AI
AI
资讯
alishangtian.com
首页
大模型
智能体
开源项目
研究前沿
行业动态
知识库
主题色 · THEME
靛蓝(默认)
极光
落日
薰衣草
海洋
森林
暮橙
石墨
自定义
恢复默认
提交线索
agent
anthropic
openai
huggingface daily papers
ai安全
gpu
jake wharton
it之家
solidot
港股
搜索:
Action
共命中 50 条(服务端检索)
Palantir Foundry 深度研究(四):
Action
Types 与 Functions,让本体「能动手」
系列前作说过「动力元素是把本体从数据模型变成操作系统级契约的关键」,本篇把这句话拆到机制层:动作类型的四件套(参数、编辑规则、提交条件、副作用)、本体用户编辑与数据管道写入的边界、webhook 失败后的补偿责任、函数的读逻辑与版本语义、OSDK 的类型安全代码生成与权限作用域,以及 OSv2 的
Action
编辑模型为什么值得关注。
后端技术
精选
· 用户投稿 · 今天
阅读 4
·
访客 4
Ego Guidance: Enhancing Robot Policy Learning with
Action
-Free Human Egocentric Videos
In this paper, we investigate how human egocentric videos can benefit robot policy learning without
action
supervision. …
智能体
HuggingFace Daily Papers · 11-10
阅读 1
·
访客 1
SWAM: Scaling World
Action
Models with Cross-Modal Alignment
World
action
models jointly predict video and
action
s conditioned on language. Existing studies focus primarily on archi…
行业动态
HuggingFace Daily Papers · 11-9
阅读 13
·
访客 13
Skeleton-Grounded Latent
Action
Model for Robot World Models
Robot world models simulate how environments evolve in response to robot
action
s. Latent
action
models enable learning d…
智能体
HuggingFace Daily Papers · 10-22
阅读 68
·
访客 67
Self-Distilling Future Video Representations for World
Action
Models
World
Action
Models (WAMs) have emerged as a promising approach to learning generalist robot policies using rich spatiot…
智能体
HuggingFace Daily Papers · 10-21
阅读 58
·
访客 58
MambaAct: Efficient Mamba
Action
Experts for Flow-Matching Vision-Language-
Action
Models
Vision-language-
action
(VLA) models have shown strong promise for generalist robotic manipulation, but their inference c…
智能体
HuggingFace Daily Papers · 10-16
阅读 48
·
访客 48
A Safe
Action
Is Not Enough: Feasible-Future Decoding for Vision-Language-
Action
Policies
A safe
action
is not necessarily a viable one. A frozen vision-language-
action
(VLA) policy can favor a locally admissib…
行业动态
HuggingFace Daily Papers · 10-6
阅读 31
·
访客 31
CARE: Certifying Acceleration for Vision-Language-
Action
Inference
While vision-language-
action
(VLA) models have advanced rapidly, running them at every control step remains expensive. P…
行业动态
HuggingFace Daily Papers · 10-6
阅读 26
·
访客 25
Magic-W0: A Structured World-
Action
Foundation Model for Physical Intelligence
World-
action
models (WAMs) augment robot policies with
action
-conditioned environment dynamics, yet existing approaches …
智能体
HuggingFace Daily Papers · 10-3
阅读 71
·
访客 71
Fewer Tokens, Better
Action
: GPT-6 Astra Robot Agents with 14% Higher Success Rate but 65% Fewer Tokens
Vision language model (VLM) agents can control robots through visual feedback and
action
primitives, but repeated model …
智能体
HuggingFace Daily Papers · 10-1
阅读 69
·
访客 68
Kinematic MeanFlow: One-Step
Action
Generation Policy for Robotic Foundation Models
In this paper, we study how to achieve one-step
action
generation in Robotic Foundation Models (RFMs), aiming to overcom…
智能体
HuggingFace Daily Papers · 10-1
阅读 74
·
访客 74
DroneWAM: Efficient World
Action
Model for Drone Visual Navigation
World-
action
models give visual navigation agents a way to anticipate how candidate
action
s will change future observati…
智能体
HuggingFace Daily Papers · 9-27
阅读 72
·
访客 71
Black Forest Labs launches FLUX 3
Action
, an open robotics AI model
Sep 24, 2026 Black Forest Labs is releasing FLUX 3
Action
, an open AI model designed for robotics.** It builds on the mu…
智能体
The Decoder · 9-25
阅读 118
·
访客 114
Black Forest Labs Releases FLUX 3
Action
: A 7B Open-Weights World
Action
Model That Tops RoboLab-120
Black Forest Labs (BFL), the lab behind the FLUX image models, has released FLUX 3
Action
. It is a 7B open-weights World…
智能体
MarkTechPost · 9-25
阅读 103
·
访客 101
InternW0-Δ: A World
Action
Model Bridging Predictive Dynamics and
Action
s with 20K+ Hours of Open Data
World
Action
Models (WAMs) jointly model visual dynamics and
action
generation for generalist robot manipulation. A cent…
智能体
HuggingFace Daily Papers · 9-25
阅读 71
·
访客 71
MemBodied: Recurrent Associative Memory for Vision-Language-
Action
Models
Vision-Language-
Action
models provide a strong foundation for general-purpose robot control, yet a vast majority of poli…
智能体
HuggingFace Daily Papers · 9-23
阅读 80
·
访客 78
DeltaWAM: Delta World
