REVIEW 7 cited by
Meta-Transformer: A Unified Framework for Multimodal Learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Meta-Transformer: A Unified Framework for Multimodal Learning
read the original abstract
Multimodal learning aims to build models that can process and relate information from multiple modalities. Despite years of development in this field, it still remains challenging to design a unified network for processing various modalities ($\textit{e.g.}$ natural language, 2D images, 3D point clouds, audio, video, time series, tabular data) due to the inherent gaps among them. In this work, we propose a framework, named Meta-Transformer, that leverages a $\textbf{frozen}$ encoder to perform multimodal perception without any paired multimodal training data. In Meta-Transformer, the raw input data from various modalities are mapped into a shared token space, allowing a subsequent encoder with frozen parameters to extract high-level semantic features of the input data. Composed of three main components: a unified data tokenizer, a modality-shared encoder, and task-specific heads for downstream tasks, Meta-Transformer is the first framework to perform unified learning across 12 modalities with unpaired data. Experiments on different benchmarks reveal that Meta-Transformer can handle a wide range of tasks including fundamental perception (text, image, point cloud, audio, video), practical application (X-Ray, infrared, hyperspectral, and IMU), and data mining (graph, tabular, and time-series). Meta-Transformer indicates a promising future for developing unified multimodal intelligence with transformers. Code will be available at https://github.com/invictus717/MetaTransformer
Forward citations
Cited by 7 Pith papers
-
Mixture of Probes: Learning from Privileged Modalities in Multimodal LLMs Through Probing
Structured intermediate probing that separates modality-specific from modality-general signals lets privileged training modalities improve single-modality MLLM inference by large margins over naive multimodal training.
-
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...
-
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 mu...
-
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 retri...
-
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.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.