Auron: Depth-Efficient Language Models via Hybrid Recurrent-Attention Weight Sharing
•
2
NEW Articles from Team or Enterprise organizations will get promoted to the main section.
vindex-infer — Run LLMs without CUDA, without PyTorch, from flat binary files
•
1
easyaligner: Forced alignment of text and audio, made easy
•
4
Building OmniBench Aegis Env: A Reproducible Multi-Domain OpenEnv for Agent Evaluation
1.37x Faster on Alibaba's 80B Code Model: EAGLE3 for Qwen3-Coder-Next
80% of AI LLM Fine-Tuning Compute Is Wasted — Here's How We Proved It
•
1
Querying a Neural Network Like a Database — and Making That Tool Available to Everyone
•
1
lucky_pick_scheduler
•
1
Darwin-TTS: We Gave a TTS Model 3% of an LLM's Brain — It Started Showing Emotion
•
7
1.7x Faster on a 218B Model: EAGLE3 Speculative Decoding for GLM-4.7
Stop benchmarking inference providers
•
8
Latest Agentic AI Trends to Watch in 2026: Market Shifts, Adoption Patterns, and What Comes Next
When Speech AI Meets the Long Tail of Languages: Inside the VAANI Dataset
•
8
Agentic AI vs Generative AI vs Predictive AI: What's the Difference? (2026 Guide)
Nucleus-Image: Scaling Text-to-Image with Sparse Mixture of Experts
•
8
Releasing LiteCoder-Terminal-SFT
•
4
"Darwin-27B-Opus: Surpassing the Foundation Model Without Training"
•
12
SylloGym: A Multi-Turn Legal Reasoning Environment for RL Training
pgvector vs Elasticsearch vs Qdrant vs Pinecone vs Weaviate: A 14-Case Benchmark
•
1
