arXiv:2511.03845v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) are reshaping how modern agentic systems reason over sequential user-behavior data. However, whether textual or image representations of user behavior data are more effective for maximizing MLLM performance remains underexplored. We present textttBehaviorLens, a systematic benchmarking framework for assessing modality trade-offs in user-behavior reasoning across […]
Optimizing Reasoning Efficiency through Prompt Difficulty Prediction
arXiv:2511.03808v1 Announce Type: cross Abstract: Reasoning language models perform well on complex tasks but are costly to deploy due to their size and long reasoning traces. We propose a routing approach that assigns each problem to the smallest model likely to solve it, reducing compute without sacrificing accuracy. Using intermediate representations from s1.1-32B, we train […]
Scaling Agent Learning via Experience Synthesis
arXiv:2511.03773v1 Announce Type: new Abstract: While reinforcement learning (RL) can empower large language model (LLM) agents by enabling self-improvement through interaction, its practical adoption remains challenging due to costly rollouts, limited task diversity, unreliable reward signals, and infrastructure complexity, all of which obstruct the collection of scalable experience data. To address these challenges, we introduce […]
Improving Diagnostic Performance on Small and Imbalanced Datasets Using Class-Based Input Image Composition
arXiv:2511.03891v1 Announce Type: cross Abstract: Small, imbalanced datasets and poor input image quality can lead to high false predictions rates with deep learning models. This paper introduces Class-Based Image Composition, an approach that allows us to reformulate training inputs through a fusion of multiple images of the same class into combined visual composites, named Composite […]
How Different Tokenization Algorithms Impact LLMs and Transformer Models for Binary Code Analysis
arXiv:2511.03825v1 Announce Type: new Abstract: Tokenization is fundamental in assembly code analysis, impacting intrinsic characteristics like vocabulary size, semantic coverage, and extrinsic performance in downstream tasks. Despite its significance, tokenization in the context of assembly code remains an underexplored area. This study aims to address this gap by evaluating the intrinsic properties of Natural Language […]
RLHF: A comprehensive Survey for Cultural, Multimodal and Low Latency Alignment Methods
arXiv:2511.03939v1 Announce Type: cross Abstract: Reinforcement Learning from Human Feedback (RLHF) is the standard for aligning Large Language Models (LLMs), yet recent progress has moved beyond canonical text-based methods. This survey synthesizes the new frontier of alignment research by addressing critical gaps in multi-modal alignment, cultural fairness, and low-latency optimization. To systematically explore these domains, […]
Climbing the label tree: Hierarchy-preserving contrastive learning for medical imaging
arXiv:2511.03771v1 Announce Type: new Abstract: Medical image labels are often organized by taxonomies (e.g., organ – tissue – subtype), yet standard self-supervised learning (SSL) ignores this structure. We present a hierarchy-preserving contrastive framework that makes the label tree a first-class training signal and an evaluation target. Our approach introduces two plug-in objectives: Hierarchy-Weighted Contrastive (HWC), […]
Towards Scalable Meta-Learning of near-optimal Interpretable Models via Synthetic Model Generations
arXiv:2511.04000v1 Announce Type: cross Abstract: Decision trees are widely used in high-stakes fields like finance and healthcare due to their interpretability. This work introduces an efficient, scalable method for generating synthetic pre-training data to enable meta-learning of decision trees. Our approach samples near-optimal decision trees synthetically, creating large-scale, realistic datasets. Using the MetaTree transformer architecture, […]
Current validation practice undermines surgical AI development
arXiv:2511.03769v1 Announce Type: new Abstract: Surgical data science (SDS) is rapidly advancing, yet clinical adoption of artificial intelligence (AI) in surgery remains severely limited, with inadequate validation emerging as a key obstacle. In fact, existing validation practices often neglect the temporal and hierarchical structure of intraoperative videos, producing misleading, unstable, or clinically irrelevant results. In […]
DeNoise: Learning Robust Graph Representations for Unsupervised Graph-Level Anomaly Detection
arXiv:2511.04086v1 Announce Type: cross Abstract: With the rapid growth of graph-structured data in critical domains, unsupervised graph-level anomaly detection (UGAD) has become a pivotal task. UGAD seeks to identify entire graphs that deviate from normal behavioral patterns. However, most Graph Neural Network (GNN) approaches implicitly assume that the training set is clean, containing only normal […]