HuggingFace 每日AI论文速递 - 节目列表

本期的 13 篇论文如下：[00:25] 🗺 RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation（RPG：用于统一可扩展代码库生成的仓库规划图）[01:00] 🌉 MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer（MANZANO：基于混合视觉词元器的简洁可扩展统一多模态模型）[01:42] 🧩 Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification（潜区分网络：生成建模、表示学习与分类的统一原理）[02:25] 🎯 BaseReward: A Strong Baseline for Multimodal Reward Model（BaseReward：多模态奖励模型的强力基线）[02:56] 🏠 SPATIALGEN: Layout-guided 3D Indoor Scene Generation（SpatialGen：布局引导的3D室内场景生成）[03:46] 🧠 BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent（BTL-UI：面向GUI智能体的“眨眼-思考-连接”脑启发推理模型）[04:30] 🎭 Lynx: Towards High-Fidelity Personalized Video Generation（Lynx：面向高保真个性化视频生成）[05:20] 🤖 A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning（用于机器人真实强化学习的视觉-语言-动作-评价模型）[05:54] 📹 RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes（动态场景下仅基于RGB视频监督的相机参数优化）[06:21] 🗣 Do You Hear What I Mean? Quantifying the Instruction-Perception Gap in Instruction-Guided Expressive Text-To-Speech Systems（你听见的是我想表达的吗？量化指令感知差距的表达型文本转语音系统研究）[07:07] 🎬 Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents（Video2Roleplay：面向视频引导角色扮演智能体的多模态数据集与框架）[07:50] 🗣 WhisTLE: Deeply Supervised, Text-Only Domain Adaptation for Pretrained Speech Recognition Transformers（WhisTLE：面向预训练语音识别Transformer的纯文本深度监督域适应方法）[08:30] 🗣 Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue（主动询问以澄清：通过多轮对话消解指令歧义）【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速递在小宇宙查看该单集文稿

本期的 5 篇论文如下：[00:43] TOP1(🔥95) | 🌍 OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling（OmniWorld：面向4D世界建模的多领域多模态大规模数据集）[02:51] TOP2(🔥93) | 🔍 WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research（WebWeaver：面向开放型深度研究的动态提纲式网络证据结构化框架）[05:09] TOP3(🔥91) | 🤖 Scaling Agents via Continual Pre-training（基于持续预训练扩展智能体系统规模的研究）[07:33] TOP4(🔥88) | 🖥 ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data（ScaleCUA：基于跨平台数据的开源计算机智能体规模化方案）[10:48] TOP5(🔥79) | 🌊 FlowRL: Matching Reward Distributions for LLM Reasoning（FlowRL：通过流匹配奖励分布提升大语言模型推理能力）【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速递在小宇宙查看该单集文稿

本期的 15 篇论文如下：[00:26] 🖥 ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data（ScaleCUA：基于跨平台数据的开源计算机智能体规模化方案）[01:01] 🌊 FlowRL: Matching Reward Distributions for LLM Reasoning（FlowRL：通过流匹配奖励分布提升大语言模型推理能力）[01:57] 🧭 Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Delibration（跨越边界推理：借助测试时深思提升规范对齐）[02:55] 🧬 Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation（无需标签即可让语言模型自我进化：多数选择驱动，新颖性促进变异）[03:34] 🎨 Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation（先理解再生成：面向自回归图像生成的自引导训练）[04:12] 🔍 FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning（FinSearchComp：迈向真实专家级金融搜索与推理评测）[04:56] 🤖 RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation（RynnVLA-001：利用人类示范提升机器人操作能力）[05:39] 🔮 AToken: A Unified Tokenizer for Vision（AToken：面向视觉的统一Tokenizer）[06:10] 🌌 WorldForge: Unlocking Emergent 3D/4D Generation in Video Diffusion Model via Training-Free Guidance（WorldForge：无需训练即可在视频扩散模型中解锁3D/4D生成的涌现能力）[06:58] 🖼 MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Tasks（MultiEdit：面向多样复杂任务的指令式图像编辑新突破）[07:54] 🎮 RecoWorld: Building Simulated Environments for Agentic Recommender Systems（RecoWorld：为智能推荐系统打造仿真训练沙盒）[08:28] 🎯 Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding（释放多模态大模型零样本时空视频定位潜能）[09:03] 🔍 Mind the Gap: A Closer Look at Tokenization for Multiple-Choice Question Answering with LLMs（留意空格：面向LLM选择题问答的Tokenization再审视）[09:51] 🩺 EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence（EchoVLM：面向通用超声智能的动态混合专家视觉-语言模型）[10:34] 🛰 FSG-Net: Frequency-Spatial Synergistic Gated Network for High-Resolution Remote Sensing Change Detection（FSG-Net：频-空协同门控网络用于高分辨率遥感变化检测）【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速递在小宇宙查看该单集文稿

