👍 114
11/01 08:00
Agent decisions depend on empirical relationships that deployment observations reveal and task descriptions alone may leave unresolved. We introduce Decoupled Predictive Decision Making (DPDM), an architecture that formulates heterogeneous agent decisions as conditional prediction with a shared pret
中文介绍 针对异构代理决策依赖部署经验而任务描述不明确的问题,提出解耦预测决策(DPDM)架构,将决策形式化为基于共享预训练条件的预测问题,以利用观测关系并提升决策可靠性。
👍 96
11/05 08:00
Models for physical AI tasks, such as robotics and autonomous driving, need not reason solely in language. They can use visual plans--points, bounding boxes, and trajectories--to represent spatial goals and anticipate motion. However, autoregressive vision-language models generate these plans one co
中文介绍 针对自回归视觉语言模型生成视觉计划(点、框、轨迹)逐坐标生成、效率低下的问题,提出VFlash,通过闪式原语解码快速生成视觉计划,以实现高效的物理AI任务规划。
👍 95
11/05 08:00
Reliable robotic manipulation requires both semantic understanding and precise control in three-dimensional space. However, vision-language-action (VLA) foundations largely inherit visual representations from 2D vision-language pre-training, while spatial supervision is often introduced only during
中文介绍 针对视觉-语言-动作(VLA)模型依赖2D视觉预训练而缺乏空间监督的问题,提出SLA,通过持续预训练扩展空间-语言-动作模型,结合语义理解与3D精确控制,提升机器人操作的可靠性。
👍 55
11/03 08:00
Harness evolution from a common base exhibits Locality, Complementarity, and Nonstationarity: variants repair different failures, and their utility changes as the policy learns. Rather than seeking a universally superior harness, we introduce Harness-S to selectively rescue failures of a base execut
中文介绍 提出Harness-S,利用兄弟训练框架的局部性、互补性和非平稳性,选择性修复基础执行器的失败,而非寻找普遍最优的训练方式,实现更通用的代理训练。
👍 50
10/31 08:00
Benchmark compression reduces the often prohibitive time and cost of model evaluation by evaluating models on a small benchmark subset that closely matches full-benchmark results. To quantify estimation error, we derive an accurate analytical approximation to the error distribution when estimating f
中文介绍 提出BestRand基准压缩方法,通过精确的误差分布近似和随机选择子集,实现稳定且低成本的模型评估,在保持与全基准高度吻合的同时大幅降低评估时间和成本。
👍 39
11/05 08:00
We present WeLM-Image, a unified image foundation model that integrates multimodal understanding into text-to-image generation, instruction-guided editing, and multi-reference synthesis. Designed for single-GPU deployment in WeChat's large-scale consumer applications, the model processes text, refer
中文介绍 提出WeLM-Image,一个统一的图像基础模型,将多模态理解集成到文本到图像生成、指令引导编辑和多参考合成中。面向微信大规模消费应用,支持单GPU部署,实现高效的视觉智能。
👍 38
11/03 14:45
A frontier AI model is trained in an AI data center, on tens of thousands of accelerators joined by a dedicated network, and every training step ends with all of them exchanging data at once. Between racks, that network is optical, and each of its four layers, from lasers to switches, runs a fixed o
中文介绍 提出Halley预测控制平面,针对AI数据中心光网络中训练步骤间的集体通信,通过预测流量模式动态优化光网络层配置,以减少训练等待时间,提升网络利用率。
👍 20
11/02 08:00
Long-term memory enables large language model (LLM) agents to provide continuous personalized assistance by retaining user information across interactions. Existing systems support this process through fact extraction, organization, updating, and retrieval, but largely maintain memories as independe
中文介绍 提出EvoMemState,一种演化记忆状态机制,使LLM代理能够通过动态更新和关联记忆来提供持续个性化服务,克服传统独立记忆存储的局限性,实现长期记忆的有效利用。
👍 18
11/05 08:00
Autoregressive approaches with large language models, such as long chain-of-thought reasoning, have become the default for new AI applications because they reach higher accuracy on a wide range of tasks. In production, however, they give inconsistent answers, require parsing of outputs, and add cost
中文介绍 提出Drex,一种基础决策模型,采用非自回归方法进行预测,提供一致、可解析且低成本的决策,以替代LLM长链思维推理,适用于生产环境中的高效决策任务。
👍 18
11/04 08:00
Target-conditioned diffusion drafters predict candidate tokens in parallel, yet each new block must wait for updated target-model hidden states. This forces drafting and verification to run sequentially, limiting speedup even though each block is generated in one pass. We introduce D3D, a standalone
中文介绍 提出D3D,一种解耦扩散起草方法,用于异步推测解码。通过独立的目标条件扩散草稿模型,在生成新块时并行预测候选token,实现起草与验证异步进行,从而提升推理速度。
👍 17
11/03 08:00
Multimodal agents use web and image tools to answer questions beyond their internal knowledge. Some search tasks use images mainly to identify an initial entity, then rely on text retrieval. These tasks offer limited insight into how agents connect information across images, objects, and search step
中文介绍 提出VisSearch-Bench基准,评估多模态代理在长时视觉搜索任务中的能力,考察代理如何在图像、物体和搜索步骤间连接信息,以揭示多模态检索的性能瓶颈。
👍 16
11/01 22:05
LLM-based agentic systems are increasingly combined with CoT reasoning to solve tasks that require accurate reasoning, external knowledge, and multi-step deliberation. Yet, explicit CoT incurs substantial generation overhead, while implicit CoT, which replaces textual rationales with compact continu
中文介绍 提出TAC-CoT,通过交错显式token增强隐式链式思维,结合工具使用实现高效推理,减少生成开销并提升多步推理的准确性,适用于需要外部知识的任务。
👍 15
11/04 08:00
Egocentric human video offers a scalable source of manipulation priors for robot learning, yet translating raw data scale into generalizable robot policies demands rigorous data curation and training recipes. We introduce Open-HumanScale, the first fully open recipe for scaling egocentric pretrainin
中文介绍 提出Open-HumanScale,首个完全开放的食谱,用于扩展以自我为中心的人类视频预训练,通过严格的数据管理和训练策略,实现从人类经验到具身基础模型的可扩展学习。
👍 14
10/30 16:38
Computer-use agents increasingly tackle tasks ranging from everyday desktop activities to long-horizon professional workflows. Yet interfaces centered on screenshots and mouse-and-keyboard actions can impose a human-interaction prior, requiring repeated screen interpretation while leaving the comput
中文介绍 提出混合计算机使用界面,统一程序化、语义和视觉交互,使通用代理能够更高效地执行从桌面任务到长时专业工作流程的各类任务,减少屏幕解析开销。
👍 12
11/04 21:33
Prefill-to-Autoregressive Cross-model Transfer (PACT), a form of latent communication between language models, combines a larger model's prompt representations with a smaller model's efficient generation, offering a promising way to balance capability and inference cost. However, existing systems pr
中文介绍 探讨预填充到自回归的跨模型转移(PACT),通过更大模型的提示表示与较小模型的高效生成结合,平衡能力与推理成本,分析挑战并展望机会。
👍 11
11/05 00:46
Coding agents powered by models such as GPT-6-Astra connect spatial reasoning with executable robot behavior, raising the question of how such agents can produce lasting improvements in robot capabilities from physical interaction. In this work, we study embodied recursive self-improvement (RSI) thr
中文介绍 提出PyRUA-REAL,通过真实世界的机器人交互和递归自我改进(RSI),使编码代理能够从物理交互中产生持久的能力提升,实现机器人探索与自适应学习。
👍 9
11/02 08:00
Generative AI is billed per token, yet tokens are not equally expensive. Each token enters the KV-cache and raises the cost of those that follow, so energy grows non-linearly along a sequence whose tokens look identical. No analytical model states what a token costs, and the most accurate SOTA model
中文介绍 提出SIMPLE定律,用于描述LLM推理的能耗成本,通过分析KV缓存对后续token的影响,建立解析模型以准确估算每个token的能量消耗,优化生成成本。
👍 7
11/06 00:18
Mathematical modeling turns an open-ended real-world problem into assumptions, a model, a solution, and a defended recommendation, and its answers matter only if they are both close to a credible reference and physically feasible; existing benchmarks either score solver fragments or grade reports wi
中文介绍 提出终端风格数学建模基准,首个代理式且可验证的基准,评估数学建模全流程(假设、模型、求解、辩护),确保结果既接近可靠参考又物理可行。
👍 7
11/04 08:00
Chunk-interleaved full-duplex speech language models listen and speak in fixed time chunks, and each chunk must be processed before the next one arrives. Their workload is asymmetric across chunks: listen chunks leave compute idle while awaiting audio, and speak and tool-call chunks require serial g
中文介绍 提出推测性监听技术,用于块交错全双工语音语言模型。通过预测即将到来的音频块,在监听块期间并行处理,减少计算空闲,提高全双工交互的效率和实时性。
👍 5
11/04 02:59
For a decade, progress in artificial intelligence has been measured by how much a machine can do on its own. Large foundation models now write code and run multistep tasks, and personal agents act on a person's behalf. Yet people still forget what they once knew, miss what they are not looking at, f
中文介绍 探讨从自主代理到认知共生体的转变,提出AI增强人类智能的框架,强调基础模型与人类协作,弥补记忆和注意力局限,实现人机协同认知提升。