8 papers
Denoising Blocks, Not Tokens: Efficient Compressed Continuous Diffusion with Branching Token Realization
Xinsong Feng, Peng Du, Zhizhuo Yang +3
Diffusion language models (DLMs) generate text through iterative parallel refinement, offering the potential for higher throughput than autoregressive (AR) decoding. However, most…
Palmyra x6 Technical Report: An Agentic, Tool-Use Model Post-Trained via Anchored Supervised Fine-Tuning
Peng Du, Kiran Kamble, Rakshith Vasudev +5
Palmyra x6 is a large language model optimized for use with enterprise-oriented agentic tasks. The model was built by post-training a Mixture-of-Experts base model with Anchored Su…
TraceCAD: Trace-Guided Repair for Agentic CAD Generation
Fengxiao Fan, Jingzhe Ni, Fan Sang +5
LLM-based CAD agents produce executable parametric programs, but their correction loops may lose evidence about satisfied requirements, faulty operations, and prior repairs. We int…
CADIR: A Cross-Backend Editable Intermediate Representation for Agentic CAD Generation
Yu Liu, Jingzhe Ni, Yiming Chen +4
Large language models have made it possible to generate executable computer-aided design (CAD) programs from natural-language descriptions or images. However, existing methods repr…
MidSurfNet: Learning Face Pairing for Mid-surface Abstraction of Thin-walled CAD Models
Li Ye, Xinhang Zhou, Xingyu Yang +4
Mid-surface abstraction is an important preprocessing step for finite element analysis of thin-walled CAD models, and face pairing is its central subproblem. Existing face-pairing…
RewardHarness: Self-Evolving Agentic Post-Training
Yuxuan Zhang, Penghui Du, Bo Li +11
Aligning generative models with human preferences remains a central challenge. While RLHF is widely adopted, it relies on large-scale preference data. This limitation is particular…
CADDesigner: Conceptual CAD Model Generation with a General-Purpose Agent
Fengxiao Fan, Jingzhe Ni, Xiaolong Yin +6
Computer-Aided Design (CAD) is widely used for conceptual design and parametric 3D modeling, but typically requires a high level of expertise from designers. To lower the entry bar…
RLCAD: Reinforcement Learning Training Gym for Revolution Involved CAD Command Sequence Generation
Xiaolong Yin, Xingyu Lu, Jiahang Shen +5
A CAD command sequence is a typical parametric design paradigm in 3D CAD systems where a model is constructed by overlaying 2D sketches with operations such as extrusion, revolutio…