Ax Divyat Mahajan, Sachin Goyal, Badr Youbi Idrissi, Mohammad Pezeshki, Ioannis Mitliagkas, David Lopez-Paz, Kartik Ahuja 3/26/2026

Beyond Multi-Token Prediction: Pretraining LLMs with Future Summaries

Proposes future summary prediction as alternative to next-token prediction during LLM pretraining, improving long-horizon reasoning and planning capabilities.

Ax Woo-Jin Ahn, Sang-Ryul Baek, Yong-Jun Lee, Hyun-Duck Choi, Myo-Taeg Lim 3/26/2026

OffSim: Offline Simulator for Model-based Offline Inverse Reinforcement Learning

OffSim: Model-based offline inverse reinforcement learning framework that learns environment dynamics and reward functions from offline data without manual specification.

Ax Asim Mohamed, Martin Gubri 3/26/2026

Is Multilingual LLM Watermarking Truly Multilingual? Scaling Robustness to 100+ Languages via Back-Translation

Multilingual LLM watermarking robustness study showing current methods fail on low-resource languages, proposes back-translation approach for 100+ language coverage.

Ax Zhixiong Zhao, Haomin Li, Fangxin Liu, Yuncheng Lu, Zongwu Wang, Tao Yang, Li Jiang, Haibing Guan 3/26/2026

QUARK: Quantization-Enabled Circuit Sharing for Transformer Acceleration by Exploiting Common Patterns in Nonlinear Operations

QUARK: FPGA acceleration framework leveraging quantization and common patterns in nonlinear operations to accelerate transformer inference.

Ax Sebasti\'an Andr\'es Cajas Ord\'o\~nez, Luis Fernando Torres Torres, Mackenzie J. Meni, Carlos Andr\'es Duran Paredes, Eric Arazo, Cristian Bosch, Ricardo Simon Carbajo, Yuan Lai, Leo Anthony Celi 3/26/2026

Uncertainty Makes It Stable: Curiosity-Driven Quantized Mixture-of-Experts

Curiosity-driven quantized Mixture-of-Experts framework using Bayesian uncertainty routing for accurate inference on resource-constrained devices.

Ax Radman Rakhshandehroo, Daniel Coombs 3/26/2026

Reward Engineering for Spatial Epidemic Simulations: A Reinforcement Learning Platform for Individual Behavioral Learning

ContagionRL: Gymnasium-compatible RL platform for reward engineering in spatial epidemic simulations, enabling systematic evaluation of behavioral learning strategies.

Ax Yara Bahram, M\'elodie Desbos, Mohammadhadi Shateri, Eric Granger 3/26/2026

Uni-DAD: Unified Distillation and Adaptation of Diffusion Models for Few-step Few-shot Image Generation

Unified distillation and adaptation framework for diffusion models enabling fast, high-quality image generation in novel domains with single-stage pipeline.

Ax Zhihao Zhan, Jiaying Zhou, Likui Zhang, Qinhan Lv, Hao Liu, Jusheng Zhang, Weizheng Li, Ziliang Chen, Tianshui Chen, Ruifeng Zhai, Keze Wang, Liang Lin, Guangrun Wang 3/26/2026

E0: Enhancing Generalization and Fine-Grained Control in VLA Models via Tweedie Discrete Diffusion

Vision-Language-Action models enhanced via Tweedie discrete diffusion for improved generalization and fine-grained control in robotic manipulation tasks.

Ax Shutong Chen, Qi Liao, Adnan Aijaz, Yansha Deng 3/26/2026

Goal-Oriented Multi-Agent Semantic Networking: Unifying Intents, Semantics, and Intelligence

Proposes goal-oriented multi-agent semantic networking architecture for 6G services integrating AI-native communication with network-level intelligence.

Ax Kun Yuan, Min Woo Sun, Zhen Chen, Alejandro Lozano, Xiangteng He, Shi Li, Nassir Navab, Xiaoxiao Sun, Nicolas Padoy, Serena Yeung-Levy 3/26/2026

From Panel to Pixel: Zoom-In Vision-Language Pretraining from Biomedical Scientific Literature

Biomedical vision-language pretraining approach that captures fine-grained correspondences in scientific figures and text, improving domain-specific representations.

Ax Jialuo Li, Bin Li, Jiahao Li, Yan Lu 3/26/2026

Divide, then Ground: Adapting Frame Selection to Query Types for Long-Form Video Understanding

Proposes adaptive frame selection method for long-form video understanding with large multimodal models, reducing computational overhead while maintaining query awareness.

