Dynamic Correction of Erroneous State Estimates via Diffusion Bayesian Exploration
arXiv:2512.03102v2 Announce Type: replace-cross Abstract: In emergency response and other high-stakes societal applications, early-stage state estimates critically shape downstream outcomes.…
Hierarchical Vision Language Action Model Using Success and Failure Demonstrations
arXiv:2512.03913v1 Announce Type: cross Abstract: Prior Vision-Language-Action (VLA) models are typically trained on teleoperated successful demonstrations, while discarding numerous failed…
A Survey on Recommendation Unlearning: Fundamentals, Taxonomy, Evaluation, and Open Questions
arXiv:2412.12836v2 Announce Type: replace-cross Abstract: Recommender systems have become increasingly influential in shaping user behavior and decision-making, highlighting their growing…
VICoT-Agent: A Vision-Interleaved Chain-of-Thought Framework for Interpretable Multimodal Reasoning and Scalable Remote Sensing Analysis
arXiv:2511.20085v3 Announce Type: replace Abstract: The current remote sensing image analysis task is increasingly evolving from traditional object recognition to…
SLO-aware GPU Frequency Scaling for Energy Efficient LLM Inference Serving
arXiv:2408.05235v2 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) gain traction, their reliance on power-hungry GPUs places ever-increasing energy…
AMPED: Adaptive Multi-objective Projection for balancing Exploration and skill Diversification
arXiv:2506.05980v4 Announce Type: replace-cross Abstract: Skill-based reinforcement learning (SBRL) enables rapid adaptation in environments with sparse rewards by pretraining a…