GGBench: A Geometric Generative Reasoning Benchmark for Unified Multimodal Models
arXiv:2511.11134v1 Announce Type: new Abstract: The advent of Unified Multimodal Models (UMMs) signals a paradigm shift in artificial intelligence, moving from passive perception to active, cross-modal generation. Despite their unprecedented ability to synthesize information, a critical gap persist
Softmax as a Lagrangian-Legendrian Seam
arXiv:2511.11573v1 Announce Type: new Abstract: This note offers a first bridge from machine learning to modern differential geometry. We show that the logits-to-probabilities step implemented by softmax can be modeled as a geometric interface: two potential-generated, conservative descriptions (fr
LLM on a Budget: Active Knowledge Distillation for Efficient Classification of Large Text Corpora
arXiv:2511.11574v1 Announce Type: new Abstract: Large Language Models (LLMs) are highly accurate in classification tasks, however, substantial computational and financial costs hinder their large-scale deployment in dynamic environments. Knowledge Distillation (KD) where a LLM "teacher" trains a sm
Detecting Statistically Significant Fairness Violations in Recidivism Forecasting Algorithms
arXiv:2511.11575v1 Announce Type: new Abstract: Machine learning algorithms are increasingly deployed in critical domains such as finance, healthcare, and criminal justice [1]. The increasing popularity of algorithmic decision-making has stimulated interest in algorithmic fairness within the academ
DAOpt: Modeling and Evaluation of Data-Driven Optimization under Uncertainty with LLMs
arXiv:2511.11576v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have accelerated research on automated optimization modeling. While real-world decision-making is inherently uncertain, most existing work has focused on deterministic optimization with known parameters,
Decoupling Positional and Symbolic Attention Behavior in Transformers
arXiv:2511.11579v1 Announce Type: new Abstract: An important aspect subtending language understanding and production is the ability to independently encode positional and symbolic information of the words within a sentence. In Transformers, positional information is typically encoded using Position
The Anatomy of a Triton Attention Kernel
arXiv:2511.11581v1 Announce Type: new Abstract: A long-standing goal in both industry and academia is to develop an LLM inference platform that is portable across hardware architectures, eliminates the need for low-level hand-tuning, and still delivers best-in-class efficiency. In this work, we dem
Parallel and Multi-Stage Knowledge Graph Retrieval for Behaviorally Aligned Financial Asset Recommendations
arXiv:2511.11583v1 Announce Type: new Abstract: Large language models (LLMs) show promise for personalized financial recommendations but are hampered by context limits, hallucinations, and a lack of behavioral grounding. Our prior work, FLARKO, embedded structured knowledge graphs (KGs) in LLM prom
Output Supervision Can Obfuscate the Chain of Thought
arXiv:2511.11584v1 Announce Type: new Abstract: OpenAI (2025) showed that training against a chain of thought (CoT) monitor can cause obfuscated CoTs, which contain bad behavior the monitor cannot detect. They proposed to keep CoTs monitorable by training only against output monitors that do not ha
Parameter-Efficient and Personalized Federated Training of Generative Models at the Edge
arXiv:2511.11585v1 Announce Type: new Abstract: Large generative models (for example, language and diffusion models) enable high-quality text and image synthesis but are hard to train or adapt in cross-device federated settings due to heavy computation and communication and statistical/system heter
WildfireGenome: Interpretable Machine Learning Reveals Local Drivers of Wildfire Risk and Their Cross-County Variation
arXiv:2511.11589v1 Announce Type: new Abstract: Current wildfire risk assessments rely on coarse hazard maps and opaque machine learning models that optimize regional accuracy while sacrificing interpretability at the decision scale. WildfireGenome addresses these gaps through three components: (1)
Mind Your Entropy: From Maximum Entropy to Trajectory Entropy-Constrained RL
arXiv:2511.11592v1 Announce Type: new Abstract: Maximum entropy has become a mainstream off-policy reinforcement learning (RL) framework for balancing exploitation and exploration. However, two bottlenecks still limit further performance improvement: (1) non-stationary Q-value estimation caused by
Sound Logical Explanations for Mean Aggregation Graph Neural Networks
arXiv:2511.11593v1 Announce Type: new Abstract: Graph neural networks (GNNs) are frequently used for knowledge graph completion. Their black-box nature has motivated work that uses sound logical rules to explain predictions and characterise their expressivity. However, despite the prevalence of GNN
Loss Given Default Prediction Under Measurement-Induced Mixture Distributions: An Information-Theoretic Approach
arXiv:2511.11596v1 Announce Type: new Abstract: Loss Given Default (LGD) modeling faces a fundamental data quality constraint: 90% of available training data consists of proxy estimates based on pre-distress balance sheets rather than actual recovery outcomes from completed bankruptcy proceedings.
Aspiration-based Perturbed Learning Automata in Games with Noisy Utility Measurements. Part A: Stochastic Stability in Non-zero-Sum Games
arXiv:2511.11602v1 Announce Type: new Abstract: Reinforcement-based learning has attracted considerable attention both in modeling human behavior as well as in engineering, for designing measurement- or payoff-based optimization schemes. Such learning schemes exhibit several advantages, especially
Enhancing failure prediction in nuclear industry: Hybridization of knowledge- and data-driven techniques
arXiv:2511.11604v1 Announce Type: new Abstract: The convergence of the Internet of Things (IoT) and Industry 4.0 has significantly enhanced data-driven methodologies within the nuclear industry, notably enhancing safety and economic efficiency. This advancement challenges the precise prediction of
Clustering-Based Weight Orthogonalization for Stabilizing Deep Reinforcement Learning
arXiv:2511.11607v1 Announce Type: new Abstract: Reinforcement learning (RL) has made significant advancements, achieving superhuman performance in various tasks. However, RL agents often operate under the assumption of environmental stationarity, which poses a great challenge to learning efficiency
Small Vocabularies, Big Gains: Pretraining and Tokenization in Time Series Models
arXiv:2511.11622v1 Announce Type: new Abstract: Tokenization and transfer learning are two critical components in building state of the art time series foundation models for forecasting. In this work, we systematically study the effect of tokenizer design, specifically scaling and quantization stra
Early GVHD Prediction in Liver Transplantation via Multi-Modal Deep Learning on Imbalanced EHR Data
arXiv:2511.11623v1 Announce Type: new Abstract: Graft-versus-host disease (GVHD) is a rare but often fatal complication in liver transplantation, with a very high mortality rate. By harnessing multi-modal deep learning methods to integrate heterogeneous and imbalanced electronic health records (EHR
MedFedPure: A Medical Federated Framework with MAE-based Detection and Diffusion Purification for Inference-Time Attacks
arXiv:2511.11625v1 Announce Type: new Abstract: Artificial intelligence (AI) has shown great potential in medical imaging, particularly for brain tumor detection using Magnetic Resonance Imaging (MRI). However, the models remain vulnerable at inference time when they are trained collaboratively thr