Ax Raunak Jain 3/26/2026

Collaborative Causal Sensemaking: Closing the Complementarity Gap in Human-AI Decision Support

Research on LLM-based agents for decision support, proposing collaborative sensemaking approach where agents act as partners rather than answer engines to improve human-AI complementarity.

Ax Guoqiang Zou, Wanyu Wang, Hao Zheng, Longxiang Yin, Yinhe Han 3/26/2026

ODMA: On-Demand Memory Allocation Strategy for LLM Serving on LPDDR-Class Accelerators

ODMA proposes on-demand memory allocation strategy for efficient LLM serving on low-bandwidth accelerators, addressing limitations of static pre-allocation and fine-grained paging.

Ax Tao Liu, Taiqiang Wu, Runming Yang, Shaoning Sun, Junjie Wang, Yujiu Yang 3/26/2026

ProFit: Leveraging High-Value Signals in SFT via Probability-Guided Token Selection

Probability-guided token selection for SFT to address overfitting to single reference answers. Leverages multiple references while managing data costs.

Ax Hengyu Shen, Tiancheng Gu, Bin Qin, Lan Wu, Yuling Wu, Shuo Tan, Zelong Sun, Jun Wang, Nan Wu, Xiang An, Weidong Cai, Ziyong Feng, Kaicheng Yang 3/26/2026

DanQing: An Up-to-Date Large-Scale Chinese Vision-Language Pre-training Dataset

100M high-quality Chinese image-text dataset for vision-language pre-training. Addresses bottleneck in Chinese VLP model development.

Ax Yu Yang, Ig-Jae Kim, Dongwook Yoon 3/26/2026

PASTA: A Scalable Framework for Multi-Policy AI Compliance Evaluation

Scalable compliance evaluation framework for multi-policy AI governance. Integrates comprehensive model-card format and streamlines policy compliance burden.

Ax Kla Tantithamthavorn, Hong Yi Lin, Patanamon Thongtanunam, Wachiraphan Charoenwet, Minwoo Jeong, Ming Wu 3/26/2026

HalluJudge: A Reference-Free Hallucination Detection for Context Misalignment in Code Review Automation

Reference-free hallucination detection for LLM-generated code review comments. Identifies context misalignment without ground truth, enabling practical adoption in code review automation.

Ax Raunak Jain 3/26/2026

From Sycophancy to Sensemaking: Premise Governance for Human-AI Decision Making

Framework addressing sycophancy in LLM decision support systems through premise governance. Proposes structured verification for deep-uncertainty decisions.

Ax Natnael Mola, Leonardo S. B. Pereira, Carolina R. Kelsch, Luis H. Arribas, Juan C. S. M. Avedillo 3/26/2026

SPARE: Self-distillation for PARameter-Efficient Removal

Self-distillation approach for machine unlearning in text-to-image diffusion models. Balances effective forgetting with retention of unrelated concepts.

Ax Bjarni Haukur Bjarnason, Andr\'e Silva, Martin Monperrus 3/26/2026

On Randomness in Agentic Evals

Statistical analysis of variance in agentic system evaluations. Shows single-run pass@1 scores on SWE-Bench vary substantially (2.2-6.0%), calling for improved evaluation methodology.

Ax Lei Ma, Jinyang Liu, Tieying Zhang, Peter M. VanNostrand, Dennis M. Hofmann, Lei Cao, Elke A. Rundensteiner, Jianjun Chen 3/26/2026

KRONE: Hierarchical and Modular Log Anomaly Detection

Hierarchical framework for log anomaly detection that preserves component execution structure. Addresses spurious correlations in flat-sequence approaches.

Ax Yuzhu Cai, Zexi Liu, Xinyu Zhu, Cheng Wang, Siheng Chen 3/26/2026

AceGRPO: Adaptive Curriculum Enhanced Group Relative Policy Optimization for Autonomous Machine Learning Engineering

AceGRPO combines adaptive curriculum learning with GRPO for autonomous ML engineering agents. Addresses behavioral stagnation and data inefficiency in long-horizon optimization tasks.

Ax Jeffrey T. H. Wong, Zixi Zhang, Junyi Liu, Yiren Zhao 3/26/2026

Team of Thoughts: Efficient Test-time Scaling of Agentic Systems through Orchestrated Tool Calling

Heterogeneous multi-agent framework treating diverse LLM models as specialized tools. Introduces orchestrator calibration for efficient test-time scaling through coordinated tool calling.

