🏢 Carnegie Mellon University

Unlocking Causal Structures: New algorithms identify latent causal relationships from interventions, even when multiple variables are affected simultaneously.

Boosting complex visual reasoning, a new Iterative and Parallel Reasoning Mechanism (IPRM) outperforms existing methods by combining step-by-step and simultaneous computations, improving accuracy and …

Learning social welfare functions from past decisions is possible! This paper shows how to efficiently learn power mean functions, a widely used family, using both cardinal and pairwise welfare compar…

This paper introduces a novel tensor rank condition for identifying causal structures among discrete latent variables, advancing causal discovery in complex scenarios.

This paper introduces a novel framework for learning discrete concepts from high-dimensional data, establishing theoretical conditions for identifying underlying hierarchical causal structures and pro…

Faster John ellipsoid computation achieved via lazy updates and fast matrix multiplication, improving efficiency and enabling low-space streaming algorithms.

This study presents CADIM, an adaptive algorithm using interventions to learn true causal relationships from mixtures of DAGs, achieving near-optimal intervention sizes and providing quantifiable opti…

IsCiL: a novel adapter-based continual imitation learning framework that efficiently adapts to new tasks by incrementally learning and retrieving reusable skills.

Transformers learn contextual information for generalization to unseen examples and tasks, even with limited training data, converging linearly to a global minimum.

Researchers significantly boosted the efficiency and quality of rectified flow, a method for generating samples from diffusion models, by introducing novel training techniques that surpass state-of-th…

Unified framework for imprecise label learning handles noisy, partial, and semi-supervised data, improving model training efficiency and accuracy.

Weighted pretrained features implicitly regularize models, and this paper reveals equivalent paths between weighting schemes and ridge regularization, enabling efficient hyperparameter tuning.

This paper introduces seq-NMF, a novel method for unsupervised subtask discovery in reinforcement learning that leverages selection variables to enhance generalization and data efficiency.

This study introduces a novel framework for individualized reinforcement learning, guaranteeing the identifiability of latent factors influencing state transitions and providing a practical method for…

Hydra: Bidirectional sequence modeling redefined with quasiseparable matrix mixers, outperforming existing models on various benchmarks!

Hamba: a novel graph-guided framework for single-view 3D hand reconstruction, significantly outperforms existing methods by efficiently modeling spatial relationships between joints using a fraction o…

Restless multi-armed bandits with global rewards (RMAB-G) are introduced, extending the model to handle non-separable rewards and offering novel index-based and adaptive policies that outperform exist…

GL-NeRF accelerates NeRF rendering by using Gauss-Laguerre quadrature, drastically reducing MLP calls without needing additional networks or data structures.

This paper introduces a novel geometric approach to concept-based representation learning, provably recovering interpretable concepts from diverse data without strict causal assumptions or many interv…

This paper introduces federated natural policy gradient and actor-critic methods achieving near dimension-free global convergence for decentralized multi-task reinforcement learning, a significant bre…