arXiv:2603.19519v2 Announce Type: replace-cross Abstract: We address a not-widely-recognized subset of exploratory search, where a user sets out on a typically long “search quest” for the perfect wedding dress, overlooked research topic, killer company idea, etc. The first few outputs of current large language models (LLMs) may be helpful but only as a start, since […]
Mind the Gap: A Framework for Assessing Pitfalls in Multimodal Active Learning
arXiv:2603.29677v1 Announce Type: cross Abstract: Multimodal learning enables neural networks to integrate information from heterogeneous sources, but active learning in this setting faces distinct challenges. These include missing modalities, differences in modality difficulty, and varying interaction structures. These are issues absent in the unimodal case. While the behavior of active learning strategies in unimodal settings […]
Sampling at intermediate temperatures is optimal for training large language models in protein structure prediction
arXiv:2603.29529v1 Announce Type: cross Abstract: We investigate the parameter space of transformer models trained on protein sequence data using a statistical mechanics framework, sampling the loss landscape at varying temperatures by Langevin dynamics to characterize the low-loss manifold and understand the mechanisms underlying the superior performance of transformers in protein structure prediction. We find that, […]
DIAL: Decoupling Intent and Action via Latent World Modeling for End-to-End VLA
arXiv:2603.29844v1 Announce Type: cross Abstract: The development of Vision-Language-Action (VLA) models has been significantly accelerated by pre-trained Vision-Language Models (VLMs). However, most existing end-to-end VLAs treat the VLM primarily as a multimodal encoder, directly mapping vision-language features to low-level actions. This paradigm underutilizes the VLM’s potential in high-level decision making and introduces training instability, frequently […]
How do LLMs Compute Verbal Confidence
arXiv:2603.17839v2 Announce Type: replace-cross Abstract: Verbal confidence — prompting LLMs to state their confidence as a number or category — is widely used to extract uncertainty estimates from black-box models. However, how LLMs internally generate such scores remains unknown. We address two questions: first, when confidence is computed – just-in-time when requested, or automatically during […]
Interview-Informed Generative Agents for Product Discovery: A Validation Study
arXiv:2603.29890v1 Announce Type: cross Abstract: Large language models (LLMs) have shown strong performance on standardized social science instruments, but their value for product discovery remains unclear. We investigate whether interview-informed generative agents can simulate user responses in concept testing scenarios. Using in-depth workflow interviews with knowledge workers, we created personalized agents and compared their evaluations […]
Baby Scale: Investigating Models Trained on Individual Children’s Language Input
arXiv:2603.29522v1 Announce Type: cross Abstract: Modern language models (LMs) must be trained on many orders of magnitude more words of training data than human children receive before they begin to produce useful behavior. Assessing the nature and origins of this “data gap” requires benchmarking LMs on human-scale datasets to understand how linguistic knowledge emerges from […]
Rethinking AI Literacy Education in Higher Education: Bridging Risk Perception and Responsible Adoption
arXiv:2603.29935v1 Announce Type: cross Abstract: As AI becomes increasingly embedded across societal domains, understanding how future AI practitioners, particularly technology students, perceive its risks is essential for responsible development and adoption. This study analyzed responses from 139 students in Computer Science, Data Science/Data Analytics, and other disciplines using both explicit AI risk ratings and scenario-based […]
Hybrid Framework for Robotic Manipulation: Integrating Reinforcement Learning and Large Language Models
arXiv:2603.30022v1 Announce Type: cross Abstract: This paper introduces a new hybrid framework that combines Reinforcement Learning (RL) and Large Language Models (LLMs) to improve robotic manipulation tasks. By utilizing RL for accurate low-level control and LLMs for high level task planning and understanding of natural language, the proposed framework effectively connects low-level execution with high-level […]
TrafficMoE: Heterogeneity-aware Mixture of Experts for Encrypted Traffic Classification
arXiv:2603.29520v1 Announce Type: cross Abstract: Encrypted traffic classification is a critical task for network security. While deep learning has advanced this field, the occlusion of payload semantics by encryption severely challenges standard modeling approaches. Most existing frameworks rely on static and homogeneous pipelines that apply uniform parameter sharing and static fusion strategies across all inputs. […]
From seasons to decades: Solar radiation, cloud cover, and CO$_2$ shape young leaf phenology in a tropical forest over 26 years
arXiv:2501.07620v2 Announce Type: replace Abstract: 1. Climate change is altering plant phenology globally with potential deleterious impacts on animal species and entire ecosystems, yet the long-term effects of climate change on tropical leaf production remain poorly understood. 2. We analyzed 26 years of young leaf phenology field data from Kibale National Park, Uganda, focusing on […]
FERA: A Pose-Based Framework for Rule-Grounded Multimedia Decision Support with a Foil Fencing Case Study
arXiv:2509.18527v5 Announce Type: replace Abstract: Multimedia decision support requires more than recognition; it requires explicit state estimates that can be checked against rules, audited by humans, and consumed by downstream decision logic. We present the FEncing Referee Assistant (FERA), a pose-based framework for this setting, and study it through foil fencing, where decisions depend on […]