ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search

Om avsnittet

A fully open 7B model that pairs reasoning with tool use and claims results close to models many times its size on math and search tasks. Authors: Jiyan He, Guang Liang, Hao Liu, Haoxiang Guan, Jinbo Sun, Junyi Guo, Wenjun Feng, Yantai Xie, Yifei Shen, Bin Shao, Chuyang Wei, Kai Chen, Kexin Zhou, Minghang Zhu, Shuxin Zheng, Tie-Yan Liu, Taine Zhao, Wenhui Zhu, Xueyin Xu, Xiaoqing Zhang, Yatao Li, Yuxuan Ren Paper: https://arxiv.org/abs/2609.13356v1

Om avsnittet

Fler avsnitt

Anchoring Clinical Events in Time: UID-Preserving Multimodal Reconstruction and Source-Grounded Adjudication

Embodied-BenchForge: A Closed-Loop Agentic Workflow for Embodied Benchmark Construction

Dynin-Robotics: Omnimodal Unified Diffusion Vision-Language-Action Model

Attention Quantization for Tabular Foundation Models

Comfort by Construction: Adaptive, Comfort-Bounded Action Spaces for Learned Driving Policies

MAxBench: A Multinomial Concept Recovery Benchmark

MP-Bench: Evaluating Voice Agents as a Multiparty Conversation Participant

Autonomous Research for Open-Ended Problems: A Case Study on Telecom Ticket Retrieval

Rethinking Heterogeneous System Disaggregation for Subquadratic Attention

How Good Are Frontier Models at Physics? Expert Re-Grading Reveals Broken Evaluations and Near-Saturation of Leading Benchmarks