Agile Flight Emerges from Multi-Agent Competitive Racing

Pasumarti, Bianchi & Loquercio

Stronger Normalization-Free Transformers

Chen et al.

Performance Benchmarking of Tensor Trains for accelerated Quantum-Inspired Homogenization on TPU, GPU and CPU architectures

Hauck, Kabel & Gauger

RRAEDy: Adaptive Latent Linearization of Nonlinear Dynamical Systems

Mounayer et al.

Rectifying Latent Space for Generative Single-Image Reflection Removal

Li et al.

Hyperparameter Transfer Enables Consistent Gains of Matrix-Preconditioned Optimizers Across Scales

Qiu et al.

EventQueues: Autodifferentiable spike event queues for brain simulation on AI accelerators

Landsmeer et al.

Assessment of the GraphCast AI model for precipitation forecasting and its potential in extreme event prediction over Bangladesh

Hasan, Yildiz & Kamruzzaman

Arbitrage: Efficient Reasoning via Advantage-Aware Speculation

Maheswaran et al.

Defense That Attacks: How Robust Models Become Better Attackers

Awad, Akrm & Gomaa

Improved Mean Flows: On the Challenges of Fastforward Generative Models

Geng et al.

MLIPAudit: A benchmarking tool for Machine Learned Interatomic Potentials

Wehrhan et al.

Code-Switch Pretraining for Improved Cross-Lingual Alignment in Low-Resource Languages

Visser, Grobler & Dunaiski

Scaling Behavior of Encoder Language Models in Low-Resource Settings

Visser, Grobler & Dunaiski

Flow Map Distillation Without Data

Tong et al.

CDLM: Consistency Diffusion Language Models For Faster Sampling

Kim et al.

TempoPFN: Towards Synthetic Pre-training of Linear RNNs for Zero-shot Time Series Forecasting

Moroshan et al.

Geospatial Open Building Stack

Jindal & Kumar

Transformers Are Optimal Effective Fields

Fu

Aspect-Based Sentiment Analysis for Stock Price Movement Prediction

Dang et al.

Relative Scaling Laws for LLMs

Held et al.

HTU at MAHED Shared Task: Ensemble-Based Classification of Arabic Hate and Hope Speech Using Pre-trained Dialectal Arabic Models

Saleh & Biltawi

HalleluBERT: Let every token that has meaning bear its weight

Scheible-Schmitt

SindBERT, the Sailor: Charting the Seas of Turkish NLP

Scheible-Schmitt & Schweter

Simple Context Compression: Mean-Pooling and Multi-Ratio Training

Feldman & Artzi

Scaling and Taming Adversarial Training with Synthetic Data

Wu et al.

PyTorchSim: A Comprehensive, Fast, and Accurate NPU Simulation Framework

Yang et al.

Diffusion Transformers with Representation Autoencoders

Zheng et al.

Beyond Conventional Transformers: A Medical X-ray Attention Block for Improved Multi-Label Diagnosis

Rand & Ibrahim

Beyond Next-Token Prediction: A Performance Characterization of Diffusion versus Autoregressive Language Models

Kim et al.

PUREVQ-GAN: Defending Data Poisoning Attacks through Vector-Quantized Bottlenecks

Branch et al.

Comparative Analysis of Chemical Structure String Representations for Neural Machine Translation

Rajan, Zielesny & Steinbeck

Cheminformatics Microservice V3: a web portal for chemical structure manipulation and analysis

Rajan et al.

CayleyPy Growth: Efficient growth computations and hundreds of new conjectures on Cayley graphs

Chervov et al.

Artificial Neural Networks and Machine Learning

Senn et al.

How to Scale Second-Order Optimization

Chen et al.

Martingale Posterior Neural Networks for Fast Sequential Decision Making

Duran-Martin et al.

Breaking the Performance Ceiling in Reinforcement Learning requires Inference Strategies

Chalumeau et al.

Memory-Enhanced Neural Solvers for Routing Problems

Chalumeau et al.

On Evaluating LLM Alignment by Evaluating LLMs as Judges

Liu, Liu & Cohan

Oryx: a Scalable Sequence Model for Many-Agent Coordination in Offline MARL

Formanek et al.

BC-predict: mining of signal biomarkers and production of models for early-stage breast cancer subtyping and prognosis

Muthamilselvan, Vaithilingam & Palaniappan

Pre-training under infinite compute

Kim et al.

PortBERT: Navigating the Depths of Portuguese Language Models

Scheible-Schmitt, He & Mendes

World Modeling with Probabilistic Structure Integration

Kotar et al.

Experiments with data-augmented modeling of ADME and potency endpoints in the ASAP-Polaris-OpenADMET Antiviral Challenge

Srilakshmi, Tituss & Palaniappan

Building High-Quality Datasets for Portuguese LLMs: From Common Crawl Snapshots to Industrial-Grade Corpora

Almeida, Nogueira & Pedrini

Creating a Large Clean Web Corpus for Turkish

Uzun et al.

Fantastic Pretraining Optimizers and Where to Find Them

Wen et al.

OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning

Liu et al.

Democracy-in-Silico: Institutional Design as Alignment in AI-Governed Polities

Srinivasan & Patapati

Age-Normalized HRV Features for Non-Invasive Glucose Prediction: A Pilot Sleep-Aware Machine Learning Study

Azam & Singh

XQuant: Breaking the Memory Wall for LLM Inference with KV Cache Rematerialization

Tomar et al.

Loss Landscape Degeneracy and Stagewise Development in Transformers

Hoogland et al.

Representing Speech Through Autoregressive Prediction of Cochlear Tokens

Tuckute et al.

ReGate: Enabling Power Gating in Neural Processing Units

Xue & Huang

HTU at SemEval-2025 Task 11: Divide and Conquer-Multi-Label emotion classification using 6 DziriBERTs submodels with Label-fused Iterative Mask Filling technique for low-resource data augmentation.

Saleh & Biltawi

Clinical-Grade Blood Pressure Prediction in ICU Settings: An Ensemble Framework with Uncertainty Quantification and Cross-Institutional Validation

Azam & Singh

Discovering and using Spelke segments

Venkatesh et al.

Topographic Vision Transformers

Shah & Yamins

Ref-Long: Benchmarking the Long-context Referencing Capability of Long-context Language Models

Wu et al.

Taming generative video models for zero-shot optical flow extraction

Kim et al.

Reward Under Attack: Evaluating the Sensitivity of Process Reward Models

Bamba et al.

Small Batch Size Training for Language Models: When Vanilla SGD Works, and Why Gradient Accumulation Is Wasteful

Marek et al.

MARCUS: Molecular Annotation and Recognition for Curating Unravelled Structures

Rajan et al.

Bimodal masked language modeling for bulk RNA-seq and DNA methylation representation learning

Gélard et al.

Outlier-Safe Pre-Training for Robust 4-Bit Quantization of Large Language Models

Park et al.

MeshSlice: Efficient 2D Tensor Parallelism for Distributed DNN Training

Nam, Gerogiannis & Torrellas

SciVer: Evaluating Foundation Models for Multimodal Scientific Claim Verification

Wang et al.

Don't throw the baby out with the bathwater: How and why deep learning for ARC

Cole & Osman

Multipole Attention for Efficient Long Context Reasoning

Hooper et al.

Scalable Generalized Bayesian Online Neural Network Training for Sequential Decision Making

Duran-Martin et. al

Visual Pre-Training on Unlabeled Images using Reinforcement Learning

Ghosh & Levine

Diffuse and Disperse: Image Generation with Representation Regularization

Wang & He

A Stable Whitening Optimizer for Efficient Neural Network Training

Franz, Levine & Abbeel

Language Representation Models for Low-and Medium-Resource Languages

Daðason

Cheminformatics Microservice V-3: A Web Portal for Chemical Structure Manipulation and Analysis

Rajan et al.

Is an Exponentially Growing Action Space Really that Bad? Validating a Core Assumption for using Multi-Agent RL

de Kock, Pretorius & Shock

Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models

Deitke et al.

Classification of Epilepsy Seizure Types in Pediatrics Based on Turkish EEG Reports

Aslan et al.

MetaFaith: Faithful Natural Language Uncertainty Expression in LLMs

Liu et al.

Predicting gene expression using millions of yeast promoters reveals cis-regulatory logic

Dash & Bornelöv

Efficient and Unbiased Sampling from Boltzmann Distributions via Variance-Tuned Diffusion Models

Zhang, Midgely & Hernández-Lobato

Breaking the Performance Ceiling in Complex Reinforcement Learning requires Inference Strategies

Chalumeau et al.