Ax Shouyu Yin, Zhao Tian, Junjie Chen, Shikai Guo 5/5/2026

Improving LLM Code Generation via Requirement-Aware Curriculum Reinforcement Learning

Improves LLM code generation for complex requirements using requirement-aware curriculum reinforcement learning.

Ax Xin Du, Kumiko Tanaka-Ishii 5/5/2026

Escaping Mode Collapse in LLM Generation via Geometric Regulation

Addresses mode collapse in LLM text generation through geometric regulation using dynamical systems perspective.

Ax Kenneth J. K. Ong 5/5/2026

Impact of Task Phrasing on Presumptions in Large Language Models

Studies how task phrasing affects LLM presumptions and adaptation using iterated prisoner's dilemma experiments.

Ax P. Rosciszewski, A. Krzywaniak, S. Iserte, K. Rojek, P. Gepner 5/5/2026

Adaptation of AI-accelerated CFD Simulations to the IPU platform

Evaluates Intelligence Processing Units for AI-accelerated CFD simulations using TensorFlow and Poplar SDK.

Ax Lu Dai, Liang Sun, Fanpu Cao, Ziyang Rao, Cehao Yang, Hao Liu, Hui Xiong 5/5/2026

LLM-Oriented Information Retrieval: A Denoising-First Perspective

Perspective on LLM-oriented information retrieval from denoising-first angle, addressing attention budgets and hallucination vulnerabilities in RAG.

Ax Zhanwei Wang, Huiling Yang, Min Sheng, Khaled B. Letaief, Kaibin Huang 5/5/2026

Space Network of Experts: Architecture and Expert Placement

Architecture for deploying large LLMs across satellite networks leveraging solar energy with optimized expert placement strategies.

Ax Abdurrahman Javat, Allan Kazakov 5/5/2026

Silicon Showdown: Performance, Efficiency, and Ecosystem Barriers in Consumer-Grade LLM Inference

Empirical analysis comparing Nvidia and Apple Silicon ecosystems for local LLM inference on consumer hardware with 70B+ models.

Ax Dongxin Guo, Jikun Wu, Siu Ming Yiu 5/5/2026

SAGA: Workflow-Atomic Scheduling for AI Agent Inference on GPU Clusters

SAGA: Workflow-atomic scheduling system for GPU clusters treating entire AI agent workflows as first-class units, reducing latency 3-8x.

Ax Ziwen Zhao, Menglin Yang 5/5/2026

Hierarchical Abstract Tree for Cross-Document Retrieval-Augmented Generation

Hierarchical abstract tree method for cross-document multi-hop retrieval-augmented generation addressing clustering and distribution challenges.

Ax Junda Ying, Yuxuan Wang, Bowen Yang, Peijie Zhou, Lei Zhang 5/5/2026

Beyond Continuity: Simulation-free Reconstruction of Discrete Branching Dynamics from Single-cell Snapshots

Method for reconstructing discrete cellular trajectories from snapshots using unbalanced optimal transport accounting for birth-death dynamics.

Ax Michito Takeshita, Takuro Kawada, Takumi Ohashi, Shunsuke Kitada, Hitoshi Iyatomi 5/5/2026

A11y-Compressor: A Framework for Enhancing the Efficiency of GUI Agent Observations through Visual Context Reconstruction and Redundancy Reduction

A11y-Compressor: Framework compressing accessibility trees for GUI agents by reconstructing visual context and reducing redundancy.

Ax James Mooney, Zae Myung Kim, Young-Jun Lee, Dongyeop Kang 5/5/2026

Structure Liberates: How Constrained Sensemaking Produces More Novel Research Output

SCISENSE: Framework operationalizing scientific ideation as structured cognitive stages with 100K-scale citation-conditioned dataset.

Ax Aharon Azulay, Jan Dubi\'nski, Zhuoyun Li, Atharv Mittal, Yossi Gandelsman 5/5/2026

Jailbreaking Vision-Language Models Through the Visual Modality

Four jailbreak attacks against vision-language models exploiting visual modality through symbol encoding, substitution, and manipulation.

Ax Yao Ni, Jeremie Houssineau, Yew Soon Ong, Piotr Koniusz 5/5/2026

Possibilistic Predictive Uncertainty for Deep Learning

Possibilistic approach to epistemic uncertainty modeling in deep neural networks balancing Bayesian rigor with computational efficiency.

