🌲 P-Research
A self-updating, continuously running frontier-AI research intelligence.
Weekly arXiv sweeps · living paper database · growing systematic survey.
1130 papers tracked (92 full-text verified) across 6 pillars · last sweep 2026-10-26
Latest papers
- SceneBloom: Agentic Indoor Environment Generation with Realistic and Diverse Layouts for Embodied Learning (2610.32978v1) — LLM Reasoning / Test-time Compute
- UniAction: Unified Action Conditioning for World Models (2610.32977v1) — Multimodal / World Models
- RobustRLlib: A Unified Library and Benchmark for Robust Reinforcement Learning Algorithms (2610.32971v1) — LLM Reasoning / Test-time Compute
- On the continuity of conditional distributions and stratification for derivative pricing (2610.32970v1) — Quant × AI
- DexPort: A Hand-Held Skill Interface for Dexterous Hand Data Collection (2610.32969v1) — Agentic AI / Deep Research Systems
- MiD-VLM: Detecting and Grounding Global Semantic Misinformation in Image-Caption Pairs (2610.32967v1) — Multimodal / World Models
- Measure Before You Train: Typed Decision Models vs. a Classical Baseline vs. a Generative LLM for Routing a Personal Multilingual Inbox (2610.32955v1) — Agentic AI / Deep Research Systems
- Where Rounding Happens Matters: Rounding-Location Alignment Stabilizes LLM Reinforcement Learning (2610.32951v1) — LLM Reasoning / Test-time Compute
Weekly digests
Publications
Deepresearch notes
Repository