2025.05.16 | 推理模型元能力提升;系统提示优化与鲁棒性增强

本期的 15 篇论文如下: [00:24] 💡 Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models(超越“Aha!”时刻:迈向大型推理模型中系统性元能力对齐) [01:02] 🤖 System Prompt Optimization with Meta-Learning(基于元学习的系统提示优化) [01:47] 🤖 EnerVerse-AC: Envisioning Embodied Environments with Action Condition(EnerVerse-AC:通过动作条件设想具身环境) [02:29] 🧠 The CoT Encyclopedia: Analyzing, Predicting, and Controlling how a Reasoning Model will Think(CoT百科全书:分析、预测和控制推理模型如何思考) [03:17] 🤖 EWMBench: Evaluating Scene, Motion, and Semantic Quality in Embodied World Models(EWMBench:具身世界模型中场景、运动和语义质量的评估) [03:57] 🖼 End-to-End Vision Tokenizer Tuning(端到端视觉标记器调优) [04:34] 📈 WorldPM: Scaling Human Preference Modeling(世界偏好建模:扩展人类偏好模型) [05:13] 🤖 MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering(MLE-Dojo:用于增强机器学习工程中LLM代理的交互式环境) [06:01] 🧩 Achieving Tokenizer Flexibility in Language Models through Heuristic Adaptation and Supertoken Learning(通过启发式适配和超Token学习实现语言模型中的Tokenizer灵活性) [06:43] 🎨 Style Customization of Text-to-Vector Generation with Image Diffusion Priors(基于图像扩散先验的文本到矢量生成风格定制) [07:25] 🧠 J1: Incentivizing Thinking in LLM-as-a-Judge via Reinforcement Learning(J1:通过强化学习激励LLM作为裁判时的思考) [08:07] 👉 PointArena: Probing Multimodal Grounding Through Language-Guided Pointing(PointArena:通过语言引导的指向探测多模态理解) [08:47] 🖼 Depth Anything with Any Prior(任意先验的深度感知) [09:29] 🖼 OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning(OpenThinkIMG: 通过视觉工具强化学习,学习用图像思考) [10:14] 🚀 Parallel Scaling Law for Language Models(语言模型的并行扩展法则) 【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

11分钟
51
2天前

2025.05.15 | 解耦学习提升感知性能;多模态模型优化图像生成。

本期的 11 篇论文如下: [00:23] 🖼 DeCLIP: Decoupled Learning for Open-Vocabulary Dense Perception(DeCLIP:用于开放词汇密集感知的解耦学习) [01:02] 🖼 BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset(BLIP3-o:一族完全开放的统一多模态模型——架构、训练和数据集) [01:41] 💡 Insights into DeepSeek-V3: Scaling Challenges and Reflections on Hardware for AI Architectures(DeepSeek-V3 的深度剖析:AI 架构的扩展挑战与硬件思考) [02:24] 🎨 Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysis(Marigold:用于图像分析的基于扩散的图像生成器的经济型适配) [03:00] 🤖 UniSkill: Imitating Human Videos via Cross-Embodiment Skill Representations(UniSkill:通过跨具身技能表征模仿人类视频) [03:42] 🐛 SweRank: Software Issue Localization with Code Ranking(SweRank:基于代码排序的软件问题定位) [04:23] 🤔 VCRBench: Exploring Long-form Causal Reasoning Capabilities of Large Video Language Models(VCRBench:探索大型视频语言模型在长程因果推理方面的能力) [05:14] 🖼 CAST: Component-Aligned 3D Scene Reconstruction from an RGB Image(CAST:基于RGB图像的组件对齐三维场景重建) [05:49] 🤔 Omni-R1: Do You Really Need Audio to Fine-Tune Your Audio LLM?(Omni-R1: 微调音频大语言模型真的需要音频数据吗?) [06:27] 🤔 Visually Interpretable Subtask Reasoning for Visual Question Answering(视觉问答中基于视觉可解释性的子任务推理) [06:59] 🚁 DetReIDX: A Stress-Test Dataset for Real-World UAV-Based Person Recognition(DetReIDX:一个用于现实世界无人机人员识别的压力测试数据集) 【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

