Ax Nan Fang, Yijun Wang, Hao Liao, Sikun Yang 24d ago

Poisson-Gamma Modeling of Inter-Relational Dependencies in Dynamic Knowledge Graphs

PGRE probabilistic model for temporal and relational dependencies in dynamic knowledge graphs.

Ax Zihao Hu, Yuan Yao, Jiheng Zhang, Zhengyuan Zhou 24d ago

Dynamic Regret for Non-Stationary Linear Bandits via Misspecification Reductions

Dynamic regret analysis for non-stationary linear bandits with time-varying action sets and drifting reward models.

Ax Hamish Ogilvy 24d ago

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models

Variable Bit-width Quantization technique where weight groups learn per-group precision for efficient language model compression.

Ax Binglin Ji, Anindya Sarkar, Hengchang Lu, Jens Sj\"olund, Yevgeniy Vorobeychik 24d ago

Bootstrap Flow-Map Tree Sampling Enables Online Feedback Driven Search

Bootstrap sampling method for observation-guided exploration in scientific discovery with limited sampling budget and sequential feedback.

Ax Di Wu, Hongyi Sun, Haichao Xu, Jia Chen, Zhong Chen, Jie Yang 24d ago

CoFEND: A Cross-Modal Fusion End-to-End Network for Cold-Start Drug-Drug Interaction Prediction

CoFEND network for cold-start drug-drug interaction prediction using cross-modal fusion of biomedical entity relationships.

Ax Amirpasha Hedayat, Laura Balzano, Karthik Duraisamy 24d ago

In-span learning: adapting reduced-order models using their own predictions

In-span learning method for adapting reduced-order models using their own predictions without external data.

Ax Soyeon Park, Charmgil Hong 24d ago

Missingness as Signal: Channel-Independent Spectrogram Learning for Clinical Time Series Prediction

CISM framework for clinical time series prediction that models missingness as informative signal in ICU data.

Ax Yujin Kim, Charmgil Hong 24d ago

A Precedent-Guided Co-Scientist for Side-Effect-Aware Drug Redesign

PRECEDE system uses LLM orchestration with knowledge graphs for side-effect-aware drug redesign, framing drug development as evidence-grounded reasoning.

Ax Joy Bose 24d ago

Rank-Order N-of-M Codes for Sparse Distributed Memory: Disentangling Representation and Learning Effects in Noise Robustness Against Contemporary Neuromorphic Architectures

Evaluation of rank-order N-of-M encoding for sparse distributed memory as alternative to threshold-binary encoding for continual learning systems.

Ax Yaniv Shulman, Shaghayegh Akbarpour, Jack B. Muir 24d ago

MABLE: Masked Autoencoding with Bi-Lipschitz Decoding for Embeddings and Graph Metric Learning

MABLE self-supervised framework combining masked reconstruction with bi-Lipschitz decoding for learning node and graph embeddings from heterogeneous graphs.

Ax Joonho Kim, Seyoung Park 24d ago

Transfer Learning in High-dimensional Ising Models

Trans-Ising transfer learning method for high-dimensional Ising model estimation using source screening and two-stage estimation with auxiliary data.

Ax Wenda Wang, Jinjia Feng, Zhewei Wei 24d ago

Back to Basics: Improving Molecular Understanding in LLMs via SMILES-Graph Translation

Molecular LLM improvement via SMILES-graph translation for better structural grounding in chemistry understanding, aligning with structure-determines-function principle.

Ax Beatrice Zanchi, Giuliana Monachino, Alvise Dei Rossi, Luigi Fiorillo, Georgia Sarquella-Brugada, Giulio Conte, Francesca Dalia Faraci 24d ago

Do ECG Foundation Models Transfer to Rare Cardiac Diseases? Evidence from Brugada Syndrome Detection

Evaluation of ECG foundation models on rare cardiac disease detection (Brugada syndrome), assessing transferability to clinically rare phenotypes.

Ax Stefan Horoi, Benjamin Th\'erien, Guy Wolf, Eugene Belilovsky 24d ago

Can Model Merging Improve Aggregation in DiLoCo?

Investigation of model merging techniques for improving aggregation in DiLoCo distributed learning, combining independent finetuned models.

Ax Yuan-Bin Zhu, Shuang Qiao, Shi-Ju Ran 24d ago

Out-of-distribution Neural Inference in Dynamical Ising Models

Study of neural networks for inferring interaction graphs in Ising models, evaluating out-of-distribution generalization across CNN, GNN, and Transformer architectures.

Ax Shijie Cao, Qingyu Zhang, Boxi Yu, Yuzhong Zhang, Boxi Cao, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun 24d ago

OmniFocus: Query-Guided Modality-Balanced Token Compression for Omni-Modal Large Language Models

OmniFocus token compression for multimodal LLMs processing audio-video inputs using query-guided modality-balanced compression to reduce inference cost.

Ax Tomoya Mizuguchi, Bum Jun Kim 24d ago

SHiPPO: Recurrent Memory with Transported Polynomial Projections

SHiPPO extends HiPPO with transported polynomial projections for selective SSMs, enabling token-dependent control and channel interaction in recurrent memory.

