7 papers
The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence
MiniMax, :, Aili Chen +219
We introduce the MiniMax-M2 series, a family of Mixture-of-Experts language models built around the principle that mini activations can unleash maximum real-world intelligence. The…
Convex Dataset Valuation for Post-Training
Siqi Zeng, Christopher Jung, Rui Li +7
Improving LLM performance on downstream tasks sometimes requires leveraging auxiliary datasets during post-training. In practice, however, developers face constraints on compute, l…
What Happens Before Decoding? Prefill Determines GUI Grounding in VLMs
Jiaping Lin, Fei Shen, Junzhe Li +4
Existing training-free approaches for GUI grounding often rely on multiple inference runs, such as iterative cropping or candidate aggregation, to identify target elements. Despite…
ORACLE: Anticipating Scams from Partial Trajectories in Streaming App Usage
Wenbo Gao, Songbai Tan, Zhongan Wang +6
Smartphone scams are increasingly prevalent and typically manifest as multi-stage, cross-application processes with gradually emerging intent. Effective intervention thus requires…
Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters
Ailin Huang, Ang Li, Aobo Kong +213
We introduce Step 3.5 Flash, a sparse Mixture-of-Experts (MoE) model that bridges frontier-level agentic intelligence and computational efficiency. We focus on what matters most wh…
Step-3 is Large yet Affordable: Model-system Co-design for Cost-effective Decoding
StepFun, :, Bin Wang +195
Large language models (LLMs) face low hardware efficiency during decoding, especially for long-context reasoning tasks. This paper introduces Step-3, a 321B-parameter VLM with hard…