Ax Buyun Liang, Jinqi Luo, Liangzu Peng, Kwan Ho Ryan Chan, Darshan Thaker, Kaleab A. Kinfu, Fengrui Tian, Hamed Hassani, Ren\'e Vidal 5/14/2026

REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations

Method for generating realistic adversarial prompts that elicit LLM hallucinations through constrained optimization of semantically coherent inputs.

Ax Benjamin Turtel, Paul Wilczewski, Kris Skotheim 5/14/2026

Training Large Language Models to Predict Clinical Events

Foresight Learning approach for training LLMs on longitudinal clinical notes from MIMIC-III for predicting future patient events.

Ax Patrick Zhao, David Huu Pham, Nicholas Vincent 5/14/2026

Mechanism Plausibility in Generative Agent-Based Modeling

Research testing whether LLM-based agent simulations generate mechanistically plausible phenomena in social simulations and game-theoretic scenarios.

Ax Chien Van Nguyen, Chaitra Hegde, Van Cuong Pham, Ryan A. Rossi, Franck Dernoncourt, Thien Huu Nguyen 5/14/2026

Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion

Orthrus framework unifying autoregressive LLM fidelity with diffusion model parallel token generation for efficient high-throughput inference.

Ax Kaixiang Zhao, Tianrun Yu, Aoxu Zhang, Junhao Su, Porter Jenkins, Amanda Hughes 5/14/2026

FRAME: Forensic Routing and Adaptive Multi-path Evidence Fusion for Image Manipulation Detection

Deep learning approach for detecting image manipulation and AI-generated content using forensic routing and multi-path evidence fusion.

Ax Kaixiang Zhao, Bolin Shen, Yuyang Dai, Shayok Chakraborty, Yushun Dong 5/14/2026

GraphIP-Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It?

Research on model extraction attacks against Graph Neural Networks and defense mechanisms, addressing GNN theft vulnerability as cloud services.

Ax Kaiyang Li, Shaobo Han, Qing Su, Shihao Ji 5/14/2026

Bayesian Model Merging

Proposes Bayesian approach for merging task-specific expert models without retraining. Leverages anchor model bias for parameter estimation in model merging.

Ax Davi Bastos Costa, Renato Vicente 5/14/2026

Persona-Model Collapse in Emergent Misalignment

Hypothesizes emergent misalignment in fine-tuned LLMs involves persona-model collapse. Tests behavioral degradation using moral susceptibility and robustness metrics.

Ax Zhongkai Yu, Yichen Lin, Chenyang Zhou, Yuwei Zhang, Kun Zhou, Junxia Cui, Haotian Ye, Zhengding Hu, Zaifeng Pan, Ruiyi Wang, Yujie Zhao, Hejia Zhang, Jingbo Shang, Jishen Zhao, Yufei Ding 5/14/2026

ChipMATE: Multi-Agent Training via Reinforcement Learning for Enhanced RTL Generation

Multi-agent reinforcement learning system for RTL hardware code generation. Addresses vendor air-gap security and proprietary codebase training constraints in chip design.

Ax Timothy Zhou, Loris D'Antoni, Nadia Polikarpova 5/14/2026

Language-Based Agent Control

Introduces language-based agent control (LBAC) programming model using static typing and runtime enforcement for agentic applications. Brings security concepts from programming languages to agent control.

Ax Zvi Topol 5/14/2026

Quantifying LLM Safety Degradation Under Repeated Attacks Using Survival Analysis

Proposes survival analysis framework for evaluating LLM robustness to repeated jailbreak attacks. Captures temporal dynamics of adversarial pressure beyond binary success metrics.

Ax Hengwei Ye, Jiasheng Mao, Zhenhan Guan, Zheng Tian 5/14/2026

EcoGEO: Trajectory-Aware Evidence Ecosystems for Web-Enabled LLM Search Agents

Studies how LLM web-search agents' influence depends on trajectory through multiple documents. Extends generative engine optimization to agentic multi-step browsing scenarios.

Ax Rohith Reddy Bellibatlu 5/14/2026

RISED: A Pre-Deployment Safety Evaluation Framework for Clinical AI Decision-Support Systems

Proposes RISED framework for pre-deployment evaluation of clinical AI systems across reliability, inclusivity, sensitivity, equity, and deployability dimensions.

