A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Unknown
This paper introduces flow matching and diffusion models, explaining and deriving flow matching as a scalable algorithm underlying large-scale generative models.
Unknown
Proposes conformal-calibrated rewards with procedural regeneration to mitigate benchmark contamination in scientific RLVR.
Unknown
Proposes a low-rank factor analysis paradigm for LLM evaluation, testing whether benchmark performance reflects many independent abilities or a few shared underlying skills.
Unknown
A survey of recent advances in world models for autonomous driving, covering data augmentation and scene evaluation.
Unknown
IRIS introduces a Transformer-based world model that learns from pixels and achieves human-level performance on Atari 100k with high sample efficiency.
Unknown
The paper shows how to induce large language models to behave like world models by teaching them precondition and effect knowledge about actions.
Unknown
A critical examination of world models in machine learning, questioning their claims of generality, agency, and worlding in relation to cognitive systems.
Unknown
HAM-RAG formulates structure-faithful multimodal RAG and introduces HAM-Bench to evaluate hierarchy-aware interleaved generation.
Unknown
EchoWM is an omnimodal world model that generates 720p video and environmental sound in response to continuous navigation for enterable generative media.
Unknown
WorldArena is a unified benchmark for evaluating embodied world models across perception and functional utility, addressing fragmented evaluation.
Unknown
Introduces Code World Models, where an LLM synthesizes explicit human-readable programs as world models for reinforcement learning.
Unknown
A survey of world models for robotic manipulation, tracing their evolution from task-specific predictors toward more general and capable systems.