Ax Egor Denisov, Svetlana Glazyrina, Maksim Kryzhanovskiy, Roman Ischenko 3/26/2026

Smooth Gate Functions for Soft Advantage Policy Optimization

Smooth gate functions for stabilizing GRPO LLM training. Replaces hard clipping with sigmoid-based gating to improve optimization stability in reasoning tasks.

Ax Xiang Li, Yuheng Zhang, Nan Jiang 3/26/2026

Beyond State-Wise Mirror Descent: Offline Policy Optimization with Parametric Policies

Theoretical analysis of offline reinforcement learning with general function approximation and parametric policies, extending beyond finite action spaces.

Ax Andrew Chin, Dongkwan Kim, Yu-Fu Fu, Fabian Fleischer, Youngjoon Kim, HyungSeok Han, Cen Zhang, Brian Junekyu Lee, Hanqing Zhao, Taesoo Kim 3/26/2026

OSS-CRS: Liberating AIxCC Cyber Reasoning Systems for Real-World Open-Source Security

Open-source framework for deploying DARPA AIxCC cyber reasoning systems locally. Makes competition CRSs usable outside original infrastructure with improved accessibility.

Ax Anupam Purwar, Aditya Choudhary 3/26/2026

MM-tau-p$^2$: Persona-Adaptive Prompting for Robust Multi-Modal Agent Evaluation in Dual-Control Settings

Evaluation framework for persona-adaptive LLM-powered agents in multi-modal settings, addressing user-aware behavior in customer experience management.

Ax Zekun Wu, Adriano Koshiyama, Sahan Bulathwela, Maria Perez-Ortiz 3/26/2026

AgentDrift: Unsafe Recommendation Drift Under Tool Corruption Hidden by Ranking Metrics in LLM Agents

Red-teaming Vision-Language-Action models through quality diversity prompt generation to improve robot policy robustness.

Ax Haoan Feng, Sri Harsha Musunuri, Guan-Ming Su 3/26/2026

Geometry-Guided Camera Motion Understanding in VideoLLMs

AgentDrift: reveals safety risks in LLM agent recommendations when tools are corrupted, hidden by standard metrics.

Ax Seokmin Lee, Yunghee Lee, Byeonghyun Pak, Byeongju Woo 3/26/2026

Pixel-level Scene Understanding in One Token: Visual States Need What-is-Where Composition

Framework for improving VideoLLM understanding of camera motion through benchmarking, diagnosis, and explicit geometry injection.

Ax Eman M. AbouNassar, Amr Elshall, Sameh Abdulah 3/26/2026

FedPBS: Proximal-Balanced Scaling Federated Learning Model for Robust Personalized Training for Non-IID Data

Visual state representations for robotic agents using what-is-where composition for dynamic scene understanding.

Ax Mikoto Kudo, Takumi Tanabe, Akifumi Wachi, Youhei Akimoto 3/26/2026

Sample-Efficient Hypergradient Estimation for Decentralized Bi-Level Reinforcement Learning

FedPBS: federated learning algorithm for personalized training on non-IID data with improved robustness.

Ax Yeounoh Chung, Rushabh Desai, Jian He, Yu Xiao, Thibaud Hottelier, Yves-Laurent Kom Samo, Pushkar Kadilkar, Xianshun Chen, Sam Idicula, Fatma \"Ozcan, Alon Halevy, Yannis Papakonstantinou 3/26/2026

100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models

Sample-efficient hypergradient estimation for decentralized bi-level reinforcement learning in strategic decision-making.

Ax Md. Asraful Haque, Aasar Mehdi, Maaz Mahboob, Tamkeen Fatima 3/26/2026

Mitigating LLM Hallucinations through Domain-Grounded Tiered Retrieval

Proxy models reduce cost and latency of AI queries in SQL databases by 100x through approximation techniques.

Ax Sam Ganzfried 3/26/2026

Evolutionarily Stable Stackelberg Equilibrium

Domain-grounded tiered retrieval architecture to reduce LLM hallucinations through retrieval-based verification.

Ax Mohamed Youssef, Mayar Elfares, Anna-Maria Meer, Matteo Bortoletto, Andreas Bulling 3/26/2026

Ontology-Guided Diffusion for Zero-Shot Visual Sim2Real Transfer

Evolutionarily Stable Stackelberg Equilibrium: game theory solution concept for asymmetric leader-follower games.

Ax Marcelo Fernandez (TraslaIA) 3/26/2026

Agent Control Protocol: Admission Control for Agent Actions

Ontology-Guided Diffusion for zero-shot sim2real transfer using neuro-symbolic approach to bridge simulation-reality gap.

