2026.05.07 | 奖励蒸馏让像素会“挑重点”;测试时扩展逐块稳长视频

2026.05.07 | 奖励蒸馏让像素会“挑重点”;测试时扩展逐块稳长视频

14分钟 ·
播放数94
·
评论数0

【目录】
本期的 15 篇论文如下:
[00:24] 🎥 Stream-R1: Reliability-Perplexity Aware Reward Distillation for Streaming Video Generation(Stream-R1:面向流式视频生成的可靠性-困惑度感知奖励蒸馏)
[01:27] 🎥 Stream-T1: Test-Time Scaling for Streaming Video Generation(Stream-T1:面向流式视频生成的测试时扩展)
[02:06] 🔍 OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents(OpenSearch-VL:前沿多模态搜索智能体的开放配方)
[03:07] 🤖 RLDX-1 Technical Report(RLDX-1技术报告)
[04:06] 🚗 HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation(HERMES++:迈向统一驾驶世界模型,用于3D场景理解与生成)
[04:50] ⚙ PhysForge: Generating Physics-Grounded 3D Assets for Interactive Virtual World(PhysForge:为交互式虚拟世界生成物理基础的3D资产)
[05:40] 🎨 D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models(D-OPSD:用于持续调优步蒸馏扩散模型的在策略自蒸馏方法)
[06:38] 🔍 Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems(重新思考推理密集型检索:评估与推进智能体搜索系统中的检索器)
[07:46] ⚡ Lightning Unified Video Editing via In-Context Sparse Attention(基于上下文稀疏注意力的闪电式统一视频编辑)
[08:38] 🧠 Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation(在多模态统一理解与生成中唤醒空间智能)
[09:27] 🎯 Parameter-Efficient Multi-View Proficiency Estimation: From Discriminative Classification to Generative Feedback(参数高效的多视角技能评估:从判别分类到生成式反馈)
[10:11] 🎵 APEX: Large-scale Multi-task Aesthetic-Informed Popularity Prediction for AI-Generated Music(APEX:面向AI生成音乐的大规模多任务审美感知流行度预测)
[10:54] 🧠 ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning(ResRL:通过负样本投影残差强化学习提升大语言模型推理能力)
[11:47] 🧩 Diffusion Model as a Generalist Segmentation Learner(扩散模型作为通用分割学习器)
[12:26] 🔬 MedSkillAudit: A Domain-Specific Audit Framework for Medical Research Agent Skills(MedSkillAudit:面向医学研究智能体技能的领域特定审计框架)

【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