Monarch-MoE introduces structured experts for multimodal continual instruction tuning by replacing dense LoRA factors with block‑diagonal ones linked by a fixed permutation, enabling blockwise gradient isolation. This design reduces adapter parameters by up to 75% and 50% on two benchmarks while keeping first‑task forgetting below 0.52 and 0.10 percentage points, respectively. The method is optimized for memory‑limited hardware, allowing fine‑tuning and inference on a single 24 GB RTX 4090 with lower memory usage and competitive runtime.
arXiv:2601. 13020v2 Announce Type: replace-cross Abstract: Continual instruction tuning (CIT) requires multimodal large language models (MLLMs) to adapt to a stream of tasks without forgetting prior capabilities.
CRAM (Centroid‑Routing and Adaptive MoE) is a method for Multimodal Continual Instruction Tuning that isolates task‑specific patterns into independent modules to reduce catastrophic forgetting. It uses adaptive‑rank instantiation to allocate only the necessary parameters for new tasks, and centroid‑guided routing with an orthogonality penalty to reuse existing experts while preventing interference. Experiments on diverse benchmarks show CRAM outperforms existing approaches.
arXiv:2605. 20247v2 Announce Type: replace-cross Abstract: Catastrophic forgetting remains a major obstacle to continual learning in large language models (LLMs) and vision--language models (VLMs).
The paper introduces SAME (Stabilized Mixture-of-Experts) to address challenges in Multimodal Continual Instruction Tuning (MCIT) for large language models. SAME mitigates router drift by decomposing routing dynamics into orthogonal subspaces and updating only task-relevant directions, while preventing expert drift through curvature‑aware scaling that uses historical input covariance without rehearsal. The method also employs adaptive expert activation to freeze selected experts during training, reducing redundant computation and cross‑task interference, and demonstrates state‑of‑the‑art performance on a new long‑task‑sequence benchmark.
arXiv:2607. 20511v1 Announce Type: new Abstract: Multimodal Continual Instruction Tuning (MCIT) is crucial for adapting Multimodal Large Language Models (MLLMs) to evolving a sequence of downstream tasks.
arXiv:2604.23036v2 Announce Type: replace-cross Abstract: Despite MoE models leading many benchmarks, supervised fine-tuning (SFT) for the MoE architectures remains difficult because its router layer...
arXiv:2509. 13211v4 Announce Type: replace Abstract: The ability to learn continuously over time remains a major challenge for modern machine learning systems, even in the era of Foundation Models.
The paper introduces CART, a method for Multimodal Continual Instruction Tuning that coordinates adaptation between a projector and a language model by using task‑specific experts and weighted mixtures. CART jointly infers expert weights based on relevance and cross‑module compatibility, and it controls model growth through relevance‑guided expert consolidation. Experiments show that CART achieves state‑of‑the‑art performance on multimodal continual learning tasks.
arXiv:2606. 10406v1 Announce Type: cross Abstract: We argue that forgetting is not confined to continual learning but is a general optimization phenomenon: during standard training, dominant mini-batch gradients suppress rare but useful update directions, causing short-term forgetting at every step.
arXiv:2501.05559v2 Announce Type: replace Abstract: Have we made mitigating catastrophic forgetting more complicated than it needs to be? Continual adaptation often degrades performance on earlier ta...
arXiv:2607. 04364v1 Announce Type: new Abstract: Continual post-training is becoming a central paradigm for adapting vision-language models to evolving tasks.
We argue that forgetting is not confined to continual learning but is a general optimization phenomenon: during standard training, dominant mini-batch gradients suppress rare but useful update directions, causing short-term forgetting at every step. When such knowledge is never revisited, these losses compound into long-term forgetting-the classical failure mode of continual learning.