Ax Qiheng Sun, Hongwei Zhang, Junxu Liu, Xiaokai Mao, Jinfei Liu, Kui Ren, Haibo Hu 7/13/2026

DaDaDa: A Dataset for Data Pricing in Data Marketplaces

Dataset for studying data pricing mechanisms in data marketplaces, addressing valuation challenges for data products.

Ax Tao Lu, Haoyu Wang, Zonghui Wang, Keshen Xiang, Jiaheng Zhang, Wenzhi Chen 7/13/2026

Accelerating GPU Inference of Large Language Models with Moderately Unstructured Sparse Weight Matrices

GPU kernel optimization for LLM inference acceleration using moderately sparse weight matrices, addressing performance gaps in sparse matrix multiplication.

Ax Sunshine Jiang, John Marangola, David Zhang, Raghuram Kowdeed, Ruiyang Luo, Nitish Dashora, Richard Li, Pulkit Agrawal, Zhang-Wei Hong 7/13/2026

Prompt-Driven Exploration

Method using LLMs and vision-language-action models to improve exploration in reinforcement learning by generating diverse policy perturbations via natural language prompts.

Ax William W. Yang, Andrew M. Saxe, Peter E. Latham 7/13/2026

How are linear representations learned? Exact solutions to the dynamics of abstraction

Research on how linear representations emerge during neural network training, foundational for interpretability methods like linear probes and activation steering.

Ax Ege \c{C}akar, Hannah Guan, Kayden Kehe 7/13/2026

Optimizing Against Safety Representations: Activation-Guided Adversarial Suffixes and the Geometry of Refusal

Study of adversarial attacks on LLM safety representations via activation-guided optimization and refusal geometry.

Ax Minett Tran, Taehee Jeong 7/13/2026

Pattern-Aware Graph Neural Networks for Handling Missing Data

GNN approach that encodes missing data patterns alongside values for handling incomplete datasets.

Ax Yuanjie Zhu, Liangwei Yang, Ke Xu, Weizhi Zhang, Shanghao Li, Zihe Song, Philip S. Yu 7/13/2026

BlockServe: Block-Grained Continuous Batching for High-Throughput Diffusion LLM Serving

Continuous batching framework for efficient diffusion LLM serving with block-grained scheduling to reduce latency.

Ax Fangxu Yu, Tao Feng, Dehai Min, Lu Cheng, Ge Liu, Tianyi Zhou 7/13/2026

TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning

Dynamic routing system selecting between LLMs and VLMs for time series reasoning based on modality characteristics.

Ax Nick Souligne, Isabella Mixton-Garcia, Vignesh Subbian 7/13/2026

FairSelect: A Systematic Evaluation of Multi-Level and Intersectional Algorithmic Fairness

Toolkit for systematic evaluation of algorithmic fairness across intersectional subgroups and modeling lifecycle stages.

Ax Ning Liu, Kalle Kujanp\"a\"a, Zhaoxuan Zhu, P Aditya Sreekar, Kaiwen Liu, Chuanneng Sun, Jorge Marchena Menendez, Matthew Bales, Tianyu Yang, Shahnawaz Alam, Rose Yu, Baoyuan Liu, Kristina Klinkner, Shervin Malmasi 7/13/2026

Eluna: An Agentic LLM System for Automating Warehouse Operations with Reasoning and Task Execution

Production-deployed agentic LLM system for warehouse operations using graph-guided multi-agent framework for SOP execution.

Ax Berkay Anahtarci 7/13/2026

NL-PAC: Specification Ambiguity and Certified Minimax Risk Floors in LLM-Mediated Supervision

Framework for handling specification ambiguity in LLM-based labeling with certified minimax risk bounds.

Ax Bishmoy Paul, Youngmin Yi, Hoeseok Yang 7/13/2026

Sensitivity-Aware Thresholding and Token Routing for Activation Sparsification in Large Language Models

Method for efficient LLM inference via MLP activation sparsification and token routing using sensitivity-aware thresholding.

