A five-platform framework and 250-task benchmark for evaluating hybrid computer-use agents that explore, build, and verify software recreations.
Open-source Agentic models specialized on Long-horizon tasks.
Graph-search-based end-to-end MLE task solver.
Unlocking the full potential of ViT-based stereo matching.
System review of reward hacking.
Intern-S1-Pro: one-trillion-parameter scientific multimodal foundation model.
InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery.
A Multi-Agent System emulates LSTM’s hierarchical information flow and gated memory mechanisms for long-context understanding.
A unified benchmarking toolkit designed to evaluate AI models for science across a broad range of scientific disciplines and task capabilities.
Graph-search-based end-to-end MLE task solver.