Exploring Hard Negative Mining with NV-Retriever in Korean Financial Text By Albertmade • 3 days ago • 8
🐺🐦⬛ LLM Comparison/Test: Phi-4, Qwen2 VL 72B Instruct, Aya Expanse 32B in my updated MMLU-Pro CS benchmark By wolfram • 4 days ago • 2
TerjamaBench: A Cultural Benchmark for English-Darija Machine Translation By imomayiz • 4 days ago • 19
Beyond Image Preferences - Rich Human Feedback for Text-to-Image Generation By RapidataAI • 5 days ago • 13
Exploring Hard Negative Mining with NV-Retriever in Korean Financial Text By Albertmade • 3 days ago • 8
🐺🐦⬛ LLM Comparison/Test: Phi-4, Qwen2 VL 72B Instruct, Aya Expanse 32B in my updated MMLU-Pro CS benchmark By wolfram • 4 days ago • 2
TerjamaBench: A Cultural Benchmark for English-Darija Machine Translation By imomayiz • 4 days ago • 19
Beyond Image Preferences - Rich Human Feedback for Text-to-Image Generation By RapidataAI • 5 days ago • 13