Ax Massimo Rondelli, Francesco Pivi, Maurizio Gabbrielli 5/5/2026

BlenderRAG: High-Fidelity 3D Object Generation via Retrieval-Augmented Code Synthesis

BlenderRAG: Retrieval-augmented generation system for generating Blender code from natural language using 500 curated multimodal examples.

Ax Jiali Cui, Zhiqiang Lao, Heather Yu 5/5/2026

Learning Multimodal Energy-Based Model with Multimodal Variational Auto-Encoder via MCMC Revision

Energy-based models combined with multimodal VAEs via MCMC for learning complex dependencies in multimodal data.

Ax Zhijie Cai, Haolong Chen, Guangxu Zhu 5/5/2026

AdaMeZO: Adam-style Zeroth-Order Optimizer for LLM Fine-tuning Without Maintaining the Moments

AdaMeZO: Adam-style zeroth-order optimizer for LLM fine-tuning that reduces GPU memory by using only forward passes, improving convergence over prior MeZO method.

Ax Andrzej Ruszczynski, Tiangang Zhang 5/5/2026

Reinforcement Learning with Markov Risk Measures and Multipattern Risk Approximation

Q-learning method with multipattern risk-averse Markov decision processes and mini-batch risk measures with regret bounds.

Ax Jiaming Zhang, Yujie Yang, Yao Lyu, Shengbo Eben Li, Liping Zhang 5/5/2026

Augmented Lagrangian Multiplier Network for State-wise Safety in Reinforcement Learning

Augmented Lagrangian multiplier network for enforcing state-wise safety constraints in reinforcement learning with improved training stability.

Ax Ziyu Zheng, Yaming Yang, Zhe Wang, Ziyu Guan, Wei Zhao 5/5/2026

Empowering Heterogeneous Graph Foundation Models via Decoupled Relation Alignment

Decoupled relation alignment approach extends graph foundation models to multi-domain heterogeneous graphs while preserving type-specific semantics.

Ax Zihao Ding, Beining Wu, Jun Huang 5/5/2026

EASE: Federated Multimodal Unlearning via Entanglement-Aware Anchor Closure

EASE method enables federated unlearning in multimodal models by decoupling entangled knowledge across image-text modalities and client gradients.

Ax Xihao Chen, Yangyang Guo, Roger Zimmermann 5/5/2026

Make Your LVLM KV Cache More Lightweight

LightKV reduces KV cache memory overhead in large vision-language models by exploiting token redundancy during inference prefill stage.

Ax Alfredo Madrid-Garc\'ia, Miguel Rujas 5/5/2026

When RAG Chatbots Expose Their Backend: An Anonymized Case Study of Privacy and Security Risks in Patient-Facing Medical AI

Security assessment of patient-facing RAG medical chatbot exposing privacy and backend vulnerabilities, highlighting governance gaps in medical AI.

Ax Ziyang Huang, Yi Cao, Ali K. Shargh, Jing Luo, Ruidong Mei, Mohd Zaki, Zhan Liu, Wyatt Bunstine, William Jurayj, Somdatta Goswami, Tyrel McQueen, Michael Shields, Jaafar El-Awady, Paulette Clancy, Benjamin Van Durme, Nicholas Andrews, William Walden, Daniel Khashabi 5/5/2026

Can Coding Agents Reproduce Findings in Computational Materials Science?

Evaluates coding agents on computational materials science workflows, testing domain-specific procedure navigation and scientific result interpretation.

Ax Siyuan Huang, Xiaoye Qu, Yafu Li, Tong Zhu, Zefeng He, Muxin Fu, Daizong Liu, Wei-Long Zheng, Yu Cheng 5/5/2026

Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs

Persistent Visual Memory module prevents visual attention decay in autoregressive LVLMs by sustaining perception across long generated sequences.

Ax Preston Rozwood, Edward Mehrez, Ludger Paehler, Wen Sun, Steven L. Brunton 5/5/2026

Koopman-Assisted Reinforcement Learning

Koopman operator-based reinforcement learning algorithms linearize high-dimensional nonlinear systems for tractable control and decision-making.

Ax Guangyu Zhao, Kewei Lian, Haoxuan Ru, Borong Zhang, Haowei Lin, Zhancun Mu, Haobo Fu, Qiang Fu, Shaofei Cai, Zihao Wang, Yitao Liang 5/5/2026

Preference Goal Tuning: Post-Training as Latent Control for Frozen Policies

Preference goal tuning formulates post-training adaptation as latent control problem using continuous goal embeddings for frozen policy behavior modulation.

