Ax Ruoxi Shang, Dan Marshall, Edward Cutrell, Denae Ford 3/31/2026

Mimetic Alignment with ASPECT: Evaluation of AI-inferred Personal Profiles

ASPECT: Pipeline using LLMs to assess personal communication traits for AI agents mimicking individual communication styles without per-person fine-tuning.

Ax Emilie Panek, Alexander Roman, Gaurav Shukla, Leonardo Pagliaro, Katia Matcheva, Konstantin Matchev 3/31/2026

ASTER -- Agentic Science Toolkit for Exoplanet Research

ASTER: AI agents toolkit automating exoplanet atmospheric analysis by combining archival queries, literature search, and Bayesian retrieval frameworks.

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

Online Statistical Inference of Constant Sample-averaged Q-Learning

Statistical online inference framework for sample-averaged Q-learning to reduce variance and instability in reinforcement learning algorithms.

Ax Shaoliang Yang, Jun Wang, Yunsheng Wang 3/31/2026

AutoSiMP: Autonomous Topology Optimization from Natural Language via LLM-Driven Problem Configuration and Adaptive Solver Control

LLM-driven autonomous pipeline (AutoSiMP) that converts natural language structural problem descriptions into topology optimization solutions without manual configuration.

Ax Mohamad Zbib, Mohamad Bazzi, Ammar Mohanna, Hasan Abed Al Kader Hammoud, Bernard Ghanem 3/31/2026

TAPS: Task Aware Proposal Distributions for Speculative Sampling

Task-aware proposal distributions improve speculative decoding speed by training draft models on task-specific corpora like MathInstruct.

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

Unsupervised policy compression for deep reinforcement learning using low-dimensional latent manifolds to improve sample efficiency.

Ax Jianhua Yang, Kerem \"Oge, Adrian von M\"uhlenen, Abdullah Bilal Akbulut, Tanya Suzanne Carey, Chidi Okorro 3/31/2026

Multi-Level Barriers to Generative AI Adoption Across Disciplines and Professional Roles in Higher Education

Multi-method survey of 272 higher education professionals examining structural barriers to generative AI adoption across disciplines and roles.

Ax Mao Li, Frederick G. Conrad 3/31/2026

Persona-Based Simulation of Human Opinion at Population Scale

Framework using LLMs to simulate consistent human opinions and decision-making across contexts at population scale.

Ax Hossein Salemi, Jitin Krishnan, Hemant Purohit 3/31/2026

Debiasing Large Language Models toward Social Factors in Online Behavior Analytics through Prompt Knowledge Tuning

Method for debiasing LLMs using prompt knowledge tuning to correct social attribution biases in online behavior analytics.

Ax Jovana Kondic, Pengyuan Li, Dhiraj Joshi, Isaac Sanchez, Ben Wiesel, Shafiq Abedin, Amit Alfassy, Eli Schwartz, Daniel Caraballo, Yagmur Gizem Cinar, Florian Scheidegger, Steven I. Ross, Daniel Karl I. Weidele, Hang Hua, Ekaterina Arutyunova, Roei Herzig, Zexue He, Zihan Wang, Xinyue Yu, Yunfei Zhao, Sicong Jiang, Minghao Liu, Qunshu Lin, Peter Staar, Luis Lastras, Aude Oliva, Rogerio Feris 3/31/2026

ChartNet: A Million-Scale, High-Quality Multimodal Dataset for Robust Chart Understanding

ChartNet: 1.5 million multimodal dataset with code-guided synthesis for improving vision-language model chart understanding and reasoning.

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

Dynamic resource matching in manufacturing using deep reinforcement learning

Deep reinforcement learning system for dynamic resource matching and capacity sharing in manufacturing industries.

Ax Neelam Modi Jain, Dan J. Wang 3/31/2026

Voice-based debate with an AI adversary is associated with increased divergent ideation

Study shows voice-based debate with AI increases divergent ideation compared to text-based interaction, examining communication modality effects.

