Ax Muyang Li, Yucheng Liu, Jianbo Ma, Elliot Osborne, Bo Han, Tongliang Liu 5/5/2026

Rethinking Model Selection in VLM Through the Lens of Gromov-Wasserstein Distance

Systematic investigation of vision encoder-LLM alignment in Vision-Language Models using Gromov-Wasserstein distance for principled model selection.

Ax Lei Gao, Zhuoming Li, Mengxi Jia, Jiakang Yuan, Hongbo Sun, Hao Sun, Xuelong Li 5/5/2026

Segment-Aligned Policy Optimization for Multi-Modal Reasoning

Segment-Aligned Policy Optimization (SAPO) for LLM reinforcement learning that aligns credit assignment with reasoning step structure in multi-modal tasks.

Ax Anjie Liu, Ziqin Gong, Yan Song, Yuxiang Chen, Xiaolong Liu, Hengtong Lu, Kaike Zhang, Chen Wei 5/5/2026

Active Reasoning Vision-Language Models via Sequential Experimental Design

Vision-language models with active reasoning via sequential Bayesian decision-making. VLM improvement through adaptive visual perception.

Ax Jianze Wang, Ying Liu, Jinlong Chen, Xuchun Hu, Qilong Zhang, Yu Cao, Jun Wang, Hua Yang, Yong Xie, Qianglong Chen 5/5/2026

MAD-OPD: Breaking the Ceiling in On-Policy Distillation via Multi-Agent Debate

Multi-agent debate for on-policy distillation in agentic tasks. Teacher-student learning framework with agent trajectory optimization.

Ax Burin Naowarat, Hao Tang, Sharon Goldwater 5/5/2026

A framework for analyzing concept representations in neural models

Framework for analyzing concept representations in neural networks via linear subspaces. Interpretability research applicable to model understanding.

Ax Yao Du, Shanshan Li, Xiaomeng Li 5/5/2026

Injecting Distributional Awareness into MLLMs via Reinforcement Learning for Deep Imbalanced Regression

Using RL to improve MLLMs on imbalanced regression tasks via distributional awareness. LLM training methodology addressing long-tailed distributions.

Ax Shuaipeng Zhou, Yu Zhang 5/5/2026

SCALE-LoRA: Auditing Post-Retrieval LoRA Composition with Residual Merging and View Reliability

Framework for composing and auditing LoRA adapters from open pools for tasks. Parameter-efficient fine-tuning and model composition.

Ax Mehmet Iscan 5/5/2026

Feedback-Normalized Developer Memory for Reinforcement-Learning Coding Agents: A Safety-Gated MCP Architecture

LLM coding agents with persistent memory, RAG, and RL feedback for software engineering. Architecture for agent memory and tool use.

Ax Tingting Dan, Guorong Wu 5/5/2026

From Cortical Synchronous Rhythm to Brain Inspired Learning Mechanism: An Oscillatory Spiking Neural Network with Time-Delayed Coordination

Brain-inspired spiking neural network with time-delayed coordination for learning. Neuroscience-focused theoretical work on oscillatory dynamics.

Ax Xihang Shan, Da Zhou 5/5/2026

PRCD-MAP: Learning How Much to Trust Imperfect Priors in Causal Discovery

Causal discovery method with per-edge trust scores for heterogeneously reliable external priors from diverse sources.

Ax Qiao Liu 5/5/2026

Missingness-aware Data Imputation via AI-powered Bayesian Generative Modeling

Bayesian generative modeling framework for missing data imputation with uncertainty quantification.

Ax Samhita Kuili, Mohammadreza Amini, Burak Kantarci 5/5/2026

Toward Resilient 5G Networks: Comparative Analysis of Federated and Centralized Learning for RF Jamming Detection

Federated learning approach for RF jamming detection in 5G networks preserving privacy vs. centralized learning.

Ax Yipin Guo, Siddharth Joshi 5/5/2026

SplitZip: Ultra Fast Lossless KV Compression for Disaggregated LLM Serving

Lossless KV cache compression technique for efficient disaggregated LLM serving with reduced transfer bottleneck.

