Ax Stefano Grassi 3/31/2026

Feedback-Coupled Memory Systems: A Dynamical Model for Adaptive Coordination

Dynamical framework for adaptive coordination in multi-agent systems using feedback-coupled memory systems.

Ax Zekun Wu, Adriano Koshiyama, Sahan Bulathwela, Maria Perez-Ortiz 3/31/2026

AgentDrift: Unsafe Recommendation Drift Under Tool Corruption Hidden by Ranking Metrics in LLM Agents

AgentDrift identifies safety vulnerabilities in tool-augmented LLM agents through paired-trajectory protocol testing under tool corruption.

Ax Reva Schwartz, Gabriella Waters 3/31/2026

Real-World AI Evaluation: How FRAME Generates Systematic Evidence to Resolve the Decision-Maker's Dilemma

FRAME methodology for real-world AI evaluation generating systematic evidence of system behavior across diverse deployment contexts.

Ax Lawrence Adu Gyamfi, Paul Azunre, Stephen Edward Moore, Joel Budu, Akwasi Asare, Mich-Seth Owusu, Jonathan Ofori Asiamah 3/31/2026

GhanaNLP Parallel Corpora: Comprehensive Multilingual Resources for Low-Resource Ghanaian Languages

GhanaNLP parallel corpora dataset with 41,513 sentence pairs for five low-resource Ghanaian languages: Twi, Fante, Ewe, Ga, Kusaal.

Ax Jiayuan Du, Yuebing Song, Yiming Zhao, Xianghui Pan, Jiawei Lian, Yuchu Lu, Liuyi Wang, Chengju Liu, Qijun Chen 3/31/2026

Deconfounded Lifelong Learning for Autonomous Driving via Dynamic Knowledge Spaces

DeLL framework for lifelong learning in autonomous driving using Dirichlet process mixture models to address catastrophic forgetting.

Ax G. Ciarfaglia, A. Rosanova, S. Cipolla, J. Bartoli, A. Di Domenico, C. Fioroni, A. Fontana, M. R. Scoleri, M. I. Mone, D. Franchi, M. C. Del Gaudio, A. Leodori, F. Cinti, M. Capozzi, C. Baston, F. Picariello, M. Gabusi, S. Bonura, V. Morreale, I. Bailo 3/31/2026

EngGPT2: Sovereign, Efficient and Open Intelligence

EngGPT2-16B Italian LLM achieving competitive performance on MMLU-Pro, GSM8K, and HumanEval with 5-50% lower inference cost.

Ax Jian Yang, Wei Zhang, Jiajun Wu, Junhang Cheng, Shawn Guo, Haowen Wang, Weicheng Gu, Yaxin Du, Joseph Li, Fanglin Xu, Yizhi Li, Lin Jing, Yuanbo Wang, Yuhan Gao, Ruihao Gong, Chuan Hao, Ran Tao, Aishan Liu, Tuney Zheng, Ganqu Cui, Zhoujun Li, Mingjie Tang, Chenghua Lin, Wayne Xin Zhao, Xianglong Liu, Ming Zhou, Bryan Dai, Weifeng Lv 3/31/2026

InCoder-32B: Code Foundation Model for Industrial Scenarios

InCoder-32B code foundation model optimized for industrial programming tasks with hardware semantics and resource constraints.

Ax Andrew Choi, Xinjie Wang, Zhizhong Su, Wei Xu 3/31/2026

Scaling Sim-to-Real Reinforcement Learning for Robot VLAs with Generative 3D Worlds

Sim-to-real reinforcement learning approach for vision-language-action robot models using generative 3D world environments.

Ax Bartosz Trojan, Filip G\k{e}bala 3/31/2026

HypeLoRA: Hyper-Network-Generated LoRA Adapters for Calibrated Language Model Fine-Tuning

HypeLoRA framework using hyper-networks for parameter-efficient fine-tuning of language models with improved calibration on GLUE.

Ax Chien-Ping Lu 3/31/2026

Modernizing Amdahl's Law: How AI Scaling Laws Shape Computer Architecture

Reformulation of Amdahl's Law for modern heterogeneous systems with AI scaling dynamics and resource constraints.