本期的 14 篇论文如下：[00:19] 🐪 Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale（Hala技术报告：规模化构建阿拉伯语为中心的指令与翻译模型）[00:56] 🚀 SAIL-VL2 Technical Report（SAIL-VL2技术报告）[01:42] 🌐 PANORAMA: The Rise of Omnidirectional Vision in the Embodied AI Era（全景视界：具身AI时代的360°视觉崛起）[02:33] 🎓 GenExam: A Multidisciplinary Text-to-Image Exam（GenExam：多学科文本到图像生成考试基准）[03:25] 🧹 Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning（擦除敏感记忆！用机器遗忘技术为代码大模型“去隐私”）[03:59] 🩺 MedResearcher-R1: Expert-Level Medical Deep Researcher via A Knowledge-Informed Trajectory Synthesis Framework（MedResearcher-R1：基于知识引导轨迹合成的专家级医学深度研究智能体）[04:37] 🔍 MARS2 2025 Challenge on Multimodal Reasoning: Datasets, Methods, Results, Discussion, and Outlook（MARS2 2025多模态推理挑战赛：数据集、方法、结果、讨论与展望）[05:22] 🎭 Wan-Animate: Unified Character Animation and Replacement with Holistic Replication（Wan-Animate：统一角色动画与替换的完整复现框架）[05:59] 🧮 THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning（THOR：融合工具的分层强化学习优化数学推理）[06:40] 🔍 Improving Context Fidelity via Native Retrieval-Augmented Reasoning（提升上下文保真度的原生检索增强推理方法）[07:20] 🌍 AERIS: Argonne Earth Systems Model for Reliable and Skillful Predictions（AERIS：面向可靠且高技巧地球系统预测的阿尔贡地球系统模型）[08:13] 🎛 SteeringControl: Holistic Evaluation of Alignment Steering in LLMs（SteeringControl：对大模型对齐操控的全景评估）[08:48] ⚛ Quantum Variational Activation Functions Empower Kolmogorov-Arnold Networks（量子变分激活函数赋能Kolmogorov-Arnold网络）[09:37] 🚀 Hybrid Quantum-Classical Model for Image Classification（用于图像分类的混合量子-经典模型）【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速递在小宇宙查看该单集文稿

本期的 11 篇论文如下：[00:27] 🔍 WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research（WebWeaver：面向开放型深度研究的动态提纲式网络证据结构化框架）[01:08] 🤖 Scaling Agents via Continual Pre-training（基于持续预训练扩展智能体系统规模的研究）[01:52] ⛵ WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning（WebSailor-V2：依托合成数据与可扩展强化学习跨越开源与私有代理鸿沟）[02:36] 🧠 Towards General Agentic Intelligence via Environment Scaling（迈向通用智能体的环境规模化之路）[03:09] 🔍 WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents（WebResearcher：在长程智能体中释放无界推理能力）[03:59] 🧠 ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization（ReSum：基于上下文压缩的无限视界搜索智能解锁）[04:39] 🚀 Single-stream Policy Optimization（单流策略优化：大语言模型强化学习的去组化革新）[05:19] 🎮 Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation（Hunyuan3D工作室：面向游戏级3D资产生成的端到端AI管线）[06:00] 🧩 3D Aware Region Prompted Vision Language Model（具备3D感知能力的区域提示视觉语言模型）[06:36] 💡 EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving（EconProver：面向自动定理证明的更经济测试时扩展方法）[07:07] ⚛ Exact Coset Sampling for Quantum Lattice Algorithms（量子格点算法的精确陪集采样）【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速递在小宇宙查看该单集文稿