Ax Zhuowen Liu, Longkun Hao, Shiyu Feng, Xiaowen Chang, Ruiqun Li, Changqun Li 24d ago

LACE-SVD: Loss-Aware SVD with Cumulative Error Correction for LLM Compression

LACE-SVD compression method for LLMs using loss-aware SVD with cumulative error correction for efficient low-rank compression.

Ax Zhilong Zhang, Hongli Yu, Huan-ang Gao, Hanlin Wu, Yuxuan Song, Wei-Ying Ma, Ya-Qin Zhang, Hao Zhou 24d ago

Spectral Rewiring for Exploration, Purification, and Model Merging

Spectral rewiring technique for RL post-training of LLMs, addressing reasoning saturation and model merging interference through targeted parameter updates.

Ax Nicolas Sournac, Ahmed Baha Ben Jmaa, Bertrand Braeckeveldt 24d ago

Robustness Meets Uncertainty: Evidential Adversarial Training for Robust Selective Classification

Framework combining adversarial training with evidential uncertainty for robust selective classification in safety-critical applications.

Ax Nirhoshan Sivaroopan, Albert Zomaya, Kanchana Thilakarathna 24d ago

STELLA: Efficient Sensor-to-LLM Translation for On-Device Human Activity Recognition

STELLA framework for on-device human activity recognition using efficient sensor-to-LLM translation with lightweight tokenization for edge deployment.

Ax Aymen Sarhane, Fouad Lbakali, Mouad Souissi, Jonathan Lys, Giulia Lioi 24d ago

Stacked LoRA for Subject-Adaptive EEG Foundation Models in Motor Imagery Decoding

Stacked LoRA adapters for subject-adaptive EEG foundation models in motor imagery decoding, addressing cross-subject generalization challenges.

Ax Naoya Chiba, Satoshi Sugiyama, Yuki Uranishi 24d ago

Observable- and Positional-Encoding-Dependent Symmetry Readout from Neural Network Weights

Analysis of symmetry structures recovered from neural network weights with positional encodings and observability hierarchies.

Ax Georg Sch\"afer, Jakob Rehrl, Stefan Huber 24d ago

Integrating Physics-Informed Neural Networks for Safe Reinforcement Learning in a 1-DoF Helicopter System

Physics-informed neural networks integrated into PPO actor loss for safe DRL in cyber-physical systems with hardware constraints.

Ax Zijun Xie, Yuyang You, Yongzhi Li, Enlei Gong, Zeyu Chen, Quan Chen, Yanhua Cheng, Peng Jiang, Yadong Mu 24d ago

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

ACPO method for token-level credit assignment in RL-finetuned LLMs, using fine-grained surrogate entropy for improved reasoning ability.

Ax Georg Sch\"afer, Jakob Rehrl, Stefan Huber, Simon Hirlaender 24d ago

Anticipatory Reinforcement Learning for Trajectory Tracking

Deep RL with predictive formulation for trajectory tracking using PPO, augmenting state space with target velocities to reduce lag and overshoot.

Ax Georg Sch\"afer, Jakob Rehrl, Stefan Huber, Simon Hirlaender 24d ago

Sample-Efficient Pareto Front Modeling for Energy-Aware Reinforcement Learning Using Bayesian Optimization

Multi-objective RL for industrial automation using Bayesian optimization to model Pareto fronts for energy-efficient control strategies.

Ax Alexandre L. M. Levada 24d ago

CuBAS: Information Geometric Curvature-Based Adaptive Sampling for Supervised Classification

CuBAS: information-geometric framework for adaptive data sampling in supervised classification using curvature-based selection.

Ax Muhammad Sabih, Frank Hannig, J\"urgen Teich 24d ago

Rethinking Neural Nonlinearity as Gating

Shows neural nonlinearity can be achieved through input-conditioned threshold gating as alternative to activation functions, unifying standard activations.

Ax Rajat Ghosh 24d ago

Reduced-Order Models: The Mother of World Models

Connects world models in modern deep learning to classical model-order-reduction and control theory, showing shared functional anatomy.

Ax Jialiang Wang, Xianming Liu, Xiong Zhou, Hui Liu, Haoliang Li 24d ago

Unbiased Alignment for Large Language Models with Noisy Preferences

Proposes Unbiased Reward Model loss and Unbiased DPO for robust LLM alignment from noisy preference datasets.

Ax Bing Cheng, Yi-Shuai Niu, Howell Tong, Shing-Tung Yau 24d ago

Statistically Meaningful Geometry (SMG) Beyond the Euclidean Paradigm, with Application to Generative AI

Proposes statistically meaningful geometry framework for analyzing generalization in over-parameterized models like transformers, addressing hallucination issues.

Ax Jakob Hartmann, James Harvey, Jhonathan Navott, Erik Y. Wang, Luckeciano C. Melo, Flaviu Cipcigan, Cheng Zhang, Alessandro Abate 24d ago

Amortising Bayesian Experimental Design for Sequential Information Gathering in LLMs

Proposes ASIG, a fine-tuning approach using Bayesian Experimental Design to improve information gathering in multi-turn LLM decision-making settings.

