arXiv:2605.06054v1 Announce Type: new Abstract: Large language model (LLM) outputs arise from complex interactions among prompts, system instructions, model parameters, and architecture. We refer to specific configurations of these factors as generation conditions, each of which can bias outputs in various ways. Understanding how different generation conditions shape model behaviors is essential for tasks such […]
FunctionalAgent: Towards end-to-end on-top functional design
arXiv:2605.06215v1 Announce Type: cross Abstract: Multiconfiguration pair-density functional theory (MC-PDFT) offers an efficient and accurate framework for computing electronic energies in strongly correlated molecular systems, with the quality of the on-top functional being a key determinant of its predictive accuracy. Here we introduce FunctionalAgent, an agentic system for fully automated functional development. FunctionalAgent orchestrates a […]
StableTTA: Improving Vision Model Performance by Training-free Test-Time Adaptation Methods
arXiv:2604.04552v3 Announce Type: replace-cross Abstract: Ensemble methods improve predictive performance but often incur high memory and computational costs. We identify an aggregation instability induced by nonlinear projection and voting operations. To address both efficiency challenges and this inconsistency, we propose StableTTA, a training-free test-time adaptation method with two variants. StableTTA-I targets coherent-batch inference settings, where […]
Fast and Efficient Gossip Algorithms for Robust and Non-smooth Decentralized Learning
arXiv:2601.20571v2 Announce Type: replace-cross Abstract: Decentralized learning on resource-constrained edge devices demands algorithms that are communication-efficient, robust to data corruption, and lightweight in memory. State-of-the-art gossip-based methods address communication efficiency, but achieving robustness remains challenging. Methods for robust estimation and optimization typically rely on non-smooth objectives (textite.g., pinball loss, $ell_1$ loss), yet standard gossip methods […]
Learning Lifted Action Models from Unsupervised Visual Traces
arXiv:2604.19043v2 Announce Type: replace Abstract: Efficient construction of models capturing the preconditions and effects of actions is essential for applying AI planning in real-world domains. Extensive prior work has explored learning such models from high-level descriptions of state and/or action sequences. In this paper, we tackle a more challenging setting: learning lifted action models from […]
Attribution-Guided Pruning for Insight and Control: Circuit Discovery and Targeted Correction in Small-scale LLMs
arXiv:2506.13727v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are widely deployed in real-world applications, yet their internal mechanisms remain difficult to interpret and control, limiting our ability to diagnose and correct undesirable behaviors. Mechanistic interpretability addresses this challenge by identifying circuits — subsets of model components responsible for specific behaviors. However, discovering such circuits […]
Feature Dimensionality Outweighs Model Complexity in Breast Cancer Subtype Classification Using TCGA-BRCA Gene Expression Data
arXiv:2605.06562v1 Announce Type: cross Abstract: Accurate classification of breast cancer subtypes from gene expression data is critical for diagnosis and treatment selection. However, such datasets are characterized by high dimensionality and limited sample size, posing challenges for machine learning models. In this study, we evaluate the impact of model complexity and feature selection on subtype […]
Unifying Goal-Conditioned RL and Unsupervised Skill Learning via Control-Maximization
arXiv:2605.06145v1 Announce Type: cross Abstract: Unsupervised pretraining has driven empirical advances in goal-conditioned reinforcement learning (GCRL), but its theoretical foundations remain poorly understood. In particular, an influential class of methods, mutual information skill learning (MISL), discovers behaviorally diverse skills that can later be used for downstream goal-reaching. However, it remains a theoretical mystery why skills […]
Measuring Evaluation-Context Divergence in Open-Weight LLMs: A Paired-Prompt Protocol with Pilot Evidence of Alignment-Pipeline-Specific Heterogeneity
arXiv:2605.06327v1 Announce Type: cross Abstract: Safety benchmarks are routinely treated as evidence about how a language model will behave once deployed, but this inference is fragile if behavior depends on whether a prompt looks like an evaluation. We define evaluation-context divergence as an observable within-item change in behavior induced by framing a fixed task as […]
DARK: Diagonal-Anchored Repulsive Knowledge Distillation for Vision-Language Models under Extreme Compression
arXiv:2603.05421v3 Announce Type: replace-cross Abstract: Compressing vision-language models for on-device deployment is increasingly important in clinical settings, but knowledge distillation (KD) degrades sharply when the teacher-student capacity gap spans an order of magnitude or more. We argue that, under such gaps, strict imitation of the teacher is a poor objective: much of the teacher’s pairwise […]
Enhancing Science Classroom Discourse Analysis through Joint Multi-Task Learning for Reasoning-Component Classification
arXiv:2604.21137v2 Announce Type: replace-cross Abstract: Analyzing the reasoning patterns of students in science classrooms is critical for understanding knowledge construction mechanism and improving instructional practice to maximize cognitive engagement, yet manual coding of classroom discourse at scale remains prohibitively labor-intensive. We present an automated discourse analysis system (ADAS) that jointly classifies teacher and student utterances […]
COVID-19 Infodemic. Understanding content features in detecting fake news using a machine learning approach
arXiv:2605.06435v1 Announce Type: cross Abstract: The use of content features, particularly textual and linguistic for fake news detection is under-researched, despite empirical evidence showing the features could contribute to differentiating real and fake news. To this end, this study investigates a selection of content features such as word bigrams, part of speech distribution etc. to […]