Diffusion language models (DLMs) generate text through iterative parallel refinement, offering the potential for higher throughput than autoregressive (AR) decoding. However, most DLMs still maintain one generative state per token, so every denoising step processes a state sequence as long as the output sequence, limit...
Xin-Song Feng, Peng Du, Zhi-Zhuo Yang et al.· 0 citations
The model shows substantial gains over the previous default model for Writer Agent, and compares favorably with several recent models on public benchmarks, scoring the highest on BFCL Core at $0.785$ and posts the highest six-benchmark mean of the cohort.
Peng Du, Kiran P. Kamble, R. Vasudev et al.· 0 citations
This work presents MidSurfNet, a learning-based face-pairing method that couples a learned face-pair scorer with a deterministic face-group composition, and demonstrates practical utility by generating mid-surfaces from the composed face groups through an industrial mid-surface API and running finite element analyses o...
Lin-Rong Ye, Xin-Hang Zhou, Xing-Yu Yang et al.· 0 citations
The introduction of TraceCAD, a recovery layer that links requested features, modeling steps, failure evidence, and candidate outcomes as persistent state, demonstrates that persistent, localized, and reusable recovery improves final CAD quality and repair reliability.
Fengxiao Fan, Jingzhe Ni, F. Sang et al.· 0 citations
CADIR, an agent-friendly executable intermediate representation for CAD generation and cross-backend editing, and a construction-graph retrieval method for text and image queries that supports both full-graph and subgraph retrieval, enabling agents to leverage complete models and modeling substructures.
Yu Liu, Jingzhe Ni, Yi-Ming Chen et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