Ax Praneel Panchigar, Torlach Rush, Matthew Canabarro 3/31/2026

Sovereign Context Protocol: An Open Attribution Layer for Human-Generated Content in the Age of Large Language Models

Open protocol for attributing human-generated content used by LLMs during training and inference, addressing creator attribution in AI value chains.

Ax Hongzhuo Chen, Zhanliang Wang, Quan M. Nguyen, Gongbo Zhang, Chunhua Weng, Kai Wang 3/31/2026

Autonomous Agent-Orchestrated Digital Twins (AADT): Leveraging the OpenClaw Framework for State Synchronization in Rare Genetic Disorders

Framework for autonomous agent-orchestrated digital twins in rare genetic disorders using OpenClaw for real-time state synchronization of clinical and genomic data.

Ax Aditya Dhodapkar, Farhaan Pishori 3/31/2026

SafetyDrift: Predicting When AI Agents Cross the Line Before They Actually Do

Method for predicting when LLM agent action sequences will violate safety constraints before execution, modeling trajectories as absorbing Markov chains.

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

Training acceleration framework for deep Graph Neural Networks on circuit graphs using grouped sparse reversible architectures to reduce GPU memory and compute.

Ax Jinhu Fu, Yihang Lou, Qingyi Si, Shudong Zhang, Yan Bai, Sen Su 3/31/2026

Diagnosing and Repairing Unsafe Channels in Vision-Language Models via Causal Discovery and Dual-Modal Safety Subspace Projection

Framework for identifying and repairing unsafe behavior channels in vision-language models through causal mediation analysis and dual-modal safety projection.

Ax Antheas Kapenekakis, Bent Thomsen, Katja Hose, Michele Albano 3/31/2026

Amalgam: Hybrid LLM-PGM Synthesis Algorithm for Accuracy and Realism

Hybrid synthesis algorithm combining Probabilistic Graphical Models and LLMs to generate synthetic datasets with both realistic complexity and accurate statistical properties.

Ax Martin Vogel, Falk Meyer-Eschenbach, Severin Kohler, Elias Gr\"unewald, Felix Balzer 3/31/2026

Codebase-Memory: Tree-Sitter-Based Knowledge Graphs for LLM Code Exploration via MCP

Open-source system using Tree-Sitter and Model Context Protocol to build knowledge graphs for LLM coding agents, enabling efficient codebase exploration across 66 languages without repeated token consumption.

Ax Chitralekha Gupta, Jing Peng, Ashwin Ram, Shreyas Sridhar, Christophe Jouffrais, Suranga Nanayakkara 3/31/2026

Beyond Descriptions: A Generative Scene2Audio Framework for Blind and Low-Vision Users to Experience Vista Landscapes

Scene2Audio generative framework producing nonverbal audio representations of landscapes for blind and low-vision users via psychoacoustics principles.

Ax Stoyan Nikolov, Bernhard Konrad, Moritz Gronbach, Niket Kumar, Ann Yan, Varun Singh, Yaning Liang, Parthasarathy Ranganathan 3/31/2026

A Multi-agent AI System for Deep Learning Model Migration from TensorFlow to JAX

Multi-agent AI system automating deep learning model migration from TensorFlow to JAX, replacing manual expert work with LLM-based agents.

Ax Alejandro Carrasco, Mariko Storey-Matsutani, Victor Rodriguez-Fernandez, Richard Linares 3/31/2026

GUIDE: Guided Updates for In-context Decision Evolution in LLM-Driven Spacecraft Operations

GUIDE: non-parametric policy improvement framework enabling LLM agents to adapt spacecraft operations via evolving natural-language decision rules.

Ax Jia Li, Zeyang Zhuang, Zhuangbin Chen, Yuxin Su, Wei Meng, Michael R. Lyu 3/31/2026

ComBench: A Repo-level Real-world Benchmark for Compilation Error Repair

ComBench: repository-level benchmark for evaluating Automated Compilation Error Repair techniques on real-world source code.

Ax Yu Zhang, Karl Mason 3/31/2026

D-SPEAR: Dual-Stream Prioritized Experience Adaptive Replay for Stable Reinforcement Learninging Robotic Manipulation

D-SPEAR: dual-stream prioritized experience replay method for stable off-policy RL in contact-rich robotic manipulation tasks.

