Model Detail
Step-3.7-Flash-NVFP4
▲ 24.7%Step-3.7-Flash-NVFP4 is a code generation model with 51.9B parameters released by stepfun-ai. The model is registered under the image-text-to-text pipeline tag on Hugging Face, distributed under the permissive apache-2.0 license.
Step-3.7-Flash-NVFP4 ships with 51.9B parameters. Total weight footprint is approximately 103.8 GB, which is the relevant figure when planning local-inference VRAM. The apache-2.0 license is permissive, allowing commercial deployment and derivative work without per-seat fees, though attribution requirements still apply.
Downloads of Step-3.7-Flash-NVFP4 have moved +24.7% over the past 24 hours. That is a slight downtrend, consistent with normal cooling as newer models compete for the same workloads. These numbers are signal, not guarantee — week-over-week download counts on Hugging Face also reflect mirror traffic, CI scrapes, and one-off benchmarking runs.
Step-3.7-Flash-NVFP4 is best fit for code completion, repository-scale Q&A, and pair-programming integrations. It is a less obvious choice for one-shot generation of security-critical code without review. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.
Scaling Limits of Constant-Stepsize SGD at Flat Minima
arXiv:2607.16384v1 Announce Type: new Abstract: For stochastic gradient descent (SGD) with a constant stepsize $\alpha$, the invariant law of the iterates, centered at a minimizer, describes the behavior of the algorithm over long time horizons. In the strongly convex case, this invariant law has th
Tensor-Train Joint Modeling for Few-Step Discrete Diffusion
arXiv:2607.03788v2 Announce Type: replace Abstract: Discrete diffusion promises orders-of-magnitude faster generation than autoregressive (AR) models for sequential discrete data, yet its full potential of few-step generation has remained out of reach due to a fundamental structural limitation. The
CaloTrilogy: Toward a Breakthrough in One-Step, End-to-End, Physics-Guided Shower Generation for Modern Calorimeters
arXiv:2606.04165v2 Announce Type: replace-cross Abstract: High-precision calorimeter simulation at current and future colliders imposes rapidly growing computational demands, motivating the development of machine-learning surrogates for traditional Monte Carlo tools such as Geant4. Flow matching and
One-step lowest-variance selection in a Gaussian random-field model motivated by masked diffusion: Total correlation and a square root collision threshold
arXiv:2607.17522v1 Announce Type: cross Abstract: Motivated by confidence-guided parallel unmasking in masked discrete diffusion, we study a single selection step in a stylized Gaussian random-field model. A locally dependent nonnegative score field represents position wise uncertainty, and the sche
Adaptive Multi-Step Lookahead Decoding for Diffusion Language Models
arXiv:2607.15655v1 Announce Type: new Abstract: Masked diffusion language models (DLMs) enable parallel text generation by iteratively refining masked tokens, offering a promising alternative to autoregressive decoding. Recent lookahead-based decoding methods improve the accuracy--efficiency trade-o
Agent Step Value: Auditing Evaluator-Channel Reversals in Black-Box Agent Traces
arXiv:2607.04419v4 Announce Type: replace Abstract: Pooling, substituting, or reusing evaluator-derived step rewards assumes that their direction survives a change of evaluation channel. The same frozen transition can violate that assumption. Process rewards vary agent states, while evaluator audits
