👍 97
06/17 08:00
While 10B-level industrial foundation models have pushed the boundaries of image inpainting, their prohibitive computational costs severely hinder practical deployment. Constructing a highly optimized task-specific specialist offers a promising solution; however, extreme structural compression inevi
中文介绍 提出Moebius,0.2B参数的轻量级图像修复框架,通过极端结构压缩达到10B级性能,大幅降低计算成本,实现高效部署。
👍 61
06/13 08:00
Dexterous interaction with articulated objects is important for household, assistive, and humanoid manipulation, where multi-finger hands can provide compliant contact patterns beyond parallel-jaw grasping. However, articulated-object manipulation differs from static-object manipulation: the target
中文介绍 提出DragMesh-2,实现物理合理的灵巧手与铰接物体交互,通过多指手提供合规接触模式,提升操控真实感和泛化能力。
👍 41
06/17 08:00
Motion forecasting is central to visual intelligence: agents must anticipate how objects will move in order to plan actions, reason about physical interactions, and synthesize realistic futures. We argue that 3D points in world coordinates provide a general representation that is class-agnostic, vie
中文介绍 提出MolmoMotion,基于语言指令预测3D世界坐标点的轨迹,以类无关通用表示实现运动预测,支持物理交互推理。
👍 35
06/17 08:00
Current agentic robot systems can write executable Code-as-Policy programs, observe feedback, and revise behavior across multiple attempts, but they remain largely task-driven: reusable skills are acquired only after explicit instructions. We study Playful Agentic Robot Learning, where an embodied c
中文介绍 研究Playful Agentic Robot Learning,让机器人通过「玩耍」自主学习可复用技能,无需明确指令,减少人工监督并提升效率。
👍 27
06/18 08:00
Real-world spatial intelligence requires reasoning over a continuous and evolving 3D world, yet existing VLMs and tool-augmented agents largely remain tied to static, stateless inference from isolated visual observations. We introduce \textsc{S-Agent}, a spatial tool-use agentic paradigm for underst
中文介绍 提出S-Agent,通过空间工具使用范式实现连续3D世界推理,突破VLMs和工具智能体在静态场景中的局限。
👍 26
06/18 08:00
LiveCodeBench (LCB) has recently become a widely adopted benchmark for evaluating large language models (LLMs) on code-generation tasks. By curating competitive programming problems, constantly adding fresh problems to the set, and filtering them by release dates, LCB provides contamination-aware ev
中文介绍 扩展LiveCodeBench至多编程语言(Multi-LCB),持续更新竞编程题目并过滤污染,提供更全面的跨语言代码生成评估基准。
👍 21
06/18 08:00
Agent benchmarks are growing fast, but no single benchmark touches more than four or five of the dimensions that deployment exposes. This paper aggregates the largest coordinated deep-dive of one MCP-based industrial-agent benchmark to date: fourteen parallel implementation studies covering new asse
中文介绍 综合14项并行实现研究,提出超越静态排行榜的评估框架,强调LLM智能体评测的预测有效性,覆盖部署关键维度。
👍 18
06/18 08:00
Style-content dual-reference generation aims to synthesize an image that preserves the structure and semantics of a content reference while adopting the style of a separate style reference.Despite recent progress, this setting remains challenging because models must balance content fidelity, style a
中文介绍 提出FreeStyle,从社区LoRA挖掘实现风格-内容双参考生成,平衡内容保真度与风格迁移,提升生成质量。
👍 9
06/18 08:00
Advances in radiance fields have enabled photorealistic novel view synthesis. In several domains, large-scale real-world datasets have been developed to support comprehensive benchmarking and to facilitate progress beyond scene-specific reconstruction. However, for distractor-free radiance fields, a
中文介绍 构建DF3DV-1K大规模无干扰新视角合成数据集,含1000个场景,为无干扰辐射场提供全面基准,推动场景无关重建进展。
👍 8
06/16 08:00
As an increasing majority of global video content is consumed on social platforms for interactive social purposes, video generation models built for social worlds are important but largely overlooked by previous studies. In this work, we define the position of social world models and build a prototy