Ax Xinyue Liu, Niloofar Mireshghallah, Jane C. Ginsburg, Tuhin Chakrabarty 3/31/2026

Alignment Whack-a-Mole : Finetuning Activates Verbatim Recall of Copyrighted Books in Large Language Models

Study showing finetuning bypasses alignment safeguards causing LLMs to verbatim recall copyrighted training data.

Ax Shuai Wang, Yinan Yu, Earl Barr, Dhasarathy Parthasarathy 3/31/2026

LLM-Powered Workflow Optimization for Multidisciplinary Software Development: An Automotive Industry Case Study

LLM-powered workflow optimization for multidisciplinary software development in automotive industry bridging domain experts and developers.

Ax Shuai Wang, Yinan Yu 3/31/2026

KG-Hopper: Empowering Compact Open LLMs with Knowledge Graph Reasoning via Reinforcement Learning

KG-Hopper: Framework enabling compact open LLMs to perform multi-hop knowledge graph reasoning via reinforcement learning.

Ax Yan Xie, Tiansheng Wen, Tangda Huang, Bo Chen, Chenyu You, Stefanie Jegelka, Yifei Wang 3/31/2026

Scaling Attention via Feature Sparsity

Sparse Feature Attention: Method to reduce transformer self-attention complexity via feature sparsity instead of sequence-level sparsity.

Ax Yuntong Zhang, Zhiyuan Pan, Imam Nur Bani Yusuf, Haifeng Ruan, Ridwan Shariffdeen, Abhik Roychoudhury 3/31/2026

Code Review Agent Benchmark

Code Review Agent Benchmark: Dataset for evaluating AI agents on code quality assurance and review tasks.

Ax Seungju Han, Konwoo Kim, Chanwoo Park, Benjamin Newman, Suhas Kotha, Jaehun Jung, James Zou, Yejin Choi 3/31/2026

Synthetic Mixed Training: Scaling Parametric Knowledge Acquisition Beyond RAG

Synthetic Mixed Training method combining synthetic QA and document generation to improve LLM knowledge acquisition beyond RAG performance.

Ax Rishikesh Sahay, Bell Eapen, Weizhi Meng, Md Rasel Al Mamun, Nikhil Kumar Dora, Manjusha Sumasadan, Sumit Kumar Tetarave, Rod Soto, Elyson De La Cruz 3/31/2026

Policy-Guided Threat Hunting: An LLM enabled Framework with Splunk SOC Triage

LLM-enabled automated threat hunting framework for SOC analysts integrating Splunk log analysis with policy guidance.

Ax Di Cao, Dongjie Fu, Hai Yu, Siqi Zheng, Xu Tan, Tao Jin 3/31/2026

X-OPD: Cross-Modal On-Policy Distillation for Capability Alignment in Speech LLMs

X-OPD: Cross-modal on-policy distillation method to align end-to-end speech LLMs with text-based performance.

Ax Sicheng Zuo, Yuxuan Li, Wenzhao Zheng, Zheng Zhu, Jie Zhou, Jiwen Lu 3/31/2026

Vega: Learning to Drive with Natural Language Instructions

Vision-language-action model for autonomous driving with natural language instruction following capability.

Ax Kyudan Jung, Jihwan Kim, Soyoon Kim, Jeonghoon Kim, Jaegul Choo, Cheonbok Park 3/31/2026

Sommelier: Scalable Open Multi-turn Audio Pre-processing for Full-duplex Speech Language Models

Multi-speaker audio preprocessing framework for full-duplex speech language models with conversational data.

Ax Moritz Nottebaum, Matteo Dunnhofer, Christian Micheloni 3/31/2026

CPUBone: Efficient Vision Backbone Design for Devices with Low Parallelization Capabilities

Efficient vision backbone architecture designed for low-parallelization CPU devices.

Ax Xinqi Lucas Liu, Ruoxi Hu, Alejandro Ojeda Olarte, Zhuoran Chen, Kenny Ma, Charles Cheng Ji, Lerrel Pinto, Raunaq Bhirangi, Irmak Guzey 3/31/2026

Ruka-v2: Tendon Driven Open-Source Dexterous Hand with Wrist and Abduction for Robot Learning

Open-source tendon-driven dexterous robot hand (Ruka-v2) with 11 DOF for robot learning applications.

Ax Eugene Lee, Yu-Chi Lin, Jiajie Diao 3/31/2026

Learning to Select Visual In-Context Demonstrations

Method for selecting optimal visual in-context demonstrations for multimodal LLMs using sequential selection.

