热点
"视频理解" 相关文章
AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning
cs.AI updates on arXiv.org 2025-07-30T04:12:03.000000Z
2025.07.22 | MiroMind-M1提升数学推理；GUI-G$^2$高斯奖励助GUI定位。
HuggingFace 每日AI论文速递 2025-07-22T23:02:56.000000Z
[酷工作] [项目外包] 寻找视频理解外包团队
V2EX 2025-07-21T08:17:22.000000Z
Generalist Forecasting with Frozen Video Models via Latent Diffusion
cs.AI updates on arXiv.org 2025-07-21T04:06:32.000000Z
VideoITG: Multimodal Video Understanding with Instructed Temporal Grounding
cs.AI updates on arXiv.org 2025-07-18T04:13:59.000000Z
TwelveLabs video understanding models are now available in Amazon Bedrock
AWS Blogs 2025-07-15T23:40:21.000000Z
ViTCoT: Video-Text Interleaved Chain-of-Thought for Boosting Video Understanding in Large Language Models
cs.AI updates on arXiv.org 2025-07-15T04:26:57.000000Z
Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs
cs.AI updates on arXiv.org 2025-07-11T04:04:20.000000Z
Time-R1突破视频时序定位挑战：多模态强化学习后训练框架仅用2.5K数据刷新SOTA
小米技术 2025-07-09T21:17:44.000000Z
AI技术获全球顶级学术会议认可，小米2篇论文入选ICCV 2025
小米技术 2025-07-08T10:20:08.000000Z
HV-MMBench: Benchmarking MLLMs for Human-Centric Video Understanding
cs.AI updates on arXiv.org 2025-07-08T04:33:50.000000Z
750城市+5000小时第一人称视频，上海AI Lab开源面向世界探索高质量视频数据集
智源社区 2025-07-06T04:23:01.000000Z
Gemini负责人爆料！多模态统一token表示，视觉至关重要
智源社区 2025-07-04T08:58:44.000000Z
COEF-VQ: Cost-Efficient Video Quality Understanding through a Cascaded Multimodal LLM Framework
cs.AI updates on arXiv.org 2025-07-04T04:08:28.000000Z
Can Video Large Multimodal Models Think Like Doubters-or Double-Down: A Study on Defeasible Video Entailment
cs.AI updates on arXiv.org 2025-06-30T04:14:28.000000Z
AI秒懂短视频，快手大模型Keye-VL理解力爆表！技术细节全开源
新智元 2025-06-27T05:25:20.000000Z
3B挑战70B！月之暗面Kimi-VL新版开源：数学、视频等多项指标超越GPT-4o
2025-06-23T14:56:49.000000Z
一文看尽字节跳动2025重磅AI开源成果：从图像生成到智能体系统
我爱计算机视觉 2025-06-21T13:32:19.000000Z
万帧？单卡！智源研究院开源轻量级超长视频理解模型Video-XL-2
机器之心 2025-06-03T06:51:16.000000Z
2025.05.15 | 解耦学习提升感知性能；多模态模型优化图像生成。
HuggingFace 每日AI论文速递 2025-05-15T23:02:55.000000Z