Ax Kevin Wang, Kevin Yang, Arjun Prakash, Amy Greenwald 9d ago

Towards Learning Representations of Policies in Two-Player Zero-Sum Imperfect-Information Games

Methods for creating policy datasets and learning policy embeddings in two-player zero-sum imperfect-information games with evaluation tasks.

Ax Lukas Haverbeck, Carmen Amo Alonso, Andres Felipe Posada-Moreno, Sebastian Trimpe, Marco Pavone 9d ago

The risk of KV cache compression

Theoretical analysis of KV cache compression in transformer inference showing when compression is impossible and deriving fundamental limits.

Ax Jiatong Li, Samuel Yeh, Sharon Li 9d ago

Multi-Head Recurrent Memory Agents

Multi-Head Recurrent Memory Agents diagnose reliability degradation in long-context LLMs, attributing failures to memory retention rather than capture.

Ax Abdullah Al Tasim, Wei Sun 9d ago

Wind-Aware Reinforcement Learning Control of a Small Quadrotor Using Learned Onboard Wind Estimation in Simulated Atmospheric Turbulence

Two-stage learning pipeline for quadrotor control: estimates wind from onboard sensors, then uses estimates in RL flight controller.

Ax Ege Onur Taga, Yilin Zhuang, M. Emrullah Ildiz, Petros Mol, Abhimanyu Das, Karthik Duraisamy, Samet Oymak 9d ago

Evolutionary Feature Engineering for Structured Data

EFE framework uses LLM-based evolutionary optimization to discover preprocessing transformations for structured data as Python programs.

Ax Leyan Li, Rennong Yang, Zhenxing Zhang, Liping Hu 9d ago

X-LogSMask: Expand Transformer for Graph-Structured Data

X-LogSMask modifies transformer architecture with explainable multi-head attention for improved performance on sparse, structured graph data.

Ax Aria Masoomi, Mahsa Bazzaz, Adel Javanmard, Vahab Mirrokni 9d ago

Geometric Signatures of Reasoning: A Spectral Perspective on Task Hardness

Studies geometric properties of chain-of-thought reasoning trajectories in transformer hidden states to understand task difficulty and reasoning mechanisms.

Ax Zewen Liu 9d ago

BOUNDARY_SYNC: Measuring Communication-Induced Representational Coupling in Multi-Agent LLM Systems

BOUNDARY_SYNC measures representational coupling in multi-agent LLM systems, quantifying how inter-agent communication causes convergence or divergence.

Ax Saoud Aldowaish, Yashwanth Karumanchi, Kai-Chen Chiang, Mohammed Ayman Habib, Finn Murphy, Rishen Cao, Morteza Fayazi 9d ago

SINA: A Fully Automated Circuit Schematic Image to Netlist Generator Using Artificial Intelligence

SINA uses AI to convert circuit schematic images to machine-readable netlists for electronic design automation tasks.

Ax Wenbo Zhang 9d ago

MKGR: Multimodal Knowledge-Graph Representation Learning for Cold-Start Protein-Protein Interaction Prediction

MKGR multimodal framework predicts protein-protein interactions for cold-start scenarios combining knowledge graphs and representation learning.

Ax Haotian Xie, Junlin Chen, Mingkai Zheng, Lishan Yang, Zhao Zhang 9d ago

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

DeadPool enables resilient LLM training at scale by implementing hot-swapping with zero-overhead checkpointing for GPU failure recovery.

Ax Jueqi Wang, Zachary Jacokes, John Darrell Van Horn, Kevin A. Pelphrey, Michael C. Schatz, Archana Venkataraman 9d ago

CALM: Interpretable Cross-Modal Alignment for Biomarker Discovery from Unpaired Data

CALM framework learns interpretable associations between brain ROIs and genetic pathways from disjoint populations using cross-modal alignment.

Ax Wei Xu, An Liu 9d ago

Message Passing Based Two-Timescale Bayesian Learning for Joint Channel and Memory Hardware Impairments Tracking

Message-passing Bayesian deep learning framework for joint channel and hardware impairment tracking in MIMO systems.

Ax Hao Zhou, Xiaoyu Wang, Chang Yao, Mingli Song, Yuanyu Wan 9d ago

Revisiting Decentralized Online Convex Optimization with Compressed Communication

Follow-the-regularized-leader algorithms for decentralized online convex optimization with compressed communication.

Ax Ronghui Xu, Tongxin Wu, Guozhen Zhang, Yihan Li, Chenjuan Guo, Bin Yang, Yong Li 9d ago

UniWind: Toward Unified Day-Ahead Wind Power Forecasting via Physics-Informed State Routing

Physics-informed state routing for unified wind power forecasting with meteorological and operational constraints.

Ax Mingkai Zheng, Junlin Chen, Haotian Xie, Zhao Zhang 9d ago

SCAPE: Accurate and Efficient LLM Training with Extreme Sparse Communication

Communication-efficient LLM training via extreme sparse gradient synchronization with stable sparse Adam optimizer.

Ax Tzu-Heng Huang, Aditya Goyal, John Cooper, Frederic Sala 9d ago

WARP: Weight-Space Analysis for Recovering Training Data Portfolios

Method for inferring training data mixture weights and source distributions from released foundation models.