Ax Siyuan Liu (IIIS, Tsinghua University), Tinghong Chen (College of AI, Tsinghua University,Shanghai Qi Zhi Institute), Xinghan Li (IIIS, Tsinghua University), Yifei Wang (Amazon AGI SF Lab), Jingzhao Zhang (IIIS, Tsinghua University,Shanghai Qi Zhi Institute) 5/14/2026

Data Difficulty and the Generalization--Extrapolation Tradeoff in LLM Fine-Tuning

Studies data difficulty's role in LLM fine-tuning from empirical and theoretical perspectives. Examines tradeoff between generalization and extrapolation in supervised fine-tuning.

Ax Vardhan Dongre, Dilek Hakkani-T\"ur 5/14/2026

Embodied Multi-Agent Coordination by Aligning World Models Through Dialogue

Proposes multi-agent coordination through dialogue-based world model alignment in partially observable environments. Addresses communication as bridge for embodied agent collaboration.

Ax Priyam Sahoo, Gaurav Mittal, Xiaomin Li, Shengjie Ma, Benjamin Steenhoek, Pingping Lin, Yu Hu 5/14/2026

AgentLens: Revealing The Lucky Pass Problem in SWE-Agent Evaluation

Identifies 'lucky pass' problem in SWE-Agent evaluation where agents pass tests through trial-and-error rather than principled solutions. Analyzes 2,614 trajectories to show outcome-only metrics miss process quality.

Ax Zhiyu Zhao, Xuejie Liu, Muhan Zhang, Anji Liu 5/14/2026

The Expressivity Boundary of Probabilistic Circuits: A Comparison with Large Language Models

Comparative analysis of probabilistic circuits and transformers for autoregressive language modeling, identifying expressivity gaps.

Ax Young Hyun Cho, Will Wei Sun 5/14/2026

When Should an AI Workflow Release? Always-Valid Inference for Black-Box Generate-Verify Systems

Statistical framework for determining optimal release timing in iterative LLM generate-verify workflows using always-valid inference.

Ax Chao Hao, Jun Xu, Ji Du, Shuo Ye, Ziyue Qiao, Xiaodong Cun, Guangcong Wang, Xubin Zheng, Zitong Yu 5/14/2026

Seg-Agent: Test-Time Multimodal Reasoning for Training-Free Language-Guided Segmentation

Test-time multimodal agent for language-guided segmentation using iterative reasoning between MLLMs and foundation models.

Ax Xiao Yang, Yingzhe Ma, Haoxuan Yu, Zixin Li, Ning Qin 5/14/2026

AdaFocus: Adaptive Relevance-Diversity Sampling with Zero-Cache Look-back for Efficient Long Video Understanding

Efficient long video understanding through adaptive relevance-diversity frame sampling with zero-cache memory overhead.

Ax Hisashi Miyashita, Mgnite Inc 5/14/2026

Controlling Logical Collapse in LLMs via Algebraic Ontology Projection over F2

Algebraic method projecting LLM hidden states into Galois Field F2 to control logical consistency and verify ontological relations.

Ax Feng Zhang, Xinhong Ma, Ziqiang Dong, Xi Leng, Jianfei Zhao, Xin Sun, Yang Yang, Guanjun Jiang 5/14/2026

Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive Perspective

Contrastive perspective on reinforcement learning with verifiable rewards, reformulating GRPO as weighted score difference optimization.

Ax Jun He, Deying Yu 5/14/2026

Protocol-Driven Development: Governing Generated Software Through Invariants and Evidence

Protocol-driven development framework for governing generated software through algebraic invariants and evidence collection.

Ax Adarsh Kumarappan, Ananya Mujoo 5/14/2026

Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent Sycophancy

Investigation of sycophancy in multi-agent LLM pipelines, showing alignment training alone insufficient to fix disagreement-induced errors.

Ax Yilie Huang, Xun Yu Zhou 5/14/2026

Amortized Guidance for Image Inpainting with Pretrained Diffusion Models

Method for image inpainting with pretrained diffusion models using reusable offline-trained guidance modules.