Ax Maziar Kianimoghadam Jouneghani 3/31/2026

Culturally Adaptive Explainable LLM Assessment for Multilingual Information Disorder: A Human-in-the-Loop Approach

Human-in-the-loop approach for culturally-adaptive LLM assessment of multilingual information disorder with explainability focus.

Ax Naveen Mysore 3/31/2026

Diagnosing Non-Markovian Observations in Reinforcement Learning via Prediction-Based Violation Scoring

Prediction-based scoring method to diagnose non-Markovian observation violations in RL, separating this source of suboptimality from other performance issues.

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

Conditional Factuality Controlled LLMs with Generalization Certificates via Conformal Sampling

Conditional Factuality Control (CFC): post-hoc conformal framework for test-time hallucination control in LLMs 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

Training-free method (LatentBiopsy) for detecting harmful prompts in LLMs by analyzing geometric patterns in residual stream activations.

Ax Nimesh Khandelwal, Shakti S. Gupta 3/31/2026

Agent-Driven Autonomous Reinforcement Learning Research: Iterative Policy Improvement for Quadruped Locomotion

Case study of agent-driven autonomous RL research where an AI agent executes quadruped locomotion tasks under human direction, handling diagnosis, configuration editing, and monitoring.

Ax Guilin Zhang, Wulan Guo, Ziqi Tan, Hailong Jiang 3/31/2026

CarbonEdge: Carbon-Aware Deep Learning Inference Framework for Sustainable Edge Computing

CarbonEdge framework for carbon-aware deep learning inference on edge devices. Extends model partitioning with environmental impact optimization.

Ax Xinran Zhao, Aakanksha Naik, Jay DeYoung, Joseph Chee Chang, Jena D. Hwang, Tongshuang Wu, Varsha Kishore 3/31/2026

Improving Attributed Long-form Question Answering with Intent Awareness

Enhances LLM long-form question answering with intent awareness to improve report generation quality. Intent-guided knowledge synthesis method.

Ax Giorgio Giannone, Anna Clare Doris, Amin Heyrani Nobari, Kai Xu, Akash Srivastava, Faez Ahmed 3/31/2026

GIFT: Bootstrapping Image-to-CAD Program Synthesis via Geometric Feedback

GIFT framework bootstraps image-to-CAD program synthesis via geometric feedback. Uses LLM reasoning with visual geometry alignment for design automation.

Ax Jakub B\k{a}ba, Jaros{\l}aw A. Chudziak 3/31/2026

Multi-Agent Dialectical Refinement for Enhanced Argument Classification

Multi-agent dialectical refinement framework for argument classification using LLMs. Multi-agent system for improved structural reasoning without fine-tuning.

