4arXiv cs.LG (Machine Learning)·
Co-learning framework for multi-modal classification with arbitrary missing modalities
A new arXiv preprint introduces a co-learning framework for multi-modal classification that handles arbitrary missing modalities at inference time, without assuming predefined missing patterns. Two complementary methods are proposed — one operating at the feature level and one at the decision level — evaluated on two multi-modal benchmarks. The approach prioritizes inter-modal collaboration over fusion, showing robustness gains across both minimal and extreme missing-modality conditions.
Related guides (1)
Related events (8)
Latent World Recovery: multimodal learning framework for missing modalities in bioscience
A new arXiv preprint introduces Latent World Recovery (LWR), a framework for multimodal learning when some modalities are unavailable at training or inference time. LWR aligns modality-specific embeddings in a shared latent space and fuses only available modalities, avoiding explicit reconstruction of missing ones. The approach is evaluated on incomplete multi-omics benchmarks for cancer phenotype classification and survival prediction, demonstrating robustness under partial observation.
Phase diagram framework for choosing between cross-modal alignment and prediction in multimodal learning
A new arXiv preprint develops a unified linear framework to determine when cross-modal alignment (CA) versus cross-modal prediction (CP) is the better objective for multimodal representation learning. Under a spiked signal-plus-noise model, the authors derive separation ratios that expose complementary failure modes for each paradigm, producing a four-regime phase diagram (Both, CA only, CP only, Neither). A data-driven procedure lets practitioners locate their dataset in this diagram using a small labeled subsample before committing to training. Experiments on synthetic data, stereo-vision, image-caption pairs, and astrophysical data validate the framework, including a 'Neither' regime where cross-modal training is actively harmful.
MODUS: Decoder-only architecture for any-to-any multimodal modeling without modality-specific heads
Researchers at EPFL introduce Modus, a decoder-only model that treats all modalities symmetrically for any-to-any prediction without modality-specific heads, losses, or task pipelines. Unlike prior any-to-any models that use encoder-decoder or diffusion architectures trained from scratch, Modus leverages pre-trained decoder-only models as a prior. The model supports chained generation through intermediate modalities and cross-modal self-verification, achieving competitive performance with specialist and multitask baselines across benchmarks. All materials are open-sourced.
LoRA-based cascaded multimodal fusion framework for action recognition in medical training environments
A new arXiv preprint proposes a cascaded Low-Rank Adaptation (LoRA) framework for multimodal fusion applied to action and activity recognition in healthcare training settings. The architecture integrates modalities sequentially without retraining prior components, enabling scalable adaptation across datasets with different modality sets. Evaluation on two healthcare datasets (NurViD and Nurse Training) shows competitive performance against dataset-specific baselines. The work is a narrow application of parameter-efficient fine-tuning techniques to a specialized domain.
CoMet: Decomposed uncertainty estimation for multimodal LLMs without repeated sampling
Researchers from Princeton introduce CoMet, a post-hoc uncertainty estimation method for multimodal large language models that decomposes uncertainty into a context-specific term (prompt/task ambiguity) and a multiplicity-specific term (number of plausible answers compatible with the input). A lightweight module is trained to estimate these quantities without requiring autoregressive generation or repeated sampling, making it computationally efficient. Experiments across open-ended multimodal benchmarks, hallucination detection, and visual QA show consistent improvements over existing baselines.
AIR: Adaptive Interleaved Reasoning with Code in Multimodal LLMs via Reinforcement Learning
Researchers propose AIR, a system that trains multimodal large language models to adaptively interleave reasoning with code execution for numerical computation tasks, going beyond prior work that focused only on visual operations. The approach combines a two-stage cold-start data pipeline, RL dataset filtering, and a group-constrained reward function for tool-invocation decisions. Experiments show a 6.1 percentage point average improvement on evaluation benchmarks, with interleaved reasoning samples gaining 9.9 pp and tool-use success exceeding 95%.
LoMo: Local Modality Substitution for Deeper Vision-Language Fusion
This paper identifies a 'carrier sensitivity' problem in Vision-Language Models (VLMs), where replacing textual queries with rendered-image equivalents causes significant performance degradation due to asymmetric roles of text and images in training data. The authors propose Local Modality Substitution (LoMo), a data curation paradigm that reformulates single-modality prompts into interleaved multimodal sequences by dynamically rendering text spans as images, enforcing cross-modal representational invariance. Evaluated across 13 multimodal benchmarks, LoMo improves over standard supervised fine-tuning by 2.67 points on LLaVA-OneVision-1.5-8B and 2.82 points on Qwen3.5-9B. The approach is architecture-agnostic and lightweight, requiring no changes to model architecture.
Cross-modal masking framework improves silent speech synthesis from sEMG and lipreading
Researchers propose a masked multimodal speech synthesis framework that jointly trains on surface electromyography (sEMG) and video-based lipreading signals using modality masking to improve robustness to sensor failure or degradation. In multispeaker settings, the approach reduces word error rate by up to 14 absolute percentage points over the strongest unimodal baseline. Masking strategies outperform degradation-specific data augmentation for handling missing modalities, with phone-level analysis revealing complementary contributions across vowels and consonant groups.