🏢 Stanford University

Higher-Order Causal Message Passing (HO-CMP) accurately estimates treatment effects in complex systems with unknown interference by using observed data to learn the system’s dynamics over time.

Robots can now dexterously grasp objects based on natural language commands thanks to DexGYS, a new language-guided dexterous grasp generation framework and dataset.

GraphMETRO tackles complex graph distribution shifts by using a Mixture-of-Experts model to decompose shifts into interpretable components, achieving state-of-the-art results.

Graph Uncertainty boosts LLM factuality by 6.8% using graph centrality to estimate claim-level uncertainty and a novel uncertainty-aware decoding process.

Unbalanced initializations dramatically accelerate neural network feature learning by modifying the geometry of learning trajectories, enabling faster feature extraction and improved generalization.

GeoTDM: First diffusion model generating realistic 3D geometric trajectories, capturing complex spatial interactions and temporal correspondence, significantly improving generation quality.

This paper introduces two novel algorithms, achieving optimal regret in generalized linear contextual bandits despite limited policy updates, a significant advancement for real-world applications.

FACTORSim generates full, coded simulations from natural language descriptions, outperforming existing methods in accuracy and zero-shot transfer learning by using a factored POMDP representation.

Provably sample-efficient robust RL via interactive data collection is achieved by introducing the vanishing minimal value assumption to mitigate the curse of support shift, enabling near-optimal algo…

New sub-optimality bounds for gradient descent leverage directional smoothness, a localized gradient variation measure, achieving tighter convergence guarantees and adapting to optimization paths.

Depth Anywhere enhances 360-degree monocular depth estimation by cleverly using perspective models to label unlabeled 360-degree data, significantly improving accuracy.

Deep learning tackles Markov chain convergence rate analysis! Deep Contractive Drift Calculator (DCDC) provides sample-based bounds in Wasserstein distance, surpassing traditional methods’ limitations…

CRONOS: Scaling convex neural network training to ImageNet!

Convolutional Differentiable Logic Gate Networks achieve state-of-the-art accuracy on CIFAR-10 with 29x fewer gates than existing models, demonstrating highly efficient deep learning inference.

Trust Sampling enhances guided diffusion by iteratively optimizing constrained generation at each step, improving efficiency and accuracy in image and 3D motion generation.

Neural causal models consistently estimate partial causal effects, even with continuous/categorical variables, thanks to Lipschitz regularization.

CALDERA: a new post-training LLM compression algorithm achieving state-of-the-art zero-shot performance using low-rank, low-precision decomposition.

Collaborative Video Diffusion (CVD) generates multiple consistent videos from various camera angles using a novel cross-video synchronization module, significantly improving consistency compared to ex…

Boosting conformal prediction intervals improves accuracy and precision by tailoring them to specific desired properties via machine learning.

Learners can improve accuracy in strategic classification by selectively revealing partial classifier information to agents, strategically guiding agent behavior and maximizing accuracy.