Ax Jasmine Brazilek, Miles Tidmarsh 4/23/2026

Alignment midtraining for animals

Study on robustness of value alignment through finetuning with synthetic documents, releasing Animal Harm Benchmark for evaluating model compassion.

Ax Sebastian Nagl, Matthias Grabmair 4/23/2026

BenGER: A Collaborative Web Platform for End-to-End Benchmarking of German Legal Tasks

BenGER: Open-source web platform for end-to-end benchmarking of LLMs on German legal tasks with integrated annotation and evaluation workflows.

Ax Ahmad Dawar Hakimi, Lea Hirlimann, Isabelle Augenstein, Hinrich Sch\"utze 4/23/2026

Do We Still Need Humans in the Loop? Comparing Human and LLM Annotation in Active Learning for Hostility Detection

Comparison of LLM and human annotation in active learning for hostility detection on German political TikTok comments dataset.

Ax Louie Hong Yao, Vishesh Anand, Yuan Zhuang, Tianyu Jiang 4/23/2026

Rhetorical Questions in LLM Representations: A Linear Probing Study

Linear probing study analyzing how LLMs represent rhetorical questions in internal representations across social media discourse contexts.

Ax Yitong Shou, Manhao Guan 4/23/2026

Mechanistic Decoding of Cognitive Constructs in Large Language Models

Cognitive Reverse-Engineering framework for interpreting how LLMs internally process complex emotions and affective states through mechanistic analysis.

Ax Zihao Xu, John Harvill, Ziwei Fan, Yizhou Sun, Hao Ding, Hao Wang 4/23/2026

Compressing Sequences in the Latent Embedding Space: $K$-Token Merging for Large Language Models

K-Token Merging method for compressing long sequences in LLM latent embedding space to reduce quadratic self-attention costs during inference.

Ax Burak Susam, Tingting Mu 4/23/2026

Explainable Iterative Data Visualisation Refinement via an LLM Agent

LLM agent system for iterative data visualization refinement, automatically adjusting embedding algorithm configurations for high-dimensional exploratory analysis.

Ax Kevin Stowe, Kailash Patil 4/23/2026

Spotlights and Blindspots: Evaluating Machine-Generated Text Detection

Evaluation of 15 machine-generated text detection models across 7 test sets to compare effectiveness and benchmark detection approaches.

Ax Francesco Sovrano, Gabriele Dominici, Alberto Bacchelli 4/23/2026

Mitigating Prompt-Induced Cognitive Biases in General-Purpose AI for Software Engineering

Research on prompt-induced cognitive biases in AI for software engineering decision support, showing how phrasing shifts affect model outputs.

Ax Shuang Ma, Chon Lam Lao, Zhiying Xu, Zhuang Wang, Ziming Mao, Delong Meng, Jia Zhen, Jun Wu, Ion Stoica, Yida Wang, Yang Zhou 4/23/2026

UCCL-Zip: Lossless Compression Supercharged GPU Communication

UCCL-Zip integrates lossless compression into GPU communication primitives for LLM training without numerical errors or convergence degradation.

Ax Marcelo Fernandez (TraslaIA) 4/23/2026

Atomic Decision Boundaries: A Structural Requirement for Guaranteeing Execution-Time Admissibility in Autonomous Systems

Research on atomic decision boundaries for enforcing admissibility constraints in autonomous systems at exact state transition moments.

Ax Andrew Zhang, Tong Ding, Sophia J. Wagner, Caiwei Tian, Ming Y. Lu, Rowland Pettit, Joshua E. Lewis, Alexandre Misrahi, Dandan Mo, Long Phi Le, Faisal Mahmood 4/23/2026

A multimodal and temporal foundation model for virtual patient representations at healthcare system scale

Apollo is multimodal temporal foundation model for patient representations trained on 30 years of longitudinal hospital data from 7.2M patients and 25B clinical records.

Ax Yunke Ao, Le Chen, Bruce D. Lee, Assefa S. Wahd, Aline Czarnobai, Philipp F\"urnstahl, Bernhard Sch\"olkopf, Andreas Krause 4/23/2026

Bounded Ratio Reinforcement Learning

Bounded Ratio Reinforcement Learning framework bridges theory-practice gap in PPO by formalizing trust region methods with bounded ratio constraints.

