, evaluating the quality of AIGC-generated videos remains challenging due to limited…

We propose VISTA, a V-JEPA Integrated StillFast Temporal Anticipator for the Ego4D Short-Term Object Interaction Anticipation (STA) Challenge at EgoVis 2026. Given an egocentric video timestamp, the task requires anticipating the next…

Video generation models produce visually compelling results but systematically violate physical commonsense -- on VideoPhy-2, the best model achieves only 32.6% joint accuracy. We identify a specification bottleneck: text prompts are lossy…

Text-driven video editing enables users to modify video content only using text queries. While existing methods can modify video content if explicit descriptions of editing targets with precise spatial locations and temporal boundaries are…

We present a framework for optimizing prompts in vision-language models to elicit multimodal reasoning without model retraining. Using an evolutionary algorithm to guide prompt updates downstream of visual tasks, our approach improves upon…

DiT-based video generation has achieved remarkable results, but research into enhancing existing models remains relatively unexplored. In this work, we introduce a training-free approach to enhance the coherence and quality of DiT-based…

Visual Prompt Tuning (VPT) has emerged as a parameter-efficient fine-tuning paradigm for vision transformers, with conventional approaches utilizing dataset-level prompts that remain the same across all input instances. We observe that this…