Ax Teng-Ruei Chen 24d ago

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

Analyzes routing gaps between learned routers and oracles for LLM selection, decomposing the gap into reproducible specialist advantage and label noise components.

Ax Yanbo Wang, Jinhua Hao, Yuze Shi, Kun Yuan, Ming Sun 24d ago

No Time Like the Present: Agentic Test-Time Training for LLM Agents

Research on continuous test-time training for LLM agents to adapt model weights during multi-turn episodes, addressing performance degradation over long trajectories.

Ax Eric Lei, Hsiang Hsu, Chun-Fu Chen 24d ago

Best-of-Better-$N$: Generating Pre-Aligned Responses with In-Context Learning

Best-of-Better-N method uses in-context learning to generate pre-aligned LLM responses without requiring additional training.

Ax Wei Zhang, Lin Tang, Ming Zhao, Yuxuan Wang 24d ago

Co-Adaptive Multi-Task LoRA: Transfer-Aware, Label-Free Control of Domain Participation

Co-adaptive multi-task LoRA fine-tuning framework that adaptively controls domain participation without labels for transfer-aware learning.

Ax Gaoxiang Luo, Yifan Wu, Sinian Zhang, Aryan Deshwal, Ju Sun 24d ago

Aligning Language Models with Selective Prediction

Enhances LLM reliability through selective prediction, allowing models to abstain on uncertain inputs to reduce error rate.

Ax Aron Asefaw, Konstantinos Tzevelekakis, Damian Falk, L\'eo Meynent, Damian Borth 24d ago

WeightCLIP: Aligning Datasets and Models for Weight Space Learning

WeightCLIP learns dataset-aligned latent space for neural network weights, aligning datasets and models for weight space learning.

Ax Sang Il Han 24d ago

Teacher Supervision over Representation Equivalence Classes

Reframes knowledge distillation to match teacher representation equivalence classes rather than absolute feature coordinates.

Ax Lucas Sheneman 24d ago

Differentiate the Evaluator, Not the Program: An Efficient Runtime Representation for Neuro-Symbolic Learning

Efficient neuro-symbolic learning method that optimizes evaluator differentiation rather than program differentiation for parameter calibration.

Ax Quang Hung Pham, Ryad Zemouri, Martin Gagnon, Luc Vouligny 24d ago

Modular Foundation Models for Time-Series Perception in Digital Twins

Modular foundation models for time-series perception in digital twins and prognostics health management systems.

Ax Xiaoyue Liu, Zheng Dong 24d ago

LLM-Guided Transportation Hub Capacity Planning with Textual Business Inputs

LLM agent framework for transportation hub capacity planning that iteratively proposes decisions guided by natural-language business context.

Ax Zhuoer Shen, Mingyi Wang, Shaofeng Zou, Yuheng Bu 24d ago

Rethinking AI-Generated Text Detection: A Strong Baseline and the Distribution-Shift Problem That Remains

Shows fine-tuned RoBERTa matches specialized detectors for AI-generated text detection; challenges recent architectural complexity in detection methods.

Ax Kaixuan Liu, Guojun Xiong, Weinan Zhang, Shengpu Tang 24d ago

Social Networks of LLM Agents

Studies how populations of LLM agents form collective beliefs and whether they aggregate genuine knowledge or collapse into false consensus.

Ax Byoungkwon Kim, Minhyuk Sung 24d ago

Tensor-Train Joint Modeling for Few-Step Discrete Diffusion

Proposes tensor-train joint modeling to improve discrete diffusion models for faster sequential generation compared to autoregressive approaches.

Ax Yoshihiro Maruyama 24d ago

Foundations of Equivariant Deep Learning: Unifying Graph and Sheaf Neural Networks

Extends geometric deep learning with order-equivariant neural networks that generalize graph message passing and sheaf neural networks using equivariant bundle theory.

Ax Bhavesh Sood, Jaromir Savelka 24d ago

Punching Above Their Weight: Classification-Head Fine-Tuning of Tiny Language Models (TLMs) for Verifiable Multiple-Choice Tasks

Study of classification-head fine-tuning for tiny language models (under 3B parameters) on multiple-choice reasoning tasks, comparing LoRA paradigms.

Ax Benjamin Wiriyapong, Oktay Karakus, Can Eyupoglu, Kirill Sidorov 24d ago

Stable Global Weighting of Flow Mixtures using Simplex Exponential Moving Average

Two-stage framework for normalizing flow mixtures using simplex exponential moving average for stable weighting across heterogeneous posterior geometries.

Ax Zhen Huang, Peicheng Xu, Junbiao Pang, Yulong Zheng 24d ago

Adversarial LassoNet: Robust Feature Selection via Stability-Driven Sparse Learning

Adversarial training approach for robust feature selection in high-dimensional learning, improving stability of sparse feature supports under noise.