热点
"模型无关" 相关文章
ScaleDiff: Higher-Resolution Image Synthesis via Efficient and Model-Agnostic Diffusion
cs.AI updates on arXiv.org 2025-10-31T04:04:19.000000Z
ProfileXAI: User-Adaptive Explainable AI
cs.AI updates on arXiv.org 2025-10-28T04:04:24.000000Z
PruneHal: Reducing Hallucinations in Multi-modal Large Language Models through Adaptive KV Cache Pruning
cs.AI updates on arXiv.org 2025-10-23T04:16:34.000000Z
PruneHal: Reducing Hallucinations in Multi-modal Large Language Models through Adaptive KV Cache Pruning
cs.AI updates on arXiv.org 2025-10-23T04:16:34.000000Z
ProSh: Probabilistic Shielding for Model-free Reinforcement Learning
cs.AI updates on arXiv.org 2025-10-20T04:14:34.000000Z
From Refusal to Recovery: A Control-Theoretic Approach to Generative AI Guardrails
cs.AI updates on arXiv.org 2025-10-16T04:22:12.000000Z
Artificial Intelligence Virtual Cells: From Measurements to Decisions across Modality, Scale, Dynamics, and Evaluation
cs.AI updates on arXiv.org 2025-10-15T04:43:19.000000Z
The Geometry of Truth: Layer-wise Semantic Dynamics for Hallucination Detection in Large Language Models
cs.AI updates on arXiv.org 2025-10-07T04:17:52.000000Z
mucAI at BAREC Shared Task 2025: Towards Uncertainty Aware Arabic Readability Assessment
cs.AI updates on arXiv.org 2025-09-22T04:32:46.000000Z
STRIDE: Scalable and Interpretable XAI via Subset-Free Functional Decomposition
cs.AI updates on arXiv.org 2025-09-12T04:19:07.000000Z
CoViPAL: Layer-wise Contextualized Visual Token Pruning for Large Vision-Language Models
cs.AI updates on arXiv.org 2025-09-03T04:18:21.000000Z
You Don't Bring Me Flowers: Mitigating Unwanted Recommendations Through Conformal Risk Control
cs.AI updates on arXiv.org 2025-07-24T05:31:00.000000Z
Large Language Models as Innovators: A Framework to Leverage Latent Space Exploration for Novelty Discovery
cs.AI updates on arXiv.org 2025-07-21T04:06:34.000000Z
MUPAX: Multidimensional Problem Agnostic eXplainable AI
cs.AI updates on arXiv.org 2025-07-18T04:14:11.000000Z
Agents Are All You Need for LLM Unlearning
cs.AI updates on arXiv.org 2025-07-09T04:02:00.000000Z