Pai 的 AI 雷达

模型与评测

今天:数学代理作弊与 AI 政策(Agent 原型),洛杉矶建筑变迁可视化(Article URL:)。并行还有 A Tesla ran、Replaceable but Employed、Agent 编程不确定性闸门。

日期
2026/09/08
今日条目
108
当前类目
56
#49

A Schema Bounded Language Model for Refining Robot Policies Without Destabilizing Local Learning

This paper addresses navigation by composite heterogeneous robots in a decentralized system when policy reasoning and local control operate at different update levels. In a NetLogo--Python implementation, three robots share motion dynamics but use different LLM backends. Each rob

推荐理由「A Schema Bounded Language Model…」偏机器人,对造物者有用的是方法能不能迁到自己的 Agent 或生成管线,不是把标题再念一遍。
模型与评测papers.cool cs.AI Atom
#50

MedFlow: Class-Aware Multi-Scale Generation for Medical Time-Series Synthesis

Synthetic medical time-series generation can alleviate data scarcity and support the development of reliable clinical prediction models. However, existing methods mainly focus on matching the overall distribution and temporal dynamics of real data, which does not necessarily ensu

推荐理由「MedFlow: Class-Aware Multi-Scale…」对造物者有用的是方法能不能迁到自己的 Agent 或生成管线,不是把标题再念一遍。
模型与评测生信医疗papers.cool cs.AI Atom
#51

Linguistic Trajectory Encoding for Efficient Long-Horizon Spatial Memory in Embodied Agents

Embodied agents performing long-horizon tasks require a memory representation in which the state transitions of dynamic objects remain queryable in natural language across hours-to-days observation horizons. Existing systems either drop fine-grained motion (clip-level video-langu

推荐理由「Linguistic Trajectory Encoding f…」偏Agent,对造物者有用的是方法能不能迁到自己的 Agent 或生成管线,不是把标题再念一遍。
模型与评测机器人具身papers.cool cs.AI Atom
#52

Diffusion Language Models for Mobile Edge Agentic AI: Foundations, Applications, and Challenges

Diffusion language models (DLMs) offer a non-autoregressive alternative for mobile edge agentic artificial intelligence (AI) by refining tokens through iterative denoising rather than left-to-right decoding. Compared with autoregressive Transformer-based large language models (LL

推荐理由「Diffusion Language Models for Mo…」偏生成模型,对造物者有用的是方法能不能迁到自己的 Agent 或生成管线,不是把标题再念一遍。
模型与评测papers.cool cs.AI Atom
#53

Resilience Beyond Stationary Client Unavailability: Unlocking Efficient and Unbiased Federated Learning

Due to resource constraints or external and internal uncertainties, clients in real-world federated learning systems are often intermittently available edge devices. In highly dynamic environments, the parameter server lacks prior real-time knowledge of clients' availability, mak

推荐理由「Resilience Beyond Stationary Cli…」对造物者有用的是方法能不能迁到自己的 Agent 或生成管线,不是把标题再念一遍。
模型与评测硬件边缘papers.cool cs.LG
#54

PetQA: Benchmarking Veterinary Knowledge and Clinical Reasoning

We introduce PetQA, a Korean long-form question-answering (QA) benchmark for evaluating veterinary knowledge and clinical reasoning in large language models (LLMs) and large vision-language models (LVLMs). PetQA contains 10,076 text-only and 8,751 multimodal QA pairs derived from

推荐理由「PetQA: Benchmarking Veterinary K…」偏视觉语言,对造物者有用的是方法能不能迁到自己的 Agent 或生成管线,不是把标题再念一遍。
模型与评测生信医疗papers.cool cs.CL
#56

I thought I will never say this about Fable

Just tried OpenAI Astra , I thought I will never say this , it’s lit , OpenAI cooked something spectacular, and I have a strong feeling this will pull lot of Fable 5 users towards it , and it’s fast, not sure if it’s AGI, but it feels fresh and a very very serious competition to

推荐理由I thought I will never say this about:Just tried OpenAI Astra , I thought I will never say this , it’s lit , OpenAI cooked。
模型与评测Anthropic Watch 非官方