Action
Models for Bimanual Manipulation
World-
action
models (WAMs) transfer visual and motion priors from pretrained video generators to robot control by jointl…
智能体
HuggingFace Daily Papers · 9-23
阅读 86
·
访客 86
CARE: Experience-Guided Atomic Corrective Execution for Vision-Language-
Action
Policies
Vision-Language-
Action
(VLA) policies achieve strong performance in robotic manipulation but remain brittle once executi…
智能体
HuggingFace Daily Papers · 9-21
阅读 65
·
访客 65
VLA-Precision: Asymmetric Co-Bootstrapping for Efficient Real-World Online RL of Vision-Language-
Action
Models
Pretrained vision-language-
action
(VLA) models enable broad manipulation but remain unreliable in tasks demanding precis…
行业动态
HuggingFace Daily Papers · 9-18
阅读 30
·
访客 30
Action
Piece: Rethinking
Action
Tokenization for Autoregressive Vision-Language-
Action
Models
Action
tokenizers play a central role in autoregressive vision-language-
action
(VLA) models, determining both the target…
智能体
HuggingFace Daily Papers · 9-16
阅读 72
·
访客 69
Modality-Autoregressive World-
Action
Models
World-
action
models (WAMs) jointly model future observations and
action
s, typically predicting the future as RGB images.…
行业动态
HuggingFace Daily Papers · 9-15
阅读 36
·
访客 35
E2A-Bench: Benchmarking Evidence-to-
Action
Reliability in Financial Chart Reasoning
Can financial vision-language models (VLMs) turn chart evidence into reliable
action
recommendations? Existing hallucina…
研究前沿
HuggingFace Daily Papers · 9-13
阅读 35
·
访客 35
Action
Splice: In-Flight
Action
Editing for Interactive World Models
Chunk-autoregressive video world models typically condition each generated chunk on one
action
. An
action
received durin…
行业动态
HuggingFace Daily Papers · 9-8
阅读 17
·
访客 17
OpenWAM: An Open, Modular Exploration Towards Systematic World-
Action
Model Pretraining
World-
Action
Models inherit world knowledge from video-generative priors, and channel it into executable control signals…
行业动态
HuggingFace Daily Papers · 9-7
阅读 36
·
访客 36
GE-Act 2.0: Pretraining and Scaling a World-
Action
Model for Robotic Manipulation
World-
action
models (WAM) predict future states to guide robot
action
s, enabling learning from both
action
-free video an…
智能体
HuggingFace Daily Papers · 9-4
阅读 79
·
访客 78
ShieldVLA: Feasibility-Aware Safety Alignment for Vision-Language-
Action
Models
Vision-Language-
Action
(VLA) models demonstrate strong generalization in robotic manipulation and navigation, but existi…
智能体
HuggingFace Daily Papers · 9-2
阅读 75
·
访客 75
SimpleMemVLA: A Simple but Effective Native-Video Memory for Vision-Language-
Action
Models
Long-horizon manipulation is partially observable: the information needed to choose the next
action
may appear only in o…
行业动态
HuggingFace Daily Papers · 9-2
阅读 41
·
访客 40
ScaleVLA: Scaling Vision-Language-
Action
Models to 552 Billion Parameters
Frontier Vision-Language Models (VLMs) such as GPT-6 Astra have demonstrated remarkable capabilities in robot control, s…
智能体
HuggingFace Daily Papers · 2天前
阅读 1
·
访客 1
ODE Policy: Robot Learning via
Action
Dynamics, Not
Action
s
Most robot policies, whether trained by imitation learning (IL) or reinforcement learning (RL), map observations to acti…
智能体
HuggingFace Daily Papers · 11-1
阅读 10
·
访客 10
Lost in Recovery: Demystifying Recovery Behavior of Computer-Use Agents via Goal-Oriented
Action
Replay
Recent advances in large (vision) language models have enabled computer-use agents that automate digital workflows via f…
智能体
HuggingFace Daily Papers · 10-20
阅读 16
·
访客 16
Sensor-Language-
Action
Models
Sensors are useful not only for understanding the world but also for deciding what to do next. Existing sensor models ho…
行业动态
HuggingFace Daily Papers · 10-6
阅读 32
·
访客 32
From Evidence to
Action
: How Tool-Using Agents Fail
Tool-using agents make consequential changes to external state, yet correct outcomes do not guarantee that their
action
s…
智能体
HuggingFace Daily Papers · 10-6
阅读 68
·
访客 67
Conditional Trajectory Peaks: Single-Pass Multimodal Policies over
Action
Chunks
Multimodal imitation learning requires diverse executable futures under the same observation and consistent behavior acr…
行业动态
HuggingFace Daily Papers · 10-5
阅读 14
·
访客 14
World
Action
Learning via Inter
action
