conftrace_

learnable weight

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

perplexity (1) agent functions (1) agentoptimizer (1) early-stop strategy (1) roll-back strategy (1) layer output (1) large language model (1) model quality (1) cross attention (1) residual connection (1)

Papers

DeepCrossAttention: Supercharging Transformer Residual Connections ICML 2025 Offline Training of Language Model Agents with Functions as Learnable Weights ICML 2024