Ax Haocheng Xi, Shuo Yang, Yilong Zhao, Muyang Li, Han Cai, Xingyang Li, Yujun Lin, Zhuoyang Zhang, Jintao Zhang, Xiuyu Li, Zhiying Xu, Jun Wu, Chenfeng Xu, Ion Stoica, Song Han, Kurt Keutzer 5/5/2026

Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization

Technique using 2-bit KV-cache quantization to reduce memory bottlenecks in autoregressive video generation models from 30GB to deployable sizes.

Ax Junxiong Wang, Fengxiang Bie, Jisen Li, Zhongzhu Zhou, Zelei Shao, Yubo Wang, Yinghui Liu, Qingyang Wu, Avner May, Sri Yanamandra, Yineng Zhang, Ce Zhang, Tri Dao, Percy Liang, Ben Athiwaratkun, Shuaiwen Leon Song, Chenfeng Xu, Xiaoxia Wu 5/5/2026

When RL Meets Adaptive Speculative Training: A Unified Training-Serving System

Unified system integrating reinforcement learning with adaptive speculative decoding to accelerate LLM serving while enabling continuous speculator training.

Ax Timoth\'ee Chauvin, Cl\'ement Lalanne, Erwan Le Merrer, Jean-Michel Loubes, Fran\c{c}ois Ta\"iani, Gilles Tredan 5/5/2026

Token-Efficient Change Detection in LLM APIs

arXiv paper on black-box detection of LLM API changes using low-cost token-level observation via border input approach.

Ax Mingze Li, Yu Rong, Songyou Li, Lihong Wang, Jiacheng Cen, Liming Wu, Anyi Li, Zongzhao Li, Qiuliang Liu, Rui Jiao, Tian Bian, Pengju Wang, Hao Sun, Jianfeng Zhang, Ji-Rong Wen, Deli Zhao, Shifeng Jin, Tingyang Xu, Wenbing Huang 5/5/2026

Agentic Fusion of Large Atomic and Language Models to Accelerate Superconductor Discovery

Agentic system fusing atomic-scale models and LLMs for accelerated superconductor discovery via multi-dimensional reasoning.

Ax Xuan Shen, Yizhou Wang, Yufa Zhou, Xiangxi Shi, Pu Zhao, Yanzhi Wang, Jiuxiang Gu 5/5/2026

Efficient Reasoning with Hidden Thinking

Heima framework compresses chain-of-thought reasoning in multimodal LLMs into abstract tokens for efficiency gains.

Ax Benedikt Kantz, Peter Waldert, Stefan Lengauer, Clemens Staudinger, Stefan Schuster, Tobias Schreck 5/5/2026

Parameter Space Analysis through Guided Visual Interpolations

Proposes ParamInter tool for analyzing high-dimensional parameter spaces using guided visual interpolations and t-SNE representations.