Ax Bin Lei, Weitai Kang, Zijian Zhang, Winson Chen, Xi Xie, Shan Zuo, Mimi Xie, Ali Payani, Mingyi Hong, Yan Yan, Caiwen Ding 5/5/2026

InfantAgent-Next: A Multimodal Generalist Agent for Automated Computer Interaction

InfantAgent-Next multimodal generalist agent integrates tool-based and vision agents in modular architecture for automated computer interaction.

Ax Yisen Gao, Jiaxin Bai, Tianshi Zheng, Qingyun Sun, Ziwei Zhang, Xingcheng Fu, Jianxin Li, Yangqiu Song 5/5/2026

Controllable Logical Hypothesis Generation for Abductive Reasoning in Knowledge Graphs

Controllable logical hypothesis generation for abductive reasoning in knowledge graphs with applications to clinical diagnosis and discovery.

Ax Nitish Jaipuria, Lorenzo Gatto, Zijun Kan, Shankey Poddar, Bill Cheung, Diksha Bansal, Ramanan Balakrishnan, Aviral Suri, Jose Estevez 5/5/2026

CASE: An Agentic AI Framework for Enhancing Scam Intelligence in Digital Payments

CASE agentic AI framework detects sophisticated payment scams using multi-surface intelligence and social engineering pattern recognition.

Ax Linhao Luo, Zicheng Zhao, Junnan Liu, Zhangchi Qiu, Junnan Dong, Serge Panev, Chen Gong, Thuy-Trang Vu, Gholamreza Haffari, Dinh Phung, Alan Wee-Chung Liew, Shirui Pan 5/5/2026

G-reasoner: Foundation Models for Unified Reasoning over Graph-structured Knowledge

G-reasoner foundation models enable unified reasoning over graph-structured knowledge, improving retrieval-augmented generation for knowledge-intensive tasks.

Ax Songyuan Sui, Zihang Xu, Xia Hu 5/5/2026

Training-Free Time Series Classification via In-Context Reasoning with LLM Agents

FETA multi-agent framework performs training-free time series classification via in-context reasoning with exemplars, using reasoning-oriented LLMs.

Ax Richard Dewey, Janos Botyanszki, Ciamac C. Moallemi, Andrew T. Zheng 5/5/2026

Outbidding and Outbluffing Elite Humans: Mastering Liar's Poker via Self-Play and Reinforcement Learning

Solly AI agent masters Liar's Poker via self-play reinforcement learning with multi-player dynamics and imperfect information.

Ax Jinu Lee, Kyoung-Woon On, Simeng Han, Arman Cohan, Julia Hockenmaier 5/5/2026

Evaluating Legal Reasoning Traces with Legal Issue Tree Rubrics

LEGIT dataset (24K instances) for evaluating LLM-generated legal reasoning traces using hierarchical issue tree rubrics for expert domain validation.

Ax Kaixiang Wang, Yidan Lin, Jiong Lou, Zhaojiacheng Zhou, Bunyod Suvonov, Jie Li 5/5/2026

E-mem: Multi-agent based Episodic Context Reconstruction for LLM Agent Memory

E-mem framework preserves logical integrity in LLM agent memory through episodic context reconstruction, enabling System 2 reasoning over extended horizons.

Ax Henry Han, Xiyang Liu, Xiaodong Wang, Fei Han, Xiaodong Li 5/5/2026

The Quantization Trap: Breaking Linear Scaling Laws in Multi-Hop Reasoning

Demonstrates quantization paradox where reducing model precision increases energy consumption in multi-hop reasoning tasks, breaking expected scaling laws.

Ax Xiaochen Zhao, Kaikai Wang, Xiaowen Zhang, Chen Yao, Aili Wang 5/5/2026

HyMem: Hybrid Memory Architecture with Dynamic Retrieval Scheduling

HyMem hybrid memory architecture with dynamic scheduling balances efficiency and effectiveness in LLM agent memory management for extended dialogues.

Ax Alejandro Breen Herrera, Aayush Sheth, Steven G. Xu, Zhucheng Zhan, Charles Wright, Marcus Yearwood, Hongtai Wei, Sudeep Das, Danny Nightingale, Meg Watson, Charles Pollnow V 5/5/2026

Build, Judge, Optimize: A Blueprint for Continuous Improvement of Multi-Agent Consumer Assistants

Framework for evaluating and optimizing multi-agent conversational shopping assistants, addressing production challenges in multi-turn interactions.

