Skip to content
conftrace_

attention logit

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

self-attention modulation (1) lamb (1) merit (1) trust ratio (1) intermediate feature (1) multimodal in-context learning (1) large batch training (1) large language model (1) position generalization (1) positional relevance (1)

Papers

Make LVLMs Focus: Context-Aware Attention Modulation for Better Multimodal In-Context Learning AAAI 2026 Computation Mechanism Behind LLM Position Generalization ACL 2025 MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training ICML 2025