Related papers: SeqBench: Benchmarking Sequential Narrative Genera…

Despite remarkable recent progress, existing long-form VideoQA datasets fall short of meeting the criteria for genuine long-form video understanding. This is primarily due to the use of short videos for question curation, and the reliance…

We consider incorporating topic information into the sequence-to-sequence framework to generate informative and interesting responses for chatbots. To this end, we propose a topic aware sequence-to-sequence (TA-Seq2Seq) model. The model…

Using neural networks to generate replies in human-computer dialogue systems is attracting increasing attention over the past few years. However, the performance is not satisfactory: the neural network tends to generate safe, universally…

While current video generation focuses on text or image conditions, practical applications like video editing and vlogging often need to seamlessly connect separate clips. In our work, we introduce Video Connecting, an innovative task that…

Text-to-video (T2V) synthesis has advanced rapidly, yet current evaluation metrics primarily capture visual quality and temporal consistency, offering limited insight into how synthetic videos perform in downstream tasks such as…

While text-to-visual models now produce photo-realistic images and videos, they struggle with compositional text prompts involving attributes, relationships, and higher-order reasoning such as logic and comparison. In this work, we conduct…

While Text-To-Video (T2V) models have advanced rapidly, they continue to struggle with generating legible and coherent text within videos. In particular, existing models often fail to render correctly even short phrases or words and…

Text-to-Time Series generation holds significant potential to address challenges such as data sparsity, imbalance, and limited availability of multimodal time series datasets across domains. While diffusion models have achieved remarkable…

While sequence-to-sequence (seq2seq) models achieve state-of-the-art performance in many natural language processing tasks, they can be too slow for real-time applications. One performance bottleneck is predicting the most likely next token…

Text-to-Video (T2V) generation has benefited from recent advances in diffusion models, yet current systems still struggle under complex scenarios, which are generally exacerbated by the ambiguity and underspecification of text prompts. In…

With the rapid development of Multi-modal Large Language Models (MLLMs), an increasing number of benchmarks have been established to evaluate the video understanding capabilities of these models. However, these benchmarks focus on…

Audio-visual generation is rapidly advancing from short clips to minute-long content, while existing evaluation protocols remain largely confined to short-form settings. Existing benchmarks primarily focus on 5--10 second text-conditioned…

The rapid advancement of talking-head deepfake generation fueled by advanced generative models has elevated the realism of synthetic videos to a level that poses substantial risks in domains such as media, politics, and finance. However,…

Recent advances in video generation have enabled the synthesis of videos with strong temporal consistency and impressive visual quality, marking a crucial step toward vision foundation models. To evaluate these video generation models,…

Video understanding requires models to continuously track and update world state during playback. While existing benchmarks have advanced video understanding evaluation across multiple dimensions, the observation of how models maintain…

Existing video captioning benchmarks and models lack causal-temporal narrative, which is sequences of events linked through cause and effect, unfolding over time and driven by characters or agents. This lack of narrative restricts models'…

Evaluating the quality of synthesized images remains a significant challenge in the development of text-to-image (T2I) generation. Most existing studies in this area primarily focus on evaluating text-image alignment, image quality, and…

A truly capable AI system must do more than detect objects or recognize activities in isolation. It must form unified, grounded representations of who is acting, what they are doing, and when and where these actions unfold. These…

Diffusion-based text-to-video (T2V) models have achieved significant success but continue to be hampered by the slow sampling speed of their iterative sampling processes. To address the challenge, consistency models have been proposed to…

In this paper, we focus on enhancing a diffusion-based text-to-video (T2V) model during the post-training phase by distilling a highly capable consistency model from a pretrained T2V model. Our proposed method, T2V-Turbo-v2, introduces a…