Granite 4.2 Language Models Collection Efficient reasoning and thinking language models for multilingual generation, coding, and AI assistant workflows. • 3 items • Updated 3 days ago • 32
MoE-SpAc: Efficient MoE Inference Based on Speculative Activation Utility in Heterogeneous Edge Scenarios Paper • 2603.09983 • Published Feb 12 • 4
FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution Paper • 2608.16157 • Published 12 days ago • 100
From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement Paper • 2607.23802 • Published Jul 26 • 106
Agents-A1 Collection Agents-A1 is a Long-horizon Agentic Model that reaches trillion-parameter-level performance by scaling the agent horizon. • 12 items • Updated Jul 16 • 42
DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation Paper • 2607.05147 • Published Jul 6 • 47
Laguna XS 2.1 Collection Designed for agentic coding and long-horizon work on a local machine. Licensed under OpenMDW-1.1. • 9 items • Updated Jul 2 • 24
Tmax Collection Data and models associated with "Tmax: A simple recipe for terminal agents". paper: https://arxiv.org/abs/2606.23321 • 23 items • Updated Jun 23 • 19
SenseNova-U1 Collection SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-Unify Architecture • 12 items • Updated 14 days ago • 76
Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation Paper • 2601.22813 • Published Jan 30 • 63
Quartet: Native FP4 Training Can Be Optimal for Large Language Models Paper • 2505.14669 • Published May 20, 2025 • 79