8分钟
57
3天前

2025.05.14 | 零样本语音合成新模型;多维度评估LLM指令能力

本期的 8 篇论文如下: [00:25] 🗣 MiniMax-Speech: Intrinsic Zero-Shot Text-to-Speech with a Learnable Speaker Encoder(MiniMax-Speech:具有可学习说话人编码器的内在零样本语音合成) [01:00] 🤖 A Multi-Dimensional Constraint Framework for Evaluating and Improving Instruction Following in Large Language Models(用于评估和改进大型语言模型指令遵循能力的多维度约束框架) [01:47] 🎮 Measuring General Intelligence with Generated Games(基于生成游戏测量通用智能) [02:29] 🎦 SkillFormer: Unified Multi-View Video Understanding for Proficiency Estimation(SkillFormer:用于评估技能水平的统一多视角视频理解) [03:14] 🤖 NavDP: Learning Sim-to-Real Navigation Diffusion Policy with Privileged Information Guidance(NavDP:基于特权信息引导的Sim-to-Real导航扩散策略学习) [03:51] 🔍 Optimizing Retrieval-Augmented Generation: Analysis of Hyperparameter Impact on Performance and Efficiency(优化检索增强生成:超参数对性能和效率影响的分析) [04:28] 🇻 ViMRHP: A Vietnamese Benchmark Dataset for Multimodal Review Helpfulness Prediction via Human-AI Collaborative Annotation(ViMRHP:一个人机协作标注的越南语多模态评论有用性预测基准数据集) [05:04] 📖 Advancing Arabic Reverse Dictionary Systems: A Transformer-Based Approach with Dataset Construction Guidelines(推进阿拉伯语逆向词典系统:一种基于Transformer的方法与数据集构建指南) 【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

6分钟
87
4天前

2025.05.13 | 视觉-语言模型提升多模态能力;优化训练策略增强推理潜力。

本期的 15 篇论文如下: [00:24] 💡 Seed1.5-VL Technical Report(Seed1.5-VL 技术报告) [01:04] 🧠 MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining(MiMo:释放语言模型的推理潜力——从预训练到后训练) [01:48] 🖼 Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets(Step1X-3D:迈向高质量和可控的纹理3D资产生成) [02:29] 🤝 Learning from Peers in Reasoning Models(推理模型中的同伴学习) [03:08] 🎨 Unified Continuous Generative Models(统一连续生成模型) [03:49] 🤖 REFINE-AF: A Task-Agnostic Framework to Align Language Models via Self-Generated Instructions using Reinforcement Learning from Automated Feedback(REFINE-AF:一种通过强化学习和自动反馈,以自生成指令对齐语言模型的任务无关框架) [04:44] 💃 DanceGRPO: Unleashing GRPO on Visual Generation(DanceGRPO:在视觉生成领域释放GRPO的潜力) [05:25] 🧠 AttentionInfluence: Adopting Attention Head Influence for Weak-to-Strong Pretraining Data Selection(AttentionInfluence:采用注意力头影响进行弱到强预训练数据选择) [06:10] 🌐 WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratch(WebGen-Bench:评估大型语言模型从零生成交互式和功能性网站的能力) [06:53] 📈 Learning Dynamics in Continual Pre-Training for Large Language Models(大型语言模型持续预训练中的学习动态) [07:28] 🏆 Skywork-VL Reward: An Effective Reward Model for Multimodal Understanding and Reasoning(Skywork-VL Reward:一种用于多模态理解和推理的有效奖励模型) [08:11] 🧠 Reinforced Internal-External Knowledge Synergistic Reasoning for Efficient Adaptive Search Agent(用于高效自适应搜索代理的增强型内外知识协同推理) [08:50] 🤖 H$^{\mathbf{3}}$DP: Triply-Hierarchical Diffusion Policy for Visuomotor Learning(H$^{\mathbf{3}}$DP:用于视觉运动学习的三重分层扩散策略) [09:36] 🎨 Continuous Visual Autoregressive Generation via Score Maximization(基于得分最大化的连续视觉自回归生成) [10:26] 🧠 Overflow Prevention Enhances Long-Context Recurrent LLMs(溢出预防增强长文本循环LLM) 【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

11分钟
99+
5天前
EarsOnMe

加入我们的 Discord

与播客爱好者一起交流

立即加入

播放列表

自动播放下一个

播放列表还是空的

去找些喜欢的节目添加进来吧