Models, methods, and the machinery of intelligence.
arXiv
Verdict: NotableStreaming video LLMs must retain evidence before its relevance to future tasks is known and respond when sufficient evidence becomes available.
An emerging hypothesis about reinforcement learning (RL) post-training of large language models (LLMs) is that it merely sharpens existing behaviors of a base model, improving single-shot accuracy at the cost of…
Evolutionary search with large language models (LLMs) can stall when progress requires external knowledge the model lacks.
Discrete diffusion language models offer a compelling alternative to autoregressive generation for tasks demanding bidirectional reasoning and global constraint satisfaction.
World action models (WAMs) have emerged as a promising paradigm for robotic control by jointly predicting future visual dynamics and actions from an initial observation and instruction.
Successful trajectories on difficult tasks provide valuable supervision for model improvement, but specialized harnesses introduce interventions that may be unavailable during deployment.
Large language model (LLM) agents can now undertake increasingly complex tasks, but the way they organize interaction history into memory does not ensure a coherent understanding of the ....
As interactive 3D worlds are increasingly used to study intelligent behavior, it becomes important to develop efficient pipelines for identifying anomalies in these simulated ....
GUI agents require high-quality interaction trajectories to learn how software environments respond to actions, maintain state, and support multi-step workflows.