arXiv:2608.21376v1 Announce Type: cross Abstract: Many NLP tasks require systems to provide attribution in their outputs–i.e. citations to grounding…
Category: AI
RoboShape: Information-Theoretic Point Cloud Representations for Privacy-Aware Robot Perception
arXiv:2608.21380v1 Announce Type: cross Abstract: With the increased adoption of robotic agents operating in human environments by scanning and sharing 3D…
PepLLM: ESM-Guided Llama for Structured Protein-Peptide Binding Interface Analysis
arXiv:2608.21367v1 Announce Type: cross Abstract: Protein-peptide interactions are central to cellular regulation and peptide-based drug discovery, yet…
Agentic Scaffolding Amplifies Sycophantic Behavior in Large Language Models
arXiv:2608.21377v1 Announce Type: cross Abstract: Sycophancy in large language models, the tendency to prioritize user agreement over truthful responses,…
Correcting Variable Importance Scored by Random Forests
arXiv:2606.10770v1 Announce Type: cross Abstract: Variable importance produced by Random Forests (RF) is used widely in statistical data analysis, and has…
KSE-Web: An Analysis of Hybrid Retrieval and LLM-Assisted Query Expansion for Low-Resource Khmer Semantic Search
arXiv:2608.21365v1 Announce Type: cross Abstract: As a low-resource language, Khmer presents several retrieval challenges, including limited annotated…
Triangular Fuzzy Rescaling Distance
arXiv:2608.19234v1 Announce Type: cross Abstract: Decision-making in complex systems often involves dealing with imprecise or uncertain information,…
Small Language Model enabled Autonomous agent for Language-Conditioned Cognitive Radar
arXiv:2608.11596v1 Announce Type: cross Abstract: Modern radar systems require adapting their processing strategies in response to changing interference,…
Distinguishing Revision and Delayed Elaboration in Incremental Narrative Interpretation
arXiv:2608.21364v1 Announce Type: cross Abstract: Both human and AI systems that process narrative or long-form content operate incrementally: input is…
Correcting a learned physical invariant improves world-model rollouts
arXiv:2608.23526v1 Announce Type: new Abstract: World models can predict video without learning dynamics that they reliably preserve. We test whether a…