0:000:00
<p>本期的 15 篇论文如下：</p><p>[00:21] 🖼 VCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual Representation（VCode：以SVG为符号视觉表征的多模态代码评测基准）</p><p>[01:12] 🧠 When Visualizing is the First Step to Reasoning: MIRA, a Benchmark for Visual Chain-of-Thought（当可视化成为推理第一步：MIRA视觉思维链基准测试）</p><p>[01:48] ⚖ When Modalities Conflict: How Unimodal Reasoning Uncertainty Governs Preference Dynamics in MLLMs（当模态冲突时：单模态推理不确定性如何左右多模态大模型的偏好）</p><p>[02:36] 🪙 Shorter but not Worse: Frugal Reasoning via Easy Samples as Length Regularizers in Math RLVR（更短却更好：用易题作长度正则化实现节俭推理）</p><p>[03:11] 🧠 Brain-IT: Image Reconstruction from fMRI via Brain-Interaction Transformer（Brain-IT：基于脑交互Transformer的fMRI图像重建）</p><p>[03:49] 👁 Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization（别让VLA变盲：对齐视觉表征实现分布外泛化）</p><p>[04:33] 🎨 LTD-Bench: Evaluating Large Language Models by Letting Them Draw（LTD-Bench：让大模型画画来测评空间推理力）</p><p>[05:15] 🤖 TWIST2: Scalable, Portable, and Holistic Humanoid Data Collection Syst...