Ax Zhongying Deng, Cheng Tang, Ziyan Huang, Jiashi Lin, Ying Chen, Junzhi Ning, Chenglong Ma, Jiyao Liu, Wei Li, Yinghao Zhu, Shujian Gao, Yanyan Huang, Sibo Ju, Yanzhou Su, Pengcheng Chen, Wenhao Tang, Tianbin Li, Haoyu Wang, Yuanfeng Ji, Hui Sun, Shaobo Min, Liang Peng, Feilong Tang, Haochen Xue, Rulin Zhou, Chaoyang Zhang, Wenjie Li, Shaohao Rui, Weijie Ma, Xingyue Zhao, Yibin Wang, Kun Yuan, Zhaohui Lu, Shujun Wang, Jinjie Wei, Lihao Liu, Dingkang Yang, Lin Wang, Yulong Li, Haolin Yang, Yiqing Shen, Lequan Yu, Xiaowei Hu, Yun Gu, Yicheng Wu, Benyou Wang, Minghui Zhang, Angelica I. Aviles-Rivero, Qi Gao, Hongming Shan, Xiaoyu Ren, Fang Yan, Hongyu Zhou, Haodong Duan, Maosong Cao, Shanshan Wang, Bin Fu, Xiaomeng Li, Zhi Hou, Chunfeng Song, Lei Bai, Yuan Cheng, Yuandong Pu, Xiang Li, Wenhai Wang, Hao Chen, Jiaxin Zhuang, Songyang Zhang, Huiguang He, Mengzhang Li, Bohan Zhuang, Zhian Bai, Rongshan Yu, Liansheng Wang, Yukun Zhou, Xiaosong Wang, Xin Guo, Guanbin Li, Xiangru Lin, Dakai Jin, Mianxin Liu, Wenlong Zhang, Qi Qin, Conghui He, Yuqiang Li, Ye Luo, Nanqing Dong, Jie Xu, Wenqi Shao, Bo Zhang, Qiujuan Yan, Yihao Liu, Jun Ma, Zhi Lu, Yuewen Cao, Zongwei Zhou, Jianming Liang, Shixiang Tang, Qi Duan, Dongzhan Zhou, Chen Jiang, Yuyin Zhou, Yanwu Xu, Jiancheng Yang, Shaoting Zhang, Xiaohong Liu, Siqi Luo, Yi Xin, Chaoyu Liu, Haochen Wen, Xin Chen, Alejandro Lozano, Min Woo Sun, Yuhui Zhang, Yue Yao, Xiaoxiao Sun, Serena Yeung-Levy, Xia Li, Jing Ke, Chunhui Zhang, Zongyuan Ge, Ming Hu, Jin Ye, Zhifeng Li, Yirong Chen, Yu Qiao, Junjun He 3/31/2026

Project Imaging-X: A Survey of 1000+ Open-Access Medical Imaging Datasets for Foundation Model Development

Survey of 1000+ open-access medical imaging datasets for foundation model development. Dataset curation resource for medical AI.

Ax Dipkumar Patel 3/31/2026

TurboAngle: Near-Lossless KV Cache Compression via Uniform Angle Quantization

TurboAngle: Near-lossless KV cache compression via uniform angle quantization with per-layer precision allocation. Optimizes inference for 1B-7B parameter models.

Ax Suraj Ranganath, Vaishak Menon, Anish Patnaik 3/31/2026

KV Cache Quantization for Self-Forcing Video Generation: A 33-Method Empirical Study

Empirical study of 33 KV cache quantization methods for self-forcing video generation. Systems optimization for memory-efficient long-horizon generation.

Ax Chongyang Zhao, Mingsong Li, Haodong Lu, Dong Gong 3/31/2026

On Token's Dilemma: Dynamic MoE with Drift-Aware Token Assignment for Continual Learning of Large Vision Language Models

Mixture of Experts architecture with drift-aware token assignment for continual learning in large vision language models. Addresses catastrophic forgetting.

Ax Feiding, Yongkang Zhang, Yuhao Liao, Zijian Zeng, Chunzheng Zhu, Yaozong Zheng, Yafei Liu, Yeling Peng, Youwei Wang, Sibo Wang, Huiming Yang, Linglin Liao, Shunzhi Yang 3/31/2026

Difference Feedback: Generating Multimodal Process-Level Supervision for VLM Reinforcement Learning

Differential Feedback method for process-level supervision in VLM reinforcement learning. Improves credit assignment in multi-step visual reasoning tasks.

Ax Zhaopeng Feng, Liangcai Su, Zhen Zhang, Xinyu Wang, Xiaotian Zhang, Xiaobin Wang, Runnan Fang, Qi Zhang, Baixuan Li, Shihao Cai, Rui Ye, Hui Chen, Jiang Yong, Joey Tianyi Zhou, Chenxiong Qian, Pengjun Xie, Bryan Hooi, Zuozhu Liu, Jingren Zhou 3/31/2026

AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web Agents

Adaptive parallel context management routing for long-horizon LLM web agents. Addresses context capacity bottleneck with dynamic strategy selection during navigation.