Ax Long Minh Bui, Tuan Anh Le Van, Tung Phi Duc, Phi Le Nguyen, Jana Doppa, Trong Nghia Hoang 9d ago

Model Merging as Probabilistic Inference in Fine-Tuning Parameter Space

Probabilistic inference framework for merging task-specific fine-tuned models into multi-task solutions.

Ax Jianfeng Lu 9d ago

A Mathematical Introduction to Diffusion Models

Mathematical introduction to diffusion models covering sampling dynamics, error analysis, and inference-time control.

Ax Xiong Xiong, Ruonan Zhai, Zheng Zeng, Sheng Zhou, Rongchun Hu, Zichen Deng 9d ago

Frequency Shift Physics-Informed Extreme Learning Machine for Solving High-Frequency Partial Differential Equations

Physics-informed extreme learning machine addressing spectral bias for solving high-frequency PDEs.

Ax Nikolai Smolyanskiy 9d ago

Predicting Closed-Loop Performance of Latent World Models: Offline Checkpoint Selection for MPC and Model-Based RL Under Non-Markovian Rewards in LunarLander

Validation diagnostics for selecting optimal checkpoints of latent world models in model predictive control and model-based RL.

Ax Cheng Wan, Quyu Kong, Feng Zhou 9d ago

Efficient Temporal Point Processes via Monotone Alternating Splines

Monotone alternating splines for efficient temporal point process modeling via cumulative conditional intensity.

Ax He Huang, Lu Shen, Yunfeng Huang, Li Qi 9d ago

Role-Aware Neural Convex Divergence Heads for Asymmetric Representation Learning

Neural divergence heads for asymmetric representation learning in directed relational tasks.

Ax Meng Wang, Haohan Zhao, Wenzhuo Liu, Lu Yang, Geng Liu, Haiyang Guo, Guo-Sen Xie, Gaofeng Meng, Hongbin Liu, Fei Zhu 9d ago

Denser $\neq$ Better: Limits of On-Policy Self-Distillation for Continual Post-Training

Analysis of self-distillation for continual post-training showing trade-offs between in-domain specialization and knowledge preservation.

Ax Marianne Arriola, Volodymyr Kuleshov 9d ago

Set Diffusion: Interpolating Token Orderings Between Autoregression and Diffusion for Fast and Flexible Decoding

Discrete diffusion model for language generation combining autoregressive and diffusion decoding with flexible token ordering.

Ax Jiaxing Wang, Kaitao Chen, Zhubin Han, Chenyu Hou, Bin Cao, Jing Fan, Ji Zhang 9d ago

EHHN: An Event-driven Heterogeneous Hypergraph Network for Object-Centric Next Activity Prediction

Event-driven hypergraph network for predicting next activity in object-centric business process logs.

Ax Ahin Lee, Sehyun Yun, Taesik Gong 9d ago

EPnG: Adaptive Expert Prune-and-Grow for Parameter-Efficient MoE Fine-tuning

Adaptive prune-and-grow framework for parameter-efficient fine-tuning of Mixture-of-Experts models using LoRA.

Ax Rowan Hussein, Mohamed Ouf 9d ago

Single-Channel EEG-Based Cognitive Load Assessment in Online Learning: A Hybrid Deep Learning Approach

Deep learning approach for assessing cognitive load from single-channel EEG data during online education.

Ax Rodrigo Mendoza-Smith 9d ago

Expander Sparse Autoencoders: Parameter-Efficient Dictionaries for Mechanistic Interpretability

Parameter-efficient sparse autoencoders for interpreting neural network activations using expander graphs.

Ax Jiatong Li, Weida Wang, Changmeng Zheng, Shufei Zhang, Yatao Bian, Xiao-yong Wei, Qing Li 9d ago

Do LLMs Truly Generalize in the Molecular Domain? A Perturbation-Based Analysis

Research on whether LLMs generalize in molecular discovery tasks beyond local neighborhoods of sequence representations.

Ax Nikil Roashan Selvam, Jay Baxter, Sophie Hilgard, Brad Miller, Keith Coleman, Ellen Vitercik, Sanmi Koyejo 9d ago

Gaming Consensus: Coordinated Manipulation in Crowdsourced Fact-Checking

Study of coordinated manipulation attacks on crowdsourced fact-checking systems used by social media platforms.

Ax Dazhi Fu, Jiuding Yang, Yiwen Guo, Jicong Fan 9d ago

Many Voices, One Reward: Multi-Role Rubric Generation for LLM Judging and Reward Modeling

Multi-role rubric generation for LLM evaluation addressing dimensional blind spots in preference-based reward modeling.

Ax Emmanuel C. Chukwu, Rianne M. Schouten, Monique Tabak, Mykola Pechenizkiy 9d ago

Adaptive Group-Based Counterfactual Explanations for Time-Series Rehabilitation Data

Adaptive group-based counterfactual explanations for multivariate time-series classifiers in rehabilitation movement analysis.

