SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue Paper • 2609.26780 • Published 15 days ago • 103
The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks Paper • 2609.25804 • Published 15 days ago • 164
🧙 MoM Nano Collection long context models for MoM multilingual classifier (domain, jailbreak, pii, factual, feedback, modality) • 14 items • Updated 24 days ago • 4
🌊 MoM 1.0 Collection long context models for MoM multilingual embeddings • 5 items • Updated 24 days ago • 4
⛵ Vela 1.0 Collection The model family for intelligent routing. • 15 items • Updated 6 days ago • 27
🎲 Decision 1.0 Collection Towards Open Decision Foundation Models • 7 items • Updated 6 days ago • 23
FLUX.1 ONNX Collection ONNX exports of our FLUX.1 models. • 5 items • Updated Nov 25, 2025 • 58
FLUX.1 Collection A collection of our FLUX.1 models and LoRAs. • 13 items • Updated Jan 2 • 350
FLUX 3 Action Collection Open weights 7B world action model: base and shared encoders, SO-101 and DROID policies. Code: https://github.com/black-forest-labs/flux-action • 3 items • Updated 5 days ago • 41
SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness Paper • 2609.20519 • Published 20 days ago • 139
ACE Collection Ai2 Climate Emulator (ACE) is a family of fast ML models that simulate weather and climate variability over time scales from hours to centuries. • 14 items • Updated 18 days ago • 18
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression Paper • 2609.19969 • Published 20 days ago • 224
view article Article ALTK‑Evolve: On‑the‑Job Learning for AI Agents ibm-research • Apr 8 • 32