本期的 14 篇论文如下：[00:24] 🌍 OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling（OmniWorld：面向4D世界建模的多领域多模态大规模数据集）[01:12] 🤖 UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning（UI-S1：基于半在线强化学习的图形界面自动化新进展）[01:51] 🏠 InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts（InternScenes：具备真实布局的大规模可模拟室内场景数据集）[02:27] 🖱 LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondence（LazyDrag：通过显式对应关系在多模态扩散Transformer上实现稳定拖拽编辑）[02:58] 📊 Locality in Image Diffusion Models Emerges from Data Statistics（图像扩散模型中的局部性源于数据统计特性）[03:29] 🤔 Measuring Epistemic Humility in Multimodal Large Language Models（多模态大模型中的认知谦逊评估研究）[03:57] 🤖 Nav-R1: Reasoning and Navigation in Embodied Scenes（Nav-R1：具身场景中的推理与导航）[04:25] 🔍 Lost in Embeddings: Information Loss in Vision-Language Models（迷失在嵌入空间：视觉-语言模型中的信息损失）[04:54] 🌐 CognitiveSky: Scalable Sentiment and Narrative Analysis for Decentralized Social Media（CognitiveSky：面向去中心化社交媒体的情感与叙事可扩展分析框架）[05:19] 🔍 Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models（再审视，慢思考：增强视觉语言模型的视觉反思能力）[05:57] 🧠 EthicsMH: A Pilot Benchmark for Ethical Reasoning in Mental Health AI（心理健康AI伦理推理的试验基准：EthicsMH）[06:30] ⚖ Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting（通过动态奖励加权实现多目标对齐优化学习）[07:16] 🧠 PersonaX: Multimodal Datasets with LLM-Inferred Behavior Traits（PersonaX：基于大语言模型推断行为特质的多模态数据集）[07:52] 🔍 GAPrune: Gradient-Alignment Pruning for Domain-Aware Embeddings（GAPrune：面向领域感知嵌入的梯度对齐剪枝方法）【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速递在小宇宙查看该单集文稿

本期的 14 篇论文如下：[00:25] 📚 IntrEx: A Dataset for Modeling Engagement in Educational Conversations（IntrEx：面向教育对话中参与度建模的数据集）[01:02] 📏 The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs（“收益递减的幻觉”：衡量大语言模型的长时程执行能力）[01:54] 🧩 X-Part: high fidelity and structure coherent shape decomposition（X-Part：高保真且结构一致的三维形状分解）[02:33] 🖼 InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesis（InfGen：分辨率无关的可扩展图像合成新范式）[03:04] 🔍 HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering（HANRAG：面向多跳问答的启发式精准抗噪检索增强生成方法）[03:50] 🎙 VStyle: A Benchmark for Voice Style Adaptation with Spoken Instructions（VStyle：基于语音指令的语音风格自适应基准）[04:44] 🌸 FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies（FLOWER：以高效视觉-语言-动作流策略普及通用机器人策略）[05:20] 🎨 Inpainting-Guided Policy Optimization for Diffusion Large Language Models（面向扩散大语言模型的基于文本补全引导的策略优化方法）[05:58] 🤖 Virtual Agent Economies（虚拟代理经济）[06:28] 📈 QuantAgent: Price-Driven Multi-Agent LLMs for High-Frequency Trading（QuantAgent：面向高频交易的价格驱动多智能体大语言模型框架）[07:02] 🧪 MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools（MCP-AgentBench：基于MCP中介工具的通用语言智能体真实性能评测）[07:41] 🎨 Color Me Correctly: Bridging Perceptual Color Spaces and Text Embeddings for Improved Diffusion Generation（精准上色：连接感知色彩空间与文本嵌入以提升扩散生成质量）[08:31] 🦎 LoFT: Parameter-Efficient Fine-Tuning for Long-tailed Semi-Supervised Learning in Open-World Scenarios（LoFT：面向开放世界长尾场景的参数高效半监督微调方法）[09:13] 🗞 CMHG: A Dataset and Benchmark for Headline Generation of Minority Languages in China（CMHG：中国少数民族语言新闻标题生成数据集与评测基准）【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速递在小宇宙查看该单集文稿

