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
Peking University
A leading Chinese research university in Beijing, prominent in natural language processing, multimodal learning, and AI research.
MiniMax Sparse Attention: 1M Context Without Dense Attention
MiniMax Sparse Attention keeps only 2,048 selected KV tokens per query group and reports 28.4x lower attention FLOPs plus 14.2x prefill speedup at 1M context.
AI Agents · TokenRhythm Technologies
Claw-SWE-Bench: Why Coding Agent Harnesses Matter
Claw-SWE-Bench evaluates OpenClaw-style coding-agent harnesses on 350 GitHub issue tasks. OpenClaw jumps from 19.1% to 73.4% Pass@1 with a full adapter.
Multimodal Models · Peking University
Watch, Remember, Reason: A Human-View Map of Video MLLMs
A survey that reframes long-video MLLMs as three abilities (watch, remember, reason), comparing against 11 prior surveys and organizing 100+ methods plus 5 application domains.
LLM Reasoning · Samsung Research
TrOPD: Trust-Region On-Policy Distillation for Small LLMs
TrOPD masks on-policy distillation to the tokens where the teacher is actually trustworthy, adding +3.06 to +3.52 average points over standard OPD on math, code, and STEM benchmarks with 1.5B-1.7B students.
Video2GUI: Mining 12M GUI Agent Trajectories From Internet Videos
Video2GUI turns 500M unlabeled tutorial videos into WildGUI — 12M grounded GUI interaction trajectories across 1,500+ apps and sites — and pretraining Qwen2.5-VL and Mimo-VL on it lifts GUI benchmarks by 5-20%.