CoLT: Teaching Multi-Modal Models to Think with Chain of Latent Thoughts Paper • 2606.31986 • Published 24 days ago • 1
RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources Paper • 2606.29538 • Published 8 days ago • 137
Program-as-Weights: A Programming Paradigm for Fuzzy Functions Paper • 2607.02512 • Published 22 days ago • 124
SproutRAG: Attention-Guided Tree Search with Progressive Embeddings for Long-Document RAG Paper • 2606.18381 • Published Jun 16 • 19
Holistic Data Scheduler for LLM Pre-training via Multi-Objective Reinforcement Learning Paper • 2606.24133 • Published about 1 month ago • 11
Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance Paper • 2606.19195 • Published Jun 17 • 141
SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning Paper • 2606.13673 • Published Jun 11 • 111
view article Article **LoRA Fine-Tuning BitNet b1.58 LLMs on Heterogeneous Edge GPUs via QVAC Fabric** qvac • Mar 17 • 19
LaRA: Layer-wise Representation Analysis for Detecting Data Contamination in RL Post-Training Paper • 2605.29888 • Published May 28 • 34
Running 1 The Physical AI Inference Gap in Batch-1 LLM Decode 🪜 1 Interactive companion to the batch-1 LLM decode paper