Newest papers

SolarRenderer: Few-Step Generative Reference Rendering

Guian Fang, Shengju Qian, Dongyue Lu, Junchao Huang, Lutao Jiang, Xin Wang, Yiren Song, Li Jiang · 2026 · arXiv

DOI: 10.48550/arXiv.2610.28630 · open-access PDF

Korean

게임 엔진과 코딩 에이전트는 장면의 레이아웃, 움직임 및 카메라를 지정할 수 있지만, 그러한 거친 구조를 현실적인 비디오로 바꾸는 것은 구조를 따르고 그것이 열려있는 모양을 완료하는 렌더링을 필요로합니다.현재의 렌더링은 하나의 엔진의 표현에 묶여 있으며, 수십 가지의 렌더링 단계 또는 비용이 많이 드는 증류가 필요하며, 목표 비디오와 일치하지 않는 조건에서 배울 수 있습니다.우리는 렌더링을 선보입니다.SolarRenderer는 두 가지 가벼운 LoRA를 가진 냉동 된 MiniMax-H3 33B 척추를 적응하는 구조 조절 된 비디오 렌더링을 제공합니다.

Machine translation (Meta M2M100); the English original follows.

Abstract

Game engines and coding agents can specify the layout, motion, and camera of a scene, yet turning such coarse structure into realistic video requires a renderer that follows the structure and completes the appearance it leaves open. Existing renderers are tied to the representation of one engine, need tens of denoising steps or a costly distillation of their own, and learn from conditions that are not aligned with their target videos. We present SolarRenderer, a structure-conditioned video renderer that adapts a frozen MiniMax-H3 33B backbone with two lightweight LoRAs. Structural videos enter

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28630, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange