Models, methods, and the machinery of intelligence.
arXiv
Verdict: RoutineMultimodal language models (MLLMs) exhibit promising spatial reasoning capabilities, yet the internal mechanisms supporting them remain poorly understood.
Continual learning requires models to accumulate past experience and transfer it to new tasks.
Online reinforcement learning (RL) fine-tunes diffusion models with black-box rewards, but reverse-process methods such as Flow-GRPO are limited in efficiency by poor credit assignment, while forward-process methods…
Computer-use agents (CUAs) are rapidly improving, yet synthesizing diverse and reliable software environments at scale remains challenging.
Humans effortlessly react to the world; they adeptly return a tennis shot, catch a falling cup, step aside from a passing cart, or pass a box tossed during truck unloading.
Reinforcement learning (RL) is the central training paradigm for advancing large foundation models towards self-improvement.
Continual post-training faces a dual challenge of acquisition and retention: models must learn new capabilities while preserving prior knowledge.
Coding agents are increasingly used to build programs from scratch as software engineers do rather than to resolve issues within a repository or to generate a repository from a given ....
Recursive self-improvement (RSI) aims to transform interaction experience into persistent improvements, yet external feedback is costly and world-model predictions may become unreliable ....