👍 238
10/29 08:00
One-step and few-step text-to-image generation must accurately render the details specified in the prompt despite limited opportunities for refinement. Distribution matching distillation (DMD) uses score differences to bring the generated distribution closer to a reference distribution. Following pr
中文介绍 针对少步文生图模型细节渲染不足的问题,提出内在分布匹配蒸馏方法。通过利用分数差异将生成分布拉近参考分布,同时避免梯度干扰。该方法支持一步或多步生成,显著提升文本细节的忠实度,实现更准确的高保真图像合成。
👍 157
10/28 08:00
Recursive self-improvement requires models not only to acquire useful training experience, but also to decide when their current experience has ceased to be useful. Existing methods often focus on what experience to generate next, while paying less attention to when fresh experience should be introd
中文介绍 递归自提升通常依赖固定的经验生成策略,忽略了引入新经验的时机。A-RSI 提出自适应任务刷新机制,在零数据多模态自提升中动态决定何时更新训练任务。该方法能有效避免经验过时,提高模型持续学习效率和最终性能。
👍 143
10/21 08:00
A benchmark is not merely a collection of test questions; it naturally induces an empirical measure over difficulty. In this work, we develop this measure-based view of benchmark evaluation. This perspective allows us to identify and formalize two central failure modes: measure mismatch, where the b
中文介绍 将基准测试视为难度上的经验测度,形式化了两种主要失败模式:测度失配和覆盖率不足。此视角为基准设计提供了理论框架,揭示了现有评估在难度分布上的偏差,有助于更准确地解读模型性能差异和泛化能力。
👍 91
10/27 08:00
Diffusion vision-language models (DVLMs) process their entire input at every denoising step. Since visual tokens make up 89-97% of this input on the benchmarks we study, most of the decoding computation is spent repeatedly processing the same image. Visual token pruning methods partially relieve thi
中文介绍 扩散视觉语言模型在所有去噪步骤中处理全部视觉token,而视觉信息占比高达89-97%,计算效率低下。提出证书引导的视觉路由策略,仅在需要时处理关键视觉区域,显著减少重复计算。在保持生成质量的同时,大幅降低推理延迟。
👍 55
10/29 08:00
We present Youtu-Parsing-Omni, an omni-modal parser that converts documents, images, audio, and video into structured records grounded in space and time, providing a perception layer for agents that read, locate, and cite evidence across modalities. Its design rests on one encoder for every modality
中文介绍 提出Youtu-Parsing-Omni,一个统一的全模态解析器,将文档、图像、音频和视频转化为时空对齐的结构化记录。基于单一编码器与统一模式,为智能体提供跨模态的证据读取、定位与引用能力,简化了多模态信息处理流程。
👍 34
10/29 08:00
Interactive world models generate visual content conditioned on user actions, yet maintaining spatial consistency over long-horizon exploration in real time remains challenging. Existing approaches rely on either temporal context or explicit 3D memory, both of which scale poorly because memory grows
中文介绍 针对长时交互式世界生成中的空间一致性难题,提出L3G-World,采用潜在3D高斯记忆实现实时无限世界生成。通过将记忆存储于潜在空间而非显式3D结构,避免内存随探索增长而线性膨胀。在保持实时性能的同时,实现长期空间一致性。
👍 30
10/27 08:00
Scaling supervised training for working agents requires diverse professional tasks that yield reliable expert demonstrations. However, missing or inconsistent task information can obstruct teacher execution and weaken the resulting supervision. We propose WorkFactory, a scalable framework for constr
中文介绍 为可扩展智能体训练,提出WorkFactory框架,将专业意图转化为可执行任务。该框架自动生成多样化的专业任务,并确保缺失或不一致的信息被补充,从而产生可靠的专家演示。通过提升任务质量和监督信号,增强工作智能体的训练效果和泛化能力。
👍 28
10/23 08:00
Locating relevant evidence in long inputs is a core capability of Multimodal Large Language Models. Prior studies attribute this capability to retrieval heads, a sparse set of attention heads that transfer information from the context to the output. However, these analyses are confined to a limited
中文介绍 先前对多模态大语言模型检索头的研究局限于少量设置。本文在更广泛的模型、模态和输入长度上系统分析检索头行为,发现其功能与位置分布具有显著不一致性。研究揭示了检索头在长上下文证据定位中的核心作用,并为改进多模态注意力机制提供新见解。
👍 19
10/26 08:00
Evaluating human-AI co-design requires testing whether coding agents can translate real users' multimodal requests into working application revisions. We introduce Co-Design Bench, a reference-free benchmark of 273 tasks curated from 37,463 deduplicated queries across 26,314 real user coding session
中文介绍 提出Co-Design Bench,一个无参考基准,包含273个真实多模态协同编码任务,源自26,314个真实用户会话。用于评估编码智能体将用户多模态请求转化为可用应用修改的能力。该基准填补了人机协同设计的评估空白,支持对智能体协作质量的有效度量。
👍 18
10/22 08:00
Large language model agents have enabled software development through natural-language interaction, but extending this paradigm to end-to-end game development remains challenging. Building a playable game requires coordinating code, scenes, assets, animations, physics, and configurations, while allo
中文介绍 针对端到端游戏开发中代码、场景、资源与物理引擎协调的复杂性,提出VibeGame框架,采用AI原生引擎与自进化对抗智能体团队。通过自然语言提示实现从概念到可玩游戏的全流程开发,对抗智能体自动发现并修复缺陷,提升开发效率与生成质量。
👍 17
10/28 08:00
