# Daily Arxiv

전 세계에서 발간되는 인공지능 관련 논문을 정리하는 페이지 입니다.
본 페이지는 Google Gemini를 활용해 요약 정리하며, 비영리로 운영 됩니다.
논문에 대한 저작권은 저자 및 해당 기관에 있으며, 요약본 공유 시 출처만 명기하면 됩니다.
This service is supported by Google Gemini.

- [CF-VLA: Efficient Coarse-to-Fine Action Generation for Vision-Language-Action Policies](https://slashpage.com/haebom/qrx6zk258gee6mv314y5)
- [RAS: a Reliability Oriented Metric for Automatic Speech Recognition](https://slashpage.com/haebom/d367nxm38y55n2j98pv1)
- [MemeScouts@LT-EDI 2026: Asking the Right Questions -- Prompted Weak Supervision for Meme Hate Speech Detection](https://slashpage.com/haebom/xjqy1g2v9j887m6vd54z)
- [Improving Robustness of Tabular Retrieval via Representational Stability](https://slashpage.com/haebom/93nzyxmdvpzzwmwk6r45)
- [From Skill Text to Skill Structure: The Scheduling-Structural-Logical Representation for Agent Skills](https://slashpage.com/haebom/n8pw9x2zengg9mg7yrqv)
- [TCOD: Exploring Temporal Curriculum in On-Policy Distillation for Multi-turn Autonomous Agents](https://slashpage.com/haebom/n5w9812gkjzz424kpgze)
- [Zoom In, Reason Out: Efficient Far-field Anomaly Detection in Expressway Surveillance Videos via Focused VLM Reasoning Guided by Bayesian Inference](https://slashpage.com/haebom/ndvwx7287errqm3z6jpg)
- [AIPsy-Affect: A Keyword-Free Clinical Stimulus Battery for Mechanistic Interpretability of Emotion in Language Models](https://slashpage.com/haebom/3p4kj92ypx888m57q1x8)
- [OptProver: Bridging Olympiad and Optimization through Continual Training in Formal Theorem Proving](https://slashpage.com/haebom/943zqpmqxgkk72wnvy87)
- [K-SENSE: A Knowledge-Guided Self-Augmented Encoder for Neuro-Semantic Evaluation of Mental Health Conditions on Social Media](https://slashpage.com/haebom/36nj8v2wqr88p25ykq9z)
- [A Milestone in Formalization: The Sphere Packing Problem in Dimension 8](https://slashpage.com/haebom/4z7pvx2ken5592ek8653)
- [Mixture of Heterogeneous Grouped Experts for Language Modeling](https://slashpage.com/haebom/dwy5rvmjpx44nmp46zn9)
- [Hard to See, Hard to Label: Generative and Symbolic Acquisition for Subtle Visual Phenomena](https://slashpage.com/haebom/91kwev26853y62y46jpg)
- [Quantifying and Mitigating Self-Preference Bias of LLM Judges](https://slashpage.com/haebom/qrx6zk258ge16mv314y5)
- [SketchVLM: Vision language models can annotate images to explain thoughts and guide users](https://slashpage.com/haebom/4w67rj24g8p38m5yq8ep)
- [WeatherSeg: Weather-Robust Image Segmentation using Teacher-Student Dual Learning and Classifier-Updating Attention](https://slashpage.com/haebom/ywk9j72976ky42gpqvnd)
- [Behavioral Intelligence Platforms: From Event Streams to Autonomous Insight via Probabilistic Journey Graphs, Behavioral Knowledge Extraction, and Grounded Language Generation](https://slashpage.com/haebom/xjqy1g2v9j8p7m6vd54z)
- [PermaFrost-Attack: Stealth Pretraining Seeding(SPS) for planting Logic Landmines During LLM Training](https://slashpage.com/haebom/n8pw9x2zengr9mg7yrqv)
- [Optimal Question Selection from a Large Question Bank for Clinical Field Recovery in Conversational Psychiatric Intake](https://slashpage.com/haebom/ndvwx7287eryqm3z6jpg)
- [You Don't Need Public Tests to Generate Correct Code](https://slashpage.com/haebom/7vgjr4m1qw91qmdwpy86)

For the site tree, see the [root Markdown](https://slashpage.com/haebom.md).