Ax Kwan Soo Shin 5/5/2026

The Compliance Gap: Why AI Systems Promise to Follow Process Instructions but Don't

Analysis of compliance gap in AI agents: verbal agreement vs. actual behavior divergence in following explicit instructions.

Ax Zhilong Zhang, Wenyu Luo, Haonan Wang, Yifei Sheng, Yidi Wang, Hanyuan Guo, Haoxiang Ren, Xinghao Du, Yuhan Che, Tongtong Cao, Lei Yuan, Yang Yu 5/5/2026

Anticipation-VLA: Solving Long-Horizon Embodied Tasks via Anticipation-based Subgoal Generation

Vision-Language-Action model with anticipation-based subgoal generation for long-horizon embodied robotic tasks.

Ax Ashik Abrar Naeem, Mohammad Ariful Haque 5/5/2026

Zero-Shot, Safe and Time-Efficient UAV Navigation via Potential-Based Reward Shaping, Control Lyapunov and Barrier Functions

RL-based UAV navigation combining control Lyapunov functions and barrier functions for safe autonomous flight.

Ax Haohan Yu, Jinmiao Cong, Shengzhi Wang, Lu Wang, Chanjuan Liu 5/5/2026

MAGIC: Multi-Step Advantage-Gated Causal Influence for Multi-agent Reinforcement Learning

Multi-agent reinforcement learning framework using multi-step causal influence extraction for improved agent coordination.

Ax Szymon Kobus, Deniz G\"und\"uz 5/5/2026

Remote Action Generation: Remote Control with Minimal Communication

Communication-efficient multi-agent control framework for remote action generation with bandwidth constraints.

Ax Hongkun Pan, Yuwei Wu, Wanyi Hong, Shenghui Hu, Qitong Yan, Yi Yang, Rufei Han, Changju Zhou, Minfeng Zhu, Dongming Han, Wei Chen 5/5/2026

Chart-FR1: Visual Focus-Driven Fine-Grained Reasoning on Dense Charts

Multimodal LLM approach for understanding dense charts with fine-grained visual reasoning and focus-driven mechanisms.

Ax Sebastian Engelke, Nicola Gnecco, Anne Sabourin 5/5/2026

Extrapolation in Statistical Learning with Extreme Value Theory

Extreme value theory applied to machine learning for extrapolation, regression, and anomaly detection in data-sparse regimes.

Ax Shengzhe Lyu, Yuhan She, Patrick S. Y. Hung, Ray C. C. Cheung, Weitao Xu 5/5/2026

ViM-Q: Scalable Algorithm-Hardware Co-Design for Vision Mamba Model Inference on FPGA

Hardware-software co-design for Vision Mamba inference on FPGA with quantization optimization.

Ax Luo Ji, Qi Qin, Ningyuan Xi, Teng Chen, Qingqing Gu, Hongyan Li 5/5/2026

Learn-to-learn on Arbitrary Textual Conditioning: A Hypernetwork-Driven Meta-Gated LLM

Meta-learning framework for LLMs using hypernetworks and adaptive gating. LLM architecture innovation.

Ax Vishnu Teja Kunde, Jean-Francois Chamberland, Krishna R. Narayanan, Jamison Ebert 5/5/2026

Real-Time Text Transmission via LLM-Based Entropy Coding over Fixed-Rate Channels

LLM-based entropy coding for text transmission over fixed-rate channels. Combines compression with neural networks.

Ax Christopher Kelly, Angelica Chowdhury, Alexandra Campili, Bimpe Ayoola, Devin Barbour, Thomas Chen Dawson, Ze Shen Chin, Rokas Gipi\v{s}kis 5/5/2026

Principles and Guidelines for Randomized Controlled Trials in AI Evaluation

Framework for standardizing randomized controlled trials in AI evaluation. Establishes RCT best practices.

Ax Vik Pant, Eric Yu 5/5/2026

Coopetition-Gym v1: A Formally Grounded Platform for Mixed-Motive Multi-Agent Reinforcement Learning under Strategic Coopetition

Benchmark platform for multi-agent reinforcement learning with mixed cooperation/competition. Open research environment.