Ax Abhishek Bhandwaldar, Mihir Choudhury, Ruchir Puri, Akash Srivastava 5/5/2026

Agent Factories for High Level Synthesis: How Far Can General-Purpose Coding Agents Go in Hardware Optimization?

Agent factory pipeline uses multiple autonomous coding agents to optimize hardware designs from high-level specifications without hardware-specific training.

Ax Xiujiang Tan (Guangzhou Academy of Fine Arts, Guangzhou, China) 5/5/2026

The Topology of Multimodal Fusion: Why Current Architectures Fail at Creative Cognition

Identifies topological limitations in multimodal AI architectures (CLIP, GPT-4V, diffusion models) based on modal separability concept, with philosophical grounding.

Ax Zan Kai Chong, Hiroyuki Ohsaki, Bryan Ng 5/5/2026

Compiling Deterministic Structure into SLM Harnesses

Semantic Gradient Descent framework compiles agentic workflows into discrete execution plans (DAG topologies, prompts, code) for efficient small language model deployment.

Ax Damiano Fornasiere, Mirko Bronzi, Spencer Kitts, Alessandro Palmas, Yoshua Bengio, Oliver Richardson 5/5/2026

Language models recognize dropout and Gaussian noise applied to their activations

arXiv research: Language models can detect, localize and verbalize activation perturbations like dropout and Gaussian noise.

Ax Behnaz Ranjbar, Kirankumar Raveendiran, Sudeep Pasricha, Samarjit Chakraborty, Cecilia Carbonelli, Akash Kumar 5/5/2026

Autonomous Systems Dependability in the era of AI: Design Challenges in Safety, Security, Reliability and Certification

Design challenges for safety-critical autonomous systems integrating AI components, covering safety, security, reliability, and certification across abstraction layers.

Ax Alex Petrov, Alexander Gusak, Denis Mukha, Dima Korolev 5/5/2026

From Unstructured Recall to Schema-Grounded Memory: Reliable AI Memory via Iterative, Schema-Aware Extraction

Schema-aware memory architecture for AI agents enabling exact fact storage, state tracking, updates, and structured retrieval beyond text embeddings.

Ax Hanane Nour Moussa, Yifei Li, Zhuoyang Li, Yankai Yang, Cheng Tang, Tianshu Zhang, Nesreen K. Ahmed, Ali Payani, Ziru Chen, Huan Sun 5/5/2026

D3-Gym: Constructing Real-World Verifiable Environments for Data-Driven Discovery

D3-Gym dataset with 565 verifiable tasks from real scientific repositories for evaluating LLM and agent capabilities in data-driven discovery.

Ax Yujun Wu, Dongxu Zhang, Xinchen Li, Jinhang Xu, Yiling Duan, Yumou Liu, Jiabao Pan, Qiyuan Zhu, Xuanhe Zhou, Jingxuan Wei, Siyuan Li, Jintao Chen, Conghui He, Cheng Tan 5/5/2026

Intern-Atlas: A Methodological Evolution Graph as Research Infrastructure for AI Scientists

Research infrastructure mapping methodological evolution in AI as a graph structure to support AI-driven research agents accessing scientific knowledge.

Ax Simeon Allmendinger, Domenique Zipperling, Lukas Struppek, Niklas K\"uhl 5/5/2026

CollaFuse: Collaborative Diffusion Models

Collaborative diffusion models for synthetic image generation addressing data availability, computational requirements, and privacy challenges.

Ax Dylan Bouchard 5/5/2026

Bring Your Own Prompts: Use-Case-Specific Bias and Fairness Evaluation for LLMs

Decision framework for systematic evaluation of bias and fairness in LLMs across different deployment contexts and use cases.

Ax Washim Uddin Mondal, Vaneet Aggarwal 5/5/2026

Last-Iterate Convergence of General Parameterized Policies in Constrained MDPs

Algorithm for learning constrained MDPs using parameterized policies with entropy and quadratic regularizers, achieving last-iterate convergence.

Ax Cameron Yetman 5/5/2026

Representation in large language models

Theoretical paper examining how large language models form internal representations, bridging disagreement between LLM optimists and pessimists.