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.

Ax Sangin Lee, Yukyung Choi 5/14/2026

CLIP Tricks You: Training-free Token Pruning for Efficient Pixel Grounding in Large VIsion-Language Models

Training-free token pruning technique for efficient vision-language models optimized for pixel grounding tasks.

Ax Hongli Liu, Yu Wang, Shengjie Zhao 5/14/2026

STAR: Semantic-Temporal Adaptive Representation Learning for Few-Shot Action Recognition

Few-shot action recognition using semantic-temporal adaptive learning with vision-language models.

Ax Xiao Liu, Nayu Liu, Junnan Zhu, Ruirui Chen, Guohui Xiang, Changjian Wang, Kaiwen Wei, Rongzhen Li, Jiang Zhong 5/14/2026

ReTool-Video: Recursive Tool-Using Video Agents with Meta-Augmented Tool Grounding

Video understanding agent with recursive tool-use, meta-augmented grounding, and fine-grained operations for temporal reasoning.

Ax Xinyu Liu, Kechen Jiao, Chunyang Xiao, Runsong Zhao, Junhao Ruan, Bei Li, Jiahao Liu, Qifan Wang, Xin Chen, Jingang Wang, Tong Xiao, JingBo Zhu 5/14/2026

Teacher-Guided Policy Optimization for LLM Distillation

LLM distillation method using teacher guidance and Reverse KL to improve student model learning from divergent distributions.

Ax Weiqing Luo, Zongye Hu, Xiao Wang, Zhiyuan Yu, Haofeng Zhang, Ziyi Huang 5/14/2026

Utility-Oriented Visual Evidence Selection for Multimodal Retrieval-Augmented Generation

Information-theoretic framework for visual evidence selection in multimodal RAG systems based on utility to downstream reasoning.

Ax Hengzhi Ye, Fengyuan Ran, Weiwei Xu, Minghui Zhou 5/14/2026

The Readability Spectrum: Patterns, Issues, and Prompt Effects in LLM-Generated Code

Study analyzing readability of LLM-generated code compared to human-written code and effects of prompt design.

Ax Ian Osband 5/14/2026

Delightful Exploration

Exploration algorithm balancing uncertainty reduction with expected improvement in large action spaces.

Ax Shubham Kumar Nigam, Suparnojit Sarkar, Piyush Patel 5/14/2026

IndicMedDialog: A Parallel Multi-Turn Medical Dialogue Dataset for Accessible Healthcare in Indic Languages

Parallel multi-turn medical dialogue dataset spanning English and nine Indic languages with LLM-generated synthetic conversations.

Ax Tom Zehle 5/14/2026

CANTANTE: Optimizing Agentic Systems via Contrastive Credit Attribution

Credit attribution framework for optimizing multi-agent LLM systems through contrastive learning to improve agent configuration.

Ax Yunheng Wang, Yuetong Fang, Taowen Wang, Lusong Li, Kun Liu, Junzhe Xu, Zizhao Yuan, Yixiao Feng, Jiaxi Zhang, Wei Lu, Zecui Zeng, Renjing Xu 5/14/2026

What Limits Vision-and-Language Navigation ?

Analysis of embodied AI agents' limitations in vision-language navigation when transitioning from simulation to real-world deployment.

Ax Viktor Moskvoretskii, Dominik Glandorf, Jorge Medina Moreira, Tanja K\"aser, Robert West 5/14/2026

Tracing Persona Vectors Through LLM Pretraining

Interpretability research tracing how LLMs represent behavioral traits like sycophancy as linear directions in internal activations.

Ax Shuqiang Wang, Wei Cao, Jiaqi Weng, Jialing Tao, Licheng Pan, Hui Xue, Zhixuan Chu 5/14/2026

Inducing Overthink: Hierarchical Genetic Algorithm-based DoS Attack on Black-Box Large Language Reasoning Models

Genetic algorithm-based DoS attack exploiting LLM reasoning model vulnerabilities by inducing excessive inference through incomplete inputs.

Ax Oscar Gilg, Pierre Beckmann, Daniel Paleka, Patrick Butlin 5/14/2026

Probing Persona-Dependent Preferences in Language Models

Mechanistic study of how LLMs implement persona-dependent preferences using linear probing of model internals.

Ax Hailin Zhong, Shengxin Zhu 5/14/2026

AI Harness Engineering: A Runtime Substrate for Foundation-Model Software Agents

Runtime substrate architecture for foundation-model software agents mediating agent-environment interaction and code generation reliability.

Ax Chaehee Song, Minseok Seo, Yeeun Seong, Doyi Kim, Changick Kim 5/14/2026

Query-Conditioned Test-Time Self-Training for Large Language Models

Test-time self-training approach enabling LLM parameter updates at inference for query-specific adaptation.

Ax Mingzhe Huang, Weijun Wang, Xin Ding, Liang Mi, Hao Wen, Yuanchun Li, Lichen Pang, Shansong Yang, Yunxin Liu, Ting Cao 5/14/2026

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models

Token pruning method for vision-language models using group-relative importance ranking for computational efficiency.

