arXiv:2601.03791v1 Announce Type: cross Abstract: Large Language Models (LLMs) have been reported to “leak” Personally Identifiable Information (PII), with successful…
arXiv:2601.03324v1 Announce Type: cross Abstract: The deployment of Large Language Models (LLMs) on edge devices is fundamentally constrained by the…
arXiv:2601.01874v1 Announce Type: cross Abstract: Despite significant progress, multimodal large language models continue to struggle with visual mathematical problem solving.…
arXiv:2601.01005v1 Announce Type: cross Abstract: Medical image segmentation faces critical challenges in semi-supervised learning scenarios due to severe annotation scarcity…
arXiv:2601.01887v2 Announce Type: cross Abstract: Fine-tuning safety-aligned large language models (LLMs) can substantially compromise their safety. Previous approaches require many…
arXiv:2511.06816v2 Announce Type: replace-cross Abstract: Model-based reinforcement learning (MBRL) typically relies on modeling environment dynamics for data efficiency. However, due…
arXiv:2601.01835v1 Announce Type: cross Abstract: In this paper, a deep learning approach for Mpox diagnosis named Customized Residual SwinTransformerV2 (RSwinV2)…
arXiv:2601.01011v1 Announce Type: cross Abstract: Every act of language generation compresses a rich internal state into a single token sequence.…
