3 papers
cs.SE2026
KAT-Coder-V2.5 Technical Report
Bo Huang, Fengxiang Li, Hao Xu +50
We present KAT-Coder-V2.5, a coding-focused agentic model trained to act autonomously inside real, executable repositories rather than as a single-turn code generator. Its capabili…
cs.LG2025
Flows and Diffusions on the Neural Manifold
Daniel Saragih, Deyu Cao, Tejas Balaji
Diffusion and flow-based generative models have achieved remarkable success in domains such as image synthesis, video generation, and natural language modeling. In this work, we ex…
cs.LG2025
Flow to Learn: Flow Matching on Neural Network Parameters
Daniel Saragih, Deyu Cao, Tejas Balaji +1
Foundational language models show a remarkable ability to learn new concepts during inference via context data. However, similar work for images lag behind. To address this challen…