Ax Md Nahid Hasan, Vishwam Tiwari, Aditya Challa, Vaskar Raychoudhury, Snehanshu Saha 4/7/2026

Multi-Agent Training-free Urban Food Delivery System using Resilient UMST Network

SpikeVPR: neuromorphic approach using event-based cameras and spiking neural networks for energy-efficient visual place recognition.

Ax Xinyu Liu, Qing Xu, Zhen Chen 4/7/2026

XAttnRes: Cross-Stage Attention Residuals for Medical Image Segmentation

Cross-Stage Attention Residuals mechanism for medical image segmentation using selective aggregation of encoder-decoder outputs.

Ax Jinwu Yang, Jiaan Wu, Zedong Liu, Xinyang Ma, Hairui Zhao, Yida Gu, Yuanhong Huang, Xingchen Liu, Wenjing Huang, Zheng Wei, Jing Xing, Yili Ma, Qingyi Zhang, Baoyi An, Zhongzhe Hu, Shaoteng Liu, Xia Zhu, Jiaxun Lu, Guangming Tan, Dingwen Tao 4/7/2026

ENEC: A Lossless AI Model Compression Method Enabling Fast Inference on Ascend NPUs

Lossless compression method for LLMs enabling fast inference on Ascend NPUs, addressing weight data transfer bottleneck.

Ax Andrew Salij, R. Seaton Ullberg, Megan C. Davis, Marc J. Cawkwell, Christopher J. Snyder, Cristina Garcia Cardona, Ivana Matanovic, Wilton J. M. Kort-Kamp 4/7/2026

Generative Chemical Language Models for Energetic Materials Discovery

Generative molecular language models pre-trained on chemical data and fine-tuned for energetic materials discovery.

Ax Karthikeyan Sankaralingam 4/7/2026

Computer Architecture's AlphaZero Moment: Automated Discovery in an Encircled World

Proposes automated discovery approach for computer architecture design using AI, addressing post-Moore's Law era challenges.

Ax Ray Zeyao Chen, Christan Grant 4/7/2026

InsightBoard: An Interactive Multi-Metric Visualization and Fairness Analysis Plugin for TensorBoard

TensorBoard plugin for interactive multi-metric visualization and fairness analysis during ML model training.

Ax Damith Chamalke Senadeera, Dimitrios Kollias, Gregory Slabaugh 4/7/2026

CoLoRSMamba: Conditional LoRA-Steered Mamba for Supervised Multimodal Violence Detection

Multimodal violence detection model combining VideoMamba and AudioMamba with conditional LoRA steering.

Ax Kenan Tang, Praveen Arunshankar, Andong Hua, Anthony Yang, Yao Qin 4/7/2026

Banana100: Breaking NR-IQA Metrics by 100 Iterative Image Replications with Nano Banana Pro

Addresses iterative image quality degradation in multi-turn editing with agentic systems using multi-modal models.

Ax Haotian Xiang, Qin Lu, Yaakov Bar-Shalom 4/7/2026

Diffusion Policy with Bayesian Expert Selection for Active Multi-Target Tracking

Diffusion policy approach with Bayesian expert selection for active multi-target tracking balancing exploration and exploitation.

Ax Daniele Solombrino, Antonio Andrea Gargiulo, Adrian Robert Minut, Luca Zhou, Alessandro Zirilli, Emanuele Rodol\`a 4/7/2026

Zero-Shot Quantization via Weight-Space Arithmetic

Zero-shot quantization technique using weight-space arithmetic to transfer quantization robustness between models without training data.

Ax Thomas Manuel Rost 4/7/2026

Inference-Path Optimization via Circuit Duplication in Frozen Visual Transformers for Marine Species Classification

Inference optimization method for frozen vision transformers through circuit duplication for marine species classification.

Ax Lamyea Maha, Tajmilur Rahman, Chanchal Roy 4/7/2026

Agile Story-Point Estimation: Is RAG a Better Way to Go?

Study comparing RAG-based approach with traditional methods for Agile story point estimation in sprint planning.

