CRANE is a post‑hoc, model‑agnostic framework that generates multimodal counterfactual explanations by retrieving real training examples from the target class. It uses nearest‑neighbour retrieval across modalities, with Multimodal Consensus Retrieval (MC‑R) intersecting per‑modality neighbour sets to find instances jointly close to the query. Experiments on four heterogeneous datasets and three fusion strategies show MC‑R consistently outperforms other multimodal strategies and remains competitive when a single modality dominates.
arXiv:2607. 05019v1 Announce Type: new Abstract: In multimodal classification, late-fusion approaches classify concatenated modality-specific features extracted by unimodal neural networks.
The paper introduces a generalized multimodal foundation model that can handle arbitrary combinations of modalities and prediction tasks. It trains on large-scale synthetic multimodal datasets with diverse causal structures to learn transferable multimodal correlations. Experiments on 18 real-world datasets across 12 modalities and 11 tasks show competitive performance compared to specialized models without task-specific adaptation.
The paper introduces Fusion Anything Model (FAM), a foundation model designed for generalized multimodal data fusion that can handle arbitrary modality combinations and prediction tasks. FAM is trained on large-scale synthetic multimodal datasets generated via Structural Multimodal Causal Models (SMCMs), enabling it to encode transferable multimodal correlations. Experiments on 18 real-world datasets across 12 modalities and 11 tasks show that FAM performs competitively with specialized models without requiring task-specific adaptation.
arXiv:2609.05518v1 Announce Type: cross Abstract: Despite the strong capabilities of multimodal large language models (MLLMs), their parametric knowledge remains incomplete and difficult to update, m...
arXiv:2505. 19614v2 Announce Type: replace Abstract: Multimodal learning has seen remarkable progress, particularly with large-scale pre-training across various modalities.
TokenSwap introduces a method to benchmark and reduce the modality gap in multimodal large language models (MLLMs) by interleaving semantically aligned images with text tokens. By transforming text-only benchmarks like MMLU into image‑interleaved versions (TokenSwap‑Bench), the authors reveal a pervasive performance drop—averaging 19.6%—across 42 MLLMs, with reasoning models showing smaller gaps. Training with TokenSwap mitigates this gap while maintaining strong text‑only and vision‑language performance.
The paper introduces Modality Self-Play (MSP), a training framework that enables multimodal large language models to learn cross‑modal interactions without requiring paired non‑text data. MSP uses proxy‑mediated textual descriptions of unseen modalities as semantic bridges, allowing a model to generate and align these proxies with observed modalities. Experiments show that MSP achieves state‑of‑the‑art or competitive performance on several multimodal benchmarks and demonstrates effective zero‑shot modality composition through learned bridges and anchor‑supporting proxy descriptions.
The paper identifies that in multimodal learning, optimization often produces asymmetric certainty gains, with the stronger modality becoming more confident than the weaker one, which leads to imbalanced contributions and suboptimal performance. The authors attribute this issue to unimodal characteristics and propose a Max Confidence Regularization (MaxCR) method that tracks each modality’s semantic confidence via a nonlinear sparsity measure and applies max suppression and excitation to balance confidence levels. Experiments on standard datasets demonstrate that MaxCR improves overall performance compared to state‑of‑the‑art multimodal baselines.
InfMasking introduces a unified multimodal learning framework that uses Infinite Masking to encourage fusion modules to capture synergistic information across modalities. By randomly masking modality features before fusion and enforcing consistency with an unmasked reference, the method discourages reliance on dominant or shared signals and promotes meaningful cross‑modal interactions. The approach models masked fused representations as Gaussian, optimizing closed‑form variational bounds, and demonstrates improved predictive performance and higher synergy metrics on benchmark datasets.
arXiv:2608. 06938v1 Announce Type: cross Abstract: The visual reasoning ability of multimodal large language models (MLLMs) is crucial for downstream applications, particularly counter-commonsense reasoning, which requires models to reason beyond common assumptions.
Multimodal representation learning has largely relied on contrastive models like CLIP that produce a single embedding per sample, which limits their ability to capture relation-dependent relevance. The proposed Relation-Conditioned Multimodal Learning (RCML) framework explicitly conditions embeddings on natural‑language relation descriptions, enabling the same sample to be represented differently under various relational contexts. RCML builds relation‑aware training pairs, incorporates a relation‑conditioned module, and uses a unified contrastive objective to jointly model cross‑modal alignment and relation‑induced structure, achieving superior performance on retrieval and classification tasks across zero‑shot, fine‑tuned, and out‑of‑domain settings.
arXiv:2610.07928v1 Announce Type: cross Abstract: Dynamic multimodal learning aims to learn robust representations by adaptively modeling information discrepancies across modalities. However, existin...