每日自动抓取：arXiv 当日新论文、近半年高被引论文、Hacker News 热门。仅供学习参考。

arXiv 今日新论文（AI / 机器学习 / 量化金融）

1. Learning to Stop without Learning to Stop: Self-Supervised Confidence Training Improves Reasoning Efficiency
Parsa Hosseini, Akasha Tigalappanavara, Sumit Nawathe 等 · 2026-09-25

Reasoning models often generate very long reasoning traces, making inference computationally expensive. Existing approaches typically improve efficiency either through inference-time early-stopping mechanisms or by …

2. Statistical attribute alignment for black-box generative AI via output post-processing
Kevin Jiang, Morgane Austern, Edgar Dobriban 等 · 2026-09-25

Generative AI systems are increasingly used, but aligning their outputs with user requirements poses a continuing challenge. Here, we aim to ensure that the distribution of an attribute of an AI-generated output aligns …

3. User Model Extraction via Belief Self-Distillation
Ali Holmov, Yiran Huang, Kirill Bykov 等 · 2026-09-25

Large language models (LLMs) implicitly infer attributes of their users and adapt their behavior accordingly, yet these beliefs remain difficult to inspect and causally manipulate. We introduce Belief Self-Distillation …

4. Compact Documentation for Coding Agents: A Benchmark, an Optimizer, and Why It Does Not Transfer
Md Shohel Arman, Igor Molybog 等 · 2026-09-25

We investigate whether natural-language documentation helps coding agents resolve software issues, and we build the tools to construct and evaluate it. We introduce a roundtrip benchmark that scores code descriptions by …

5. OC-GS: Gaussian Splatting for Irregular Turntable Capture
Jae Joong Lee, Bedrich Benes 等 · 2026-09-25

Uneven rotation and dropped frames make equal-angle assumptions unreliable for turntable reconstruction. We present OC-GS, an object-centric Gaussian splatting that refines each image's angle while maintaining a shared …

6. Strategically Diverse Sampling for Self-Training
Alexander Gurung, Esmeralda S. Whitammer, Mirella Lapata 等 · 2026-09-25

Many LLM training and inference methods, including RL and test-time scaling, depend on repeated sampling, but benefit only when the responses meaningfully differ. Self-training faces the same challenge: training data is …

7. Adapting for AI: How elementary teachers adjust their practices for an AI-integrated curriculum
Fasika Melese, Ruiyang Wu, Xinyue Cui 等 · 2026-09-25

Conversational AI tools are entering children's everyday experiences, and schools are interested in adopting them. However, successful classroom integration depends not only on the technology but also on the work …

8. DeepEdu-v1: Efficient and Scalable Agentic LLMs for Vietnamese Education
Quang Nguyen, Hieu Nguyen, Hien Hoang 等 · 2026-09-25

AI tutoring could markedly improve learning outcomes for students in developing regions such as Vietnam, yet the two obvious paths both fall short. Cloud assistants such as ChatGPT route sensitive student data to …

9. Multi-agent Scaling Across Disjunctive and Compensatory Tasks
Carolina Fortuna, Blaz Bertalanic 等 · 2026-09-25

Multi-agent LLM systems are often expected to improve as team size increases, yet the scaling behavior may depend on task structure. Our central contribution is to introduce Steiner's taxonomy of group tasks as a …

10. MexHat: A Dataset for Hate Speech Detection in Mexican Spanish Videos
Itzel Tlelo-Coyotecatl, Hugo Jair Escalante 等 · 2026-09-25

Ensuring online safety through content monitoring had raised Hate Speech Detection as a crucial task to be addressed. By essence the task demands the capture of contextual cues, which are essential for a precise …

11. Two Conformal Constructions for Adaptive Within-Document AI-Text Screening
Marco Mandap, Jerahmeel Hipolito, Arcel Galvez 等 · 2026-09-25

We study false-alert control when screening for text generated by artificial intelligence (AI). The screening procedure selects document prefixes and detectors from observed evidence and may stop before exhausting its …

12. A Flow Matching Framework for Neural Representational Dissimilarity
Zeyuan Ye, Xue-Xin Wei 等 · 2026-09-25

Neural representational dissimilarity quantifies differences between neural response distributions, and is essential for comparing neural codes across stimuli, brain areas, tasks, and models. Commonly used distance …

13. Can You Check That? The Checkability Boundary for Local LLM Network Automation
Maleeha Masood, Momina Nofal 等 · 2026-09-25

Sending every network-automation input to a third-party frontier LLM exports sensitive artifacts such as production configurations, topologies, and logs. Querying small language models (SLMs) locally avoids this egress, …

14. Statistical Foundations for a Google Play User-Review Sentiment Index: Signal Fusion, Shrinkage, Distributional Validation, and Dynamic Smoothing
Marco Mandap 等 · 2026-09-25

We develop a statistically explicit sentiment index for Google Play user reviews and establish the mathematical results supporting its construction. Normalized star ratings and text-sentiment scores are treated as noisy …

15. Muslim: A Deployed Arabic Voice AI Platform for Grounded Islamic Knowledge
Yahya Mohamed Elnawasany 等 · 2026-09-25

We present Muslim, a production Arabic voice AI platform serving grounded, sourced Islamic knowledge to real users. Beyond a real-time voice pipeline (NeMo Arabic ASR, an OpenAI-compatible LLM endpoint, self-hosted TTS) …

共 15 篇。

近半年高被引论文

AI / 机器学习方向

量化金融方向

Hacker News 热门（科技 / 创业 / 投资风向）

本日报由服务器每日自动抓取生成于凌晨，原文链接均已附在上。