Ax Yuqian Zhang, Donghua Yu, Zhengyuan Lin, Botian Jiang, Mingshu Chen, Yaozhou Jiang, Yiwei Zhao, Yiyang Zhang, Yucheng Yuan, Hanfu Chen, Kexin Huang, Jun Zhan, Cheng Chang, Zhaoye Fei, Shimin Li, Xiaogui Yang, Qinyuan Cheng, Xipeng Qiu 3/23/2026

MOSS-TTSD: Text to Spoken Dialogue Generation

MOSS-TTSD system for text-to-spoken dialogue generation handling turn-taking, acoustic consistency, and long-form stability.

Ax Van-Duy Ngo, Stergos Afantenos, Emiliano Lorini, Miguel Couceiro 3/23/2026

FrameNet Semantic Role Classification by Analogy

Semantic role classification approach using analogies over frame elements and lexical units in FrameNet datasets.

Ax Stefano Perrella, Eric Morales Agostinho, Hugo Zaragoza 3/23/2026

Span-Level Machine Translation Meta-Evaluation

Proposes span-level evaluation methodology for machine translation meta-evaluation, extending beyond scalar scores to error detection and severity assessment.

Ax Sen Jia, Ning Zhu, Jinqin Zhong, Jiale Zhou, Huaping Zhang, Jenq-Neng Hwang, Lei Li 3/23/2026

RAM: Recover Any 3D Human Motion in-the-Wild

RAM recovers 3D human motion from video using motion-aware semantic tracking, adaptive Kalman filtering, and temporal HMR module.

Ax Hugo Cazaux, Ralph Rudd, Hlynur Stef\'ansson, Sverrir \'Olafsson, Eyj\'olfur Ingi \'Asgeirsson 3/23/2026

Fine-tuning Timeseries Predictors Using Reinforcement Learning

Reinforcement learning fine-tuning methods for financial time series forecasters with supervised-to-RL backpropagation and transfer learning benefits.

Ax Yingwei Zheng, Cong Li, Shaohua Li, Yuqun Zhang, Zhendong Su 3/23/2026

Agentic Harness for Real-World Compilers

llvm-autofix agentic harness enables LLM agents to autonomously fix compiler bugs with compiler-specific tools and cross-domain expertise.

Ax Ravish Gupta (BigCommerce), Saket Kumar (University at Buffalo, The State University of New York, Buffalo, NY, USA), Shreeya Sharma (Microsoft), Maulik Dang (Amazon), Abhishek Aggarwal (Amazon) 3/23/2026

An Agentic Multi-Agent Architecture for Cybersecurity Risk Management

Six-agent AI system for cybersecurity risk assessment following NIST CSF framework, automates profiling, asset mapping, threat analysis, and risk scoring.

Ax Jingyang Lin, Jialian Wu, Jiang Liu, Ximeng Sun, Ze Wang, Xiaodong Yu, Jiebo Luo, Zicheng Liu, Emad Barsoum 3/23/2026

VideoSeek: Long-Horizon Video Agent with Tool-Guided Seeking

VideoSeek: long-horizon video agent using tool-guided seeking and video logic flow. Active frame selection reduces computation vs dense frame sampling.