Pai 的 AI 雷达

模型与评测

今天：LLM 系统工程设计的上下文建模框架，多模态服务的 EPD 推理拆分。并行还有大喜：家居博主靠 "婆婆逼生二胎送别墅" 爆火、IBM 发布 Granite 时序模型、Qwen 3.8 follows。

日期: 2026/09/10
今日条目: 78
当前类目: 26

往期2026/09/10

全部78 编码代理0 Agent与工具3 个人助理1 模型与评测26 创作成片11 开发与开源16 产品接入21

Elastic Horizon: Discovering the Effective Interaction Frontier in Agentic Reinforcement Learning

arXiv:2609.07247v1 Announce Type: new Abstract: Scaling the interaction horizon-the maximum number of environment interactions per episode-improves LLM agents on long-horizon tasks, and curriculum-based methods that progressively expand the horizon outperform fixed-horizon altern

arxiv.org打开原文

#26

Beyond One-Size-Fits-All: Sample-Adaptive Strategy Routing for Vision Token Pruning in MLLMs

Multimodal large language models (MLLMs) process hundreds or thousands of visual tokens per image, incurring prohibitive inference costs. While existing vision token pruning methods mitigate this overhead, they implicitly assume that a single fixed pruning strategy can be applied

arxiv.org打开原文