Ax Nazia Nafis, Inaki Esnaola, Alvaro Martinez-Perez, Maria-Cruz Villa-Uriol, Venet Osmani 5/15/2026

Critical Challenges and Guidelines in Evaluating Synthetic Tabular Data: A Systematic Review

Systematic review of 134 studies evaluating quality and reliability of synthetic tabular health data generation across 2067 relevant papers.

Ax Zhiqiang He, Zhi Liu 5/15/2026

Silent Neuron Theory and Plasticity Preservation for Deep Reinforcement Learning in Adaptive Video Streaming

Research on silent neuron theory and plasticity preservation in deep RL for adaptive video streaming under heterogeneous network conditions.

Ax Derian Boer, Stephen Roth, Stefan Kramer 5/15/2026

Autofocus Retrieval: An Effective Pipeline for Multi-Hop Question Answering With Semi-Structured Knowledge

Autofocus Retrieval framework for multi-hop QA combining structured knowledge graphs and unstructured documents in semi-structured knowledge bases.

Ax Shijun Li, Hilaf Hasson, Joydeep Ghosh 5/15/2026

OMAC: A Holistic Optimization Framework for LLM-Based Multi-Agent Collaboration

OMAC framework for optimizing multi-agent LLM systems, addressing handcrafted development approaches for collaborative agents in complex reasoning tasks.

Ax Caiqi Zhang, Xiaochen Zhu, Chengzu Li, Nigel Collier, Andreas Vlachos 5/15/2026

LoVeC: Reinforcement Learning for Better Verbalized Confidence in Long-Form Generations

LoVeC uses reinforcement learning to improve verbalized confidence in LLM generations, addressing hallucination detection without expensive sampling methods.

Ax Kaiwen Chen, Xin Tan, Minchen Yu, Jingzong Li, Hong Xu 5/15/2026

ReasonCache: Accelerating Large Reasoning Model Serving through KV Cache Sharing

ReasonCache optimizes inference serving for large reasoning models by sharing KV cache to reduce memory overhead and improve throughput for concurrent requests.

Ax Xinting Huang, Michael Hahn 5/15/2026

Decomposing Representation Space into Interpretable Subspaces with Unsupervised Learning

Research on decomposing neural network representation spaces into interpretable subspaces using unsupervised learning methods for mechanistic interpretability.

Ax Chang Che, Ziqi Wang, Pengwan Yang, Qi Wang, Hui Ma, Zenglin Shi 5/15/2026

LoRA in LoRA: Towards Parameter-Efficient Architecture Expansion for Continual Visual Instruction Tuning

Parameter-efficient architecture expansion using nested LoRA for multimodal LLMs to mitigate catastrophic forgetting during continual learning.

Ax Alex Chen, Renato Geh, Aditya Grover, Guy Van den Broeck, Daniel Israel 5/15/2026

The Pitfalls of KV Cache Compression

Research identifying performance pitfalls of KV cache compression in LLMs under realistic multi-instruction prompting scenarios.

Ax Chanjoo Jung, Jaehyung Kim 5/15/2026

TiTok: Transfer Token-level Knowledge via Contrastive Excess to Transplant LoRA

Token-level knowledge transfer method enabling LoRA adaptation portability across different LLM backbones via contrastive learning.

Ax Yixiao Wang, Mingxiao Huo, Zhixuan Liang, Yushi Du, Lingfeng Sun, Haotian Lin, Jinghuan Shang, Chensheng Peng, Mohit Bansal, Mingyu Ding, Masayoshi Tomizuka 5/15/2026

VER: Vision Expert Transformer for Robot Learning via Foundation Distillation and Dynamic Routing

Vision Expert Transformer distilling multiple foundation models for flexible robot learning via dynamic routing and feature selection.

Ax Donghyeok Shin, Yeongmin Kim, Suhyeon Jo, Byeonghu Na, Il-Chul Moon 5/15/2026

AMiD: Knowledge Distillation for LLMs with $\alpha$-mixture Assistant Distribution

Knowledge distillation method for LLMs using alpha-mixture assistant distribution to reduce computational costs while maintaining performance.

Ax Zheng Huang, Enpei Zhang, Weikang Qiu, Yinghao Cai, Carl Yang, Elynn Chen, Xiang Zhang, Rex Ying, Dawei Zhou, Yujun Yan 5/15/2026

Seeing Through the Brain: New Insights from Decoding Visual Stimuli with fMRI

Research reconstructing visual stimuli from fMRI signals using latent space transformation and generative models.

