Ax Ichiro Hashimoto, Stanislav Volgushev, Piotr Zwiernik 7/8/2026

Universality of Benign Overfitting in Binary Linear Classification

Theoretical study of benign overfitting in over-parametrized binary linear classification models.

Ax Marthe Ballon, Andres Algaba, Vincent Ginis 7/8/2026

The relationship between reasoning and performance in large language models--o3 (mini) thinks harder, not longer

Analysis of o3 reasoning efficiency: improved LLM performance from better reasoning rather than longer chains.

Ax Will Schwarzer, Jordan Schneider, Philip S. Thomas, Scott Niekum 7/8/2026

Supervised Reward Inference

Supervised reward inference approach handling diverse human behaviors for goal inference.

Ax Nikola Zubi\'c, Davide Scaramuzza 7/8/2026

Regularity and Stability Properties of Selective SSMs with Discontinuous Gating

Theoretical analysis of selective SSMs like Mamba through passivity and stability properties with token-dependent gating.

Ax Christiaan Meijer, E. G. Patrick Bos 7/8/2026

Explainable embeddings with Distance Explainer

Distance Explainer method for post-hoc interpretability of embedded vector spaces in ML models.

Ax Batuhan Koyuncu, Rachael DeVries, Ole Winther, Isabel Valera 7/8/2026

Temporal Variational Implicit Neural Representations

TV-INRs probabilistic framework combining implicit neural representations with latent variables for time series.

Ax Lorenzo Steccanella, Joshua B. Evans, \"Ozg\"ur \c{S}im\c{s}ek, Anders Jonsson 7/8/2026

Learning The Minimum Action Distance

Learning minimum action distance as state representation metric from trajectories without rewards or actions.

Ax Yuli Slavutsky, Ozgur Beker, David Blei, Bianca Dumitrascu 7/8/2026

Variational Learning of Disentangled Representations

Variational framework for learning disentangled representations that separate shared and condition-specific factors.

Ax Xin Ding, Yun Chen, Yongwei Wang, Kao Zhang, Sen Zhang, Peibei Cao, Xiangxue Wang 7/8/2026

Imbalance-Robust and Sampling-Efficient Continuous Conditional GANs via Adaptive Vicinal Learning and Auxiliary Regularization

Adaptive approach for continuous conditional GANs addressing imbalanced label distributions in generative modeling.

Ax David Chanin, Adri\`a Garriga-Alonso 7/8/2026

Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders

Study of L0 hyperparameter effects on sparse autoencoders for LLM feature extraction and interpretability.

Ax Mrinmay Sen, Ankita Das, Sidhant Nair, C Krishna Mohan 7/8/2026

FedDAF: Federated Domain Adaptation Using Model Functional Distance

FedDAF federated domain adaptation approach addressing domain shifts and limited labeled data across clients.

Ax Hongkang Li, Songtao Lu, Xiaodong Cui, Pin-Yu Chen, Meng Wang 7/8/2026

How Can Mamba Learn In Context with Outliers and Generalize Provably?

Theoretical analysis of in-context learning in Mamba models with outliers and generalization guarantees.

Ax Yifei Sun 7/8/2026

Solver-Integrated Adversarial Attacking and Training of Neural Operators

Research on adversarial robustness and generalizability of neural operators as PDE surrogates from solver perspective.

Ax Amin Omidvar 7/8/2026

SmartMixed: A Two-Phase Training Strategy for Adaptive Activation Function Learning in Neural Networks

Two-phase training strategy enabling per-neuron adaptive activation function selection while maintaining inference efficiency.

Ax Thaweerath Phisannupawong, Joshua Julian Damanik, Han-Lim Choi 7/8/2026

LLM4Delay: Flight Delay Prediction via Cross-Modality Adaptation of Large Language Models and Aircraft Trajectory Representation

LLM-based framework for flight delay prediction integrating aeronautical data and aircraft trajectory representations.

