Residual Reward Models for Preference-based Reinforcement Learning
arXiv:2507.00611v1 Announce Type: cross Abstract: Preference-based Reinforcement Learning (PbRL) provides a way to learn high-performance policies in environments where the…
Autonomy by Design: Preserving Human Autonomy in AI Decision-Support
arXiv:2506.23952v2 Announce Type: replace-cross Abstract: AI systems increasingly support human decision-making across domains of professional, skill-based, and personal activity. While…
DiMo-GUI: Advancing Test-time Scaling in GUI Grounding via Modality-Aware Visual Reasoning
arXiv:2507.00008v1 Announce Type: new Abstract: Grounding natural language queries in graphical user interfaces (GUIs) poses unique challenges due to the…
Refine-POI: Reinforcement Fine-Tuned Large Language Models for Next Point-of-Interest Recommendation
arXiv:2506.21599v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have been adopted for next point-of-interest (POI) recommendation tasks. Typical LLM-based…
gMBA: Expression Semantic Guided Mixed Boolean-Arithmetic Deobfuscation Using Transformer Architectures
arXiv:2506.23634v1 Announce Type: cross Abstract: Mixed Boolean-Arithmetic (MBA) obfuscation protects intellectual property by converting programs into forms that are more…
Towards Building Private LLMs: Exploring Multi-Node Expert Parallelism on Apple Silicon for Mixture-of-Experts Large Language Model
arXiv:2506.23635v1 Announce Type: cross Abstract: Large Language Models (LLMs) have revolutionized Artificial Intelligence (AI) with significant advancements such as OpenAI’s…
Dehazing Light Microscopy Images with Guided Conditional Flow Matching: finding a sweet spot between fidelity and realism
arXiv:2506.22397v2 Announce Type: replace-cross Abstract: Fluorescence microscopy is a major driver of scientific progress in the life sciences. Although high-end…
Bootstrapping Human-Like Planning via LLMs
arXiv:2506.22604v1 Announce Type: new Abstract: Robot end users increasingly require accessible means of specifying tasks for robots to perform. Two…
Exploring the Capabilities of the Frontier Large Language Models for Nuclear Energy Research
arXiv:2506.19863v2 Announce Type: replace-cross Abstract: The AI for Nuclear Energy workshop at Oak Ridge National Laboratory evaluated the potential of…
UniCA: Adapting Time Series Foundation Model to General Covariate-Aware Forecasting
arXiv:2506.22039v1 Announce Type: cross Abstract: Time Series Foundation Models (TSFMs) have achieved remarkable success through large-scale pretraining. However, their design…