Ax \.Ibrahim R{\i}za Halla\c{c}, Hasan O\u{g}ul 5/5/2026

Pair2Score: Pairwise-to-Absolute Transfer for LLM-Based Essay Scoring

LLM-based framework for essay scoring using pairwise comparison transfer learning. LLaMA fine-tuning application.

Ax Zhuoyang Lyu, Yiyang Zhang, Tongxin Wang, Ruirui Lan 5/5/2026

Ultrasound Vision-Language Alignment via Contrastive Learning

Vision-language alignment method for ultrasound images using contrastive learning. Medical imaging foundation model.

Ax Sichao Xiong, Sadok Jerad, Coralia Cartis 5/5/2026

A Parameter-Free First-Order Algorithm for Non-Convex Optimization with $\tilde{\mkern1mu O}(\epsilon^{-5/3})$ Global Rate

Parameter-free optimization algorithm achieving O(ε^-5/3) complexity for non-convex functions. Theoretical ML research.

Ax Wenyi Wu, Sibo Zhu, Kun Zhou, Biwei Huang 5/5/2026

Planner Matters! An Efficient and Unbalanced Multi-agent Collaboration Framework for Long-horizon Planning

Multi-agent LLM framework with planner, actor, and memory manager roles for long-horizon planning and complex task automation.

Ax Peggy Joy Lu, Wei-Yu Chen, Yao-Tsung Huang, Vincent Shin-Mu Tseng 5/5/2026

Heterogeneous Model Fusion for Privacy-Aware Multi-Camera Surveillance via Synthetic Domain Adaptation

Multi-agent framework with planner, actor, and memory manager roles for long-horizon LLM-based task automation.

Ax Nawar Turk, Lucas Miquet-Westphal, Leila Kosseim 5/5/2026

CLaC at SemEval-2026 Task 6: Response Clarity Detection in Political Discourse

Privacy-preserving multi-camera object detection framework using diffusion-based domain adaptation.

Ax Jianing Zhang, Zijian Zhou, Kai Sun 5/5/2026

RAFNet: Region-Aware Fusion Network for Pansharpening

Information-theoretic analysis of Pearl's causal hierarchy quantifying description complexity across causal inference levels.

Ax Abdullah Ahmad Khan, Hamid Laga, Ferdous Sohel 5/5/2026

Metric Unreliability in Multimodal Machine Unlearning: A Systematic Analysis and Principled Unified Score

AI-generated examples of graph dominating sets using transformer-based reinforcement learning tool PatternBoost.

Ax Dineth Jayakody, Pasindu Thenahandi, Chameli Dommanige 5/5/2026

MultiSense-Pneumo: A Multimodal Learning Framework for Pneumonia Screening in Resource-Constrained Settings

Systematic study of metric reliability in Vision-Language Model unlearning for GDPR compliance.

Ax Alexander Smola 5/5/2026

Submodular Benchmark Selection

Multimodal ML framework for pneumonia screening combining symptoms, respiratory patterns, and imaging.

Ax Pawel Kaplanski (Kaplanski AI Lab) 5/5/2026

Perturbation Dose Responses in Recursive LLM Loops: Raw Switching, Stochastic Floors, and Persistent Escape under Append, Replace, and Dialog Updates

Study of perturbation effects in recursive LLM loops examining context-update rules (append, replace, dialog) and persistence of redirected behavior.

Ax Yiheng Zhang, Kaiyan Zhao, Shaowu Wu, Yiming Wang, Jiajun Wu, Leong Hou U, Steve Drew, Xiaoguang Niu 5/5/2026

Anon: Extrapolating Optimizer Adaptivity Across the Real Spectrum

Anon optimizer improves adaptive methods like Adam by adjusting pre-conditioner adaptivity to generalize better across diverse optimization landscapes.

Ax Soham Wasmatkar, Subinay Adhikary, Rakshit Rohan, Shouvik Kumar Guha, Saptarshi Pyne, Kripabandhu Ghosh 5/5/2026

Can Causal Discovery Algorithms Help in Generating Legal Arguments?

