InternAgent Collection InternAgent aims to facilitate AI+X innovative research across diverse scientific domains • 13 items • Updated 4 days ago • 1
SGI-Bench Collection A Definition of Scientific General Intelligence • 8 items • Updated 5 days ago • 5
A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers Paper • 2508.21148 • Published Aug 28 • 140
Scientists' First Exam: Probing Cognitive Abilities of MLLM via Perception, Understanding, and Reasoning Paper • 2506.10521 • Published Jun 12 • 73
MME-Reasoning: A Comprehensive Benchmark for Logical Reasoning in MLLMs Paper • 2505.21327 • Published May 27 • 83
NovelSeek: When Agent Becomes the Scientist -- Building Closed-Loop System from Hypothesis to Verification Paper • 2505.16938 • Published May 22 • 120
LeX-Art: Rethinking Text Generation via Scalable High-Quality Data Synthesis Paper • 2503.21749 • Published Mar 27 • 26
Lumina-Image 2.0: A Unified and Efficient Image Generative Framework Paper • 2503.21758 • Published Mar 27 • 22
Adversarial Data Collection: Human-Collaborative Perturbations for Efficient and Robust Robotic Imitation Learning Paper • 2503.11646 • Published Mar 14 • 35
Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders Paper • 2503.03601 • Published Mar 5 • 232
SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing Paper • 2503.04629 • Published Mar 6 • 19
SEAP: Training-free Sparse Expert Activation Pruning Unlock the Brainpower of Large Language Models Paper • 2503.07605 • Published Mar 10 • 68
MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency Paper • 2502.09621 • Published Feb 13 • 28
Dolphin: Closed-loop Open-ended Auto-research through Thinking, Practice, and Feedback Paper • 2501.03916 • Published Jan 7 • 16
Training-Free Adaptive Diffusion with Bounded Difference Approximation Strategy Paper • 2410.09873 • Published Oct 13, 2024 • 3
GeoX: Geometric Problem Solving Through Unified Formalized Vision-Language Pre-training Paper • 2412.11863 • Published Dec 16, 2024 • 4
DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Language Models Paper • 2406.11633 • Published Jun 17, 2024 • 1