Models, methods, and the machinery of intelligence.
arXiv
Verdict: NotableAn 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…
Streaming video LLMs must retain evidence before its relevance to future tasks is known and respond when sufficient evidence becomes available.
Successful trajectories on difficult tasks provide valuable supervision for model improvement, but specialized harnesses introduce interventions that may be unavailable during deployment.
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.
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 ....
We introduce HyperBrowseComp, a multilingual and multimodal browsing benchmark comprising 423 manually authored and human-validated questions across 13 languages, written by native or ....
The prevailing approach to computer-use agents couples a model with a domain-specific harness: a browser or desktop environment equipped with human engineered tools that are fixed before ....
Masked diffusion language models (dLMs) offer a promising parallel alternative to autoregressive models for complex reasoning.