-Centric Spectral Latent Guidance
Learning general-purpose robot policies requires large-scale real-world inter
action
data, yet collecting robot demonstra…
智能体
HuggingFace Daily Papers · 10-2
阅读 69
·
访客 68
JevSpawn: Adaptive Agentic Inference through Compositional
Action
Spaces
LLM agents generate intermediate reasoning and
action
s token by token, making extended inter
action
s slow and computation…
智能体
HuggingFace Daily Papers · 9-30
阅读 79
·
访客 78
Decentralized Master-Mind: Joint
Action
Refinement through Iterative Intent Denoising in Multi-Agent Pathfinding
Decentralized multi-agent path finding (MAPF) with communication requires agents to reach individual goals without colli…
智能体
HuggingFace Daily Papers · 9-25
阅读 91
·
访客 88
World
Action
Agent: Harnessing VLMs for Robot Manipulation via World
Action
Rehearsal
General-purpose vision-language models (VLMs) bring broad knowledge and spatial reasoning to robot manipulation, yet exi…
智能体
HuggingFace Daily Papers · 9-24
阅读 92
·
访客 91
Grounded
Action
Model: 3D Grounding as a Foundation for Robotics
Manipulation policies must know which objects matter and where they are, yet the pretrained backbones that current robot…
智能体
HuggingFace Daily Papers · 9-20
阅读 85
·
访客 84
Zing-0.5: Toward Playable Worlds with Real-Time Joint
Action
and Text Control
We introduce Zing-0.5, a 5B autoregressive world model designed for playability: users can explore generated worlds, inf…
行业动态
HuggingFace Daily Papers · 9-15
阅读 39
·
访客 39
Dynin-Robotics: Omnimodal Unified Diffusion Vision-Language-
Action
Model
Visual goal and dynamics prediction can provide language-conditioned robot policies with both a target outcome and a rep…
智能体
HuggingFace Daily Papers · 9-11
阅读 79
·
访客 79
Breaking the Vision-
Action
Shortcut: Latent Interface Training for Generalizable Robotics Foundation Models
Robot foundation models achieve strong in-distribution performance but often degrade under visual distribution shifts. W…
智能体
HuggingFace Daily Papers · 9-11
阅读 77
·
访客 77
Memory as Plans: World-
Action
Modeling with Memory-Grounded Planning
Mainstream robotic policies often adopt a Markovian formulation, but many complex real-world manipulation tasks are inhe…
智能体
HuggingFace Daily Papers · 9-10
阅读 84
·
访客 80
Measuring Language Transfer in Robot Policies: Adding Greek to a Cosmos3 Vision-Language-
Action
Policy
Robot foundation models are trained and evaluated predominantly in English, and robot demonstration corpora do not exist…
智能体
HuggingFace Daily Papers · 9-7
阅读 57
·
访客 54
Palantir Foundry 深度研究(七):本体安全、数据治理与审计
Foundry 的安全不是「给应用接 RBAC」,而是由 markings 强制控制、对象与属性级策略、
Action
提交权限和运行时动态裁决共同组成。本文拆解资格×职责双轴授权、数据标记沿谱系传播、对象策略的读时边界、动作写权限陷阱、平台审计日志与
Action
Log 的差异,并串起 Lineage、Health Checks 与回滚限制,回答一个核心问题:当 Agent 可以改业务数据时,怎样证明它只看了该看的、只改了允许改的?
后端技术
精选
· 用户投稿 · 今天
阅读 3
·
访客 3
AllocFlow: End-to-End Portfolio Trading
Action
Generation from Raw Market Data
Real-world portfolio management requires converting noisy market observations into coordinated, simultaneous allocations…
行业动态
HuggingFace Daily Papers · 3天前
阅读 1
·
访客 1
Gamer: A Generalist Vision-Language-
Action
Foundation Model for Long-Horizon Real-Time Game Agent
We introduce Gamer, a generalist agent framework built for long-horizon tasks in complex interactive environments. Its e…
智能体
HuggingFace Daily Papers · 5天前
阅读 3
·
访客 3
Horizon-Scalable Q-Learning
Learning accurate off-policy state-
action
value functions (Q-functions) from offline datasets becomes harder as the task…
行业动态
HuggingFace Daily Papers · 11-7
阅读 12
·
访客 12
Evidence-Guided Recovery for AI Agents with Ambiguous Tool Outcomes and Partial Execution
Tool timeouts can leave AI agents facing ambiguous tool outcomes and partial execution: an
action
may have failed, commi…
智能体
HuggingFace Daily Papers · 10-30
阅读 3
·
访客 3
TILDE: Teacher-in-the-Loop Distillation from Embodied Foundation Models
Large-scale
action
pretraining equips Embodied Foundation Models (EFMs) with strong manipulation capabilities, with part…
行业动态
HuggingFace Daily Papers · 10-18
阅读 19
·
访客 19
The value of information and the emergence of communication in evolved e-puck robots
We study when communication emerges between autonomous agents and what role an innate
action
selection architecture play…
智能体
HuggingFace Daily Papers · 10-9
阅读 74
·
访客 73