【赞助商】
OpenClaw快报
每天五分钟,听听 OpenClaw 快报,带你了解最新动态和业内讨论
传送门 www.xiaoyuzhoufm.com
【目录】
本期的 15 篇论文如下:
[] 🌍 Orca: The World is in Your Mind(虎鲸:世界在你心中)
[] 🧪 Dockerless: Environment-Free Program Verifier for Coding Agents(无Docker:面向编码智能体的无环境程序验证器)
[] 🎭 DOPD: Dual On-policy Distillation(双在线策略蒸馏)
[] 🚀 BlockPilot: Instance-Adaptive Policy Learning for Diffusion-based Speculative Decoding(BlockPilot:基于扩散的推测解码的实例自适应策略学习)
[] 🧩 Scenes as Objects, Not Primitives: Instance-Structured 3D Tokenization from Unposed Views(场景即对象,而非基元:基于未标定视图的实例结构化3D分词化)
[] 🎨 GEAR: Guided End-to-End AutoRegression for Image Synthesis(GEAR:引导式端到端自回归图像合成)
[] 🧩 Multi-Block Diffusion Language Models(多块扩散语言模型)
[] 🧬 Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks(进化微调:学习在371个优化任务中发现)
[] 🔧 SkillHone: A Harness for Continual Agent Skill Evolution Through Persistent Decision History(SkillHone:基于持久决策历史的持续智能体技能演进框架)
[] 🎥 MemLearner: Learning to Query Context memory for Video World Models(MemLearner:学习为视频世界模型查询上下文记忆)
[] 🧠 Managing Procedural Memory in LLM Agents: Control, Adaptation, and Evaluation(LLM智能体中的程序性记忆管理:控制、适应与评估)
[] 🧠 DataEvolver: Self-Evolving Multi-Agent Data Construction for Text-Rich Image Generation(DataEvolver:面向文本丰富图像生成的自我进化多智能体数据构建框架)
[] 🔊 RedVox: Safety and Fairness Gaps in Speech Models Across Languages(RedVox:跨语言语音模型中的安全性与公平性差距)
[] 🧠 Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs(基于元认知反馈的强化学习激发大语言模型可靠的置信度表达)
[] 🧠 Little Brains, Big Feats: Exploring Compact Language Models(小大脑,大成就:探索紧凑型语言模型)

【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