Ax Zhiyuan Jiang, Weihao Hong, Xinlei Guan, Tejaswi Dhandu, Miles Q. Li, Meng Xu, Kuan Huang, Umamaheswara Rao Tida, Bingyu Shen, Daehan Kwak, Boyang Li 4/23/2026

LLM-as-Judge Framework for Evaluating Tone-Induced Hallucination in Vision-Language Models

Framework uses LLM-as-Judge to evaluate hallucinations in vision-language models under coercive prompt phrasing and linguistic pressure.

Ax Clara Lachenmaier, Hannah Bultmann, Sina Zarrie{\ss} 4/23/2026

Talking to a Know-It-All GPT or a Second-Guesser Claude? How Repair reveals unreliable Multi-Turn Behavior in LLMs

Study investigates how LLMs handle repair in multi-turn conversations, showing significant differences between models in self-initiated and user-initiated error correction.

Ax Alankrit Chona, Igor Kozlov, Ambuj Kumar 4/23/2026

Cyber Defense Benchmark: Agentic Threat Hunting Evaluation for LLMs in SecOps

Cyber Defense Benchmark evaluates LLM agents on threat hunting tasks using 106 real attacks from MITRE ATT&CK, measuring SOC analyst capabilities on Windows event logs.

Ax Mircea Timpuriu, Mihaela-Claudia Cercel, Dumitru-Clementin Cercel 4/23/2026

RoLegalGEC: Legal Domain Grammatical Error Detection and Correction Dataset for Romanian

Dataset for grammatical error detection and correction in Romanian legal documents, trained on domain-specific legal text.

Ax Ruocan Wei, Shufeng Wang, Ziwei Shi 4/23/2026

WorkflowGen:an adaptive workflow generation mechanism driven by trajectory experience

WorkflowGen: adaptive workflow generation framework for LLM agents that reuses trajectory experience to reduce token consumption and improve execution stability.

Ax Arnault Pachot, Thierry Petit 4/23/2026

Transparent Screening for LLM Inference and Training Impacts

Framework for estimating environmental and computational impacts of LLM inference and training across market models with limited observability.

Ax Ally Qin, Jian Wan, Sarat Mudunuri, Srinivasan Manoharan 4/23/2026

Accelerating PayPal's Commerce Agent with Speculative Decoding: An Empirical Study on EAGLE3 with Fine-Tuned Nemotron Models

EAGLE3 speculative decoding optimization for PayPal's commerce agent, reducing latency on fine-tuned Nemotron-8B.

Ax Jian Huang, Zixiang Ming, Yongli Zhu, Linna Xu 4/23/2026

On-Meter Graph Machine Learning: A Case Study of PV Power Forecasting for Grid Edge Intelligence

Graph neural networks for PV power forecasting on edge meters using GCN and GATv2 with ONNX deployment.

Ax Chaitanya Dwivedi, Binxuan Huang, Himanshu Gupta, Pratik Jayarao, Neeraj Varshney, Bing Yin 4/23/2026

Expert Upcycling: Shifting the Compute-Efficient Frontier of Mixture-of-Experts

Expert Upcycling: Mixture-of-Experts optimization shifting compute-efficient frontier for large language model scaling.

Ax Carter Adams, Rafael Oliveira, Gabriel Almeida, Sofia Torres 4/23/2026

Rethinking Reinforcement Fine-Tuning in LVLM: Convergence, Reward Decomposition, and Generalization

Theoretical analysis of reinforcement fine-tuning in vision-language models for agentic capabilities, convergence and generalization.

Ax Venus Team, Sunhao Dai, Yong Deng, Jinzhen Lin, Yusheng Song, Guoqing Wang, Xiaofeng Wu, Yuqi Zhou, Shuo Yang, Zhenzhe Ying, Zhanwei Zhang, Changhua Meng, Weiqiang Wang 4/23/2026

DR-Venus: Towards Frontier Edge-Scale Deep Research Agents with Only 10K Open Data

DR-Venus: 4B open-data deep research agent for edge deployment, optimizing data quality and utilization for small models.