Ax Chunsan Hong, Sanghyun Lee, Chieh-Hsin Lai, Satoshi Hayakawa, Yuhta Takida, Yuki Mitsufuji, Seungryong Kim, Jong Chul Ye 5/14/2026

Understanding and Accelerating the Training of Masked Diffusion Language Models

Analysis and acceleration methods for training masked diffusion models to match autoregressive model training speed.

Ax Yanggan Gu, Shuo Cai, Zihao Wang, Wenjun Wang, Yuanyi Wang, Pengkai Wang, Sirui Huang, Su Lu, Jianmin Wu, Hongxia Yang 5/14/2026

FeatCal: Feature Calibration for Post-Merging Models

Technique to reduce feature drift and improve performance of merged expert models through feature calibration.

Ax Ying Li, Hongbo Wen, Yanju Chen, Hanzhi Liu, Yuan Tian, Yu Feng 5/14/2026

No Attack Required: Semantic Fuzzing for Specification Violations in Agent Skills

Semantic fuzzing framework identifies safety specification violations in LLM-powered agent skills where benign inputs cause guardrail breaches.

Ax Ziqi Wen, Parsa Madinei, Miguel P. Eckstein 5/14/2026

Revealing the Gap in Human and VLM Scene Perception through Counterfactual Semantic Saliency

Framework to evaluate alignment between vision-language models and human perception using counterfactual semantic saliency analysis.

Ax Zeyu Huang, Adhiguna Kuncoro, Qixuan Feng, Jiajun Shen, Lucio Dery, Arthur Szlam, Marc'Aurelio Ranzato 5/14/2026

Context Training with Active Information Seeking

Method for adapting LLMs to downstream tasks via context optimization and active information seeking without weight updates.

Ax Minung Kim, Jeongmo Kim, Gwanwoo Choi, Seungyul Han 5/14/2026

Bridging Domain Gaps with Target-Aligned Generation for Offline Reinforcement Learning

Framework for cross-domain offline reinforcement learning that expands source data coverage while aligning to target distribution.

Ax Maxime Alvarez, Ryo Watanabe, Paul Crook, Afshin Zeinaddini Meymand, Suvin Kurian, Pablo Ferreiro, Genki Sano 5/14/2026

When Absolute State Fails: Evaluating Proprioceptive Encodings for Robust Manipulation

Study of proprioceptive encodings for robust robotic manipulation under distribution shift and unseen test conditions.

Ax Zubin Zheng, Jiahao Wu, Shengcai Liu 5/14/2026

Neural QAOA$^{2}$: Differentiable Joint Graph Partitioning and Parameter Initialization for Quantum Combinatorial Optimization

Differentiable approach for graph partitioning and parameter initialization in quantum approximate optimization algorithm.

Ax Louise Beyers, Batsirayi Mupamhi Ziki, Ruan van der Merwe 5/14/2026

Scaling few-shot spoken word classification with generative meta-continual learning

Scaling few-shot spoken word classification to 1000 classes with five shots per class using generative meta-continual learning.

Ax Chunyan Mu, Muhammad Najib 5/14/2026

Counterfactual Reasoning for Causal Responsibility Attribution in Probabilistic Multi-Agent Systems

Framework for allocating responsibility in multi-agent systems using counterfactual reasoning in probabilistic games.

Ax Tien-Phat Nguyen, Truong Nguyen, Minh-Phuc Truong, Tuc Nguyen, James Bailey, Trung Le 5/14/2026

Spectral Flattening Is All Muon Needs: How Orthogonalization Controls Learning Rate and Convergence

Analysis of Muon optimizer showing spectral flattening mechanism enables larger learning rates and faster convergence than other optimizers.

Ax Batsirayi Mupamhi Ziki, Louise Beyers, Ruan van der Merwe 5/14/2026

Does language matter for spoken word classification? A multilingual generative meta-learning approach

Meta-learning approach for multilingual few-shot spoken word classification using generative meta-continual learning.

Ax Kush Juvekar, Kavya Manohar, Aditya Srinivas Menon, Arghya Bhattacharya, Kumarmanas Nethil 5/14/2026

Vividh-ASR: A Complexity-Tiered Benchmark and Optimization Dynamics for Robust Indic Speech Recognition

Complexity-tiered benchmark for Indian language speech recognition identifying studio-bias in multilingual ASR models.