Ax Prakhar Bansal, Shivangi Agarwal 4/7/2026

Lightweight Query Routing for Adaptive RAG: A Baseline Study on RAGRouter-Bench

Lightweight query routing classifier for selecting optimal retrieval strategies in RAG pipelines based on query characteristics.

Ax Xiaoan Liu, DaeHo Lee, Eric J Gonzalez, Mar Gonzalez-Franco, Ryo Suzuki 4/7/2026

VisionClaw: Always-On AI Agents through Smart Glasses

Wearable AI agent on smart glasses enabling continuous perception and speech-driven task execution with OpenClaw agentic framework.

Ax Sing Hieng Wong, Hassan Sajjad, A. B. Siddique 4/7/2026

LangFIR: Discovering Sparse Language-Specific Features from Monolingual Data for Language Steering

Method using sparse autoencoders to discover language-specific features from monolingual data for controlling LLM output language without parallel data.

Ax Zihao Wu, Haoming Yang, Juncheng Dong, Vahid Tarokh 4/7/2026

Rethinking Token Prediction: Tree-Structured Diffusion Language Model

Discrete diffusion language model using tree-structured token prediction to reduce parameters and memory in language generation.

Ax Yuqi Zhu, Jintian Zhang, Zhenjie Wan, Yujie Luo, Shuofei Qiao, Zhengke Gui, Da Zheng, Lei Liang, Huajun Chen, Ningyu Zhang 4/7/2026

LightThinker++: From Reasoning Compression to Memory Management

Method for LLMs to dynamically compress intermediate reasoning thoughts into compact representations while maintaining reasoning quality.

Ax Ying Yao 4/7/2026

RL-Driven Sustainable Land-Use Allocation for the Lake Malawi Basin

Deep reinforcement learning framework for optimizing land-use allocation in Lake Malawi Basin to maximize ecosystem service value.

Ax Hiroaki Aizawa, Yuki Igaue 4/7/2026

R\'enyi Attention Entropy for Patch Pruning

Method using Rényi attention entropy for patch pruning in transformers to reduce quadratic self-attention cost.

Ax Andrew Wheeler, Kshitiz Aryal, Maanak Gupta 4/7/2026

Explainability-Guided Adversarial Attacks on Transformer-Based Malware Detectors Using Control Flow Graphs

Study on adversarial attacks against transformer-based malware detectors using control flow graphs, examining robustness of RoBERTa models.

Ax Anjun Gao, Feng Wang, Zhenglin Wan, Yueyang Quan, Zhuqing Liu, Minghong Fang 4/7/2026

SecureAFL: Secure Asynchronous Federated Learning

SecureAFL: Asynchronous federated learning framework addressing straggler problem while maintaining security.

Ax Hope McGovern, Caroline Craig, Thomas Lippincott, Hale Sirin 4/7/2026

When Models Know More Than They Say: Probing Analogical Reasoning in LLMs

Study comparing LLM probed representations with performance on narrative analogical reasoning tasks.

Ax Dalal Alharthi, Ivan Roberto Kawaminami Garcia 4/7/2026

Automating Cloud Security and Forensics Through a Secure-by-Design Generative AI Framework

Secure-by-design GenAI framework integrating PromptShield for LLM-based cloud security and forensic analysis.

Ax Fei Wang, Yutong Zhang, Xiong Wang 4/7/2026

Multimodal Structure Learning: Disentangling Shared and Specific Topology via Cross-Modal Graphical Lasso

Cross-Modal Graphical Lasso for learning interpretable multimodal representations by disentangling shared and specific topologies.

Ax Pride Kavumba, Koki Wataoka, Huy H. Nguyen, Jiaxuan Li, Masaya Ohagi 4/7/2026

Predict, Don't React: Value-Based Safety Forecasting for LLM Streaming

Value-based safety forecasting for streaming LLM outputs, improving response moderation on partial generations.

Ax Seok-Jin Kim 4/7/2026

Nearly Optimal Best Arm Identification for Semiparametric Bandits

Fixed-confidence best arm identification in semiparametric bandits with instance-optimal sample complexity bounds.

