A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Haodong Li, Shaoteng Liu, Tianyu Wang, et al.
Introduces Latent Dynamics Reasoning (LDR), a video world model that explicitly models latent dynamics via kinematic integration, achieving far better out-of-distribution extrapolation than video diffusion baselines.
Unknown
Proposes invariant Causal Representation Learning (iCaRL) for out-of-distribution generalization in nonlinear settings.
Unknown
This paper introduces generative reward models that match Bradley-Terry reward models for in-distribution prompts while offering advantages in out-of-distribution scenarios.
Unknown
This paper proposes a minimalist offline RL approach that avoids out-of-distribution value overestimation by constraining the policy to the data support, achieving strong performance with simple modifications.
Unknown
A task-oriented survey of recent advances in out-of-distribution detection, organizing methods by task and highlighting practical considerations.
Unknown
This paper proposes using deep nearest neighbors for out-of-distribution detection, scaling to large semantic spaces.
Stanislav Fort, Jie Jessie Ren, Balaji Lakshminarayanan
Large-scale pre-trained transformers significantly improve near out-of-distribution detection, setting new state-of-the-art results.
Unknown
OpenOOD is a comprehensive benchmark for generalized out-of-distribution detection, providing a unified framework to evaluate and compare methods across multiple OOD scenarios.
Unknown
This paper investigates the use of vision-language representations for out-of-distribution detection, proposing methods to scale detection to large-scale problems.
Jingkang Yang, Kaiyang Zhou, Yixuan Li, et al.
A comprehensive survey that unifies OOD detection, OOD localization, and OOD synthesis under a generalized framework, providing a taxonomy, benchmarks, and future directions.