OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis Paper • 2603.20278 • Published 7 days ago • 49
V_1: Unifying Generation and Self-Verification for Parallel Reasoners Paper • 2603.04304 • Published 20 days ago • 14
PaperBanana: Automating Academic Illustration for AI Scientists Paper • 2601.23265 • Published Jan 30 • 220
Jr. AI Scientist and Its Risk Report: Autonomous Scientific Exploration from a Baseline Paper Paper • 2511.04583 • Published Nov 6, 2025 • 5
dots.ocr: Multilingual Document Layout Parsing in a Single Vision-Language Model Paper • 2512.02498 • Published Dec 2, 2025 • 2
InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery Paper • 2602.08990 • Published Feb 9 • 75
Privasis: Synthesizing the Largest "Public" Private Dataset from Scratch Paper • 2602.03183 • Published Feb 3 • 11
LightOnOCR-2 🦉 Collection LightOnOCR-2-1B: a lightweight high-performance end-to-end OCR model family • 12 items • Updated 22 days ago • 23
Next-Embedding Prediction Makes Strong Vision Learners Paper • 2512.16922 • Published Dec 18, 2025 • 88
view article Article Tokenization in Transformers v5: Simpler, Clearer, and More Modular +4 Dec 18, 2025 • 123
On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models Paper • 2512.07783 • Published Dec 8, 2025 • 39
PaperDebugger: A Plugin-Based Multi-Agent System for In-Editor Academic Writing, Review, and Editing Paper • 2512.02589 • Published Dec 2, 2025 • 73
Wikontic: Constructing Wikidata-Aligned, Ontology-Aware Knowledge Graphs with Large Language Models Paper • 2512.00590 • Published Nov 29, 2025 • 52