Ax Shuozhi Yuan, Jinqing Wang, Zihao Liu, Miaomiao Yuan, Haoran Peng, Jin Zhao, Bingwen Wang, Haoyi Wang 3/31/2026

TED: Training-Free Experience Distillation for Multimodal Reasoning

Training-free distillation framework transferring multimodal reasoning knowledge via context-based selection.

Ax Baochen Xiong, Yifan Xu, Xiaoshan Yang, Yaguang Song, Yaowei Wang, Changsheng Xu 3/31/2026

A Step Toward Federated Pretraining of Multimodal Large Language Models

Federated learning approach for pretraining multimodal large language models on distributed private data.

Ax Jelena Markovic-Voronov, Kayhan Behdin, Yuanda Xu, Zhengze Zhou, Zhipeng Wang, Rahul Mazumder 3/31/2026

Robust Batch-Level Query Routing for Large Language Models under Cost and Capacity Constraints

Batch-level query routing framework for LLMs optimizing model assignment under cost and capacity constraints.

Ax Anisha Roy, Dip Roy 3/31/2026

MemGuard-Alpha: Detecting and Filtering Memorization-Contaminated Signals in LLM-Based Financial Forecasting via Membership Inference and Cross-Model Disagreement

Method detecting memorization in LLM-based financial forecasting using membership inference and cross-model disagreement.

Ax Gesina Schwalbe, Mert Keser, Moritz Bayerkuhnlein, Edgar Heinert, Annika M\"utze, Marvin Keller, Sparsh Tiwari, Georgii Mikriukov, Diedrich Wolter, Jae Hee Lee, Matthias Rottmann 3/31/2026

Explaining, Verifying, and Aligning Semantic Hierarchies in Vision-Language Model Embeddings

Framework to explain and align semantic hierarchies in CLIP and other vision-language model embeddings.

Ax Huanshuo Dong, Hao Wu, Hong Wang, Qin-Yi Zhang, Zhezheng Hao 3/31/2026

DSO: Dual-Scale Neural Operators for Stable Long-term Fluid Dynamics Forecasting

Neural operators for long-term fluid dynamics forecasting addressing stability and precision in PDE modeling.

Ax Filippo Cenacchi 3/31/2026

Sparse-by-Design Cross-Modality Prediction: L0-Gated Representations for Reliable and Efficient Learning

Unified sparsification framework for cross-modality prediction across graphs, language, and tabular data.

Ax Mitra Nasr Azadani, Syed Usama Imtiaz, Nasrin Alamdari 3/31/2026

PiCSRL: Physics-Informed Contextual Spectral Reinforcement Learning

Physics-informed contextual spectral reinforcement learning method for adaptive sensing in high-dimensional low-sample-size datasets using domain knowledge embeddings.

Ax Mayank Jha 3/31/2026

Throughput Optimization as a Strategic Lever in Large-Scale AI Systems: Evidence from Dataloader and Memory Profiling Innovations

Analysis of throughput optimization as critical strategic lever in large-scale LLM training, synthesizing dataloader and memory profiling innovations to reduce bottlenecks.

Ax Nathaniel Oh, Paul Attie 3/31/2026

Squish and Release: Exposing Hidden Hallucinations by Making Them Surface as Safety Signals

Squish and Release activation-patching technique exposes hidden hallucinations in LLMs that models suppress via safety circuits after identifying false premises.

Ax Andrew Lauziere, Jonathan Daugherty, Taisa Kushner 3/31/2026

A Regression Framework for Understanding Prompt Component Impact on LLM Performance

Statistical regression framework for analyzing impact of specific prompt components on LLM performance, extending XAI methods to understand LLM behavior.

Ax Alberto G. Rodriguez Salgado 3/31/2026

From Pixels to BFS: High Maze Accuracy Does Not Imply Visual Planning

MazeBench evaluates 16 multimodal AI models on visual maze solving, revealing models achieve high accuracy through token-space brute-force search rather than genuine visual planning.

Ax PengYu Chen, Shang Wan, Xiaohou Shi, Yuan Chang, Yan Sun, Sajal K. Das 3/31/2026

VAN-AD: Visual Masked Autoencoder with Normalizing Flow For Time Series Anomaly Detection

Foundation model approach for time series anomaly detection using masked autoencoder and normalizing flow to improve generalization across datasets with limited training data.

