本期的 15 篇论文如下:
00:22 🏆 Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving(Seed-Prover:自动化定理证明的深度与广度推理)
01:04 🎯 Phi-Ground Tech Report: Advancing Perception in GUI Grounding(Phi-Ground 技术报告:提升 GUI 接地感知能力)
01:30 🤔 C3: A Bilingual Benchmark for Spoken Dialogue Models Exploring Challenges in Complex Conversations(C3:探索复杂对话挑战的双语口语对话模型基准)
02:07 🚀 RecGPT Technical Report(RecGPT 技术报告)
02:36 🤖 villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models(villa-X:增强视觉-语言-动作模型中的潜在动作建模)
03:14 🤖 Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents(可扩展的多任务强化学习,赋能视觉运动智能体可泛化空间智能)
04:07 ⚖ Persona Vectors: Monitoring and Controlling Character Traits in Language Models(人格向量:语言模型中性格特征的监测与控制)
04:41 🚀 iLRM: An Iterative Large 3D Reconstruction Model(iLRM:迭代式大型3D重建模型)
05:32 ✅ TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs(TARS:多模态大语言模型幻觉抑制的最小最大词元自适应偏好策略)
06:02 💡 On the Expressiveness of Softmax Attention: A Recurrent Neural Network Perspective(Softmax注意力机制的表达能力:循环神经网络视角)
06:29 🤝 NeRF Is a Valuable Assistant for 3D Gaussian Splatting(NeRF 是 3D Gaussian Splatting 的得力助手)
07:05 🌾 AgroBench: Vision-Language Model Benchmark in Agriculture(AgroBench:农业视觉-语言模型基准)
07:36 🎨 Beyond Linear Bottlenecks: Spline-Based Knowledge Distillation for Culturally Diverse Art Style Classification(超越线性瓶颈:基于样条的知识蒸馏用于文化多样性艺术风格分类)
08:15 🔎 Enhanced Arabic Text Retrieval with Attentive Relevance Scoring(采用注意力相关性评分的增强型阿拉伯语文本检索)
08:45 🌊 Flow Equivariant Recurrent Neural Networks(流等变循环神经网络)

【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