Ax Ajay Narayanan Sridhar, Ronak Singh, Mehrdad Mahdavi, Vijaykrishnan Narayanan 7/13/2026

Correlation-Aware Contextual Bandits with Surrogate Rewards for LLM Routing

Contextual bandit algorithm with correlated arms for LLM routing using surrogate reward signals from learned models.

Ax Chaoran Cheng, Zhanghan Ni, Yanru Qu, Yuxin Chen, Ruihan Guo, Jiajun Fan, Ge Liu 7/13/2026

Variable-Length Generative Protein Design via Generalized Poisson Flow

Introduces Generalized Poisson Flow for variable-length protein generation without requiring pre-specified length via flow-based models.

Ax Iris Xu, Sunshine Jiang, John Marangola, Nitish Dashora, Richard Li, Thomas Liu, Zexue He, Yuheng Zhi, Alex Pentland, Pulkit Agrawal, Zhang-Wei Hong 7/13/2026

Learning More from Less: Reinforcement Learning from Hindsight

Improves sample efficiency in vision-language-action model RL post-training by learning from hindsight on sparse-reward manipulation tasks.

Ax Alexander Tian, Aditya Ghai, Sanjit Neelam, Zaal Vasania, Akshay Mishra 7/13/2026

COBS: Cumulant Order Block Sparse Attention

Analyzes block sparse attention in LLMs as KV cache optimization, studying DeepSeek's Native Sparse Attention block selection mechanism.

Ax Shuo Huai, Hao Kong, Shiqing Li, Xiangzhong Luo, Ravi Subramaniam, Christian Makaya, Qian Lin, Weichen Liu 7/13/2026

EvoLP: Self-Evolving Latency Predictor for Model Compression in Real-Time Edge Systems

EvoLP framework for predicting neural network inference latency on edge devices to optimize model compression for real-time deployment.

Ax Carl Hvarfner, Sam Daulton, Max Balandat, Eytan Bakshy 7/13/2026

Pitfalls and Remedies for Multi-Task Bayesian Optimization

Identifies pitfalls in multi-task Bayesian optimization with Gaussian processes and proposes remedies for cross-task correlation estimation.

Ax Linhui Xiao, Guiping Cao, Mingyue Guo, Xianchao Guan, Fan Yang, Ming Tao, Xin Li, Yuxin Peng, Yaowei Wang 7/13/2026

A Survey on the Green Development of Large Models: From Resource-Efficient Architectures to Hardware-Software Co-Design

Comprehensive survey on resource-efficient large model architectures and hardware-software co-design for sustainability and computational efficiency.

Ax Xu Liu, Kai Wan, Zihao Lu 7/13/2026

EXHOLD: Experience-Aware Real-Time Hold Control for Large-Scale Ride-Hailing Matching at DiDi

Industrial hold control system for ride-hailing using experience-aware optimization to reduce cancellations and improve matching.

Ax Lucas Pinto 7/13/2026

Present but Rescaled: Chat-to-Agent Transfer of Additive Activation Steering

Studies transfer of additive activation steering from chat to ReAct agent deployment in LLMs with behavioral measurement and representation analysis.

Ax Jiseok Chae, Donghwan Kim 7/13/2026

Understanding Schedule-Free Methods in Nonconvex Optimization: Rate Guarantees and Escaping Saddles

Provides convergence theory and worst-case analysis for schedule-free optimization methods in nonconvex settings without manual learning rate tuning.

Ax Julius St\"ork 7/13/2026

Interference and Retention in Continual Learning

Studies task interference and forgetting in continual learning through interference energy and path-averaged curvature in deep networks.

Ax Konrad \"Ozdemir, Julia Gastinger, Lukas Kirchdorfer, Heiner Stuckenschmidt 7/13/2026

Temporal Knowledge Graph Forecasting under Distribution Shifts: A Synthetic Evaluation

Evaluates temporal knowledge graph forecasting models under distribution shifts using synthetic data generation to test robustness.

Ax Jayadeva, Madhur Aswani 7/13/2026

All you need is SAMPAT

SAMPAT: three-layer interpretable neural architecture using multivariate polynomials for scientific data analysis with provable continuous function learning.