Ax Hatim Chergui, Farhad Rezazadeh, Merouane Debbah, Christos Verikoukis 5/15/2026

A Tutorial on Cognitive Biases in Agentic AI-Driven 6G Autonomous Networks

Tutorial on cognitive biases in LLM-powered agentic AI for 6G autonomous networks using multimodal reasoning.

Ax Zishuo Xu, Dezhong Yao, Yao Wan 5/15/2026

From Ranking to Reasoning: Explainable Web API Recommendation via Semantic Reasoning

WAR-R1: explainable Web API recommendation system using semantic reasoning for mashup development.

Ax Davi Bastos Costa, Felippe Alves, Renato Vicente 5/15/2026

Moral Susceptibility and Robustness under Persona Role-Play in Large Language Models

Study of moral susceptibility and robustness in LLMs under persona role-play using Moral Foundations Questionnaire.

Ax Nikos Theodoridis, Tim Brophy, Reenu Mohandas, Ganesh Sistu, Fiachra Collins, Anthony Scanlan, Ciaran Eising 5/15/2026

Descriptor: Distance-Annotated Traffic Perception Question Answering (DTPQA)

DTPQA: benchmark for evaluating Vision-Language Models on traffic scene perception with distance annotations.

Ax Shanlin Zhou, Xinpeng Wang, Jianxun Lian, Zhenghao Liu, Laks V. S. Lakshmanan, Xiaoyuan Yi, Yongtao Hao 5/15/2026

Chinese Short-Form Creative Content Generation via Explanation-Oriented Multi-Objective Optimization

Multi-objective optimization framework for Chinese short-form creative content generation with explanation-driven verification.

Ax Kirill Nagaitsev, Luka Grbcic, Samuel Williams, Costin Iancu 5/15/2026

Optimizing PyTorch Inference with LLM-Based Multi-Agent Systems

Multi-agent LLM systems for PyTorch inference optimization, outperforming traditional compilers on GPU tuning.

Ax Kairong Luo, Zhenbo Sun, Haodong Wen, Xinyu Shi, Jiarui Cui, Chenyi Dang, Kaifeng Lyu, Wenguang Chen 5/15/2026

How Learning Rate Decay Wastes Your Best Data in Curriculum-Based LLM Pretraining

Research on curriculum-based LLM pretraining showing learning rate decay wastes high-quality training data.

Ax Nathan P. Lawrence, Ali Mesbah 5/15/2026

Why Goal-Conditioned Reinforcement Learning Works: Relation to Dual Control

Theoretical analysis of goal-conditioned reinforcement learning optimality gaps from optimal control perspective.

Ax Behrooz Tahmasebi, Melanie Weber 5/15/2026

Achieving Approximate Symmetry Is Exponentially Easier than Exact Symmetry

Theoretical analysis comparing exact versus approximate symmetry in ML models, showing approximate symmetry is computationally easier with empirical benefits.

Ax Xudong Ling, Chaorong Li, Tianxi Huang, Qian Dong, Guiduo Duan 5/15/2026

LangPrecip: Language-Aware Multimodal Precipitation Nowcasting

LangPrecip framework incorporates meteorological text as semantic constraints in multimodal precipitation nowcasting to improve spatiotemporal forecasting.

Ax Dikshya Mohanty, Mohammad Saqib Hasan, Syed Mostofa Monsur, Size Zheng, Benjamin Hsiao, Niranjan Balasubramanian 5/15/2026

Teaching and Evaluating LLMs to Reason About Polymer Design Related Tasks

PolyBench dataset and training approach teaches LLMs polymer design reasoning via domain-specific knowledge to overcome capability gaps in chemistry-related tasks.

Ax Yitian Chen, Cheng Cheng, Yinan Sun, Zi Ling, Dongdong Ge 5/15/2026

OPT-Engine: Benchmarking the Limits of LLMs in Optimization Modeling via Complexity Scaling

OPT-ENGINE benchmark evaluates LLM capabilities in optimization modeling across OR problems, systematically scaling complexity from linear to mixed-integer programming.

Ax Minghao Yang, Ren Togo, Guang Li, Takahiro Ogawa, Miki Haseyama 5/15/2026

L2R: Low-Rank and Lipschitz-Controlled Routing for Mixture-of-Experts

L2R proposes low-rank and Lipschitz-controlled routing for Mixture-of-Experts models to improve expert specialization and routing discrimination in conditional computation.

