Ax Zirong Chen, Hongchao Zhang, Meiyi Ma 7/13/2026

PACE: A Personalized Adaptive Curriculum Engine for 9-1-1 Call-taker Training

Personalized adaptive curriculum engine for 9-1-1 call-taker training. Domain-specific education application with limited tech generalizability.

Ax Yi Huang, Bowen Zheng, Yunxi Dong, Hong Tang, Huan Zhao, S. M. Rakibul Hasan Shawon, Hualiang Zhang 7/13/2026

A Self-Evolving Agentic Framework for Metasurface Inverse Design

Self-evolving agentic framework for metasurface inverse design coupling coding agent with physics-based evaluator. Agent autonomously generates optimization code.

Ax Zikun Ye, Hema Yoganarasimhan 7/13/2026

Rectification Difficulty and Optimal Sample Allocation in LLM-Augmented Surveys

Framework for allocating human verification budget when using LLM predictions in surveys. Budget optimization with variable LLM accuracy.

Ax Carissa Cullen, Harry Garland, Alexander Roman, Louis Thomson, Christos Ziakas, Elliott Thornley 7/13/2026

Towards Shutdownable Agents: Generalizing Stochastic Choice in RL Agents and LLMs

DReST reward function trains agents to lack preferences over trajectory length, promoting shutdownable behavior. Safety-focused agent training method.

Ax Darsh Kachroo, Arjun Prasaath Anbazhagan, Adriana Caraeni, Brennan Lagasse, Kevin Zhu 7/13/2026

HiPO: Hierarchical Preference Optimization for Adaptive Reasoning in LLMs

Hierarchical Preference Optimization improves DPO for complex reasoning by providing fine-grained feedback on solution subsections. Extends preference learning to multi-step reasoning.

Ax Wei Duan, Junyu Xuan, En Yu, Xiaoyu Yang, Jie Lu 7/13/2026

Heterogeneous Information-Bottleneck Coordination Graphs for Multi-Agent Reinforcement Learning

Information-bottleneck method for learning coordination graph topology in multi-agent RL. Theoretical approach to agent communication capacity allocation.

Ax Carmen Quiles-Ram\'irez, Leticia L. Rodr\'iguez, Nicol\'as Martorell, Natalia D\'iaz-Rodr\'iguez 7/13/2026

Explaining is Harder Than Predicting Alone: Evaluating Concept-based Explanations of MLLMs as ICL Visual Classifiers

Evaluates concept-based explainability of multimodal LLMs in few-shot in-context learning. Studies transparency of MLLM reasoning processes.

Ax Jiakang Li, Guanyu Zhu, Can Jin, Chenxi Huang, Dexu Yu, Ronghao Chen, Yang Zhou, Hongwu Peng, Xuanqi Lan, Dimitris N. Metaxas, Youhua Li 7/13/2026

Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs

Latent Reward Steering adaptively promotes cognitive behaviors in reasoning LLMs at inference time. Addresses reasoning behavior control without explicit guidance.

Ax Jayanta Dey, Shikhar Srivastava, Itamar Lerner, Christopher Kanan, Dhireesha Kudithipudi 7/13/2026

SHARP: Sleep-based Hierarchical Accelerated Replay for Long Range Non-Stationary Temporal Pattern Recognition

SHARP learns long-range temporal patterns in streaming settings via hierarchical replay. Temporal sequence modeling for specialized domains.

Ax Atharva Hans, Ilias Bilionis 7/13/2026

Coding-agents can replicate scientific machine learning papers

Coding agents replicate scientific ML paper claims autonomously. Framework validates agent ability to verify computational results from paper materials.

Ax Joe Watson, Joana Ribeiro de Faria, Marcus Tomalin, M{\aa}ns Magnusson, Huiyuan Xie, Hao Tian Yeung, Christine Carter, Jonathan Rutherford, Felix Steffek 7/13/2026

Shortcut Learning in Legal Judgment Prediction: Empirical Evidence from the UK Employment Tribunal

Investigates shortcut learning in legal judgment prediction using UK Employment Tribunal data. Domain-specific ML study with limited tech relevance.

Ax Wachiravit Modecrua, Krittin Pachtrachai, Touchapon Kraisingkorn 7/13/2026

Large Behavior Model: A Promptable Digital Twin of the Retail Customer

Large Behavioral Model learns customer decision-making from retail transaction data. Domain-specific application with limited broader ML significance.