中文介绍 定义社交世界模型及原型MaineCoon,针对社交平台交互视频生成,实现实时音视频一致的社交内容合成。
👍 7
06/18 08:00
Achieving dexterous robotic manipulation in the real world heavily relies on human supervision and algorithm engineering, which becomes a central bottleneck in the pursuit of general physical intelligence. Although emerging coding agents can generate code to automate algorithm search, their successe
中文介绍 提出ENPIRE,实现真实世界中机器人策略自改进,通过编码智能体自动搜索算法,减少灵巧操作人工监督瓶颈。
👍 6
06/12 08:00
Vision Transformers (ViTs) have become a dominant architecture for visual representation learning, providing exceptionally strong and broadly reusable backbone features. However, ViTs are commonly operated on relatively small patch-token grids due to the quadratic cost of global self-attention, whic
中文介绍 提出ViT-Up,对Vision Transformer特征进行忠实上采样,克服全局自注意力低分辨率限制,保留细节并提升可重用性。
👍 4
06/15 08:00
Large language models (LLMs) often fail when answering requires identifying a small but decisive piece of evidence within a long or complex context, such as a single line in a tool trace or a subtle detail in an image. We propose ContextRL, a context-aware reinforcement learning (RL) method that imp
中文介绍 提出ContextRL,上下文感知强化学习方法,提升LLM在长复杂语境中识别关键证据的能力,改进智能体与多模态问答。
👍 4
06/15 08:00
Recent retrieval-augmented generation (RAG) approaches have demonstrated strong capability in handling complex queries, yet current research overlooks a critical challenge: different retrievers require fundamentally different query formulation strategies for optimal performance. In this work, we pre
中文介绍 研究环境感知信息检索中不同检索器对查询策略的需求差异,揭示适配策略对RAG性能的关键影响。
👍 4
06/17 08:00
Multi-step LLM pipelines fail through interactions among retrieval, reasoning, and formatting steps, so prompt-only optimization can miss bottlenecks in the chain. We present FAPO (Fully Autonomous Prompt Optimization), a framework that lets Claude Code optimize an LLM pipeline inside a standardized
中文介绍 提出FAPO框架,让Claude Code全自动优化多步LLM流水线中的提示,解决检索、推理、格式化步骤间交互失败问题。
👍 4
06/15 08:00
Visual thinking should not only sound right; it should show its evidence. While recent vision-language models (VLMs) can produce natural-language reasoning traces, these traces often leave the supporting image regions implicit, making them hard to verify and difficult to supervise. We introduce visu
中文介绍 引入视觉接地推理,让VLM产生推理轨迹时显式定位支持图像区域,提升可验证性和可监督性。
👍 3
06/18 08:00
Policy-adherent tool-calling agents in customer-service domains must maintain task states across turns while calling tools and obeying domain policies. Task states consist of relevant facts, identifiers, constraints, and conditions observed through user interaction and tool calls. In standard agents
中文介绍 提出LedgerAgent,用结构化状态维护客服工具调用智能体中的任务事实与约束,提高策略遵循准确性。
👍 3
06/17 08:00
Progress in legal AI increasingly depends on access to authoritative legal text at scale. Yet one of the most consequential layers of American law remains largely absent from existing machine-readable corpora: local ordinances. Local codes govern zoning, housing, business licensing, public health, n
中文介绍 构建LOCUS,首个大规模机器可读美国地方法规语料库,涵盖分区、住房、商业许可等,填补法律AI数据空白。
👍 3
06/18 08:00
Embodied foundation models are expected to benefit from data scaling like large language models, but face a much tighter data bottleneck. Teleoperated real-robot trajectories remain the dominant pretraining source due to their precise action supervision and embodiment alignment, yet their scalabilit
中文介绍 证明第一人称人类视频在具身预训练中可超越真实机器人数据,提升数据可扩展性,降低遥操作依赖。
👍 3
06/16 08:00
Offline reinforcement learning is typically analyzed under process-level reward supervision, yet many sequential decision datasets
record only trajectory-level outcomes. We develop a statistical theory for offline policy optimization from such outcome-level
supervision. We first study the canoni
中文介绍 开发离线强化学习统计理论,在仅有轨迹级结果监督下分析可识别性和样本效率,指导高效策略优化。