Explores application of causal discovery algorithms to automated legal argument generation, applying Pearl's causal reasoning methods.

Ax Yiheng Zhang, Yiming Wang, Kaiyan Zhao, Zhenglin Wan, Jiayu Chen, Leong Hou U 5/5/2026

ANO: A Principled Approach to Robust Policy Optimization

ANO framework unifies PPO and SPO by establishing trust region approach that balances gradient information retention with optimization stability in deep RL.

Ax Ahmad Dabaja, Rachid El-Azouzi 5/5/2026

FedPLT: Scalable, Resource-Efficient, and Heterogeneity-Aware Federated Learning via Partial Layer Training

FedPLT addresses federated learning challenges by partial layer training to reduce communication/computation overhead and handle device heterogeneity.

Ax Muneeb Ur Raheem Khan 5/5/2026

Decoding-Time Debiasing via Process Reward Models: From Controlled Fill-in to Open-Ended Generation

Decoding-time debiasing via process reward models reduces social biases in LLM outputs without model weight access or fine-tuning.

Ax Cosimo Galeone, Minsu Park, Giuseppe Ettorre, Daniele Ligorio 5/5/2026

When Correct Isn't Usable: Improving Structured Output Reliability in Small Language Models

Study of structured output reliability gap in 7-9B language models, evaluating joint accuracy of mathematical correctness and JSON format compliance across prompting strategies.

Ax Rahul Kumar 5/5/2026

The Compliance Trap: How Structural Constraints Degrade Frontier AI Metacognition Under Adversarial Pressure

SCHEMA evaluation framework assesses metacognitive stability of frontier AI models under adversarial pressure, studying cognitive collapse as safety failure mode.

Ax Kyle Zheng, Han Zhang, Renliang Sun, Chenchen Ye, Wei Wang 5/5/2026

FitText: Evolving Agent Tool Ecologies via Memetic Retrieval

FitText framework enables dynamic tool retrieval in AI agent reasoning loops by embedding retrieval directly in execution, addressing semantic gaps between task descriptions and API documentation.

Ax Tu Nguyen, Rasul Tutunov, Xiaotong Ji, Matthieu Zimmer 5/5/2026

The Model Knows, the Decoder Finds: Future Value Guided Particle Power Sampling

Power sampling decoding method to efficiently locate multi-step solutions in LLM reasoning by biasing toward high-probability modes without additional training.

Ax Onno Eberhard, Thibaut Cuvelier, Michal Valko, Bruno De Backer 5/5/2026

Middle-mile logistics through the lens of goal-conditioned reinforcement learning

Goal-conditioned reinforcement learning approach combining graph neural networks for middle-mile logistics routing.

Ax Christian Jestel, Nicolas Bach, Marvin Wiedemann, Jan Finke, Peter Detzner 5/5/2026

Beyond Specialization: Robust Reinforcement Learning Navigation via Procedural Map Generators

Deep reinforcement learning study using procedural map generators to improve navigation policy generalization across diverse environments.

Ax Sunghwan Kim, Junhee Cho, Beong-woo Kwak, Taeyoon Kwon, Liang Wang, Nan Yang, Xingxing Zhang, Furu Wei, Jinyoung Yeo 5/5/2026

On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon Length

Empirical study examining how task horizon length affects training dynamics for LLM-based agents solving extended interaction sequences.

Ax Andreas Maier, Moritz Zaiss, Siming Bayer 5/5/2026

Beating the Style Detector: Three Hours of Agentic Research on the AI-Text Arms Race

Agentic research system reproduces NLP study on LLM style editing in 3 hours with human-in-loop, demonstrating rapid empirical research workflow.

Ax Kevin Riehl, Andres L. Marin, Nikofors Zacharof, Fan Wu, Patrick Langer, Robert Jakob, Anastasios Kouvelas, Georgios Fontaras, Michail A. Makridis 5/5/2026

ARA: Agentic Reproducibility Assessment For Scalable Support Of Scientific Peer-Review

Framework using AI agents to automate reproducibility assessment in scientific peer review, formalizing it as structured reasoning over research artifacts.