Ax Giorgos Nikolaou, Tommaso Mencattini, Donato Crisostomi, Andrea Santilli, Yannis Panagakis, Emanuele Rodol\`a 3/16/2026

Language Models are Injective and Hence Invertible

Mathematical proof that transformer language models are injective, enabling exact input recovery from representations despite nonlinear components.

Ax Kemou Li, Qizhou Wang, Yue Wang, Fengpeng Li, Jun Liu, Bo Han, Jiantao Zhou 3/16/2026

LLM Unlearning with LLM Beliefs

Method for unlearning harmful content from LLMs by analyzing belief redistribution in probability space, avoiding unwanted side effects of gradient ascent.

Ax Yichuan Deng, Zhao Song, Kaijun Yuan, Tianyi Zhou 3/16/2026

Why Softmax Attention Outperforms Linear Attention

Comparative analysis of softmax vs linear attention mechanisms in transformer architectures, examining computational efficiency tradeoffs.

Ax Jianwei Li, Jung-Eun Kim 3/16/2026

Superficial Safety Alignment Hypothesis

Analyzes brittleness of LLM safety alignment mechanisms, proposing superficial safety alignment hypothesis explaining why standard alignment approaches are vulnerable.

Ax Vinod Raman, Hilal Asi, Satyen Kale 3/16/2026

AdaBoN: Adaptive Best-of-N Alignment

Prompt-adaptive Best-of-N alignment strategy using reward models to reduce computational cost of test-time alignment for language models.

Ax Thai-Hoc Vu, Ngo Hoang Tu, Thien Huynh-The, Kyungchun Lee, Sunghwan Kim, Miroslav Voznak, Quoc-Viet Pham 3/16/2026

Integration of TinyML and LargeML: A Survey of 6G and Beyond

Survey on integrating TinyML and LargeML for 6G networks, covering deep learning applications in mobile systems, autonomous vehicles, and smart services.

Ax Yinqiu Huang, Hao Ma, Wenshuai Chen, Zongwei Wang, Shuli Wang, Yongqiang Zhang, Xue Wei, Yinhua Zhu, Haitao Wang, Xingxing Wang 3/16/2026

Generative Bid Shading in Real-Time Bidding Advertising

Generative approach to bid shading in real-time bidding advertising using non-convex surplus optimization instead of traditional two-stage methods.

Ax Gabriele Digregorio, Marco Di Gennaro, Stefano Zanero, Stefano Longari, Michele Carminati 3/16/2026

On the (In)Security of Loading Machine Learning Models

Security evaluation of ML model sharing frameworks and hubs, assessing vulnerabilities in loading shared models and security awareness gaps among practitioners.

Ax Shuofei Qiao, Yanqiu Zhao, Zhisong Qiu, Xiaobin Wang, Jintian Zhang, Zhao Bin, Ningyu Zhang, Yong Jiang, Pengjun Xie, Fei Huang, Huajun Chen 3/16/2026

Scaling Generalist Data-Analytic Agents

DataMind: scalable data-analytic AI agents for automated discovery. Open-source agent framework handling diverse-format data files and multi-step reasoning.

Ax Hritik Bansal, Devendra Singh Sachan, Kai-Wei Chang, Aditya Grover, Gargi Ghosh, Wen-tau Yih, Ramakanth Pasunuru 3/16/2026

HoneyBee: Data Recipes for Vision-Language Reasoners

HoneyBee: data curation approaches for vision-language reasoning datasets. Analyzes impact of context, content, and format on VLM reasoning capabilities.