Ax Amit Peleg, Naman Deep Singh, Naama Pearl, Bibhabasu Mohapatra, Matthias Hein 7/13/2026

Forget Narrowly, Retain Broadly: Unlearning as an Asymmetric Generalization Problem

Machine unlearning in LLMs with improved evaluation metrics detecting under-forgetting through paraphrasing and over-forgetting through semantic probes.

Ax Kris Atallah (New York University, New York, USA) 7/13/2026

LionVote: Per-Layer Learning Rate Adaptation for Lion

Per-layer learning rate adaptation mechanism for Lion optimizer addressing 2.6-2.8x scaling disparity across attention, MLP, and normalization layers.

Ax Federico Ottomano, Gaopeng Ren, Yingzhen Li, Kim E. Jelfs, Alex M. Ganose 7/13/2026

Autoregressive latent diffusion for 3D molecule generation

Autoregressive latent diffusion approach for 3D molecule generation supporting variable-length generation and partial context conditioning.

Ax Ivan Ilin, Philip Zmushko, Peter Richt\'arik 7/13/2026

Super-Tuning: From Activation-Aware Pruning to Sparse Fine-Tuning

Super: sparse parameter-efficient fine-tuning method for LLMs using pruning saliency signals to select trainable parameters, reducing memory and storage.

Ax Pedro P. Santos, F\'abio Vital, Alberto Sardinha, Francisco S. Melo 7/13/2026

Risk-Aware General-Utility Markov Decision Processes

Risk-aware Markov Decision Processes framework enabling agents to optimize risk measures of objective value distributions while trading off expected performance.

Ax Guanquan Wang, Yoshimasa Tsuruoka 7/13/2026

Shortcut Trajectory Planning for Efficient Offline Reinforcement Learning

Shortcut Trajectory Planning: consistency-based offline RL planner reducing iterative denoising cost without two-stage distillation pipeline.

Ax Samra Sana, Giorgio Mantica, Saul Imbrici 7/13/2026

Graph Neural Networks for Scalable and Transferable Node Centrality Approximation

Graph Neural Networks for scalable approximation of betweenness and closeness centrality, studying transferability across different graphs.

Ax Foundation Model Team 7/13/2026

Mach-Mind-4-Flash Technical Report

Mach-Mind-4-Flash: 35B-parameter Mixture-of-Experts agentic model with 3B activated parameters achieving 100B-class performance through post-training and agentic RL.

Ax Rodolphe Barlogis, Ferhat Tamssaouet, Quentin Falcoz, St\'ephane Grieu 7/13/2026

Learning Physics-Informed Surrogate Model of Linear Elastic Displacement Fields from Geometry

Physics-informed DeepONet surrogate model for predicting elastic displacement fields in fractured domains without finite-element training data.

Ax Wout Mommen, Lars Keuninckx, Matthias Hartmann, Werner Van Leekwijck, Piet Wambacq 7/13/2026

Fully Trainable Deep Differentiable Logic Gate Networks and Lookup Table Networks

Novel training method for optimizing connections and gate types in deep differentiable logic gate networks and lookup table networks using probabilistic selection.

Ax Avik Bhatnagar, Anton Paule, Tobias Schuermann, Sebastian Reiter, Oliver Bringmann 7/13/2026

On-Device Adaptive Battery Power Prediction for Electric Vehicles

On-device adaptive learning approach for battery power prediction in electric vehicles using continuous fine-tuning under distribution shift.

Ax Ofir Kruzel, Itzik Klien 7/13/2026

Data-Efficient Deep Learning: Empirical Guidelines for Training Set Size Estimation in Inertial Sensor Classification

Empirical guidelines for determining minimum training set size for deep learning models in inertial sensor classification tasks like activity recognition.

Ax Nicolai Dinh Khang Truong, Richard R\"ottger 7/13/2026

SYNRARE: Synthetic Rare Disease EHR Generation for ML Benchmarking

Synthetic data generation method for creating electronic health records of rare diseases to address privacy concerns in ML-based diagnosis research.