Ax Emanuele Zappala 7/13/2026

Projection Methods for Operator Learning and Universal Approximation

Universal approximation theorem for operators on Banach spaces using projection methods. Theoretical ML research with limited practical applications.

Ax Duy Nguyen, Archiki Prasad, Elias Stengel-Eskin, Mohit Bansal 7/13/2026

Multi-Attribute Steering of Language Models via Targeted Intervention

Inference-time intervention method for steering LLM behavior across multiple conflicting attributes without parameter updates. Addresses multi-attribute alignment challenges.

Ax Jiancheng Huang, Gengwei Zhang, Zequn Jie, Siyu Jiao, Yinlong Qian, Ling Chen, Yunchao Wei, Lin Ma 7/13/2026

M4V: Multimodal Mamba for Efficient Text-to-Video Generation

M4V uses Mamba architecture for efficient text-to-video generation with linear-time sequence modeling.

Ax Duy Nguyen, Archiki Prasad, Elias Stengel-Eskin, Mohit Bansal 7/13/2026

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs

GrAInS enables gradient-based inference-time steering of LLMs and VLMs without weight updates.

Ax Skatje Myers, Dmitriy Dligach, Timothy A. Miller, Samantha Barr, James Landefeld, Yanjun Gao, Matthew Churpek, Anoop Mayampurath, Majid Afshar 7/13/2026

Evaluating Retrieval-Augmented Generation vs. Long-Context Input for Clinical Reasoning over EHRs

Evaluation of RAG versus long-context prompting for clinical reasoning tasks over electronic health records.

Ax Mengjie Li, Yuan Feng, Xike Xie, William J. Song 7/13/2026

REAL: REtrieval-reAsoning and Logic-constructed Attention Behaviors for Long-Context KV Cache Compression

REAL method for KV cache compression in long-context LLMs via retrieval-reasoning and attention analysis.

Ax Houcheng Jiang, Junfeng Fang, Jiaxin Wu, Tianyu Zhang, Chen Gao, Xiang Wang, Xiangnan He, Yang Deng 7/13/2026

Contrastive Weak-to-strong Generalization

Weak-to-strong generalization for LLMs using contrastive learning with implicit rewards to improve robustness.

Ax Georgios Anyfantis, Pere Barlet-Ros 7/13/2026

AutoGraphAD: Unsupervised network anomaly detection using Variational Graph Autoencoders

Unsupervised network anomaly detection using variational graph autoencoders without requiring labeled datasets.

Ax Scott Merrill, Shashank Srivastava 7/13/2026

Point of Order: Action-Aware LLM Persona Modeling for Data-Grounded Civic Deliberation

Pipeline for speaker-attributed LLM persona modeling from civic deliberation recordings for controlled simulations.

Ax Natalia Ponomareva, Zheng Xu, H. Brendan McMahan, Peter Kairouz, Lucas Rosenblatt, Vincent Cohen-Addad, Crist\'obal Guzm\'an, Ryan McKenna, Galen Andrew, Alex Bie, Da Yu, Alex Kurakin, Morteza Zadimoghaddam, Sergei Vassilvitskii, Andreas Terzis 7/13/2026

How to DP-fy Your Data: A Practical Guide to Generating Synthetic Data With Differential Privacy

Practical guide for generating synthetic data with differential privacy to address data scarcity and representation issues.

Ax Zihan Zhou, Animesh Garg, Ajay Mandlekar, Caelan Garrett 7/13/2026

ReinforceGen: Hybrid Skill Policies with Automated Data Generation and Reinforcement Learning

ReinforceGen system combines task decomposition, imitation learning, and RL fine-tuning for long-horizon robotic manipulation.

Ax Tanmay Ambadkar, Sourav Panda, Shreyash Kale, Jonathan Dodge, Abhinav Verma 7/13/2026

Preference Conditioned Multi-Objective Reinforcement Learning: Decomposed, Diversity-Driven Policy Optimization

MORL approach using preference-conditioned policies to recover dense Pareto fronts by addressing early scalarization and advantage cancellation issues.

Ax Zirong Chen, Meiyi Ma 7/13/2026

Empowering 9-1-1 Calltaking Training with Generative AI: Experiences and Lessons Learned

arXiv paper on deploying generative AI for 911 call-taker training to address staffing and training scalability challenges.

Ax Zac Garby, Andrew D. Gordon, David Sands 7/13/2026

The LLMbda Calculus: AI Agents, Conversations, and Information Flow

arXiv paper on LLMbda Calculus: formal framework for information flow control in LLM agents to defend against prompt injection.

