conftrace_

soft masking

5 papers

Explore in graph

Co-occurring keywords · papers mentioning both

catastrophic forgetting (3) knowledge transfer (2) modality recognition (1) dynamic assessment (1) modality missingness (1) subnetwork discovery (1) dynamic soft-masking (1) multi-agent system (1) large language model (1) domain-adaptive pre-training (1)

Papers

Two Challenges, One Solution: Robust Multimodal Learning through Dynamic Modality Recognition and Enhancement EMNLP 2025 Balancing Speciality and Versatility: a Coarse to Fine Framework for Supervised Fine-tuning Large Language Model ACL 2024 LaKD: Length-agnostic Knowledge Distillation for Trajectory Prediction with Any Length Observations NeurIPS 2024 Continual Pre-training of Language Models ICLR 2023 Sub-network Discovery and Soft-masking for Continual Learning of Mixed Tasks EMNLP 2023