SINQ: Sinkhorn-Normalized Quantization for Calibration-Free Low-Precision LLM Weights Paper • 2509.22944 • Published Sep 26 • 76
⚛️ Liquid Nanos Collection Library of task-specific models: https://www.liquid.ai/blog/introducing-liquid-nanos-frontier-grade-performance-on-everyday-devices • 20 items • Updated 6 days ago • 84
Qianfan-VL Collection Qianfan-vl model series. The models are mainly domain enhanced vision language model, targeting enterprise level multi modal understanding scenarios. • 4 items • Updated Sep 24 • 19
Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding Paper • 2509.06923 • Published Sep 8 • 21
MobileLLM Collection Optimizing Sub-billion Parameter Language Models for On-Device Use Cases (ICML 2024) https://arxiv.org/abs/2402.14905 • 46 items • Updated Sep 10 • 131
Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic Paper • 2509.01363 • Published Sep 1 • 58
InternVL3.5 Collection This collection includes all released checkpoints of InternVL3.5, covering different training stages (e.g., Pretraining, SFT, MPO, Cascade RL). • 54 items • Updated about 1 month ago • 99