本期的 5 篇论文如下：[00:40] TOP1(🔥455) | 🤝 Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing（共享即关爱：基于集体RL经验共享的高效大模型后训练）[03:19] TOP2(🔥163) | 🤖 VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model（VLA-Adapter：面向小型视觉-语言-动作模型的有效范式）[05:44] TOP3(🔥156) | 🤔 Why Language Models Hallucinate（语言模型为何产生幻觉）[07:57] TOP4(🔥139) | 💡 Reverse-Engineered Reasoning for Open-Ended Generation（面向开放式生成的逆向工程推理）[10:35] TOP5(🔥131) | 🧠 A Survey of Reinforcement Learning for Large Reasoning Models（大型推理模型的强化学习综述）【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速递在小宇宙查看该单集文稿

本期的 15 篇论文如下：[00:27] 🎭 HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning（HuMo：通过协同多模态条件控制实现以人为中心的视频生成）[01:18] 🤖 SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning（SimpleVLA-RL：通过强化学习实现VLA训练规模化）[02:02] 🗣 EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs（EchoX：基于回声训练弥合声学-语义鸿沟的语音大模型研究）[02:37] 🎭 Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis（Kling-Avatar：面向级联长时化身动画合成的多模态指令语义落地方法）[03:11] 🧭 Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents（驾驭不确定性：面向长周期LLM智能体的熵调制策略梯度方法）[03:57] 🎨 FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark（FLUX-Reason-6M和PRISM-Bench：百万级文生图推理数据集与全面评测基准）[04:34] 🤖 VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model（VLA-Adapter：面向小型视觉-语言-动作模型的有效范式）[05:14] 🔄 Can Understanding and Generation Truly Benefit Together -- or Just Coexist?（理解与生成真能互惠共进，抑或仅共存？）[05:46] 📹 SpatialVID: A Large-Scale Video Dataset with Spatial Annotations（SpatialVID大规模带空间标注的视频数据集）[06:16] 📊 Visual Programmability: A Guide for Code-as-Thought in Chart Understanding（视觉可编程性：面向图表理解的Code-as-Thought指南）[06:55] 🕵 Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval（梯度-注意力引导的双重掩码协同框架用于鲁棒的基于文本的人物检索）[07:35] 🖼 2D Gaussian Splatting with Semantic Alignment for Image Inpainting（面向图像修复的语义对齐2D高斯泼溅）[08:10] 📏 LoCoBench: A Benchmark for Long-Context Large Language Models in Complex Software Engineering（LoCoBench：面向复杂软件工程的长上下文大模型基准测试）[08:45] 🤖 OmniEVA: Embodied Versatile Planner via Task-Adaptive 3D-Grounded and Embodiment-aware Reasoning（OmniEVA：面向具身任务的自适应3D感知与本体约束联合规划器）[09:31] 🎯 The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward（散度选择：缓解可验证奖励强化学习多样性坍缩的关键）【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速递在小宇宙查看该单集文稿

本期的 10 篇论文如下：[00:24] 🧠 A Survey of Reinforcement Learning for Large Reasoning Models（大型推理模型的强化学习综述）[00:45] 🔄 RewardDance: Reward Scaling in Visual Generation（RewardDance：视觉生成中的奖励缩放）[01:08] 🌐 3D and 4D World Modeling: A Survey（3D和4D世界建模：一项综述）[01:41] 🤖 AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning（AgentGym-RL: 通过多轮强化学习训练用于长视野决策制定的LLM智能体）[02:08] 🧩 P3-SAM: Native 3D Part Segmentation（P3-SAM：原生3D部分分割）[02:40] 🌐 Hunyuan-MT Technical Report（Hunyuan-MT技术报告）[03:08] ⚠ <think> So let's replace this phrase with insult... </think> Lessons learned from generation of toxic texts with LLMs（从LLM生成有毒文本中吸取的经验教训）[03:44] 🤖 EnvX: Agentize Everything with Agentic AI（EnvX：使用代理式AI实现万物代理化）[04:13] 🤔 The Majority is not always right: RL training for solution aggregation（多数并不总是正确：用于解决方案聚合的强化学习训练）[04:33] 🤖 HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants（HumanAgencyBench：AI助手中人类代理支持的规模化评估）【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速递在小宇宙查看该单集文稿