Ax Sailesh kiran kurra, Shiek Ruksana, Vishal Borusu 4/7/2026

Unmasking Hallucinations: A Causal Graph-Attention Perspective on Factual Reliability in Large Language Models

Causal graph-attention approach to detect and mitigate hallucinations in LLMs for improved factual reliability.

Ax Houzhe Wang, Xiaojie Zhu, Chi Chen 4/7/2026

Jellyfish: Zero-Shot Federated Unlearning Scheme with Knowledge Disentanglement

Jellyfish: Zero-shot federated unlearning scheme using knowledge disentanglement for privacy-preserving federated learning.

Ax Nahyuk Lee, Zhiang Chen, Marc Pollefeys, Sunghwan Hong 4/7/2026

TORA: Topological Representation Alignment for 3D Shape Assembly

TORA: Topology-first framework for 3D shape assembly using flow-matching and pretrained 3D encoders.

Ax Hang Xu, Ling Yue, Chaoqian Ouyang, Yuchen Liu, Libin Zheng, Shaowu Pan, Shimin Di, Min-Ling Zhang 4/7/2026

FactReview: Evidence-Grounded Reviews with Literature Positioning and Execution-Based Claim Verification

FactReview: LLM-based peer review system that grounds claims in evidence from papers, related work, and code to improve ML paper reviewing.

Ax Yuanhao Liu, Zihan Zhou, Kaiying Wu, Shuo Liu, Yiyang Huang, Jiajun Guo, Aimin Zhou, Hong Qian 4/7/2026

Embedding Enhancement via Fine-Tuned Language Models for Learner-Item Cognitive Modeling

Fine-tuned language models enhance embeddings for cognitive diagnosis in online education systems by incorporating semantic representations.

Ax Arunkumar Rathinam, Jules Lecomte, Jost Reelsen, Gregor Lenz, Axel von Arnim, Djamila Aouada 4/7/2026

Efficient Onboard Spacecraft Pose Estimation with Event Cameras and Neuromorphic Hardware

Event camera and neuromorphic hardware approach for efficient spacecraft pose estimation during autonomous rendezvous operations in space.

Ax Gunn Kim 4/7/2026

Non-Equilibrium Stochastic Dynamics as a Unified Framework for Insight and Repetitive Learning: A Kramers Escape Approach to Continual Learning

Framework using non-equilibrium stochastic dynamics to address stability-plasticity dilemma in continual learning via Kramers escape theory.

Ax Adrienne Deganutti, Elad Hirsch, Haonan Zhu, Jaejung Seol, Purvanshi Mehta 4/7/2026

Graphic-Design-Bench: A Comprehensive Benchmark for Evaluating AI on Graphic Design Tasks

First comprehensive benchmark for evaluating AI models on professional graphic design tasks including layout, typography, and design intent translation.

Ax Mir Tafseer Nayeem, Davood Rafiei 4/7/2026

Which English Do LLMs Prefer? Triangulating Structural Bias Towards American English in Foundation Models

Study analyzing bias toward American English in LLMs through postcolonial lens, examining how data curation and geopolitical histories shape model development.

Ax Soham Bonnerjee, Zhipeng Lou, Wei Biao Wu 4/7/2026

Sharp asymptotic theory for Q-learning with LDTZ learning rate and its generalization

Asymptotic convergence analysis of Q-learning with linear decay to zero learning rates addressing persistent bias and slow convergence issues.

Ax Oluseyi Olukola, Nick Rahimi 4/7/2026

Pedagogical Safety in Educational Reinforcement Learning: Formalizing and Detecting Reward Hacking in AI Tutoring Systems

Formal framework and metrics for pedagogical safety in educational reinforcement learning, introducing Reward Hacking Severity Index to detect misalignment.

