Multilingual Tool Calling in 70+ Languages, On Device
•
1
NEW Articles from Team or Enterprise organizations will get promoted to the main section.
How I pre-trained a MS/MS model from scratch
Speech-to-Speech AI: A Primer
•
1
Announcing AutoBench Agentic: The Next Generation Agentic Benchmark.
•
2
Introducing the Bright Data CLI for Automated Web Data Pipelines
•
1
The Zero-Trust Gap in LLMs, How Encoders Can Protect Your AI
codeskills-bench: the code changes developers don't trust agents with
LLMs As Geopolitical Forecasters: An Iran-Israel Experiment Using LLM Council
Dual-Teacher Distillation and Strategic SLERP Merging
•
2
Vessel Browser: The Open Source Browser Designed for Autonomous Agents
•
3
We Pitted the Cheapest TPU Against an NVIDIA L4. Here's What 6 Experiments Revealed.
•
1
NVIDIA Isaac GR00T N1.7: Open Reasoning VLA Model for Humanoid Robots
•
8
Camera Choice For Robotics Data
•
1
MP3 Bitrate Sensitivity in Audio-Multimodal LLMs: A Per-Model Evaluation
Auron: Depth-Efficient Language Models via Hybrid Recurrent-Attention Weight Sharing
•
2
vindex-infer — Run LLMs without CUDA, without PyTorch, from flat binary files
•
1
easyaligner: Forced alignment of text and audio, made easy
•
5
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