👍 194
09/22 20:00
Object permanence and solidity are hallmarks of human cognitive priors. Recent studies show that video generation models, a paradigmatic class of current world models, have begun to show emerged reasoning abilities, making them ideal candidates for building human-like physical intelligence. Do video
中文介绍 论文探讨了在世界模型中训练物体常存性的问题,提出了一种利用视频生成模型的方法。该方法利用视觉信息来实现人类认知的推理能力。研究表明,该模型成功地展示了其在动态环境中的推理能力,表明其在构建类人物理智能方面的潜力。意义:对世界模型和人类智能的关联研究具有重要影响。
👍 83
09/21 20:00
Long-term conversational memory in multi-party settings requires more than retrieving relevant content from long-term conversations: it must distinguish who said what, whom each statement concerns, how individuals perceive one another, what information is shared by the group, and how states change o
中文介绍 论文提出了SpeakerMem-R1,一种针对多方对话的以说话者为中心的双轨记忆系统,旨在提升对长时间对话的理解和记忆。该系统能有效区分每个说话者的发言内容及其关系,并适应对话过程中的状态变化。此方法为多方对话的长期记忆提供了新思路,推进了在社交AI中的应用研究。
👍 62
09/23 20:00
While Large Language Models (LLMs) rely on highly non-linear components, in this work we demonstrate that they exhibit fundamental linearity: when inputs from distinct text streams are linearly combined, the model outputs a superposition of the individual next-token distributions. We term this the S
中文介绍 研究表明,大型语言模型(LLMs)在处理不同文本流时,可以通过线性组合表现出线性叠加特性。论文定义了这种现象为Superposition,并探讨其在生成预测中的应用。这一发现对理解LLMs的内部机制及其在自然语言处理中的能力至关重要,可能会影响模型的设计和优化。
👍 47
09/18 20:00
Spatial reasoning is essential for vision-language models (VLMs) to understand and act in the physical world. Reasoning in dynamic environments requires VLMs to perceive local state transitions caused by object motion and viewpoint changes and integrate them over long trajectories to maintain an upd
中文介绍 论文提出Spatial-Interactor,一种通过与可观察物理世界的互动来学习空间推理的模型。该模型能够识别动态环境中的状态变化,并整合信息以维持对物体运动的理解。这一方法对视觉语言模型(VLMs)理解和行动具有重要意义,有助于提升智能体在真实世界中的表现。
👍 41
09/20 20:00
Evaluating world models requires assessing both the quality of the worlds they generate and their consistency and responsiveness under exploration, interaction, and modification. We introduce HappyWorld-Bench, a comprehensive benchmark that evaluates whether generated worlds remain reliable as agent
中文介绍 HappyWorld-Bench是一个全面的基准测试,旨在评估世界模型的生成质量、一致性及交互性。该基准测试不仅考虑生成世界的可靠性,还关注在特殊情况下的响应能力,有助于优化智能体在复杂环境中的表现。其重要性体现在提高世界模型的评估标准方面,促进人工智能的发展。
👍 39
09/22 20:00
Advances in generative models have improved video fidelity, enabling long-horizon generation, interactive world modeling, and evolving visual environments. Autoregressive (AR) video generation extends visual sequences through causal rollouts. However, a fundamental bottleneck emerges: as the generat
中文介绍 论文分析了自回归视频生成中的记忆机制,探讨了生成模型在长时间序列生成过程中的瓶颈。通过创新性的因果展开方法,研究找到了解决生成过程失效的方法,从而提高视频生成的连续性和自然性。这一领域的突破将对动态视觉内容的生成产生深远影响。
👍 34
09/22 20:00
Agentic memory systems reuse past experience to improve future performance, yet most existing designs curate memory at write time: once a task is completed, its trajectory is distilled into a fixed artifact, such as a reflection, workflow, skill, or reasoning strategy, that is later retrieved by sim