Ax Yizhe Li (University of Birmingham, Birmingham, United Kingdom), Shixiao Wang (University of Birmingham, Birmingham, United Kingdom), Jian K. Liu (University of Birmingham, Birmingham, United Kingdom) 3/31/2026

Copilot-Assisted Second-Thought Framework for Brain-to-Robot Hand Motion Decoding

Transformer-based CNN-attention hybrid model for motor kinematics prediction from EEG data. Brain-computer interface research with limited AI/ML dev tool focus.

Ax Xuanpu Zhao, Zhentao Tan, Dianmo Sheng, Tianxiang Chen, Yao Liu, Yue Wu, Tao Gong, Qi Chu, Nenghai Yu 3/31/2026

Learning to Focus and Precise Cropping: A Reinforcement Learning Framework with Information Gaps and Grounding Loss for MLLMs

Reinforcement learning framework for multimodal LLM agents to learn autonomous image cropping for visual question answering. Agent-based workflow enhancement.

Ax Surada Suwansathit, Yuxuan Zhang, Guofei Gu 3/31/2026

A Systematic Taxonomy of Security Vulnerabilities in the OpenClaw AI Agent Framework

Systematic taxonomy of 190 security vulnerabilities in OpenClaw open-source AI agent framework. Security analysis of LLM agent runtime systems.

Ax K M Ferdous, Dipayan Banik, Kowshik Chowdhury, Shazibul Islam Shamim 3/31/2026

Safer Builders, Risky Maintainers: A Comparative Study of Breaking Changes in Human vs Agentic PRs

Comparative study of breaking changes in pull requests authored by AI coding agents vs humans. Empirical analysis of agentic software engineering systems and code quality.

Ax Phat Nguyen, Thang Pham 3/31/2026

Toward Reliable Evaluation of LLM-Based Financial Multi-Agent Systems: Taxonomy, Coordination Primacy, and Cost Awareness

Survey of LLM-based multi-agent systems for financial trading. Introduces taxonomy covering architecture, coordination, memory, and tool integration across 12 systems.

Ax A. Baki Kocaballi, Joseph Kizana, Sharon Stein, Simon Buckingham Shum 3/31/2026

Drag or Traction: Understanding How Designers Appropriate Friction in AI Ideation Outputs

Design approach introducing intentional friction in AI-generated output to encourage human contribution over passive consumption.

Ax Hayeon Jeon, Dakyeom Ahn, Sunyu Pang, Yunseo Choi, Suhwoo Yoon, Joonhwan Lee, Eun-mee Kim, Hajin Lim 3/31/2026

InnerPond: Fostering Inter-Self Dialogue with a Multi-Agent Approach for Introspection

Multi-agent system implementing dialogical self theory for introspection through inter-self dialogue between internal perspectives.

Ax Junho Kim, Hosu Lee, James M. Rehg, Minsu Kim, Yong Man Ro 3/31/2026

STRIDE: When to Speak Meets Sequence Denoising for Streaming Video Understanding

Streaming video understanding system for Video-LLMs combining temporal perception with decision timing for online deployment.

Ax Songchen Ma, Hongyi Li, Weihao Zhang, Yonghao Tan, Pingcheng Dong, Yu Liu, Lan Liu, Yuzhong Jiao, Xuejiao Liu, Luhong Liang, Kwang-Ting Cheng 3/31/2026

Expert Streaming: Accelerating Low-Batch MoE Inference via Multi-chiplet Architecture and Dynamic Expert Trajectory Scheduling

Hardware-software optimization for Mixture-of-Experts inference on edge devices using multi-chiplet architecture and dynamic scheduling.

Ax Rodney Jehu-Appiah 3/31/2026

Umwelt Engineering: Designing the Cognitive Worlds of Linguistic Agents

Framework exploring how linguistic cognitive environment design affects LLM reasoning through vocabulary constraints and medium alterations.

Ax Xinyuan Xie, Shunian Chen, Zhiheng Liu, Yuhao Zhang, Zhiqiang Lv, Liyin Liang, Benyou Wang 3/31/2026

EvA: An Evidence-First Audio Understanding Paradigm for LALMs

Evidence-first paradigm for large audio language models addressing acoustic perception bottleneck in complex scenes.