暂无中文译文，以下为英文原文。点「开始对话」，AI 可以用中文给你讲解这篇论文。 Financial agents must form forecasts and investment ...

Unified conditional image generation requires a single model to preserve different aspects of a visual input while producing a target image that follows textual guidance. Pretrained video models ...

Vision-language models are shifting from offline passive understanding toward online proactive interaction. However, prevailing methods largely rely on explicit requests while miss the implicit user ...

Multi-agent systems often rely on predefined collaboration structures, limiting their ability to adapt to diverse task ...

People have long dreamed of an assistant that is always there to guide them and remind what they forget, from new dishes to lost keys. Powered by multimodal large language models (MLLMs), egocentric ...

LLM agents are increasingly used to solve real-world problems, and their effectiveness depends on both the underlying models and the harnesses that support their operation. However, most existing ...

Video foundation models have advanced rapidly in understanding and generating visual sequences, while video world models seek ...

Cinematic video generation requires both temporal inference from limited inputs (i.e., sparse rather than frame-by-frame guidance) and factor-aware control of character, scene, action, and camera.

Autoregressive video diffusion models generate videos chunk by chunk, yet producing plausible continuations does not ...

Despite recent progress in dexterous reference tracking, existing models focus primarily on single-hand manipulation and a limited range of interactions, leaving the bimanual dexterous behaviors ...

As streaming video generation advances, enabling real-time interaction with generated video is becoming increasingly ...

Moving from controllable videos to genuinely playable worlds requires persistent world state, executable game rules, and low-latency interaction. We outline a roadmap for the next generation of Matrix ...