中文介绍 Just-in-Time Memory系统旨在为智能体学习提供任务自适应的记忆管理,改变以往在完成任务后固定存储记忆的方式,允许智能体根据任务需求动态调整记忆内容。这种方法提高了智能体在多任务处理中的灵活性和效率,推动了自适应记忆系统的研究。
👍 20
09/19 20:00
Humans can effortlessly localize the direction of a sound source and integrate it with visual cues for reasoning, yet this remains challenging for embodied agents. In particular, it is still unclear how to effectively evaluate and model spatial audio understanding in embodied settings. To address th
中文介绍 OmniEcho聚焦于赋能智能体理解空间音频,解决了人类如何有效定位声源以及将其与视觉线索整合的问题。论文提出了一种新的评估框架,支持在不同环境中测试空间音频理解能力,为增强现实和机器人等领域的应用提供了新的视角。
👍 16
09/22 20:00
Recent advances in large language models (LLMs) have enabled agents to tackle long-horizon tasks across diverse environments. To further improve agent performance, existing language world models typically predict environment observations, yet reconstructing high-entropy, execution-dependent tool res
中文介绍 本研究对大型语言模型(LLMs)的世界建模进行了重新思考,提出Agent-Editing World Model以提高在复杂环境中执行任务的能力。通过重建高熵、执行依赖工具的结果,该方法展示了提升智能体决策精度的潜力,推动了长远任务的执行及智能体性能的提升。
👍 16
09/21 20:00
Reinforcement learning has become a central component of large language model (LLM) post-training, yet token-level credit lacks a generally accepted mathematical definition, leaving its relationship to commonly used training signals unclear. We formulate three regularity conditions, namely Completen
中文介绍 这篇论文探讨了强化学习中信用分配的概念,提出了PACT框架,聚焦于在大规模语言模型(LLMs)后训练阶段中信用赋予与批评者对齐的问题。通过建立数学框架,作者明确了信用赋予与常用训练信号的关系,为随后深度学习的训练过程提供了新的见解。
👍 15
09/21 20:00
The rapid capability gains of frontier language models are widely attributed to improved reasoning abilities, yet this cannot be verified as raw CoT traces in closed-source systems are hidden. By registering a simple custom tool through a standard API feature, we induce frontier models to externaliz
中文介绍 论文揭示了前沿语言模型在推理能力快速提升背后的隐含思维链,由于封闭源系统的复杂性,验证这些改进的能力极为困难。通过API功能引入定制工具,促使模型外部化其推理过程,从而提供了研究推理机制的新途径。这一探索对于语言模型的解析与优化具有重要意义。
👍 12
09/23 20:00
Rufus-Air is an open and reproducible post-training recipe on GLM-4.5-Air-Base (106B-A12B), organized as a serial pipeline of eight stages: SFT, Reasoning RL, Coding RL, Instruction-Following RL, General Agent, Coding Agent, Search Agent, and RLHF. We document the data, reward design, infrastructure
中文介绍 Rufus-Air是一种开放、可复现的大型语言模型后训练方案,基于GLM-4.5-Air-Base设计, 包括多个阶段的管道处理。论文详细记录了数据、奖励设计和基础设施配置,为后续模型开发和应用奠定了实用基础,具有广泛的工程与科学探索潜力。
👍 11
09/19 20:00
Robotic bin packing requires long-horizon sequential decision-making, as each object placement affects the available space for subsequent packing. Existing methods primarily rely on hand-crafted geometric heuristics that optimize predefined objectives or reinforcement learning policies learned throu
中文介绍 PackLab框架为开发、训练和评估在机器人箱子装配中的多语言大模型(MLLMs)提供了全面的支持。这一方法通过应对每个物体放置所带来的限制,并优化现有的几何启发式和强化学习政策,提升了机器人箱子装配的效率,推动了这一领域的智慧化进程。
👍 11
09/22 20:00