Ax Toluwani Aremu, Nils Lukas, Jie Zhang 5/14/2026

Watermarking Should Be Treated as a Monitoring Primitive

Analysis of watermarking as monitoring primitive for generative models, examining attribution and detection under adversarial conditions.

Ax Najwa Laabid, Vikas Garg 5/14/2026

Margin-calibrated Classifier Guidance for Property-driven Synthesis Planning

Classifier guidance method for chemical synthesis planning using margin-calibrated steering of retrosynthesis models.

Ax Grigorios Alexandrou, Katerina Pramatari 5/14/2026

A Multi-Agent Orchestration Framework for Venture Capital Due Diligence

Fully automated multi-agent framework for venture capital due diligence combining LLMs with real-time web retrieval and data extraction.

Ax Jose Luna, Yankun Wu, Xiaofei Xie, Noa Garcia 5/14/2026

Context Matters: Auditing Gender Bias in T2I Generation through Risk-Tiered Use-Case Profiles

Audit framework for measuring gender bias in text-to-image generative models using risk-tiered use-case profiles.

Ax Han Yi Shin, Heeju Ko, Jaewon Mun, Qixing Huang, Jaehyeok Lee, Sung June Kim, Honglak Lee, Sujin Jang, Sangpil Kim 5/14/2026

SECOND-Grasp: Semantic Contact-guided Dexterous Grasping

Approach integrating dexterous grasping with language-guided semantics for reliable robotic manipulation.

Ax Zixing Lei, Changxing Liu, Yichen Xiong, Minhao Xiong, Yuanzhuo Ding, Zhipeng Zhang, Weixin Li, Siheng Chen 5/14/2026

Towards Long-horizon Embodied Agents with Tool-Aligned Vision-Language-Action Models

Framework combining VLM agents for high-level reasoning with specialized VLA tools for long-horizon embodied robotic tasks.

Ax Chaokai Wu, Haofu Shi, Ningxuan Ma, Jianghong Ma, Xiaofeng Zhang 5/14/2026

MLGIB: Multi-Label Graph Information Bottleneck for Expressive and Robust Message Passing

Graph neural network method addressing over-squashing in multi-label graphs using information bottleneck principles.

Ax Guoxiong Gao, Zeming Sun, Jiedong Jiang, Yutong Wang, Jingda Xu, Peihao Wu, Bryan Dai, Bin Dong 5/14/2026

LeanSearch v2: Global Premise Retrieval for Lean 4 Theorem Proving

Global premise retrieval system for Lean 4 theorem proving that identifies relevant library lemmas needed for complete proofs.

Ax Ishika Agarwal, Sofia Stoica, Emre Can Acikgoz, Pradeep Natarajan, Mahdi Namazifar, Jiaqi Ma, Dilek Hakkani-T\"ur 5/14/2026

AcquisitionSynthesis: Targeted Data Generation using Acquisition Functions

Data generation method using acquisition functions to synthesize targeted training samples and improve model quality.

Ax Jiahao Chen, Zihui Zhang, Yafei Yang, Jinxi Li, Shenxing Wei, Zhixuan Sun, Bo Yang 5/14/2026

EvObj: Learning Evolving Object-centric Representations for 3D Instance Segmentation without Scene Supervision

Unsupervised 3D instance segmentation method bridging synthetic-to-real domain gap using evolving object-centric representations.

Ax Changpeng Wang, Xin Lin, Junhan Liu, Yuheng Liu, Zhen Wang, Donglian Qi, Yunfeng Yan, Xi Chen 5/14/2026

PanoWorld: Towards Spatial Supersensing in 360$^\circ$ Panorama World

Framework for improving MLLM spatial understanding using 360-degree panoramic sensing for navigation and 3D scene understanding tasks.

Ax Ziqi Wang, Yuhao Yang, Zhiwei Ling, Wenzhuo Qian, Hailiang Zhao 5/14/2026

When Does Hierarchy Help? Benchmarking Agent Coordination in Event-Driven Industrial Scheduling

Benchmark for studying multi-agent coordination paradigms in hierarchical, dynamically evolving industrial scheduling systems with coupled constraints.