8 papers
DeepSeek Elastic Compute (DSec): A Sandbox Infrastructure for Effective Agentic Training at Scale
Jialiang Huang, Hongxuan Tang, Jingchang Chen +128
Large-scale agentic training and evaluation with large language models (LLMs) rely on isolated, stateful execution environments in which models inspect repositories, invoke tools,…
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
DeepSeek-AI, :, Anyi Xu +585
The widespread adoption of long-horizon agents has made model workloads increasingly input-heavy. Although prior work has substantially reduced the cost of long-context computation…
Kastor: An efficient fine-tuning strategy for generative emulation of PDE simulations
Guillaume Couairon, Alexis Jacq, Yu-Han Wu +4
Machine learning offers a promising avenue to accelerate physical simulations by replacing computationally expensive traditional Partial Differential Equation (PDE) solvers with fa…
DiffusionGemma Technical Report
DiffusionGemma Team, Adrien Ali Taïga, James Assiene +41
We introduce DiffusionGemma, an experimental open-weight language model that uses discrete diffusion to generate text at exceptionally high speed. Rather than decoding one token at…
Understanding diffusion models requires rethinking (again) generalization
Pierre Marion, Yu-Han Wu
This position paper argues that understanding generalization in diffusion models requires fundamentally new theoretical frameworks that go beyond both classical statistical learnin…
Optimal Stopping in Latent Diffusion Models
Yu-Han Wu, Quentin Berthet, Gérard Biau +3
We identify and analyze a surprising phenomenon of Latent Diffusion Models (LDMs) where the final steps of the diffusion can degrade sample quality. In contrast to conventional arg…
Taking a Big Step: Large Learning Rates in Denoising Score Matching Prevent Memorization
Yu-Han Wu, Pierre Marion, Gérard Biau +1
Denoising score matching plays a pivotal role in the performance of diffusion-based generative models. However, the empirical optimal score--the exact solution to the denoising sco…
Implicit regularization of deep residual networks towards neural ODEs
Pierre Marion, Yu-Han Wu, Michael E. Sander +1
Residual neural networks are state-of-the-art deep learning models. Their continuous-depth analog, neural ordinary differential equations (ODEs), are also widely used. Despite thei…