Conghui He

SKILLER achieves up to 20.4 percentage points improvement in skill generation for small language models, making high-quality task execution accessible without the prohibitive costs of closed-source solutions.

Existing document parsers may score high on benchmarks, but they still falter on real-world tables, with a top parser achieving only 85.03 TEDS.

A unified framework reveals that most optimizers only engage a fraction of their potential, providing a roadmap for more effective model training.

OmniCoT recalibrates the challenges of panoramic reasoning, enabling MLLMs to leverage global evidence for complex multi-step inference.

ReMMD-Agent achieves a remarkable 41.80% accuracy in detecting misinformation across complex multilingual and multi-image scenarios while slashing verification costs by up to 80%.

A single multimodal model outperforms specialized approaches across 80 biological tasks, redefining the landscape of biological AI applications.

Transition-level supervision can dramatically enhance multimodal model performance, revealing that coherence between text and visuals is crucial for complex reasoning tasks.

AI research agents can now reliably trace method evolution topologies thanks to a new methodological evolution graph, Intern-Atlas, that captures structured relationships between research methods.

LLMs can be systematically debugged and improved by treating training data as code, allowing for targeted "patches" that fix concept-level gaps and reasoning errors.

LLM datasets aren't independent islands: tracing their lineage reveals hidden redundancy, benchmark contamination, and opportunities for more diverse training data.

Forget simplistic synthetic data: ChartVerse generates complex charts and reliable reasoning data from scratch, enabling an 8B model to outperform its 30B teacher in chart reasoning.