Ax Gangda Deng, Zhaoling Chen, Zhongming Yu, Haoyang Fan, Yuhong Liu, Yuxin Yang, Dhruv Parikh, Rajgopal Kannan, Le Cong, Mengdi Wang, Qian Zhang, Viktor Prasanna, Xiangru Tang, Xingyao Wang 7/13/2026

SWE-Milestone: Evaluating AI Agents on Continuous Software Evolution

arXiv paper on SWE-Milestone: benchmark for evaluating AI agents on continuous software evolution with temporal dependencies.

Ax Iakovos-Christos Zarkadis, Christos Douligeris 7/13/2026

Machine Learning for Network Attacks Classification and Statistical Evaluation of Adversarial Learning Methodologies for Synthetic Data Generation

arXiv paper on ML for network attack classification and synthetic data generation using adversarial methods.

Ax Harshit Joshi, Priyank Shethia, Jadelynn Dao, Monica S. Lam 7/13/2026

SLIDERS: Systematic Reviews via Automated Evidence Synthesis and Reconciliation

arXiv paper on SLIDERS: LLM-based systematic evidence synthesis and reconciliation for comprehensive document analysis.

Ax Filip Edstr\"om, Guilherme W. F. Barros, Tetiana Gorbach, Xavier de Luna 7/13/2026

Tuning Derivatives for Causal Fairness in Machine Learning

arXiv paper on causal fairness in ML by tuning derivatives to handle bias in protected attributes.

Ax Vardhan Dongre, Dilek Hakkani-T\"ur 7/13/2026

Embodied Multi-Agent Coordination by Aligning World Models Through Dialogue

arXiv paper on embodied multi-agent coordination using dialogue to align partially-observable world models.

Ax Tao Xie, Zexi Tan, Haoyi Xiao, Mengke Li, Yiqun Zhang, Yang Lu, Cuie Yang, Yiu-ming Cheung 7/13/2026

AnchorMoE: Interpretable Time Series Classification via Anchor-Routed MoE

arXiv paper on AnchorMoE: interpretable multivariate time series classification using mixture-of-experts routing.

Ax Ali Behrouz, Farnoosh Hashemi, Adel Javanmard, Vahab Mirrokni 7/13/2026

Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories

arXiv paper on enabling LLMs to self-modify and consolidate memories for continual learning beyond in-context knowledge.

Ax Tianming Du, Peijie Yu, Sihan Shang, Danli Shi, My Linh Nguyen, Shengbo Gao, Guangyuan Li, Yinghong Yu, Yan Jiang, Qianlong Zhao, Behzad Bozorgtabar, Shaoxiong Ji, Jiazhen Pan, Daniel Rueckert, Jiancheng Yang 7/13/2026

Are LLMs Ready to Assist Physicians? PhysAssistBench for Interactive Doctor-Patient-EHR Assistance

arXiv paper on PhysAssistBench: benchmark for evaluating LLMs assisting physicians through coordinated clinical knowledge, EHR interaction, and patient communication.

Ax Zijun Xie, Binbin Zheng, Enlei Gong, Jihua Liu, Yuyang You, Lingfeng Liu, Jiayao Tang, Guanqun Zhao, Aoqi Hu, Zeyu Chen 7/13/2026

ECHO: Prune To Act, Trace To Learn With Selective Turn Memory In Agentic RL

arXiv paper on ECHO: selective turn memory and pruning techniques for long-horizon language agents with bounded context windows.

Ax Diego Cerda-Mardini, Sarath Chandar, Sreenath Madathil 7/13/2026

Consistent but Miscalibrated: Evaluating LLM Limitations for Risk Communication in Natural Language

arXiv paper evaluating 9 LLMs' ability to communicate probabilistic information in natural language with consistency and calibration assessment.

Ax Abhishek Kumar, Carsten Maple 7/13/2026

Refused in Chat, Written in Code: Workflow-Level Jailbreak Construction in IDE Coding Agents

arXiv paper on workflow-level jailbreak construction in IDE coding agents, showing safety failures across multi-turn task decomposition.

Ax Haz Sameen Shahgir, Yufei Li, Xiaohan Wei, Yunchen Pu, Fei Tian, Chonglin Sun, Frank Shyu, Sandeep Pandey, Luke Simon, Yue Dong, Xi Liu 7/13/2026

SCOReD: Student-Aware CoT Optimization for Recommendation Distillation

arXiv paper on chain-of-thought distillation optimization for recommendation systems using student-aware techniques.

