// Topic signal
Papers, surveys, and notable experiments from arXiv and top AI conferences.
<!-- CURSOR_AGENT_PR_BODY_BEGIN --> ## Description Content-only audit against [comphy-lab.org/research](https://comphy-lab.org/research). Selected Recent Papers were missing two of the three recent papers the lab lists as featured/new, and the PhD thesis `doi.org` link failed link checks with a redi
**Please check the [Github](https://github.com/pstAmbition/DailyArXiv_contentmoderation) page for a better reading experience and more papers.** ## Multimodal harmful content | **Title** | **Date** | **Comment** | | --- | --- | --- | | **[Toward Accountable AI-Generated Content on Social Platforms:
<!-- codex-pull-request-review-summary --> ## Codex Review Summary This comment shows the latest Codex review activity on this pull request. | Review | Status | Commit | Review trigger | | --- | --- | --- | --- | | 📝 **Code Review** | ✅ **Completed** <relative-time datetime="2026-10-12T08:17:47.2...
# ArXiv AI Research Weekly Digest 2026-10-12 > Source: [ArXiv](https://arxiv.org/) (cs.AI, cs.CL, cs.LG) | 50 papers | Generated: 2026-10-12 02:13 UTC --- # ArXiv AI Research Weekly Digest (2026-10-06 to 2026-10-12) ## 1. Last 7 Days' Highlights This week’s AI research centers on advancing LLM ag
## Summary Anthropic subscription AI connections created through the isolated local login stop working about 8 hours after creation. Runs then fail with `401 OAuth access token has expired`. Paperclip stores only the Claude OAuth **access token** for anthropic connections and drops the **refresh to
Research: add arXiv and clickable literature benchmark records
Research: manually run live literature benchmark in GitHub Actions
Add Fields talk, reorder papers, add mech interp paper and TA courses
In this paper, we investigate the weak invariance principle in some Besov spaces for strictly stationary sequences. In particular, we provide sufficient conditions on the moments and the dependence of a strictly stationary sequence to guaranty the weak invariance principle in these Besov spaces. Sev
In 2026, cybersecurity evaluations involving OpenAI, Anthropic, and Google agents reached real systems outside their authorized test scope. The paths were different. OpenAI agents exploited research infrastructure, coordinated across runs, and compromised parts of Hugging Face's production environme
Multimodal large language models (MLLMs) are rapidly evolving toward continuous audio--visual reasoning, creating an urgent need for evaluations that expose their capability limits. Audio--visual captioning is an ideal diagnostic task, yet current benchmarks face a coupled trade-off: whole-caption s
Recent advances in generative image models have made many manipulated images highly realistic, raising the need for detectors that are not only accurate but also able to provide visual evidence for their decisions. In this paper, we present our solution to the Explainable Deepfake Detection Challeng
Large language model (LLM) agents interact with external resources to complete complex user tasks, exposing them to indirect prompt injection (IPI), where malicious instructions redirect agents toward attacker-intended tasks. Since IPI is difficult to defend against in real-world environments, post-
Non-Gaussian features in femtoscopic observables have been observed in high-energy collisions, yet their origin remains not fully understood. This study focuses on the phenomenological approach to femtoscopy, going beyond the Gaussian approximation by utilizing Lévy-stable source distributions. Usin
Complete selected Precise footer for Research Papers
<!-- ccr-projects-attribution: {"github_login":"yrahul3910"} --> _Requested by **Rahul** · [project thread](https://claude.ai/code/project/chan_01R2bjUwB9NyB3w4JBEFjN7b?thread=cmsg_01R2bjUwB9NyB3w4JBEFjN7b8jXVqcHDZMWfGQaZScra41)_ Before: with Ollama or OpenAI as the generation provider and no reaso