EventVL introduces the first generative event-based multimodal large language model (MLLM) designed for explicit semantic understanding of event streams. The framework leverages a newly annotated dataset of nearly 1.4 million event–image/video–text pairs and incorporates an Event Spatiotemporal Representation to capture comprehensive event information, along with Dynamic Semantic Alignment to refine sparse semantic spaces. Experiments demonstrate that EventVL outperforms existing MLLM baselines in event captioning and scene description generation tasks, advancing the field of event vision.
By Pengteng Li, Yunfan Lu, Pinghao Song, Wuyang Li, Huizai Yao, Hui Xiong
arXiv:2605. 00271v3 Announce Type: replace-cross Abstract: Event cameras provide several unique advantages over standard frame-based sensors, including high temporal resolution, low latency, and robustness to extreme lighting.
By Vincenzo Polizzi, David B. Lindell, Jonathan Kelly
arXiv:2606. 13289v1 Announce Type: cross Abstract: Holistic visual tokenizers are fundamental to unified multimodal models (UMMs) as they map diverse visual inputs into a unified representation space.
By Guozhen Zhang, Xuerui Qiu, Yutao Cui, Tianhui Song, Changlin Li, Junzhe Li, Tao Huang, Xiao Zhang, Yang Li, Jianbing Wu, Miles Yang, Zhao Zhong, Liefeng Bo, Limin Wang
VIVAS is a new Vision‑Language Model pre‑training framework that addresses the lack of fine‑grained visual perception in existing VLMs. It introduces a unified token space and a dense‑structural‑semantic vision tokenizer that expands the textual vocabulary with visual tokens, enabling vision‑language unified autoregressive supervision over both visual details and linguistic content. Trained on 12.4 T tokens, VIVAS achieves state‑of‑the‑art results on 7 tasks and 39 multimodal benchmarks.
By Zhehan Kan, Yubo Zhu, Xinghua Jiang, Zhixiang Wei, Shifeng Liu, Wei Tong, Sheng Zhong, Qingmin Liao, Wenming Yang, Xin Li, Yinsong Liu, Deqiang Jiang, Xing Sun
arXiv:2610.16172v1 Announce Type: cross
Abstract: Recent multimodal large language models (MLLMs) achieve strong results on video question answering, yet often fail to recover the temporal structure...
By Guowen Zhang, Boshen Xu, Zihao Yue, Ziheng Wang, Xiaokun Liu, Xin Tao, Wenyu Qin, Pengfei Wan, Qin Jin
UVU is a vision-language unified autoregressive framework that integrates visual supervision directly into the pre-training stage of multimodal large language models. By using continuous visual encoding and a large-scale iterative hierarchical clustering algorithm to build a pixel-level visual codebook, UVU enables lossless representation of visual inputs and autoregressive generation of pixel-level image tokens alongside textual tokens. This approach synergizes pixel-level visual perception with semantic-level visual understanding, allowing models to internalize visual reconstruction capabilities and improve multimodal understanding performance.
By Zhehan Kan, Xinghua Jiang, Yubo Zhu, Yanlin Liu, Xiaochen Yang, Zhixiang Wei, Shifeng Liu, Qingmin Liao, Wenming Yang, Xin Li, Yinsong Liu, Deqiang Jiang, Xing Sun
arXiv:2511. 10260v2 Announce Type: replace-cross Abstract: Fine-Grained Visual Classification (FGVC) remains a challenging task due to subtle inter-class differences and large intra-class variations.
By Yongji Zhang, Siqi Li, Kuiyang Huang, Yue Gao, Yu Jiang
arXiv:2607. 09114v1 Announce Type: cross Abstract: Video anomaly detection (VAD) is critical for automated surveillance but remains fragile under challenging conditions such as illumination variations, fast motion, and complex backgrounds when relying solely on visible light videos.
By Peipei Zhu, Yueqing Niu, Lin Zhu, Guanchong Niu, Yang Yu, Zheng Li
arXiv:2606. 29136v1 Announce Type: cross Abstract: Event cameras capture sparse brightness changes with high temporal resolution and high dynamic range, compensating for the deficiencies of the conventional RGB frames.
By Yu Li, Yuenan Hou, Yingmei Wei, Jiangming Chen, Yanming Guo
arXiv:2608. 20127v1 Announce Type: new Abstract: Video Temporal Grounding (VTG) faces significant challenges when natural language queries must distinguish between multiple events involving visually similar entities, particularly when relying on fine-grained visual attributes that are difficult to describe accurately in words alone.
By Minghang Zheng, Jingli Wei, Hongyi Yang, Yang Liu
WALL-WM is a World Action Model that shifts video-action learning from chunk-centric optimization to event-grounded Vision-Language-Action pretraining, using semantically coherent action events as the atomic unit of learning. Existing WAMs commonly initialize from multimodal or video foundation models and then optimize fixed-length action chunks conditioned directly on the current observation and instruction.
WithinVAE is a compact variational visual autoencoder that learns semantic structure internally using a sequential bottleneck and self‑distillation from an exponential‑moving‑average copy of itself. It achieves a four‑fold compression ratio on ImageNet‑1K, improving reconstruction metrics such as PSNR by 1.36 dB over RPiAE while using half the latent capacity. The model also boosts linear probing performance, demonstrating that semantic gains arise from self‑distillation rather than external supervision.
By Yuzhou Ji, Jiepeng Wang, Tianyu Jin, Lizhuang Ma, Haibin Huang, Chi Zhang, Xuelong Li