Ax Galadrielle Humblot-Renaux, Mohammad N. S. Jahromi, Rohat Bakuri-J{\o}rgensen, Marieke Anne Heyl, Asta S. Stage Jarlner, Maria Vlachou, Anna Murphy H{\o}genhaug, Desmond Elliott, Thomas Gammeltoft-Hansen, Thomas B. Moeslund 5/14/2026

LLMs as annotators of credibility assessment in Danish asylum decisions: evaluating classification performance and errors beyond aggregated metrics

Evaluation of off-the-shelf LLMs for legal document annotation on Danish asylum credibility assessment task.

Ax Barathi Ganesh HB, Michal Ptaszynski, Rene Melendez, Juuso Eronen 5/14/2026

Continual Learning with Multilingual Foundation Model

Multilingual foundation model framework for detecting reclaimed slurs in social media across three languages.

Ax JaeHyeok Doo, Byeongguk Jeon, Seonghyeon Ye, Kimin Lee, Minjoon Seo 5/14/2026

Q-Flow: Stable and Expressive Reinforcement Learning with Flow-Based Policy

Reinforcement learning approach using flow-based models as policies with stable gradient-based optimization methods.

Ax Xingyu Wang, Pengxiang Ding, Jingkai Xu, Donglin Wang, Zhaoxin Fan 5/14/2026

CUBic: Coordinated Unified Bimanual Perception and Control Framework

Bimanual robot control framework balancing independent arm perception with coordinated interaction through visuomotor learning.

Ax Katarzyna Kobalczyk, Mihaela van der Schaar 5/14/2026

Discovery of Hidden Miscalibration Regimes

Method for discovering localized model calibration failures beyond global reliability metrics using structured analysis.

Ax Tsz Ting Chung, Lemao Liu, Mo Yu, Dit-Yan Yeung 5/14/2026

Many-Shot CoT-ICL: Making In-Context Learning Truly Learn

Study of chain-of-thought in-context learning with many-shot examples showing scaling behavior comparable to fine-tuning on reasoning tasks.

Ax Qingyun Zou, Feng Yu, Hongshi Tan, Yao Chen, Bingsheng He, WengFai Wong 5/14/2026

HLS-Seek: QoR-Aware Code Generation for High-Level Synthesis via Proxy Comparative Reward Reinforcement Learning

LLM-based high-level synthesis code generation using comparative reward reinforcement learning for hardware optimization.

Ax Ye Wang, Jing Liu, Toshiaki Koike-Akino 5/14/2026

Temper and Tilt Lead to SLOP: Reward Hacking Mitigation with Inference-Time Alignment

Inference-time alignment method for LLMs using temperature adjustment to mitigate reward hacking in model outputs.

Ax Anuj Sadani, Deepak Kumar 5/14/2026

Locale-Conditioned Few-Shot Prompting Mitigates Demonstration Regurgitation in On-Device PII Substitution with Small Language Models

On-device PII redaction pipeline using small language models with few-shot prompting for privacy-preserving text substitution.

Ax Daojie Peng, Fulong Ma, Jiahang Cao, Qiang Zhang, Xupeng Xie, Jian Guo, Ping Luo, Andrew F. Luo, Boyu Zhou, Jun Ma 5/14/2026

AttenA+: Rectifying Action Inequality in Robotic Foundation Models

Robotic foundation model training method addressing temporal heterogeneity in action sequences through weighted optimization.

Ax Asim Osman, Sasha Abramowitz, Mark Bergh, Ulrich Armel Mbou Sob, Ruan John de Kock, Omayma Mahjoub, Oussama Hidaoui, Noah De Nicola, Arnol Manuel Fokam, Felix Chalumeau, Daniel Rajaonarivonivelomanantsoa, Siddarth Singh, Refiloe Shabe, Juan Claude Formanek, Simon Verster Du Toit, Arnu Pretorius 5/14/2026

Self-Supervised On-Policy Reinforcement Learning via Contrastive Proximal Policy Optimisation

arXiv paper on AttenA+: improving robotic foundation models by addressing temporal heterogeneity in manipulation tasks.

Ax Seokha Moon, Minseung Lee, Joon Seo, Jinkyu Kim, Jungbeom Lee 5/14/2026

Causality-Aware End-to-End Autonomous Driving via Ego-Centric Joint Scene Modeling

OpenAaaS: open-source agent-as-a-service framework for distributed materials-informatics research using LLMs and autonomous agents.

Ax Namrata Shivagunde, Vijeta Deshpande, Sherin Muckatira, Anna Rumshisky 5/14/2026

Beyond Perplexity: A Geometric and Spectral Study of Low-Rank Pre-Training

arXiv paper on NAACA: training-free audio language model architecture with oscillatory working memory for salience-driven attention.