Ax SLAM Labs, :, Oleksiy Ostapenko, Raymond Li, Torsten Scholak, Alireza Mousavi-Hosseini, Aman Tiwari, Denis Kocetkov, Joel Lamy Poirier, Kelechi Ogueji, Nanda H Krishna, Rafael Pardinas, Sathwik Tejaswi Madhusudhan, Shruthan Radhakrishna, Srinivas Sunkara, Valerie Becaert 4/23/2026

Super Apriel: One Checkpoint, Many Speeds

Super Apriel: 15B-parameter supernet supporting multiple attention mechanisms switchable at inference time without reloading.

Ax Het Patel, Tiejin Chen, Hua Wei, Evangelos E. Papalexakis, Jia Chen 4/23/2026

Are LLM Uncertainty and Correctness Encoded by the Same Features? A Functional Dissociation via Sparse Autoencoders

Sparse autoencoders reveal distinct LLM features encoding uncertainty versus correctness, showing functional dissociation.

Ax Renee Gil 4/23/2026

Multi-Objective Reinforcement Learning for Generating Covalent Inhibitor Candidates

Multi-objective reinforcement learning pipeline for rational design of covalent inhibitor candidates in drug discovery.

Ax Baran Atalar, Xutong Liu, Jinhang Zuo, Siwei Wang, Wei Chen, Carlee Joe-Wong 4/23/2026

Continuous Semantic Caching for Low-Cost LLM Serving

Semantic caching framework for reducing LLM inference costs by caching responses to semantically similar queries.

Ax Yusuf Kesmen, Fay Elhassan, Jiayi Ma, Julien Stalhandske, David Sasu, Alexandra Kulinkina, Akhil Arora, Lars Klein, Mary-Anne Hartley 4/23/2026

Statistics, Not Scale: Modular Medical Dialogue with Bayesian Belief Engine

BMBE framework separating language and probabilistic reasoning in medical dialogue agents, using Bayesian belief engine for diagnostics.

Ax Saloni Garg, Amit Sagtani, Kamal Kant Hiran 4/23/2026

Federated Learning over Blockchain-Enabled Cloud Infrastructure

Integration of federated learning and blockchain technology for privacy-preserving machine learning in cloud infrastructure.

Ax Daniele Calandriello, Ioannis Koutis, Alessandro Lazaric, Michal Valko 4/23/2026

Improved large-scale graph learning through ridge spectral sparsification

Graph Laplacian learning in distributed streaming settings using ridge spectral sparsification for large-scale graphs.

Ax Aarav Gupta, Gururaj Deshpande, Chandreyi Chakraborty 4/23/2026

On the Quantization Robustness of Diffusion Language Models in Coding Benchmarks

Investigation of post-training quantization robustness for diffusion-based language models on coding benchmarks with GPTQ and HAWQ.

Ax Zongyao Lyu, William J. Beksi 4/23/2026

Energy-Based Open-Set Active Learning for Object Classification

Active learning framework for object classification handling open-set conditions with unknown classes using energy-based models.

Ax Nathan Hittesdorf, Marco Salzetta, Lu Cheng 4/23/2026

Differentiable Conformal Training for LLM Reasoning Factuality

Differentiable conformal training method to improve LLM factuality and reduce hallucinations with statistical guarantees on error rates.

Ax Yicheng Pan, Ruisong Zhou, Haijun Zou, Tianyou Li, Zaiwen Wen 4/23/2026

Learning to Solve the Quadratic Assignment Problem with Warm-Started MCMC Finetuning

Permutation learning framework (PLMA) combining neural networks with warm-started MCMC for solving quadratic assignment problems.

Ax Xuelin Zhang, Xinyue Liu, Lingjuan Wu, Hong Chen 4/23/2026

Meta Additive Model: Interpretable Sparse Learning With Auto Weighting

Sparse additive model with automatic sample reweighting for high-dimensional analysis robust to non-Gaussian noise and outliers.

