view article Article Transformers now runs llama.cpp quants +1 marcsun13, ArthurZ, lysandre • 5 days ago • 72
LensVLM: Selective Context Expansion for Compressed Visual Representation of Text Paper • 2605.07019 • Published May 7 • 6
Ovis-Embedding: Pushing the Frontiers of Universal Omni-Modal Embeddings Paper • 2609.25165 • Published 6 days ago • 66
Qwen-Image-2.1 Image-to-Image LoRAs Collection Collection of QI2.1 I2I Manipulation LoRAs • 6 items • Updated 3 days ago • 3
MiMo-V2.6 Compressions Collection Collection of MiMo-V2.6 Compressions (GGUF / MLX / FP8) • 3 items • Updated 5 days ago • 1
view article Article tokenizers v1: encode, decode and scaling, measured +2 ArthurZ, sbrandeis, mcpotato, lysandre • 6 days ago • 76
view article Article Pruning LLMs Like a Physicist: Block Removal as an Ising Optimization Problem MultiverseComputingCAI • 6 days ago • 31
RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents Paper • 2609.22000 • Published 9 days ago • 77
EvoOntology: A Self-Evolving Ontology Layer for Data Agents Paper • 2609.15779 • Published 13 days ago • 154
IntBMoE: Integrating Block-Level Conditioning into Expert Composition for Full-Participation Mixture-of-Experts Paper • 2609.21346 • Published 9 days ago • 101
Qwen-Image-2.1-PE Compressions Collection Collection of Qwen-Image-2.1-PE (Prompt Enhancer) Compressions. • 6 items • Updated 5 days ago • 1
Merge Soup — Qwen3.5 Collection Collection of Experimental Model Merges • 8 items • Updated 1 day ago • 2
VisionGuardrail Evo2 Collection Collection of VisionGuardrail Multimodal Models! • 6 items • Updated 5 days ago • 1
SenseNova-U1.5: Towards Native Unified Visual Intelligence Paper • 2609.11929 • Published 17 days ago • 274
SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem Paper • 2609.07064 • Published 20 days ago • 146
NCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept Prediction Paper • 2609.10715 • Published 18 days ago • 329