Ax Eugenio Varetti, Matteo Torzoni, Marco Tezzele, Andrea Manzoni 7/8/2026

Adaptive digital twins for predictive decision-making: Online Bayesian learning of transition dynamics

Bayesian online learning approach for adaptive digital twin state transitions in civil engineering.

Ax Zhuo Zhang, Xi Yang, Ying Miao, Xiaobin Hu, Yifu Gao, Yong Yang, Canqun Yang, Boocheong Khoo 7/8/2026

PGOT: A Physics-Geometry Operator Transformer for Complex PDEs

Transformer architecture for solving complex PDEs on unstructured meshes with geometric feature preservation.

Ax Gang Liao, Hongsen Qin, Ying Wang, Alicia Golden, Michael Kuchnik, Yavuz Yetim, Jia Jiunn Ang, Chunli Fu, Yihan He, Samuel Hsia, Zewei Jiang, Dianshi Li, Uladzimir Pashkevich, Varna Puvvada, Feng Shi, Matt Steiner, Ruichao Xiao, Liyuan Li, Nathan Yan, Xiayu Yu, Zhou Fang, Roman Levenstein, Kunming Ho, Haishan Zhu, Alec Hammond, Richard Li, Ajit Mathews, Kaustubh Gondkar, Abdul Zainul-Abedin, Ketan Singh, Hongtao Yu, Wenyuan Chi, Barney Huang, Sean Zhang, Noah Weller, Zach Marine, Wyatt Cook, Carole-Jean Wu, Gaoxiang Liu 7/8/2026

KernelEvolve: Scaling Agentic Kernel Coding for Heterogeneous AI Accelerators at Meta

Agentic framework for automated kernel code generation across heterogeneous AI accelerators at scale for recommendation models.

Ax Itai Morad, Nir Shlezinger, Yonina C. Eldar 7/8/2026

SGD-Based Knowledge Distillation with Bayesian Teachers: Theory and Guidelines

Theoretical analysis of knowledge distillation convergence with Bayesian teacher networks using SGD.

Ax Ramnath Kumar, Kyle Ritscher, Junmin Judy, Lawrence Liu, Cho-Jui Hsieh 7/8/2026

FlexAct: Why Learn when you can Pick?

Research on learning discrete activation functions using Gumbel-Softmax for task-specific neural networks.

Ax Javier Porras-Valenzuela, Samar Hadou, Alejandro Ribeiro 7/8/2026

A Constrained Optimization Perspective of Unrolled Transformers

Constrained optimization framework training transformers as descent algorithms with layerwise loss decrease guarantees.

Ax Zhiheng Jiang, Yunzhe Wang, Ryan Marr, Ellen Novoseller, Benjamin T. Files, Volkan Ustun 7/8/2026

GraphAllocBench: A Flexible Benchmark for Preference-Conditioned Multi-Objective Policy Learning

GraphAllocBench benchmark for multi-objective reinforcement learning with preference-conditioned policies and flexible resource allocation.

Ax Shicheng Fan, Kun Zhang, Lu Cheng 7/8/2026

TRACE: Trajectory Recovery for Continuous Mechanism Evolution in Causal Representation Learning

TRACE method for causal representation learning handling continuous mechanism transitions across domains.

Ax Gloria Felicia (University of Virginia), Zitha Sasindran (Indian Institute of Science Bangalore), Jinfeng He (Cornell University), Michael Eniolade (University of the Cumberlands), Hemant Kumar (University of Arizona), Milan Hussain Angati (California State University Northridge) 7/8/2026

StepShield: When, Not Whether to Intervene on Rogue Agents

StepShield benchmark for agent safety measuring detection timeliness of rogue agent behavior on 9,429 code-agent trajectories.

Ax Simon B\"uhrer, Andreas Plesner, Aczel Till, Roger Wattenhofer 7/8/2026

BitLogic: Training Framework for Gradient-Based FPGA-Native Neural Networks

BitLogic training framework for gradient-based neural networks deployable to GPU, FPGA, and ASIC with single codebase.