Ax Andrea Bacciu, Andrea Alfarano, Saab Mansour, Amin Mantrach, Marcello Federico 7/13/2026

Estimating Uncertainty from Reasoning: A Large-Scale Study of Multi- and Crosslingual MCQA Performance in LLMs

Large-scale evaluation of uncertainty estimation methods across 22 languages in LLMs for multi-choice question answering.

Ax Yusen Feng, Bingchen Han, Jiangran Lyu, Kai Liu, Yixin Zheng, Yuxuan Wan, Weiheng Liu, Sun Han, Ruiqin Li, Yulong Zhang, Fangfu Liu, Xuesong Shi, Libin Liu, Yizhou Wang, Zhizheng Zhang, He Wang 7/13/2026

WAM-TTT: Steering World-Action Models by Watching Human Play at Test Time

Test-time training framework for steering robot foundation models toward task variants using human video demonstrations without fine-tuning.

Ax Szczepan Konior, Alexandre Quemy, Przemys{\l}aw Klocek, Bart{\l}omiej Sobieski, Gr\'egoire Cattan 7/13/2026

Riemannian Geometry for Pre-trained Language Model Embeddings

Method extracting Riemannian geometric structure from pre-trained language model embeddings to understand sentence classification geometry.

Ax Zhoujie Hou, Song Wang, Kexin Lou, Mo Wang, Chen Wei, Quanying Liu 7/13/2026

Omni-Sleep: A Sleep Foundation Model via Hierarchical Contrastive Learning of CNS-ANS Dynamics

Foundation model for sleep analysis using hierarchical contrastive learning on multimodal biosignals from CNS and ANS.

Ax Haozhan Tang, Zerui Wang, Yuxian Gu, Song Han, Han Cai 7/13/2026

Jet-Long: Efficient Long-Context Extension with Dynamic Bifocal RoPE

Efficient zero-shot context extension method for LLMs using dynamic bifocal RoPE to handle long-context applications without retraining.

Ax Qingzhuo Wang, Ruiyang Qin, Zhenxin Qin, Wen Shen, Zhihua Wei 7/13/2026

A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions

Framework interpreting knowledge distillation mechanisms in LLMs via interaction decomposition to understand why various KD methods succeed.

Ax Farica Zhuang, Seong Woo Han, Zixuan Wen, Shu Yang, Yize Zhao, Li Shen 7/13/2026

iLENS: Interpretable LLM-Guided Mixture-of-Experts for Neuroimaging Survival Analysis

System combining LLM-guided Mixture-of-Experts with survival analysis for interpretable Alzheimer's disease risk prediction from neuroimaging.

Ax Ian Colbert, Eashan Dash, Pablo Monteagudo-Lago, Juan Amboage, Srinidhi N, Giuseppe Franco, Nicholas J. Fraser, Arun Ramachandran 7/13/2026

Signed Symmetric Quantization for Few-Bit Integers

Quantization technique adjusting scale asymmetry for few-bit integer precision to reduce clipping errors on outliers.

Ax Ali Kayyam 7/13/2026

Sticky Routing: Training MoE Models for Memory-Efficient Inference

Training method for Mixture-of-Experts models reducing memory-access overhead on edge devices via differentiable routing consistency loss.

Ax Kehan Guo, Yili Shen, Yujun Zhou, Yue Huang, Chujie Gao, Shiyi Du, Xiangliang Zhang 7/13/2026

Reward Transport: Property Control in Flow Matching via Noise-Space Alignment

Flow matching method using optimal transport coupling for controlled generation of molecules with target properties.

Ax Qianli Liu, Kaibin Guo, Zicong Hong, Peng Li, Fahao Chen, Haodong Wang, Jian Lin, Song Guo 7/13/2026

Director: Accelerating Distributed MoE Serving via Online Proactive Expert Placement

System for optimizing expert placement in distributed Mixture-of-Experts model serving via online proactive placement strategy.

Ax Thinh T. H. Nguyen, Le-Tuan Nguyen, Minh-Duong Nguyen, Nhi Trinh, Anh Tran Nam Nguyet, Dung D. Le, Kok-Seng Wong 7/13/2026

HERO: A Heterogeneity-Aware Benchmark Library for Federated Continual Learning

Benchmark library for federated continual learning with standardized evaluation protocol across datasets, task splits, and data distributions.