arXiv 论文速递
针对前沿模型采用次二次注意力后推理内存与算力需求变化，重新审视异构系统解耦架构设计，对高效大模型推理系统有重要指导意义。
Frontier language models are more aggressively using subquadratic attention to reduce the memory footprint and compute requirements during inference while still delivering frontier…
· 2026-09-11
Accurate prediction of equity returns remains a major challenge in computational finance due to the non-stationary, nonlinear, and low signal-to-noise ratio nature of financial tim…
Dance-to-music (D2M) generation aims to synthesize music that is rhythmically and stylistically aligned with dance videos. A key challenge arises from the semantic mismatch between…
· 2026-09-11
概率预测的校准度量是可靠性的核心，本文提出基于排序的校准度量方法，为模型不确定性评估提供更稳健的工具。
When providing forecasted probabilities with a predictive model, the ideal model offers perfect calibration: the true probability of the outcome (i.e., the probability that $Y=1$) …
· 2026-09-11
面向搜救场景中铰接履带机器人在楼梯与杂乱环境的通行难题，结合语言引导与神经运动学MPC，提升复杂地形自主穿越能力。
In urban search and rescue, articulated tracked robots (ATRs) must traverse structured but contact-rich environments such as stairwells and cluttered building interiors. Reliable a…
· 2026-09-11
Agentic systems offer a promising way to automate embodied benchmark construction, but existing approaches typically cover isolated stages or remain specialized to predefined envir…
现有语音智能体评测多限于双人对话，本文构建多方对话基准，填补语音智能体在真实多人场景下能力评估的空白。
Conversational voice agents have advanced significantly, offering increasingly natural human-machine interactions through both cascaded and end-to-end architectures. However, while…
Recent breakthroughs in LLM-based systems and their abilities in problem solving and coding have allowed progress in the AI for Science paradigm, potentially replacing human roles …
· 2026-09-11
Fine-grained control of language model behaviors (e.g., steering) is among the more actionable outcomes of interpretability research. For binary concepts such as refusal, a single …
· 2026-09-11
Enterprise Digital Twins (EDTs) promise data-driven decision support at organizational scale, but realizing them requires navigating siloed departments, tacit knowledge, and high-s…
· 2026-09-11
Clinical timelines support treatment-window analysis and leakage-free modeling, but discharge summaries often obscure chronology and structured EHR tables describe only part of the…
扩散语言模型在复杂推理与工具使用上落后于自回归模型，本文用课程强化学习弥补差距，推动并行生成范式的实用化。
Diffusion Language Models (DLMs) offer promising parallel generation capabilities but lag behind autoregressive models in complex reasoning and tool-use tasks. While Reinforcement …