本期的 14 篇论文如下：[00:22] 🧠 Parallel-R1: Towards Parallel Thinking via Reinforcement Learning（Parallel-R1: 通过强化学习实现并行思维）[00:50] 🔍 Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search（Mini-o3：扩展视觉搜索中的推理模式与交互轮次）[01:15] 👁 Visual Representation Alignment for Multimodal Large Language Models（多模态大语言模型的视觉表征对齐）[01:54] 🔄 Reconstruction Alignment Improves Unified Multimodal Models（重建对齐改进统一多模态模型）[02:19] 🔄 UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward（UMO：通过匹配奖励扩展图像定制中的多身份一致性）[02:46] 🧠 Curia: A Multi-Modal Foundation Model for Radiology（Curia：一种用于放射学的多模态基础模型）[03:06] 🔮 F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions（F1：一种连接理解与生成到行动的视觉-语言-行动模型）[03:33] 🧠 Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding（保持在最佳状态：通过能力自适应提示脚手架实现响应式推理进化）[03:56] 🔄 Language Self-Play For Data-Free Training（语言自我博弈用于无数据训练）[04:22] 🔍 Causal Attention with Lookahead Keys（带前瞻键的因果注意力）[04:43] 🎨 Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference（直接将完整扩散轨迹与细粒度人类偏好对齐）[05:07] ✅ SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge（SimpleQA Verified：衡量参数化知识的可靠事实性基准）[05:30] 🚀 Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling（Q-Sched：通过量化感知调度推动少步扩散模型的边界）[06:01] 📈 $ΔL$ Normalization: Rethink Loss Aggregation in RLVR（$ΔL$ 归一化：重新思考RLVR中的损失聚合）【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速递在小宇宙查看该单集文稿

本期的 15 篇论文如下：[00:21] 💡 Reverse-Engineered Reasoning for Open-Ended Generation（面向开放式生成的逆向工程推理）[00:47] 🌐 WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents（WebExplorer：探索与演进，用于训练长周期网络智能体）[01:17] 🚀 Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models（革新扩散大语言模型的强化学习框架）[01:38] 🤔 Does DINOv3 Set a New Medical Vision Standard?（DINOv3 能否树立医学视觉新标准？）[02:06] 🛠 Reinforced Visual Perception with Tools（基于工具的强化视觉感知）[02:26] 🤖 Reinforcement Learning Foundations for Deep Research Systems: A Survey（深度研究系统中的强化学习基础：综述）[02:55] 👁 Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning（通过对比注意力聚焦：增强VLM的视觉推理能力）[03:28] 🎥 UniVerse-1: Unified Audio-Video Generation via Stitching of Experts（UniVerse-1：通过专家模型拼接实现统一音视频生成）[03:50] 🤔 Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?（绘画易于思考：文生图模型能布景，但无法主导剧情吗？）[04:12] 🤔 Interleaving Reasoning for Better Text-to-Image Generation（通过交错推理提升文本到图像生成）[04:37] 🤖 Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agents（Paper2Agent：将研究论文重构为交互式可靠的AI代理）[05:05] ⚙ Guided Decoding and Its Critical Role in Retrieval-Augmented Generation（引导式解码及其在检索增强生成中的关键作用）[05:36] 🚀 Scaling up Multi-Turn Off-Policy RL and Multi-Agent Tree Search for LLM Step-Provers（扩展用于大型语言模型分步证明器的多轮离策略强化学习和多智能体树搜索）[06:04] 🛡 \texttt{R$^\textbf{2}$AI}: Towards Resistant and Resilient AI in an Evolving World（R$^2$AI：迈向演进世界中的抵抗性与韧性AI）[06:30] 🌍 Llama-GENBA-10B: A Trilingual Large Language Model for German, English and Bavarian（Llama-GENBA-10B：一个德语、英语和巴伐利亚语三语大型语言模型）【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速递在小宇宙查看该单集文稿