dynamic adaptation
This concept involves models or systems that can modify their behavior in response to changes in the input data or environment, enhancing performance and flexibility over time, particularly in contexts like reinforcement learning and adaptive systems.
- KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems
- Learning the Plasticity: Plasticity-Driven Learning Framework in Spiking Neural Networks
- PT-MoE: An Efficient Finetuning Framework for Integrating Mixture-of-Experts into Prompt Tuning
- Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling
- STAIR: Addressing Stage Misalignment through Temporal-Aligned Preference Reinforcement Learning
- SeerAttention: Self-distilled Attention Gating for Efficient Long-context Prefilling
- TabDPT: Scaling Tabular Foundation Models on Real Data