CMIB uses a conditional multimodal information bottleneck to create reusable agent skills that separate verbalizable text content from predictive perceptual residuals, improving execution stability.
Infobot: Trans- fer and exploration via the information bottleneck
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
method 1
citation-polarity summary
years
2026 5representative citing papers
Tri-Info uses three information theory signals on action diversity, temporal consistency, and state coupling to predict VLA model failures with cross-domain generalization to 83% real-world accuracy.
SCALE-COMM uses contrastive alignment on latent embeddings to decouple and stabilize communication learning from policy optimization in decentralized MARL, showing gains on benchmarks and a warehouse task.
CmIR uses causal inference to separate invariant causal representations from spurious ones in multimodal data, improving generalization under distribution shifts and noise via invariance, mutual information, and reconstruction constraints.
citing papers explorer
-
Skill-CMIB: Multimodal Agent Skill for Consistent Action via Conditional Multimodal Information Bottleneck
CMIB uses a conditional multimodal information bottleneck to create reusable agent skills that separate verbalizable text content from predictive perceptual residuals, improving execution stability.
-
Tri-Info: Generalizable, Interpretable Failure Prediction for VLA Models via Information Theory
Tri-Info uses three information theory signals on action diversity, temporal consistency, and state coupling to predict VLA model failures with cross-domain generalization to 83% real-world accuracy.
-
SCALE-COMM: Shared, Contrastively-Aligned Latent Embeddings for MARL Communication
SCALE-COMM uses contrastive alignment on latent embeddings to decouple and stabilize communication learning from policy optimization in decentralized MARL, showing gains on benchmarks and a warehouse task.
-
Learning Invariant Modality Representation for Robust Multimodal Learning from a Causal Inference Perspective
CmIR uses causal inference to separate invariant causal representations from spurious ones in multimodal data, improving generalization under distribution shifts and noise via invariance, mutual information, and reconstruction constraints.
- TMRL: Diffusion Timestep-Modulated Pretraining Enables Exploration for Efficient Policy Finetuning