AREA stabilizes attribute extraction with principal geodesic analysis on hyperspherical space and aggregation with lightweight task experts plus variational bottleneck and optimal transport routing, outperforming SOTA in CLIP-based CIL.
MetaTransformer: a unified framework for multimodal learning.arXiv preprint arXiv:2307.10802, 2023b
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
verdicts
UNVERDICTED 6representative citing papers
PiERN proposes token-level routing of physically-isolated experts to embed high-precision computation directly into LLMs, reporting higher accuracy and lower latency, token count, and energy use than fine-tuning or multi-agent baselines.
LanguageBind aligns video, infrared, depth, and audio to a frozen language encoder via contrastive learning on the new VIDAL-10M dataset, extending video-language pretraining to N modalities.
CodeBind uses a modality-shared-specific codebook and compositional vector quantization to decouple shared semantic features from modality-unique details, achieving state-of-the-art multimodal classification and retrieval across nine modalities without requiring fully paired data.
MedMIX combines intra-modality expert fusion, learned inter-modality fusion, and training-only large-small collaboration to deliver robust multimodal medical prediction under incomplete modalities across three benchmarks.
QA-MoE introduces a continuous reliability spectrum and uses aleatoric uncertainty to route experts, achieving competitive performance across degradation levels with a single checkpoint.
citing papers explorer
-
AREA: Attribute Extraction and Aggregation for CLIP-Based Class-Incremental Learning
AREA stabilizes attribute extraction with principal geodesic analysis on hyperspherical space and aggregation with lightweight task experts plus variational bottleneck and optimal transport routing, outperforming SOTA in CLIP-based CIL.
-
PiERN: Token-Level Routing for Integrating High-Precision Computation and Reasoning
PiERN proposes token-level routing of physically-isolated experts to embed high-precision computation directly into LLMs, reporting higher accuracy and lower latency, token count, and energy use than fine-tuning or multi-agent baselines.
-
LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment
LanguageBind aligns video, infrared, depth, and audio to a frozen language encoder via contrastive learning on the new VIDAL-10M dataset, extending video-language pretraining to N modalities.
-
CodeBind: Decoupled Representation Learning for Multimodal Alignment with Unified Compositional Codebook
CodeBind uses a modality-shared-specific codebook and compositional vector quantization to decouple shared semantic features from modality-unique details, achieving state-of-the-art multimodal classification and retrieval across nine modalities without requiring fully paired data.
-
MedMIX: Modality-Internal Expert Fusion for Multimodal Medical Diagnosis
MedMIX combines intra-modality expert fusion, learned inter-modality fusion, and training-only large-small collaboration to deliver robust multimodal medical prediction under incomplete modalities across three benchmarks.
-
QA-MoE: Towards a Continuous Reliability Spectrum with Quality-Aware Mixture of Experts for Robust Multimodal Sentiment Analysis
QA-MoE introduces a continuous reliability spectrum and uses aleatoric uncertainty to route experts, achieving competitive performance across degradation levels with a single checkpoint.