Ax Hanchen Li, Runyuan He, Qizheng Zhang, Changxiu Ji, Qiuyang Mang, Xiaokun Chen, Lakshya A Agrawal, Wei-Liang Liao, Eric Yang, Alvin Cheung, James Zou, Kunle Olukotun, Ion Stoica, Joseph E. Gonzalez 4/7/2026

Combee: Scaling Prompt Learning for Self-Improving Language Model Agents

Combee framework for scaling prompt learning in LLM agents enabling efficient self-improvement through system prompt optimization across parallel runs.

Ax Oluseyi Olukola, Nick Rahimi 4/7/2026

MC-CPO: Mastery-Conditioned Constrained Policy Optimization

MC-CPO method for constrained reinforcement learning in tutoring systems preventing reward hacking through mastery-conditioned safety constraints.

Ax Anushree Sinha, Srivaths Ranganathan, Debanshu Das, Abhishek Dharmaratnakar 4/7/2026

Beyond Fluency: Toward Reliable Trajectories in Agentic IR

Position paper analyzing failure modes in agentic IR systems where early errors cascade despite linguistic fluency, causing misalignment between reasoning and execution.

Ax Ioannis Panitsas, Leandros Tassiulas 4/7/2026

A Family of Open Time-Series Foundation Models for the Radio Access Network

Open foundation models for Radio Access Network time-series forecasting enabling AI-native optimization and closed-loop control with improved generalization.

Ax Yash Ganpat Sawant 4/7/2026

High-Stakes Personalization: Rethinking LLM Customization for Individual Investor Decision-Making

System and analysis of personalized LLM customization for individual investor decision-making, identifying fundamental limitations in current personalization paradigms.

Ax Saad Alqithami 4/7/2026

Soft Tournament Equilibrium

Soft Tournament Equilibrium framework for evaluating LLM-based agents in non-transitive competitive settings using set-valued rankings instead of linear orderings.

Ax Saurav Jha, Maryam Hashemzadeh, Ali Saheb Pasand, Ali Parviz, Min-Joong Lee, Boris Knyazev 4/7/2026

REAM: Merging Improves Pruning of Experts in LLMs

REAM method for pruning mixture-of-experts in large language models by merging experts, addressing memory challenges in deployment of billion-parameter models.

Ax Emerson Lopes Machadoa, Cristiano Jacques Miosso, Ricardo Pezzuol Jacobi 4/7/2026

Integer-Only Operations on Extreme Learning Machine Test Time Classification

Theoretical analysis of integer-only operations for extreme learning machine classifiers to reduce computational cost at test time without accuracy loss.

Ax Maohao Shen, Kaiwen Zha, Zexue He, Zhang-Wei Hong, Siru Ouyang, J. Jon Ryu, Prasanna Sattigeri, Suhas Diggavi, Gregory Wornell 4/7/2026

Decocted Experience Improves Test-Time Inference in LLM Agents

Proposes methods to improve LLM agent performance at test-time without parameter updates by optimizing inference-time computation for complex reasoning tasks.

Ax Gregory N. Frank 4/7/2026

How Alignment Routes: Localizing, Scaling, and Controlling Policy Circuits in Language Models

Identifies sparse routing mechanisms in alignment-trained LLMs using gate and amplifier heads to control refusal behavior, validated across 9 models from 6 labs.

Ax Zhimin Zhao 4/7/2026

Gradual Cognitive Externalization: From Modeling Cognition to Constituting It

Framework analyzing how ambient AI systems through causal user coupling transition from modeling to constituting part of cognitive function.

Ax Poornima Kumaresan, Shwetha Singaravelu, Lakshmi Rajendran, Santhosh Sivasubramani 4/7/2026

Eliminating Vendor Lock-In in Quantum Machine Learning via Framework-Agnostic Neural Networks

Research on framework-agnostic quantum machine learning neural networks to reduce vendor lock-in across QML platforms.

Ax Yiyao Zhang, Diksha Goel, Hussain Ahmad 4/7/2026

Explainable Autonomous Cyber Defense using Adversarial Multi-Agent Reinforcement Learning

Research on autonomous agents using multi-agent reinforcement learning for explainable cyber defense against APT techniques.