Producing long-form videos from narration requires interdependent decisions that remain coherent across shots. Existing agentic editors often use multi-stage workflows driven by general models, leaving the quality-cost trade-off of compact, task-adapted policies unclear. We address this gap with WeV
中文介绍 针对长视频叙述编辑中的连贯性决策问题,提出WeVisCut,一个紧凑型智能体,整合整个编辑流程从旁白到长视频生成。相比多阶段通用模型工作流,该智能体在成本与质量间取得更优平衡,能够生成连贯的镜头序列,并显著降低计算开销。
👍 17
10/15 08:00
Command-line interface (CLI) agents increasingly execute longer-horizon tasks, yet existing benchmarks either assume that user instructions remain fixed throughout execution or evaluate task outcomes without capturing runtime collaboration quality. In this paper, we present REALCLI, a paired benchma
中文介绍 现有CLI智能体基准常假设指令固定或忽略实时协作质量。提出REALCLI,一个成对基准,动态捕获执行过程中的人机协作互动。通过匹配真实用户指令和运行时反馈,更全面地评估智能体在长时任务中的协作能力,弥补现有评估不足。
👍 15
10/16 08:00
Computer-use agents (CUAs) are commonly evaluated against fixed task specifications, but users may omit requirements, add constraints, or require approval before consequential actions. Completing the benchmark instruction does not guarantee serving the person who asked. We introduce PersonaCUABench,
中文介绍 计算机使用智能体常被固定任务规范评估,忽略了用户可能省略需求或添加约束。引入PersonaCUABench,一个覆盖多样用户角色的基准,测试智能体在模糊、附加条件或需批准场景中的服务能力。强调满足个性化需求而非仅完成任务指令,提升评估的实用性。
👍 11
10/15 08:00
Spoken Dialogue Models (SDMs) typically share a speech-token space for generation and synthesis, leading to long autoregressive sequences and costly inference. Lower-rate speech tokenizers shorten sequences but may introduce compression-quality trade-offs and costly replacement without breaking this
中文介绍 口语对话模型通常共享语音token空间,导致生成序列长、推理成本高。提出CoSTA,压缩语音token自适应技术,采用低速率分词器缩短序列,同时通过自适应调整保持生成质量。在保证对话流畅性的同时,显著降低推理延迟和计算开销。
👍 11
10/27 08:00
Web agents require diverse, executable, and resettable website environments for reproducible training and evaluation. Human-assisted mirrors demand per-site engineering, while generative construction can diverge from specified real websites. Capture-and-replay preserves observations, with interactio
中文介绍 为可扩展智能体训练,提出WebAnything,从真实网页自动构建可执行、可重置的网站环境。方法结合捕获-重放与生成技术,保持与指定网站的交互真实性,同时支持环境重置和扩展。该框架为web智能体提供了多样化、可复现的测试与训练平台。
👍 10
10/28 08:00
Recent advances in multimodal large language models have increased interest in interaction paradigms for video understanding. The evolution from offline to streaming and proactive interaction has gradually shifted models from passive responders toward more proactive agents that can decide when to an
中文介绍 多模态大语言模型在流式视频理解中常被动响应,缺乏主动提问能力。提出AskStream,让模型在不确定时自主决定何时提问及问什么。通过主动交互机制,模型能针对性获取缺失信息,提高流式视频理解的准确性和互动效率。
👍 10
09/30 08:00
Many Indian banks serve customers through FAQ pages and scripted chatbots. Assistants based on language models could respond faster and carry out requests such as blocking a card, but only if they give correct information and follow the bank's rules. These rules prescribe a procedure, a set of requi
中文介绍 许多印度银行仅提供FAQ和脚本化聊天机器人。提出TauIndianBankBench,一个过程感知、行动导向的基准,测试工具使用对话智能体是否遵循银行规则执行操作。该基准包含程序化任务,评估智能体在真实银行规则下的正确性与合规性。
👍 9
10/28 08:00
Multi-Token Prediction (MTP) is now a common ingredient in language-model pre-training, as it improves downstream performance and enables faster inference through speculative decoding. We identify a flaw in standard MTP training, in which a residual component of the MTP gradient interferes with both
中文介绍 标准多token预测训练中存在梯度干扰成分,影响性能并阻碍投机解码加速。本文识别该缺陷并提出改进训练方法,消除残留干扰。优化后的MTP训练在预训练中提升下游性能,并保持更快的推理速度,实现更高效的模型训练。
👍 9
10/28 08:00
Financial agents must form forecasts and investment judgments from decision-time evidence, with predictions evaluated against subsequent outcomes. Existing benchmarks assess financial knowledge, research workflows, or forecasting, but evaluating the full research process requires a strictly frozen i
中文介绍 评估金融智能体需严格冻结决策时信息以防未来数据泄露。提出Investor's Last Exam,一个冻结时点基准,测试AI智能体是否能在不预见未来的情况下进行股权研究。涵盖完整研究流程,评估预测与投资决策能力,促进金融AI评估的严谨性。
👍 8
10/27 08:00
Low-cost arms such as the SO-101 have become the most common entry point to robot learning, yet no released policy performs spatially constrained, language-conditioned tasks on them out of the box, and existing SO-101 benchmarks run only on physical hardware with simple tasks and few held-out object
中文介绍 低成本机械臂如SO-101虽普及,但缺乏现成的空间约束、语言条件策略。提出SO-101 Bench,一个可访问的空间操作基准,设计多样任务并评估策略泛化。该基准支持在真实硬件上进行复杂操作,促进机器人学习的可访问性和可复现性。