本期的 15 篇论文如下:
00:24 🖼 Step1X-Edit: A Practical Framework for General Image Editing(Step1X-Edit:一个通用的图像编辑实用框架)
01:05 🖼 RefVNLI: Towards Scalable Evaluation of Subject-driven Text-to-image Generation(RefVNLI:面向主体驱动的文本到图像生成的可扩展评估)
01:48 🤖 Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning(Paper2Code:从机器学习科学论文中自动生成代码)
02:22 🖼 Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs(打破模态壁垒:基于多模态大型语言模型的通用嵌入学习)
03:02 🧠 Perspective-Aware Reasoning in Vision-Language Models via Mental Imagery Simulation(基于心智图像模拟的视觉-语言模型中的视角感知推理)
03:42 ⚖ QuaDMix: Quality-Diversity Balanced Data Selection for Efficient LLM Pretraining(QuaDMix:面向高效LLM预训练的质量-多样性平衡数据选择)
04:19 🖼 Token-Shuffle: Towards High-Resolution Image Generation with Autoregressive Models(Token-Shuffle:面向自回归模型的高分辨率图像生成)
04:58 🖼 Distilling semantically aware orders for autoregressive image generation(用于自回归图像生成的语义感知顺序蒸馏)
05:38 🗜 DyMU: Dynamic Merging and Virtual Unmerging for Efficient VLMs(DyMU:用于高效视觉语言模型的动态合并与虚拟解合并)
06:17 🇪 IberBench: LLM Evaluation on Iberian Languages(IberBench:伊比利亚语系的大语言模型评测基准)
07:01 🧠 Process Reward Models That Think(思考过程奖励模型)
07:46 🎨 Boosting Generative Image Modeling via Joint Image-Feature Synthesis(通过联合图像-特征合成增强生成图像建模)
08:21 🎬 ViSMaP: Unsupervised Hour-long Video Summarisation by Meta-Prompting(ViSMaP:基于元提示的无监督小时级视频摘要)
09:02 👗 3DV-TON: Textured 3D-Guided Consistent Video Try-on via Diffusion Models(3DV-TON:基于扩散模型的纹理3D引导一致性视频试穿)
09:44 📹 TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos(TimeChat-Online:在线流媒体视频中 80% 的视觉 tokens 天然冗余)

【关注我们】
您还可以在以下平台找到我们,获得播客内容以外更多信息
小红书: AI速递