Building MoulSot: How We Curated 1,500 Hours of Moroccan Darija Speech, Selected the Best 80 Hours for Transcription, and Fine-Tuned Qwen3-ASR on Top of It
•
1
NEW Articles from Team or Enterprise organizations will get promoted to the main section.
Organon: a skill-first agent architecture for end-to-end scientific workflows
•
1
Pixel Art Bench: Evaluating Structured Generation in Language Models
Build a legal RAG app that won't be held in contempt
•
2
PRO-D ECOSYSTEM: REI_484x
•
1
CiberIA CRS Benchmark: Technical Evaluation of GROK AUTO under Cognitive Stability and Cybersecurity Criteria
THE RANDOM CURSE <br> Train/Val split on CIFAR 10, PASCAL VOC and IMDB
•
1
From Image to Music Language: Starry's Two-Stage Approach for Complex Polyphonic OMR
Talking to a 4-Year-Old: A Multilingual Benchmark for Children's AI Companions
•
2
Feather DB on LongMemEval: embedded retrieval beats full-context GPT-4o for $2.40
Building a Multi-Task English NLP Cascade in the Open
Fused Batched Thin SVD, Part II: Extending the Jacobi Pipeline to N=6 with Configurable Convergence
Under The Hood : Trinity-Large-Thinking Disected
Under The Hood : Cohere Transcribe Deep Dive
Under The Hood : Kimi K2.5 Disected
Agentic Scientific Machine Learning for Neural Operators
•
1
Training low-bit ternary models with Axolotl
•
4