Ax Nick Whiteley 7/13/2026

Similarity search generalisation in contrastive learning with InfoNCE loss

Theoretical analysis of contrastive learning with InfoNCE loss, proving population risk converges as O(1/k) with k negative samples for similarity search.

Ax Edwin De Nicolo, Rahul Marchand, Cornelius Carlsson, Pranav Vaidhyanathan, Natalia Ares 7/13/2026

Action-Factored Multi-Agent Reinforcement Learning for Scalable Quantum Device Tuning

Multi-agent reinforcement learning approach using factored action representation for tuning quantum-dot arrays with exploitable local structure.

Ax Bruno Abrahao 7/13/2026

Neural Collapse Is Forbidden: Information Floors in Language Models

Research on within-class variance in language model representations, arguing it represents allocated information storage rather than incomplete neural collapse across 14 models.

Ax Pan Li 7/13/2026

All Explanations are Wrong, But Many Are Useful: Exploring the Rashomon Explanation Set with Large Language Models

Explores Rashomon explanation sets using LLMs to generate multiple valid model explanations, decoupling explanation from prediction as complementary objectives.

Ax Refat Ishrak Hemel, Ehsan Hallaji, Roozbeh Razavi-Far 7/13/2026

TSAI-MetaFraud: A Benchmark Dataset for Financial Fraud Transaction and Behavioral Risk Detection in Metaverse Ecosystems

TSAI-MetaFraud benchmark dataset for multimodal fraud and behavioral risk detection in metaverse virtual economies.

Ax Qitai Tan, Ruiwen Gu, Yilin Su, Mo Li, Xu Lin, Xiao-Ping Zhang 7/13/2026

GatedLinear: Adaptive Routing of Complementary Linear Bases for Time Series Forecasting

GatedLinear implements adaptive routing across complementary linear basis functions for time series forecasting, addressing diverse temporal dynamics.

Ax Gabriel Mahuas, Victoria Shevchenko, Ugo Tanielian, Yassir Bendou, Richard Gao 7/13/2026

CoCoT-EEG: Contrastive-Pretrained Multiscale Convolutional Transformer for EEG Decoding

CoCoT-EEG uses contrastive pretraining with multiscale convolutional transformers for improved EEG signal decoding, replacing masked reconstruction approaches.

Ax Cl\'audio L\'ucio do Val Lopes, Lucca Machado da Silva 7/13/2026

Semantic Pareto-DQN: A Multi-Objective Reinforcement Learning Framework for Financial Anomaly Detection

Semantic Pareto-DQN applies multi-objective reinforcement learning to financial fraud detection, addressing class imbalance without data resampling.

Ax Shilin Ou, Yifan Xu, Luyao Zhang 7/13/2026

SolarChain-Eval: A Physics-Constrained Benchmark for Trustworthy Economic Agents in Decentralized Energy Markets

SolarChain-Eval is a physics-constrained benchmark for evaluating trustworthiness and performance of autonomous agents in decentralized energy markets.

Ax Merkouris Papamichail, Konstantinos Varsos, Giorgos Flouris, Jo\~ao Marques-Silva 7/13/2026

Interval Certifications for Multilayered Perceptrons via Lattice Traversal

Theoretical framework reducing adversarial robustness verification to lattice traversal problems for multilayer perceptrons, advancing AI safety certification methods.

Ax Micah Zhang 7/13/2026

HALO: Hybrid Adaptive Latent Reasoning for Language Models

HALO adds adaptive latent refinement layers to frozen pretrained language models, enabling selective extra computation for improved transfer learning efficiency.

Ax Joshua Pickard, Wei Qi, Na Li, Ann Woolley, Lisa Cosimi, Roy Kishony, Deborah Hung 7/13/2026

EHR-MPC: Inference-Time Control for Sepsis Treatment with Generative Patient Digital Twins

EHR-MPC framework uses generative patient digital twins for inference-time adaptive sepsis treatment optimization, decoupling dynamics learning from policy optimization.