Paper Archive

Yawen Luo, Xiaoyu Shi, Junhao Zhuang, Yutian Chen, Quande Liu, Xintao Wang, Pengfei Wan, Tianfan Xue 3/26/2026 arxiv

Multi-shot video generation is crucial for long narrative storytelling, yet current bidirectional architectures suffer from limited interactivity and high latency. We propose ShotStream, a novel causal multi-shot architecture that enables interactive storytelling and efficient on-the-fly frame gener...

Yixing Lao, Xuyang Bai, Xiaoyang Wu, Nuoyuan Yan, Zixin Luo, Tian Fang, Jean-Daniel Nahmias, Yanghai Tsin, Shiwei Li, Hengshuang Zhao 3/26/2026 arxiv

Existing feed-forward 3D Gaussian Splatting methods predict pixel-aligned primitives, leading to a quadratic growth in primitive count as resolution increases. This fundamentally limits their scalability, making high-resolution synthesis such as 4K intractable. We introduce LGTM (Less Gaussians, Tex...

Bocheng Zou, Mu Cai, Mark Stanley, Dingfu Lu, Yong Jae Lee 3/26/2026 arxiv

Vision Foundation Models (VFMs) have become the cornerstone of modern computer vision, offering robust representations across a wide array of tasks. While recent advances allow these models to handle varying input sizes during training, inference typically remains restricted to a single, fixed scale...

Lei Wang, YuXin Song, Ge Wu, Haocheng Feng, Hang Zhou, Jingdong Wang, Yaxing Wang, jian Yang 3/26/2026 arxiv

Reference-to-video (R2V) generation is a controllable video synthesis paradigm that constrains the generation process using both text prompts and reference images, enabling applications such as personalized advertising and virtual try-on. In practice, existing R2V methods typically introduce additio...

Sicheng Zuo, Yuxuan Li, Wenzhao Zheng, Zheng Zhu, Jie Zhou, Jiwen Lu 3/26/2026 arxiv

Vision-language-action models have reshaped autonomous driving to incorporate languages into the decision-making process. However, most existing pipelines only utilize the language modality for scene descriptions or reasoning and lack the flexibility to follow diverse user instructions for personali...

Zehao Wang, Huaide Jiang, Shuaiwu Dong, Yuping Wang, Hang Qiu, Jiachen Li 3/26/2026 arxiv

Human driving behavior is inherently personal, which is shaped by long-term habits and influenced by short-term intentions. Individuals differ in how they accelerate, brake, merge, yield, and overtake across diverse situations. However, existing end-to-end autonomous driving systems either optimize ...

Xincheng Shuai, Song Tang, Yutong Huang, Henghui Ding, Dacheng Tao 3/26/2026 arxiv

Graphic design is a creative and innovative process that plays a crucial role in applications such as e-commerce and advertising. However, developing an automated design system that can faithfully translate user intentions into editable design files remains an open challenge. Although recent studies...

Dingxi Zhang, Fangjinhua Wang, Marc Pollefeys, Haofei Xu 3/26/2026 arxiv

Accurate estimation of large displacement optical flow remains a critical challenge. Existing methods typically rely on iterative local search or/and domain-specific fine-tuning, which severely limits their performance in large displacement and zero-shot generalization scenarios. To overcome this, w...

Yuxing Lu, Xukai Zhao, Wei Wu, Jinzhuo Wang 3/26/2026 arxiv

The knowledge base in a retrieval-augmented generation (RAG) system is typically assembled once and never revised, even though the facts a query requires are often fragmented across documents and buried in irrelevant content. We argue that the knowledge base should be treated as a trainable componen...

Jiwook Han, Geo Ahn, Youngrae Kim, Jinwoo Choi 3/26/2026 arxiv

Multimodal Large Language Models (MLLMs) have shown strong performance on Video Temporal Grounding (VTG). However, their coarse recognition capabilities are insufficient for fine-grained temporal understanding, making task-specific fine-tuning indispensable. This fine-tuning causes models to memoriz...