No article text was recorded for this version.
cross-modal catastrophic forgetting
Version 1 of 162 papers71 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Multimodal Large Language Models: A Survey
- Blog: Speechless: Speech Instruction Training Without Speech for Low Resource Languages
- Blog: Modality-Inconsistent Continual Learning of Multimodal Large Language Models
- Blog: Speech-IFEval: Evaluating Instruction-Following and Quantifying Catastrophic Forgetting in Speech-Aware Language Models
- Blog: UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision
- Blog: Seeing Before Reasoning: A Unified Framework for Generalizable and Explainable Fake Image Detection
- Blog: Wings: Learning Multimodal LLMs without Text-only Forgetting
- Blog: Sight Beyond Text: Multi-Modal Training Enhances LLMs in Truthfulness and Ethics
- Blog: CoLLaVO: Crayon Large Language and Vision mOdel
- Blog: CogVLM: Visual Expert for Pretrained Language Models
- Blog: IAA: Inner-Adaptor Architecture Empowers Frozen Large Language Model with Multimodal Capabilities
- Blog: Learn from Downstream and Be Yourself in Multimodal Large Language Models Fine-Tuning
- Blog: DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment
- Blog: SSR: Alignment-Aware Modality Connector for Speech Language Models
- Blog: On-Policy Adaptation Mitigates Hyperparameter-Sensitive Forgetting in Vision-Language Models
- Blog: CoMP: Continual Multimodal Pre-training for Vision Foundation Models
- Blog: Prompting Large Language Models with Speech Recognition Abilities
- Blog: Eve: Efficient Multimodal Vision Language Models with Elastic Visual Experts
- Blog: LoRASculpt: Sculpting LoRA for Harmonizing General and Specialized Knowledge in Multimodal Large Language Models
- Blog: Unlocking Speech–Text Compositional Powers: Instruction-Following Speech Language Models without Instruction Tuning
- Blog: Improving Multimodal Large Language Models Using Continual Learning
- Blog: SAM-Veteran: An MLLM-Based Human-like SAM Agent for Reasoning Segmentation
- Blog: Advancing Multimodal Large Language Models with Quantization-Aware Scale Learning for Efficient Adaptation
- Blog: Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models
- Blog: ChartMoE: Mixture of Diversely Aligned Expert Connector for Chart Understanding
- Blog: Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models
- Blog: Deep Pre-Alignment for VLMs
- Blog: MultiMath: Bridging Visual and Mathematical Reasoning for Large Language Models
- Blog: Jina-VLM: Small Multilingual Vision Language Model
- Blog: Are Vision-Language Transformers Learning Multimodal Representations? A Probing Perspective
- Blog: OpusLM: A Family of Open Unified Speech Language Models
- Blog: DrVoice: Parallel Speech-Text Voice Conversation Model via Dual-Resolution Speech Representations
- Blog: PostTrainBench: Can LLM Agents Automate LLM Post-Training?
- Blog: BLSP: Bootstrapping Language-Speech Pre-training via Behavior Alignment of Continuation Writing
- Blog: Unsupervised Natural Language Inference via Decoupled Multimodal Contrastive Learning
- Blog: SALMONN: Towards Generic Hearing Abilities for Large Language Models
- Blog: On Discriminative vs. Generative classifiers: Rethinking MLLMs for Action Understanding
- Blog: VILA: On Pre-training for Visual Language Models
- Blog: TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling
- Blog: More Than Generation: Unifying Generation and Depth Estimation via Text-to-Image Diffusion Models
- Blog: Get Large Language Models Ready to Speak: A Late-fusion Approach for Speech Generation
- Blog: Dual Diffusion for Unified Image Generation and Understanding
- Blog: Growing Visual Generative Capacity for Pre-Trained MLLMs
- Blog: ARGenSeg: Image Segmentation with Autoregressive Image Generation Model
- Blog: AlignFormer: Modality Matching Can Achieve Better Zero-shot Instruction-Following Speech-LLM
- Blog: Interleaved Audio/Audiovisual Transfer Learning for AV-ASR in Low-Resourced Languages
- Blog: DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment
- Blog: Bridge Thinking and Acting: Unleashing Physical Potential of VLM with Generalizable Action Expert
- Blog: u-HuBERT: Unified Mixed-Modal Speech Pretraining And Zero-Shot Transfer to Unlabeled Modality
- Blog: GAE: Unleashing Physical Potential of VLM with Generalizable Action Expert
- Blog: OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference
- Blog: Transitional Adaptation of Pretrained Models for Visual Storytelling
- Blog: Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training
- Blog: Flex-Judge: Text-Only Reasoning Unleashes Zero-Shot Multimodal Evaluators
- Blog: Vision-Language Instruction Tuning: A Review and Analysis
- Blog: F-LMM: Grounding Frozen Large Multimodal Models
- Blog: LaTtE-Flow: Layerwise Timestep-Expert Flow-based Transformer
- Blog: Multimodal Few-Shot Learning with Frozen Language Models
- Blog: UniCode: Learning a Unified Codebook for Multimodal Large Language Models
- Blog: How to Teach Large Multimodal Models New Skills
Showing 60 of 62 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_cross_modal_catastrophic_forgetting_eb547685,
title = {cross-modal catastrophic forgetting},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/cross-modal-catastrophic-forgetting/rdr_eb5476854b2e44d5b95f37e926101267},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_cross_modal_catastrophic_forgetting_eb547685_v1,
title = {cross-modal catastrophic forgetting},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/cross-modal-catastrophic-forgetting/rdr_eb5476854b2e44d5b95f37e926101267/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}