Softpick: No Attention Sink, No Massive Activations with Rectified Softmax Paper • 2504.20966 • Published 9 days ago • 25
Kaleidoscope: In-language Exams for Massively Multilingual Vision Evaluation Paper • 2504.07072 • Published 29 days ago • 8
Understanding R1-Zero-Like Training: A Critical Perspective Paper • 2503.20783 • Published Mar 26 • 48
Pensez: Less Data, Better Reasoning -- Rethinking French LLM Paper • 2503.13661 • Published Mar 17 • 5
MinorBench: A hand-built benchmark for content-based risks for children Paper • 2503.10242 • Published Mar 13 • 4
Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia Paper • 2503.07920 • Published Mar 10 • 98
Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia Paper • 2503.07920 • Published Mar 10 • 98
Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia Paper • 2503.07920 • Published Mar 10 • 98
Constructing and Expanding Low-Resource and Underrepresented Parallel Datasets for Indonesian Local Languages Paper • 2404.01009 • Published Apr 1, 2024
How Do Hackathons Foster Creativity? Towards AI Collaborative Evaluation of Creativity at Scale Paper • 2503.04290 • Published Mar 6 • 1
HiFi-KPI: A Dataset for Hierarchical KPI Extraction from Earnings Filings Paper • 2502.15411 • Published Feb 21 • 2
Sailor2: Sailing in South-East Asia with Inclusive Multilingual LLMs Paper • 2502.12982 • Published Feb 18 • 17
Sailor2: Sailing in South-East Asia with Inclusive Multilingual LLMs Paper • 2502.12982 • Published Feb 18 • 17
Sailor2: Sailing in South-East Asia with Inclusive Multilingual LLMs Paper • 2502.12982 • Published Feb 18 • 17