Ax Stefano Woerner, Seong Joon Oh, Christian F. Baumgartner 7/8/2026

Universal Algorithm-Implicit Learning

Meta-learning framework defining practical universality and generalizable learning across arbitrary task distributions.

Ax Joshua S. Schiffman 7/8/2026

Transformers converge to invariant algorithmic cores

Study extracting invariant algorithmic cores from transformers across independent training runs to identify necessary computations.

Ax Davide Tugnoli, Andrea De Lorenzo, Marco Virgolin, Giovanni Cin\`a 7/8/2026

Improving TabPFN's Synthetic Data Generation by Integrating Causal Structure

Improvement to TabPFN synthetic tabular data generation by incorporating causal structure and feature dependencies.

Ax Tycho F. A. van der Ouderaa, Mart van Baalen, Paul Whatmough, Markus Nagel 7/8/2026

Leech Lattice Vector Quantization for Efficient LLM Compression

LLM compression technique using Leech lattice vector quantization to overcome information-theoretic limits of scalar quantization.

Ax Huaiyang Wang, Xiaojie Li, Xiaohan Wang, Zhixia Zhang, Xiaodong Lu, Zixuan Huang, Jiajun Chai, Guojun Yin, Deqing Wang, Haoyi Zhou, Yaodong Yang, Jianxin Li, Yikun Ban 7/8/2026

Policy Improvement Reinforcement Learning

Policy Improvement RL method for post-training LLMs and agents that explicitly verifies policy improvements over baselines.

Ax Paul-Tiberiu Iordache, Elena Burceanu 7/8/2026

Fine-Tuning Regimes Define Distinct Continual Learning Problems

Analysis showing continual learning performance varies significantly based on fine-tuning regime (trainable parameter subspace).

Ax Yang Fu, Peng Qin, Liming Chen, Zihao Zhang, Hao Yu, Yifei Wang 7/8/2026

Joint Energy Management and Coordinated AIGC Workload Scheduling for Distributed Data Centers: A Diffusion-Aided Reward Shaping Approach

Reinforcement learning approach for scheduling AIGC workloads and managing energy in distributed data centers using diffusion-based reward shaping.

Ax Noah Farr, Aryaman Reddi, Carlo D'Eramo, Jan Peters 7/8/2026

Streaming Reinforcement Learning under Partial Observability with Real-Time Recurrent Learning

Streaming reinforcement learning method enabling online learning with partial observability using real-time recurrent backpropagation.

Ax Zili Zhang, Chengxu Yang, Shenglong Zhang, Chenyu Wang, Yufan Zhang, Tuo Dai, Zhouyang Li, Yuhong Ge, Chao Jin, Xin Jin, Yuliang Liu 7/8/2026

BigMac: Breaking the Pareto Frontier of Compute and Memory in Multimodal LLM Training

BigMac training pipeline for multimodal LLMs that improves compute-memory efficiency tradeoffs through nested encoder-generator computation.

Ax Zhiwei Li, Yong Hu 7/8/2026

SkillHone: A Harness for Continual Agent Skill Evolution Through Persistent Decision History

Framework for continual evolution of agent skills in LLM-based agents by maintaining persistent decision history across task changes.

Ax Ananth K Suresh, Arya Hariharan 7/8/2026

Reproducibility Study of "AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models"

Reproducibility study of AlphaEdit null-space constrained knowledge editing method for LLMs, validating and extending original results.

Ax Kathan Shah 7/8/2026

Token Geometry

Lightweight optimizer exploiting gradient geometry of embedding tables and LM-heads for improved training efficiency across finetuning and pretraining.

Ax Haotian Xie, Junlin Chen, Mingkai Zheng, Lishan Yang, Zhao Zhang 7/8/2026

PHOENIX: Resilient LLM Training with Hot-Swapping via Zero-Overhead Checkpoint

Fault-tolerant LLM training system using zero-overhead checkpointing and hot-swapping for resilience across hardware failures.

