Ax Bhavesh Kumar, Dylan Feng, Leonard Tang 3/25/2026

MJ1: Multimodal Judgment via Grounded Verification

arXiv paper MJ1: multimodal judge trained with RL enforcing visual grounding through structured verification chains and counterfactual consistency rewards.

Ax Sonia Laguna, Jorge da Silva Goncalves, Moritz Vandenhirtz, Alain Ryser, Irene Cannistraci, Julia E. Vogt 3/25/2026

Rethinking Machine Unlearning: Models Designed to Forget via Key Deletion

arXiv paper proposing key deletion approach for machine unlearning designed at model development stage rather than post-hoc, addressing privacy regulations and data errors.

Ax Chiyu Ma, Shuo Yang, Kexin Huang, Jinda Lu, Haoming Meng, Shangshang Wang, Bolin Ding, Soroush Vosoughi, Guoyin Wang, Jingren Zhou 3/25/2026

FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization

arXiv paper presenting FIPO reinforcement learning algorithm for improving reasoning in LLMs through fine-grained credit assignment beyond outcome-based rewards.

Ax Do Edmond Sanou, Christophe Ambroise, Genevi\`eve Robin 3/25/2026

Inference of Multiscale Gaussian Graphical Model

Gaussian Graphical Models with simultaneous clustering and graph inference for high-dimensional data. Dimensionality reduction approach.

Ax Cristian Garc\'ia-Romero, Miquel Espl\`a-Gomis, Felipe S\'anchez-Mart\'inez 3/25/2026

Smart Bilingual Focused Crawling of Parallel Documents

Web crawling method using neural networks to efficiently find parallel bilingual documents. Targets document discovery for translation.

Ax Huancheng Chen, Jingtao Li, Weiming Zhuang, Chen Chen, Lingjuan Lyu 3/25/2026

Replay-Free Continual Low-Rank Adaptation with Dynamic Memory

Continual learning technique combining parameter-efficient fine-tuning with vision transformers to prevent catastrophic forgetting. Addresses sequential task adaptation.

Ax Riccardo Bravin, Massimo Pavan, Hazem Hesham Yousef Shalby, Fabrizio Pittorino, Manuel Roveri 3/25/2026

EmbBERT: Attention Under 2 MB Memory

Transformer attention mechanism compressed to run in under 2MB memory for IoT and wearable devices. Enables NLP deployment on ultra-constrained hardware.

Ax Cheng Wang, Yu Jiang, Zhihao Peng, Chenxin Li, Changbae Bang, Lin Zhao, Wanyi Fu, Jinglei Lv, Jorge Sepulcre, Carl Yang, Lifang He, Tianming Liu, Xue-Jun Kong, Quanzheng Li, Daniel S. Barron, Anqi Qiu, Randy Hirschtick, Byung-Hoon Kim, Hongbin Han, Xiang Li, Yixuan Yuan 3/25/2026

Towards a general-purpose foundation model for fMRI analysis

NeuroSTORM foundation model for fMRI analysis learning generalizable representations with improved transferability.

Ax Raj Ghugare, Roger Creus Castanyer, Catherine Ji, Kathryn Wantlin, Jin Schofield, Karthik Narasimhan, Benjamin Eysenbach 3/25/2026

BuilderBench: The Building Blocks of Intelligent Agents

BuilderBench benchmark for evaluating intelligent agents' ability to learn through interaction and exploration beyond training data.