Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale Paper β’ 2603.25040 β’ Published Mar 26 β’ 133
Long-horizon Reasoning Agent for Olympiad-Level Mathematical Problem Solving Paper β’ 2512.10739 β’ Published Dec 11, 2025 β’ 47
Achieving Olympia-Level Geometry Large Language Model Agent via Complexity Boosting Reinforcement Learning Paper β’ 2512.10534 β’ Published Dec 11, 2025 β’ 32
OPV: Outcome-based Process Verifier for Efficient Long Chain-of-Thought Verification Paper β’ 2512.10756 β’ Published Dec 11, 2025 β’ 35
ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning Paper β’ 2512.05111 β’ Published Dec 4, 2025 β’ 50
Intern-S1: A Scientific Multimodal Foundation Model Paper β’ 2508.15763 β’ Published Aug 21, 2025 β’ 273
MIG: Automatic Data Selection for Instruction Tuning by Maximizing Information Gain in Semantic Space Paper β’ 2504.13835 β’ Published Apr 18, 2025 β’ 38
InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models Paper β’ 2504.10479 β’ Published Apr 14, 2025 β’ 309
Creation-MMBench: Assessing Context-Aware Creative Intelligence in MLLM Paper β’ 2503.14478 β’ Published Mar 18, 2025 β’ 48
Running on Zero Agents 98 Make It Animatable π 98 Authoring Animation-Ready 3D Characters with One Click
Running Agents Featured 135 Open VLM Video Leaderboard π 135 VLMEvalKit Eval Results in video understanding benchmark
HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation Paper β’ 2407.17438 β’ Published Jul 24, 2024 β’ 26