Vision-Language-Action models provide a strong foundation for general-purpose robot control, yet a vast majority of policies do not preserve and leverage episode-level information beyond the current observation. This limitation is consequential in history-dependent manipulation tasks that depend on
中文介绍 MemBodied提出了在视觉-语言-行动模型中引入递归关联记忆的概念,以增强机器人在操控任务中的表现。该模型通过保存事件级别的信息,有效支持历史依赖的操作,显示了其在复杂任务中的实用性,对未来智能机器人系统的设计和控制意义重大。
👍 11
09/22 20:00
Language-model agents increasingly face long-horizon tasks with evolving state, interdependent decisions, and delayed outcomes. Scaling their training requires diverse agentic environments, dependable outcome signals, and low extension cost. Existing generation pipelines commonly construct an enviro
中文介绍 论文探讨了如何从已解决机制生成动态强化学习环境,以应对智能体在长时间任务中面临的挑战。提出了一种多样化的智能体环境生成管道,强调可依赖的结果信号与低扩展成本相结合。这项研究为未来的智能体训练提供了更强大的框架。
👍 10
09/23 20:00
The rapid progression of large language models is extending AI from passive content generation into the active workflows of engineering and scientific discovery. This shift raises a compelling question: can AI be both the object of development and an active participant in building next-generation AI
中文介绍 Qwen-Planner-Agent框架为真实世界中的移动规划智能体提供了一种闭环AI开发模式,探讨了AI在工程和科学发现中的主动参与。此框架推动了AI从内容生成过渡到主动工作流程,具有广泛的应用潜力,尤其是在智能应用程序开发领域。
👍 10
09/22 20:00
We present Hunyuan-A13B, an open-source large language model based on a Mixture-of-Experts architecture. It contains 80 billion total parameters but activates only 13 billion during inference, balancing model capability, computational efficiency, and deployment cost. The model is pretrained on a rig
中文介绍 Hunyuan-A13B是一种基于Mixture-of-Experts架构的开放源码大型语言模型,包含800亿参数,而推断时仅激活130亿,兼顾性能与计算效率。论文详细说明了预训练过程,有助于提升模型在实际应用中的部署效率,为轻量级语言模型的研究提供了借鉴。
👍 9
09/23 20:00
Deep search requires LLM agents to decompose complex queries, search for evidence, and synthesize grounded answers, yet existing ReAct-style agents suffer from two limitations: role coupling, where one policy must handle planning, evidence use, and synthesis; and context accumulation, where growing
中文介绍 IterSynth提出了一种通过角色解耦的迭代综合思想来重新思考深度搜索代理,旨在克服现有ReAct风格代理在规划与证据使用中的限制。论文讨论了有效分配角色与减少上下文累积的策略,推动了在复杂搜索任务中的智能体性能提升。
👍 9
09/22 20:00
AI research agents need reliable knowledge of how their experiments change outcomes. We introduce WhatWorkedBench to measure experimental understanding, the accuracy of predictions about component changes after budgeted experimentation. Agents inspect code, select measurements, and submit a response
中文介绍 WhatWorkedBench是一个新推出的基准工具,旨在评估AI研究代理对实验结果变化的理解能力。通过精确测量代理对实验组件变更的预测准确性,该基准为AI实验评估带来了新标准,有助于提升智能体在实验环境中的表现和学习效率。
👍 8
09/23 20:00
Task and motion planning (TAMP) problems remain difficult even with full observability and object-centric states because discrete decisions are tightly coupled to geometric, kinematic, and dynamic constraints. Generalized TAMP addresses this difficulty by exploiting regularities across problem insta
中文介绍 该论文研究了编码代理在广义任务和运动规划问题中的应用,探讨通过利用实例间的规律性来应对任务和运动规划(TAMP)的挑战。这一方法显示了在处理复杂约束下的决策能力,推动智能体在动态环境中的表现,有望应用于智能机器人和自动化领域。