Ax Guoxi Zhang, Jiawei Chen, Tianzhuo Yang, Lang Qin, Juntao Dai, Yaodong Yang, Jingwei Yi 3/31/2026

Stable Reasoning, Unstable Responses: Mitigating LLM Deception via Stability Asymmetry

Method detects LLM deception by exposing hidden hallucinations through activation patching, revealing safety circuit suppression of identified errors under conversational pressure.

Ax Chris Hays, Rachel Li, Bailey Flanigan, Manish Raghavan 3/31/2026

Strategic Candidacy in Generative AI Arenas

Analysis of strategic gaming in AI model ranking systems where producers submit multiple variants to artificially inflate rankings from noisy preference data.

Ax Snehaa Reddy, Jayaprakash Katual, Satish Mulleti 3/31/2026

Tunable Domain Adaptation Using Unfolding

Novel domain adaptation methods using unfolding approach to improve model generalization across domains with varying data distributions without separate per-domain training.

Ax Andrea Fraschini, Davide Tenedini, Riccardo Zamboni, Mirco Mutti, Marcello Restelli 3/31/2026

Unsupervised Behavioral Compression: Learning Low-Dimensional Policy Manifolds through State-Occupancy Matching

Method compresses deep reinforcement learning policy parameter space into low-dimensional latent manifold to improve sample efficiency through state-occupancy matching.

Ax Nikolaus Correll 3/31/2026

Liquid Networks with Mixture Density Heads for Efficient Imitation Learning

Liquid neural networks with mixture density heads outperform diffusion policies in imitation learning with half the parameters and 2.4x lower prediction error.

Ax Saunak Kumar Panda, Yisha Xiang, Ruiqi Liu 3/31/2026

Dynamic resource matching in manufacturing using deep reinforcement learning

arXiv: Deep reinforcement learning for dynamic manufacturing resource matching and allocation.

Ax Qiuyang Zhang, Kai Zhou, Ding Tang, Kai Lu, Cheng Li, Zhenyu Yang, Peng Xu, Jiguang Wan 3/31/2026

ScoutAttention: Efficient KV Cache Offloading via Layer-Ahead CPU Pre-computation for LLM Inference

ScoutAttention optimizes LLM inference by pre-computing KV cache on CPU ahead of GPU execution to reduce memory constraints.

Ax Hemanth Saratchandran 3/31/2026

Preconditioned Attention: Enhancing Efficiency in Transformers

Preconditioned attention mechanism addressing ill-conditioning in Transformer attention blocks for efficient training.

Ax Yuebo Luo, Shiyang Li, Yifei Feng, Vishal Kancharla, Shaoyi Huang, Caiwen Ding 3/31/2026

GSR-GNN: Training Acceleration and Memory-Saving Framework of Deep GNNs on Circuit Graph

GSR-GNN framework for efficient training of deep graph neural networks on large circuit graphs with memory optimization.

Ax Huamin Chen, Xunzhuo Liu, Bowei He, Xue Liu 3/31/2026

From Inference Routing to Agent Orchestration: Declarative Policy Compilation with Cross-Layer Verification

Semantic Router DSL for declarative LLM inference routing with content signal analysis, privacy policies, and audit traces.

Ax Wilailuck Treerath, Fabrizio Pittorino 3/31/2026

Active In-Context Learning for Tabular Foundation Models

Active learning approach for tabular foundation models using in-context learning to reduce cold-start labeling costs.

Ax Abdulrahman Albaiz, Fathi Amsaad 3/31/2026

K-Means Based TinyML Anomaly Detection and Distributed Model Reuse via the Distributed Internet of Learning (DIoL)

K-Means anomaly detection for microcontrollers with distributed model-sharing workflow via Distributed Internet of Learning.

Ax Kai Ye, Qingtao Pan, Shuo Li 3/31/2026

Conditional Factuality Controlled LLMs with Generalization Certificates via Conformal Sampling

Conditional Factuality Control framework for LLM hallucination control via conformal sampling with conditional coverage guarantees.

Ax Isaac Llorente-Saguer 3/31/2026

The Geometry of Harmful Intent: Training-Free Anomaly Detection via Angular Deviation in LLM Residual Streams

LatentBiopsy: training-free method detecting harmful prompts by analyzing residual-stream activation geometry in LLMs.