Defines foundation models, analyzes emergent capabilities and risks, emphasizes interdisciplinary research importance.

Rishi Bommasani, Drew A. Hudson, Ehsan Adeli et al.

Introduces DexMV, combining video-based 3D pose estimation and imitation transfer, boosting dexterous manipulation success rates by over 85%.

Yuzhe Qin, Yueh-Hua Wu, Shaowei Liu et al.

Perceiver IO: a universal, linear-scaling architecture for arbitrary inputs/outputs, outperforming Transformers in multi-task/multi-modal tasks.

Andrew Jaegle, Sebastian Borgeaud, Jean-Baptiste Alayrac et al.

ManiSkill benchmark introduces diverse 3D assets and large-scale demonstrations, advancing generalizable robotic manipulation skills.

Tongzhou Mu, Zhan Ling, Fanbo Xiang et al.

Proposes IV-based dynamic incentive mechanism to improve compliance and estimate treatment effects in multi-round settings.

Daniel Ngo, Logan Stapleton, Vasilis Syrgkanis et al.

NCAD combines representation learning and deep anomaly detection, achieving SOTA on univariate/multivariate time series with semi-supervised capability.

Chris U. Carmona, François-Xavier Aubet, Valentin Flunkert et al.

Distribution-free conformal prediction guarantees 90% coverage, adaptable to classification and regression tasks.

Anastasios N. Angelopoulos, Stephen Bates

Codex, a GPT-based model fine-tuned on GitHub code, achieves 28.8% success on HumanEval, with 70.2% using 100 samples, significantly surpassing GPT-3.

Mark Chen, Jerry Tworek, Heewoo Jun et al.

Proposes fMBN-E, an ensemble method combining multiple MBN structures for unsupervised clustering, achieving state-of-the-art results with hundreds-fold speedup.

Xiao-Lei Zhang

Proposes Variational Diffusion Models (VDM) achieving state-of-the-art likelihoods on image density benchmarks by optimizing noise schedules and incorporating Fourier features.

Diederik P. Kingma, Tim Salimans, Ben Poole et al.

Habitat 2.0 combines ReplicaCAD, high-speed physics simulation, and HAB benchmarks to advance long-horizon household robot tasks.

Andrew Szot, Alex Clegg, Eric Undersander et al.

Unified EVLP taxonomy, analyzing algorithms, datasets, and challenges; emphasizing model generalization and real-world deployment.

Jonathan Francis, Nariaki Kitamura, Felix Labelle et al.

Proposes CW networks with cell complexes, surpassing WL test, for enhanced graph expressivity, especially in molecular graphs.

Cristian Bodnar, Fabrizio Frasca, Nina Otter et al.

This survey comprehensively reviews techniques for making deep learning models smaller, faster, and more efficient, including pruning, quantization, architecture search, and hardware support.

Gaurav Menghani

Proposes algorithms Exp3-IP and Exp3-GR for online learning with uncertain feedback graphs, achieving sublinear regret bounds under mild conditions.

Pouya M Ghari, Yanning Shen

GDN uses graph neural networks with structure learning to detect anomalies in multivariate time series, outperforming baselines with 99% precision on SWaT and 97.5% on WADI.

Ailin Deng, Bryan Hooi

TD3+BC adds behavior cloning regularization and normalization to TD3, achieving SOTA performance on D4RL with half the computational cost.

Scott Fujimoto, Shixiang Shane Gu

Efficient parameter allocation in large sparse models using Hash Layers, improving performance.

Stephen Roller, Sainbayar Sukhbaatar, Arthur Szlam et al.

Proposes GFlowNet, a flow network-based generative model for non-iterative diverse candidate sampling, ensuring probabilities are proportional to rewards.

Emmanuel Bengio, Moksh Jain, Maksym Korablyov et al.

Proposes inverse model and contrastive learning-based Markov state abstraction, improving sample efficiency in deep RL.

Cameron Allen, Neev Parikh, Omer Gottesman et al.