conftrace_

attention entropy

11 papers

Explore in graph

Co-occurring keywords · papers mentioning both

multimodal large language model (3) attention mechanism (3) large language model (2) encoder hidden state (1) entropy collapse (1) variance sensitivity (1) model defense (1) variable resolution (1) multi-solution task (1) diffusion model adaptation (1)

Papers

Beware of Reasoning Overconfidence: Pitfalls in the Reasoning Process for Multi-solution Tasks AAAI 2026 KVSmooth: Mitigating Hallucination in Multi-modal Large Language Models through Key-Value Smoothing CVPR 2026 The Side Effects of Being Smart: Safety Risks in MLLMs’ Multi-Image Reasoning ACL 2026 Attention Entropy is a Key Factor: An Analysis of Parallel Context Encoding with Full-attention-based Pre-trained Language Models ACL 2025 Feint and Attack: Jailbreaking and Protecting LLMs via Attention Distribution Modeling IJCAI 2025 MEDA: Dynamic KV Cache Allocation for Efficient Multimodal Long-Context Inference NAACL 2025 PolaFormer: Polarity-aware Linear Attention for Vision Transformers ICLR 2025 Variance Sensitivity Induces Attention Entropy Collapse and Instability in Transformers EMNLP 2025 Stabilizing Transformer Training by Preventing Attention Entropy Collapse ICML 2023 Training-free Diffusion Model Adaptation for Variable-Sized Text-to-Image Synthesis NeurIPS 2023 Encoders Help You Disambiguate Word Senses in Neural Machine Translation EMNLP 2019