MaxProof: How MiniMax M3 Reaches Gold-Level Proof Scores
MaxProof turns MiniMax-M3 into a generator, verifier, fixer, and ranker; with population-level test-time scaling it reports 35/42 on IMO 2025 and 36/42 on USAMO 2026.
Institution
Fudan University
A leading comprehensive research university in Shanghai, China, with active computer vision and multimodal AI research groups.
TaskMem: Teaching a Video Agent What Is Worth Remembering
TaskMem trains a multimodal agent to write its own memory with RL, lifting streaming-video QA accuracy to 67.9% on VideoMME and 45.4% on EgoLife, gains of 6.3 and 7.0 points over the Qwen3-VL-30B baseline.
World Models · Fudan University
WBench: A Multi-turn Benchmark for Interactive Video World Models
WBench scores interactive video world models on five axes — quality, setting, interaction, consistency, physics — across 289 cases and 1,058 turns, and finds no single model wins on all five.