Ax Jathurshan Pradeepkumar, Zheng Chen, Jimeng Sun 5/15/2026

Neural Signals Generate Clinical Notes in the Wild

CELM foundation model for end-to-end clinical EEG report generation from long-duration variable-length EEG recordings.

Ax Jinju Park, Seokho Kang 5/15/2026

PaAno: Patch-Based Representation Learning for Time-Series Anomaly Detection

Lightweight patch-based representation learning method for time-series anomaly detection avoiding computational overhead of large models.

Ax Wenze Lin, Zhen Yang, Xitai Jiang, Xiaoteng Ma, Gao Huang 5/15/2026

Boosting LLM Reasoning via Human-Inspired Reward Shaping

Reinforcement learning approach for LLM reasoning using human-inspired reward shaping with distinct exploration and consolidation stages.

Ax Zuyao Xu, Yuqi Qiu, Lu Sun, Fasheng Miao, Fubin Wu, Xiang Li, Xinyi Wang, Haozhe Lu, Zhengze Zhang, Yuxin Hu, Jialu Li, Luo Jin, Feng Zhang, Rui Luo, Xinran Liu, Yingxian Li, Jiaji Liu 5/15/2026

GhostCite: A Large-Scale Analysis of Citation Validity in the Age of Large Language Models

Open-source framework and analysis quantifying fabricated citations in academic papers generated or assisted by LLMs.

Ax Zhiming Luo, Di Wang, Haonan Guo, Jing Zhang, Bo Du 5/15/2026

VLRS-Bench: A Vision-Language Reasoning Benchmark for Remote Sensing

Vision-language reasoning benchmark for remote sensing with 2,488 samples requiring complex reasoning beyond perception tasks.

Ax Jinzong Dong, Wei Huang, Jianshu Zhang, Zhuo Chen, Xinzhe Yuan, Qinying Gu, Zhaohui Jiang, Nanyang Ye 5/15/2026

Proximal Action Replacement for Behavior Cloning Actor-Critic in Offline Reinforcement Learning

Offline reinforcement learning method combining behavior cloning with actor-critic to address performance ceiling with suboptimal datasets.

Ax Jingkun Liu, Yisong Yue, Max Welling, Yue Song 5/15/2026

Krause Synchronization Transformers

Attention mechanism addressing representation collapse and attention sink phenomena through bounded confidence dynamics.

Ax Wenqian Chen, Yucheng Fu, Michael Penwarden, Pratanu Roy, Panos Stinis 5/15/2026

ArGEnT: Arbitrary Geometry-encoded Transformer for Operator Learning

Transformer architecture for learning solution operators on complex geometries with parametric physical settings.

Ax Gabriel Franco, Lucas M. Tassis, Azalea Rohr, Mark Crovella 5/15/2026

Finding Interpretable Prompt-Specific Circuits in Language Models

Improved circuit-tracing method ACC++ for identifying attention head mechanisms and interpretable circuits in language models.

Ax Mehrshad Taji, Arad Mahdinezhad Kashani, Iman Ahmadi, AmirHossein Jadidi, Saina Kashani, Babak Khalaj 5/15/2026

MALLVI: A Multi-Agent Framework for Integrated Generalized Robotics Manipulation

Multi-agent LLM and vision framework for closed-loop robotic manipulation with environmental feedback.

Ax Victoria Blake, Jamie Novak, Mathew Miller, Sze-yuan Ooi, Blanca Gallego 5/15/2026

CUICurate: A GraphRAG-based Framework for Automated Clinical Concept Curation for NLP applications

GraphRAG-based framework for automated curation of clinical concept sets from medical text for NLP applications.

Ax Tiantong Wang, Xinyu Yan, Tiantong Wu, Yurong Hao, Pengjun Xie, Wei Yang Bryan Lim 5/15/2026

MPU: Towards Secure and Privacy-Preserving Knowledge Unlearning for Large Language Models

Privacy-preserving unlearning framework for LLMs enabling knowledge removal without sharing server parameters or forget sets.

Ax Anthony Liang, Yigit Korkmaz, Jiahui Zhang, Minyoung Hwang, Abrar Anwar, Sidhant Kaushik, Aditya Shah, Alex S. Huang, Luke Zettlemoyer, Dieter Fox, Yu Xiang, Anqi Li, Andreea Bobu, Abhishek Gupta, Stephen Tu, Erdem Biyik, Jesse Zhang 5/15/2026

Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons

Scalable reward modeling framework for robots using trajectory comparisons instead of absolute progress labels.