Ax Stefano Colamonaco, Andrei-Bogdan Florea, Jaron Maene 5/14/2026

Weakly Supervised Segmentation as Semantic-Based Regularization

arXiv paper analyzing whether low-rank pre-training methods for LLMs generalize comparably to full-rank training.

Ax Jason Gaitonde, Frederic Koehler, Elchanan Mossel, Joonhyung Shin, Allan Sly 5/14/2026

A Hierarchical Language Model with Predictable Scaling Laws and Provable Benefits of Reasoning

Synthetic hierarchical language model with provable scaling laws and benefits of multi-step reasoning.

Ax Andrea Morandi 5/14/2026

RTLC -- Research, Teach-to-Learn, Critique: A three-stage prompting paradigm inspired by the Feynman Learning Technique that lifts LLM-as-judge accuracy on JudgeBench with no fine-tuning

RTLC three-stage prompting improves LLM-as-judge accuracy for evaluation without fine-tuning or external tools.

Ax Steven Seiden, Triss Ren, Caroline Zhang, Taein Kim, Enze Liu, Emily Wenger 5/14/2026

Identifying AI Web Scrapers Using Canary Tokens

Method using canary tokens to detect and identify web scraping by AI systems for LLM training data collection.

Ax Qian Shen (University of Florida, Gainesville, USA), Fanghua Cao (University of Florida, Gainesville, USA), Min Yao (University of Florida, Gainesville, USA), Shlok Gilda (University of Florida, Gainesville, USA), Bonnie J. Dorr (University of Florida, Gainesville, USA), Walter L. Leite (University of Florida, Gainesville, USA) 5/14/2026

Children's English Reading Story Generation via Supervised Fine-Tuning of Compact LLMs with Controllable Difficulty and Safety

Fine-tuned compact LLMs generate children's reading stories with controllable difficulty and safety constraints.

Ax Ben Wilson, Matimba Swana, Peter Winter, Matt Roach 5/14/2026

Humanwashing -- It Should Leave You Feeling Dirty

Critical analysis of 'human in the loop' as safety mechanism for AI systems, examining its limitations and misuse.

Ax Zedong Liu, Xinyang Ma, Dejun Luo, Hairui Zhao, Bing Lu, Wenjing Huang, Yida Gu, Xingchen Liu, Zheng Wei, Jinyang Liu, Dingwen Tao, Guangming Tan 5/14/2026

KVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM Serving

KVServe compresses KV cache dynamically for disaggregated LLM serving to reduce communication bottlenecks.

Ax Or Ordentlich, Yury Polyanskiy 5/14/2026

High-Rate Quantized Matrix Multiplication II

Quantization techniques for weight-only post-training of LLMs using available covariance matrix information.

Ax Tyler Alvarez, Ali Baheri 5/14/2026

Where Does Reasoning Break? Step-Level Hallucination Detection via Hidden-State Transport Geometry

Method for detecting step-level hallucinations in LLM reasoning by analyzing hidden state geometry during inference.

Ax Mohammad Reza Mousavi 5/14/2026

(How) Do Large Language Models Understand High-Level Message Sequence Charts?

Study evaluating whether LLMs consistently understand semantic content in High-Level Message Sequence Charts for software design.

Ax Mind Lab, :, Song Cao, Vic Cao, Andrew Chen, Kaijie Chen, Cleon Cheng, Steven Chiang, Kaixuan Fan, Hera Feng, Huan Feng, Arthur Fu, Jun Gao, Hongquan Gu, Aaron Guan, Nolan Ho, Mutian Hong, Hailee Hou, Peixuan Hua, Charles Huang, Miles Jiang, Nora Jiang, Yuyi Jiang, Qiuyu Jin, Fancy Kong, Andrew Lei, Kyrie Lei, Alexy Li, Lucian Li, Ray Li, Theo Li, Zhihui Li, Jiayi Lin, Kairus Liu, Kieran Liu, Logan Liu, Xiang Liu, Irvine Lu, Maeve Luo, Runze Lv, Pony Ma, Verity Niu, Anson Qiu, Vincent Wang, Rio Yang, Maxwell Yao, Carrie Ye, Regis Ye, Wenlin Ye, Josh Ying, Danney Zeng, Yuhan Zhan, Anya Zhang, Di Zhang, Ruijia Zhang, Sueky Zhang, Ya Zhang, Wei Zhao, Ada Zhou, Changhai Zhou, Yuhua Zhou, Xinyue Zhu, Murphy Zhuang 5/14/2026

MinT: Managed Infrastructure for Training and Serving Millions of LLMs

MinT infrastructure system for efficient LoRA fine-tuning and serving of millions of LLM variants using shared base models.

Ax Jonathan A. Diller, Fernando Cladera, Camillo J. Taylor, Vijay Kumar 5/14/2026

LMPath: Language-Mediated Priors and Path Generation for Aerial Exploration

LMPath uses language models to generate semantic-aware exploration paths for autonomous UAV search missions.