Wei Liu

Last Translation Benchmark

Vilém Zouhar, Niyati Bafna, Mukund Choudhary, et al.

Editable Visual Design

Junyan Ye, Wei Liu, Dongzhi Jiang, et al.

RuleMem: Active Rule Memory for Long-Term Conversational Agents

Xingyuan Zeng, Zuohan Wu, Quanming Yao, et al.

Xiaomi-TabLDM: A Tabular Foundation Model Technical Report

Xiaomi-TabLDM Team, :, Penghui Wang, et al.

UNIFUSION: Adapting Autoregressive Language Models into Discrete Diffusion under a Unified Reverse-Rate Objective

Xiaoyi Jiang, Jingyuan Li, Yixuan Jiang, et al.

Mean-to-Score Discrete Diffusion: Posterior-Mean Denoisers for Score Entropy

Jingyuan Li, Xiaoyi Jiang, Yixuan Jiang, et al.

Context-Aware Explanations for Spatialized Document Layouts

Wei Liu, John Wenskovitch, Chris North, et al.

DanceOPD: On-Policy Generative Field Distillation

Wei Zhou, Xiongwei Zhu, Zelin Xu, et al.

Reinforcement Learning for Compositional Generalization with Outcome-Level Optimization

Xiyan Fu, Wei Liu

Time-Interval-Aware Disentangled Expert Modeling for Next-Basket Recommendation

Zhiying Deng, Yuan Fu, Usman Farooq, et al.

Hidden Failure Modes of Gradient Modification under Adam in Continual Learning, and Adaptive Decoupled Moment Routing as a Repair

Yuelin Hu, Zhenbo Yu, Zhengxue Cheng, et al.

Vision-Guided Iterative Refinement for Frontend Code Generation

Hannah Sansford, Derek H. C. Law, Wei Liu, et al.

JoyAI-LLM Flash: Advancing Mid-Scale LLMs with Token Efficiency

Aichen Cai, Anmeng Zhang, Anyu Li, et al.

AVO: Agentic Variation Operators for Autonomous Evolutionary Search

Terry Chen, Zhifan Ye, Bing Xu, et al.

SOL-ExecBench: Speed-of-Light Benchmarking for Real-World GPU Kernels Against Hardware Limits

Edward Lin, Sahil Modi, Siva Kumar Sastry Hari, et al.

SOL-ExecBench is a new benchmark for evaluating AI systems that optimize GPU kernels by measuring how close they get to the theoretical maximum performance (Speed-of-Light) that the hardware can achieve, rather than just comparing against other software implementations. It includes 235 real optimization problems from actual AI models and uses a special pipeline called SOLAR to calculate what perfect performance would look like for each kernel. The benchmark includes safeguards to prevent cheating and focuses on modern NVIDIA Blackwell GPUs with various precision formats.