Sophon

Deep research agents synthesize open-web evidence into long reports, but current benchmarks do not evaluate research centered on a source video. We introduce Video-Centered Deep Research Report Generation.

As LLMs expand their language coverage, evaluating how well they understand and represent diverse cultures becomes increasingly important. However, many benchmarks remain English-centric, with limited cultural coverage and a focus on factual knowledge over its application in…

Most contemporary artificial intelligence (AI) systems are released with frozen parameters and improve through external updates, whereas an ideal system would keep improving from its own experience, a capacity we call recursive self-improvement (RSI).

Retrieval Augmented Generation (RAG) grounds large language models in external knowledge. Modern pipelines combine embedding, chunking, retrieval, reranking, query augmentation, context compression, and agentic verification, yet these techniques are typically evaluated one at a…

Enterprise agents answer questions over workplace records that evolve through team collaboration. As information is shared, corrected, and revised across documents, chats, and figures, multiple versions of the same information accumulate in the workspace.

Frontier coding agents are increasingly framed as end-to-end automated researchers, and ML for science offers a demanding test of that promise: improving a scientific model often requires domain insight beyond routine ML engineering.

Feed-forward 3D Gaussian Splatting (FF3DGS) reconstructs 3D scenes from images in a single forward pass, making it well-suited to applications that must operate within limited resource budgets.

Large Language Model (LLM) agents can handle increasingly complex tasks, navigating long trajectories of observations and actions. As these trajectories grow, key-value (KV) cache I/O and storage become the dominant cost.