Ax Zijun Xie, Yuyang You, Yongzhi Li, Enlei Gong, Zeyu Chen, Quan Chen, Yanhua Cheng, Peng Jiang, Yadong Mu 7/8/2026

ACPO: Adaptive Credit Policy Optimization via Fine-Grained Surrogate Entropy

Credit assignment optimization for RL-based LLM reasoning using fine-grained surrogate entropy for token-level rewards.

Ax Teng-Ruei Chen 7/8/2026

How Much of the Routing Gap Is Real? Decomposing the Router-to-Oracle Gap into Reproducible Specialist Advantage and Single-Draw Label Noise

Analysis decomposing router-to-oracle performance gap in LLM routing, identifying label noise versus specialist advantage contributions.

Ax Jaeyeon Kim, Jewon Lee, Bo-Kyeong Kim 7/8/2026

Quantize the Target, Quantize the Drafter: Efficient Inference with Qwen3.5-4B

Efficient inference system combining quantization and speculative decoding for Qwen3.5-4B LLM on resource-constrained hardware.

Ax Jianyi Zhang, Hao Frank Yang, Ang Li, Xin Guo, Pu Wang, Haiming Wang, Yiran Chen, Hai Li 7/8/2026

MLLM-LLaVA-FL: Multimodal Large Language Model Assisted Federated Learning

Federated learning framework using multimodal LLMs (LLaVA) to address data heterogeneity across distributed clients.

Ax Seemanta Bhattacharjee, MD. Muhtasim Fuad, A. K. M. Fakhrul Hossain 7/8/2026

Classification of Financial Data Using Quantum Support Vector Machine

Application of quantum support vector machines to financial data classification using Dhaka Stock Exchange dataset.

Ax Joachim Tomasi, Sandrine Anthoine, Hachem Kadri 7/8/2026

Benign Overfitting with Quantum Kernels

Theoretical study of benign overfitting in quantum kernel methods for machine learning on quantum computers.

Ax Gojko Perovic, Nuno Ferreira Duarte, Atabak Dehban, Gon\c{c}alo Teixeira, Egidio Falotico, Jos\'e Santos-Victor 7/8/2026

HERB: Human-augmented Efficient Reinforcement learning for Bin-packing

Human-augmented reinforcement learning approach for 3D bin-packing in logistics, combining RL with human feedback to reduce training time.

Ax Alireza Furutanpey, Carmen Walser, Philipp Raith, Pantelis A. Frangoudis, Schahram Dustdar 7/8/2026

Leveraging Neural Graph Compilers in Machine Learning Research for Edge-Cloud Systems

Evaluation of neural network graph compilers across heterogeneous hardware platforms, showing how vendor-specific optimizations affect performance comparisons.

Ax Alina Wernick, Kristof Meding 7/8/2026

Position: EU AI Act's Research Exemptions Can Break the Publication Norms of Major AI Conferences

Position paper on EU AI Act research exemptions and potential conflicts with academic publication norms at major conferences.

Ax Gautam Jajoo, Atharva Pandey, Pranjal A Chitale, Saksham Agarwal 7/8/2026

MASCA: LLM based-Multi Agents System for Credit Assessment

Multi-agent LLM system for credit assessment that mirrors real-world decision-making processes in financial evaluation.

Ax Constantin Venhoff, Iv\'an Arcuschin, Philip Torr, Arthur Conmy, Neel Nanda 7/8/2026

Base Models Know How to Reason, Thinking Models Learn When

Analysis of reasoning behaviors in thinking language models using Sparse Autoencoders and model diffing techniques.

Ax Scott Thornton 7/8/2026

SecureCode: A Production-Grade Multi-Turn Dataset for Training Security-Aware Code Generation Models

Production-grade dataset of 2,185 multi-turn examples for training secure code generation models covering OWASP Top 10 and ML security.