揭示LLM多智能体绕过文本离散瓶颈，用隐状态直接通信的训练-free对齐方案，前沿且实用。
arXiv:2608.13317v1 Announce Type: new Abstract: Large language model based multi-agent systems usually communicate in text, i.e., using discrete token…
大模型意图分类新研究：对比零样本与微调路线，揭示精度、鲁棒性与失败边界，值得关注。
arXiv:2608.02415v1 Announce Type: new Abstract: Intent classification in Large Language Models (LLMs) involves categorizing user prompts into predefin…
无需训练的全局回归方法，高效压缩长上下文LLM的KV缓存，兼顾速度与精度。
arXiv:2605.31105v1 Announce Type: new Abstract: Large language models (LLMs) with extended context lengths rely on the key-value (KV) cache to support…
无需训练的纯解码器注意力新策略，让语音大模型长文本同声翻译更高效稳定。
arXiv:2605.31432v1 Announce Type: cross Abstract: Simultaneous speech-to-text translation (SimulST) generates translations while speech is still unfol…
arXiv新论文提出无需训练框架，用音频和文本协同调谐实现视频运动编辑，突破生成模型局限。
arXiv:2605.15307v1 Announce Type: cross Abstract: Motion-centric video editing remains difficult for large generative video models, which often respon…
无需训练的GUI元素定位新方法，动态区域搜索提升高分辨率屏幕下的指令相关性识别效率。
arXiv:2605.15542v1 Announce Type: new Abstract: GUI agents powered by Multimodal Large Language Models (MLLMs) have demonstrated impressive capability…