Ax Lucas Maes, Quentin Le Lidec, Damien Scieur, Yann LeCun, Randall Balestriero 3/26/2026

LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

Agent Control Protocol: formal specification for admission control governance of autonomous agents with cryptographic identity and policy compliance.

Ax Ravish Gupta (BigCommerce), Saket Kumar (University at Buffalo, The State University of New York, Buffalo, NY, USA), Shreeya Sharma (Microsoft), Maulik Dang (Amazon), Abhishek Aggarwal (Amazon) 3/26/2026

An Agentic Multi-Agent Architecture for Cybersecurity Risk Management

Multi-agent AI system with six specialized agents for automated NIST CSF-aligned cybersecurity risk assessments for small organizations.

Ax Xinyue Liu, Niloofar Mireshghallah, Jane C. Ginsburg, Tuhin Chakrabarty 3/26/2026

Alignment Whack-a-Mole : Finetuning Activates Verbatim Recall of Copyrighted Books in Large Language Models

Study showing finetuning bypasses LLM safety mechanisms and triggers verbatim recall of copyrighted training data.

Ax Trung V. Phan, Thomas Bauschert 3/26/2026

DeepXplain: XAI-Guided Autonomous Defense Against Multi-Stage APT Campaigns

Explainable DRL framework for autonomous APT defense using provenance-based graphs and stage-aware modeling.

Ax Shuai Wang, Yinan Yu, Earl Barr, Dhasarathy Parthasarathy 3/26/2026

LLM-Powered Workflow Optimization for Multidisciplinary Software Development: An Automotive Industry Case Study

LLM-based workflow system for multidisciplinary software development coordinating domain experts and developers in automotive.

Ax Hyoseok Park, Yeonsang Park 3/26/2026

PRISM: Breaking the O(n) Memory Wall in Long-Context LLM Inference via O(1) Photonic Block Selection

PRISM photonic accelerator approach reducing KV cache memory bandwidth from O(n) to O(1) for long-context LLM inference.

Ax Woosung Koh, Jeyoung Jeon, Youngjin Song, Yujin Cheon, Soowon Oh, Jaehyeong Choi, Se-Young Yun 3/26/2026

mSFT: Addressing Dataset Mixtures Overfitting Heterogeneously in Multi-task SFT

mSFT algorithm for optimizing heterogeneous multi-task SFT data mixtures by dynamically adjusting compute per sub-dataset.

Ax Yuze Qin, Qingyong Li, Zhiqing Guo, Wen Wang, Yan Liu, Yangli-ao Geng 3/26/2026

Extending Precipitation Nowcasting Horizons via Spectral Fusion of Radar Observations and Foundation Model Priors

Weather prediction combining radar observations with foundation model priors for extended nowcasting horizons.

Ax Junhyeok Rui Cha, Woohyun Cha, Jaeyong Shin, Donghyeon Kim, Jaeheung Park 3/26/2026

Sim-to-Real of Humanoid Locomotion Policies via Joint Torque Space Perturbation Injection

Sim-to-real transfer for humanoid robot control using state-dependent joint torque perturbations instead of domain randomization.

Ax Davide Bucciarelli, Evelyn Turri, Lorenzo Baraldi, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara 3/26/2026

Tiny Inference-Time Scaling with Latent Verifiers

Inference-time scaling with lightweight latent verifiers instead of MLLMs to reduce computational cost in verification.

Ax Javier Ferrando, Enrique Lopez-Cuena, Pablo Agustin Martin-Torres, Daniel Hinjos, Anna Arias-Duart, Dario Garcia-Gasulla 3/26/2026

Language Models Can Explain Visual Features via Steering

Method using causal interventions and Vision-Language Models to explain sparse autoencoder features in vision models.

Ax Reza Habibi, Darian Lee, Magy Seif El-Nasr 3/26/2026

Beyond Accuracy: Introducing a Symbolic-Mechanistic Approach to Interpretable Evaluation

Interpretable evaluation combining symbolic rules with mechanistic interpretability to detect memorization vs genuine generalization.

Ax Haoyu Wang, Yuxin Chen, Liang Luo, Buyun Zhang, Ellie Dingqiao Wen, Pan Li 3/26/2026

Implicit Turn-Wise Policy Optimization for Proactive User-LLM Interaction

ITPO framework for optimizing multi-turn human-LLM interactions via RL despite sparse rewards and user stochasticity.