Model Detail
Reasoning-Medical-27B
—Reasoning-Medical-27B is a multimodal model with 27B parameters released by EpistemeAI. The model is registered under the image-text-to-text pipeline tag on Hugging Face, distributed under the permissive apache-2.0 license.
Reasoning-Medical-27B ships with 27B parameters. Total weight footprint is approximately 27.8 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.
Reasoning-Medical-27B is best fit for mixed text-and-image reasoning tasks such as document understanding. 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.
Reasoning with Continuous Latent Diffusion
arXiv:2609.35694v3 Announce Type: replace Abstract: We introduce the Continuous Embedding Diffusion Reasoner (CEDR), a training and inference pipeline for continuous latent diffusion models that achieves strong performance on mathematical reasoning and code generation. We learn compact answer repres
Present but Hard to Read: Probing Latent Reasoning with Minimal Pairs
arXiv:2610.28498v1 Announce Type: cross Abstract: Probing studies of latent reasoning often read a model's state where the answer begins and take a failed probe as evidence that a value is absent. We test this with a digit copied from the question, in the looped model Ouro-1.4B and the standard tran
When Can LLM Reasoning Reliably Reuse Intermediate Results?
arXiv:2610.27662v1 Announce Type: new Abstract: Sampling complete solutions gives large language models more chances to solve a problem, but each attempt starts again. For tasks with several subproblems, all required answers must be correct in the same attempt. Retaining intermediate results can avo
VisualEvolve: A Skill Self-Evolution Framework for Visual Reasoning
arXiv:2610.28386v1 Announce Type: cross Abstract: Visual tool use enables vision-language models (VLMs) to acquire task-relevant evidence, but its effectiveness can be limited by predefined visual operations and the tool-use strategies learned during training. Representing these operations and strat
The Culture Within: Towards Mechanistic Understanding of Cultural Reasoning in LLMs
arXiv:2610.27202v1 Announce Type: new Abstract: Large Language Models (LLMs) increasingly operate across culturally diverse settings, yet existing evaluations largely measure cultural behavior at the output level. We introduce CultureLens, a reference-grounded benchmark and mechanistic study of how
Binary Agreement for Efficient Unsupervised Confidence Calibration of Reasoning LLMs
arXiv:2604.19444v2 Announce Type: replace Abstract: Reasoning language models often lack the calibrated confidence needed for reliable deployment, particularly when correctness labels are unavailable and sampling budgets are limited. We introduce Binary Agreement for Self-consistency Calibration (BA