Ax Xuelin Zhang, Peipei Yuan 4/23/2026

On the Stability and Generalization of First-order Bilevel Minimax Optimization

Theoretical analysis of generalization and stability in first-order bilevel minimax optimization for hyperparameter optimization and reinforcement learning.

Ax Natalia Martinez Gil, Fearghal O'Donncha, Wesley M. Gifford, Nianjun Zhou, Dhaval C. Patel, Roman Vaculin 4/23/2026

Adaptive Conformal Anomaly Detection with Time Series Foundation Models for Signal Monitoring

Post-hoc adaptive conformal anomaly detection method leveraging pre-trained time series foundation models without fine-tuning for signal monitoring.

Ax Samaresh Kumar Singh, Joyjit Roy 4/23/2026

A Delta-Aware Orchestration Framework for Scalable Multi-Agent Edge Computing

Framework addressing performance degradation when scaling multi-agent reinforcement learning beyond 100 agents in edge computing environments.

Ax Zeyu Shen, Peter Henderson 4/23/2026

Temporally Extended Mixture-of-Experts Models

Proposes temporally extended mixture-of-experts layers using reinforcement learning options framework to improve GPU memory efficiency during inference.

Ax Boxin Zhao, Mladen Kolar, Jinchi Lv 4/23/2026

SMART: A Spectral Transfer Approach to Multi-Task Learning

Spectral transfer method for multi-task linear regression that assumes spectral similarity between source and target models.

Ax Luke Bailey, Kaiyue Wen, Kefan Dong, Tatsunori Hashimoto, Tengyu Ma 4/23/2026

Scaling Self-Play with Self-Guidance

Self-play scaling approach for LLMs with self-guidance to overcome learning plateaus and reward hacking.

Ax Bo-Cheng Lin, Yi Mei, Mengjie Zhang 4/23/2026

Machine Learning for Two-Stage Graph Sparsification for the Travelling Salesman Problem

ML methods for two-stage graph sparsification to improve TSP solver efficiency across instance sizes.

Ax Rickmer Schulte, David R\"ugamer 4/23/2026

Rethinking Intrinsic Dimension Estimation in Neural Representations

Analysis framework for intrinsic dimension estimation in neural network representations.

Ax Yuhan Peng, Junwen Dong, Yuzhi Zeng, Hao Li, Ce Ju, Huitao Feng, Diaaeldin Taha, Anna Wienhard, Kelin Xia 4/23/2026

Sheaf Neural Networks on SPD Manifolds: Second-Order Geometric Representation Learning

Sheaf neural networks on SPD manifolds for second-order geometric representation learning in graphs.

Ax Xiang Shi, Shuaizhi Cheng, Mingwei Li 4/23/2026

Formalising the Logit Shift Induced by LoRA: A Technical Note

Formal analysis of logit shift effects from LoRA adaptation using first-order Fréchet approximation.

Ax Aijia Cheng, Kailong Wang, Ling Shi, Yongxin Zhao 4/23/2026

R2IF: Aligning Reasoning with Decisions via Composite Rewards for Interpretable LLM Function Calling

R2IF: RL framework for LLM function calling with composite rewards aligning reasoning and tool-call decisions.

Ax Andrey Vasilyev, Yikai Wang, Xiaocheng Li, Guanting Chen 4/23/2026

Calibrating conditional risk

Methods for estimating expected loss of prediction models conditional on input features in classification and regression settings.

Ax Hung Cuong Pham, Fatih Gedikli 4/23/2026

Scalable AI Inference: Performance Analysis and Optimization of AI Model Serving

Performance analysis and optimization of BentoML-based AI inference system for scalable model serving in production environments.

Ax Xueyan Li, Johannes Zenn, Ekaterina Fadeeva, Guinan Su, Mrinmaya Sachan, Jonas Geiping 4/23/2026

Efficient Test-Time Inference via Deterministic Exploration of Truncated Decoding Trees

Distinct Leaf Enumeration (DLE) deterministic decoding method efficiently explores truncated trees for test-time inference on math and code tasks.