Ax Hung Tran, Langston Nashold, Rayan Krishnan, Antoine Bigeard, Alex Gu 5/15/2026

Vibe Code Bench: Evaluating AI Models on End-to-End Web Application Development

Benchmark for evaluating AI code generation models on complete web application development tasks with 964 browser-based workflows.

Ax Alliot Nagle, Jakhongir Saydaliev, Dhia Garbaya, Michael Gastpar, Ashok Vardhan Makkuva, Hyeji Kim 5/15/2026

TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning

TERMINATOR learns optimal stopping points for chain-of-thought reasoning in LLMs to reduce computational waste from overthinking while maintaining answer quality.

Ax Vishnu Teja Kunde, Fatemeh Doudi, Mahdi Farahbakhsh, Dileep Kalathil, Krishna Narayanan, Jean-Francois Chamberland 5/15/2026

Reinforcement Learning for Diffusion LLMs with Entropy-Guided Step Selection and Stepwise Advantages

Reinforcement learning methods for diffusion language models using entropy-guided step selection and stepwise advantage estimation without surrogate likelihoods.

Ax Mayank Mishra, Shawn Tan, Ion Stoica, Joseph Gonzalez, Tri Dao 5/15/2026

M$^2$RNN: Non-Linear RNNs with Matrix-Valued States for Scalable Language Modeling

M²RNN architecture with matrix-valued hidden states enabling non-linear RNNs for language modeling tasks requiring higher complexity than Transformer TC⁰ class.

Ax Yu-Ning Qiu, Lin-Feng Zou, Jiong-Da Wang, Xue-Rong Yuan, Wang-Zhou Dai 5/15/2026

Procedural Refinement by LLM-driven Algorithmic Debugging for ARC-AGI-2

Abduction-based debugging approach for LLM refinement on abstract reasoning tasks, formally re-checking transformations instead of outcome-level observation.

Ax Ben Chen, Siyuan Wang, Yufei Ma, Zihan Liang, Xuxin Zhang, Yue Lv, Ying Yang, Huangyu Dai, Lingtao Mao, Tong Zhao, Zhipeng Qian, Xinyu Sun, Zhixin Zhai, Yang Zhao, Bochao Liu, Jingshan Lv, Xiao Liang, Hui Kong, Jing Chen, Han Li, Chenyi Lei, Wenwu Ou, Kun Gai 5/15/2026

OneSearch-V2: The Latent Reasoning Enhanced Self-distillation Generative Search Framework

OneSearch-V2 generative retrieval framework using latent reasoning and self-distillation for improved complex query understanding in industrial search systems.

Ax Surada Suwansathit, Yuxuan Zhang, Guofei Gu 5/15/2026

A Security Analysis of the OpenClaw AI Agent Framework

Systematic security analysis of OpenClaw AI agent framework, cataloging 470 vulnerabilities across architectural layers in LLM-based agent runtimes.

Ax Junyu Guo, Shangding Gu, Ming Jin, Costas Spanos, Javad Lavaei 5/15/2026

LLMs Should Express Uncertainty Explicitly

Studies post-training methods to make LLMs explicitly signal uncertainty in their responses, reducing confident yet incorrect outputs in real-world applications.

Ax Zhiyu Zhou, Peilin Liu, Ruoxuan Zhang, Luyang Zhang, Cheng Zhang, Hongxia Xie, Wen-Huang Cheng 5/15/2026

PinpointQA: A Dataset and Benchmark for Small Object-Centric Spatial Understanding in Indoor Videos

PinpointQA dataset and benchmark for evaluating multimodal LLMs on small object localization and spatial reasoning in indoor videos.

Ax Xinyi Hu, Yuhao Shen, Baolin Zhang, Hengxin Zhang, Jun Dai, Shuang Ge, Lei Chen, Yue Li, Mingcheng Wan 5/15/2026

ECHO: Elastic Speculative Decoding with Sparse Gating for High-Concurrency Scenarios

ECHO framework for speculative decoding in LLM inference with dynamic sparse gating, optimized for high-concurrency production serving scenarios.

Ax Xuning Yang, Rishit Dagli, Alex Zook, Hugo Hadfield, Ankit Goyal, Stan Birchfield, Fabio Ramos, Jonathan Tremblay 5/15/2026

RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies

RoboLab simulation benchmark for evaluating task generalist robotic policies with reduced domain overlap between training and evaluation to test true generalization.