Ax Yewon Kim, Apurva Gandhi, David Chung, Graham Neubig, Chris Donahue 9d ago

Decomposer: Learning to Decompile Symbolic Music to Programs

Decomposer: LLM post-training framework for symbolic music decompilation recovering executable music programs from MIDI.

Ax Jen-Yen Chang, Takayuki Osa, Tatsuya Harada 9d ago

Learning the Supports for Categorical Critic in Reinforcement Learning

Gaussian Histogram Loss for learning support distributions in distributional reinforcement learning value functions.

Ax Francis Bach (SIERRA) 9d ago

Regularized Variational and Spectral Log-Density-Ratio Estimation in the Gaussian Location Model

Theoretical study of ridge-regularized log-density-ratio estimation in Gaussian location models with spectral methods.

Ax Yuriy Maksyuta, George Bredis, Ruslan Rakhimov, Daniil Gavrilov 9d ago

Rank-Then-Act: Reward-Free Control from Frame-Order Progress

Rank-Then-Act: Reward-free policy learning from expert videos using vision-language models and ordinal scoring.

Ax Yidan Xu, Xiangmin Han, Rundong Xue, Huihui Ye 9d ago

SABER: A Semantic-Aligned Brain Network Analysis Framework via Multi-scale Hypergraphs

SABER: Brain network analysis framework integrating LLM semantics with multi-scale hypergraphs for disease diagnosis.

Ax Francisco Sede\~no, Francisco Chicano, Jamal Toutouh 9d ago

Population-Based Multi-Objective Training of Discriminators for Semi-Supervised GANs

Population-based evolutionary training for semi-supervised GANs formulated as multi-objective optimization problem.

Ax Zhiren Gong, Zihao Zeng, Chau Yuen, Wei Yang Bryan Lim 9d ago

Conditional Co-Ablation: Recovering Self-Repair Backups in Transformer Circuits

Mechanistic interpretability study of transformer self-repair mechanisms during ablation using conditional co-ablation analysis.

Ax Giacomo Cappiello, Filippo Caruso, Xing Liang, Dimitrios Makris 9d ago

Hybrid quantum-classical neural network for sentiment analysis

Hybrid quantum-classical neural network for sentiment analysis on COVID-19 tweets using TF-IDF vectorization.

Ax Koki Konishi, Masataka Ushiku, Yuta Saito 9d ago

A More Accurate Algorithm Comparison through A/B Testing using Offline Evaluation Methods

Offline evaluation methods for algorithm comparison offering safer alternative to A/B testing with improved accuracy analysis.

Ax Benedikt Kaas, Manuel Treutlein, Hannes Benedikt Gerber, Oliver Neumann, Cheewan Phatthanakhuha, Oliver Resch, Ralf Mikut, Veit Hagenmeyer 9d ago

Probabilistic Low-Voltage Peak Load Forecasting with Time Series Foundation Models Evaluated on Application-Oriented Metrics

Time series foundation models for low-voltage load forecasting with uncertainty estimation and application-oriented evaluation metrics.

Ax Tasnim Shahriar 9d ago

Do Newer Lightweight CNNs Perform Better Under Resource Constraints? A Controlled Multigenerational Study of Architecture, Initialization, Training Budget, and Efficiency

Controlled comparison of nine lightweight CNN architectures across CIFAR-10/100 and Tiny ImageNet under resource constraints.

Ax Weizhi Nie, Weijie Wang, Yuting Su 9d ago

Liquid Latent State Dynamics for Interpretable Turbofan Degradation Modeling

Liquid neural networks for turbofan degradation modeling with interpretable latent state dynamics on C-MAPSS benchmark.

Ax Emanuele Mele, Massimo Cafaro, Angelo Coluccia, Italo Epicoco 9d ago

Fast and Accurate Anomaly Detection in Time Series

Survey of anomaly detection methods for time series across cybersecurity, finance, healthcare, and IoT domains.

Ax Yuval Ran-Milo, Angelos Assos, Elad Hazan 9d ago

A Memory Efficient Unified Algorithm for Online Learning of Linear Dynamical Systems

Online learning algorithm for linear dynamical systems with memory efficiency and sublinear regret guarantees.

Ax Prathamesh Patil, Arpit Jain, Aswanth Krishnan 9d ago

Beyond the Performance Illusion: Structure-Aware Stratified Partitioning and Curriculum Distributionally Robust Optimization for Spatially Correlated Domains

Analysis of dataset split failures in spatiotemporally correlated domains, proposing stratified partitioning and curriculum robust optimization.

Ax Yang Li, Pan Hu, Yan Zhang, Wenfan Yang, Tao Wu, Lianbo Guo 9d ago

SA-HGNN: Sample-Adaptive Hyperbolic Graph Neural Network for EEG-Based Depression Recognition

SA-HGNN: Graph neural network for EEG-based depression recognition using hyperbolic geometry to capture brain network hierarchies.

Ax Mahmoud Abdelfattah, Hamid Nasiri, Peter Garraghan 9d ago

kNNGuard: Turning LLM Hidden Activations into a Training-Free Configurable Guardrail

kNNGuard: Training-free guardrail for LLMs using activation space and k-NN to detect unsafe/adversarial prompts without fine-tuning.