Jun Wang

Frozen LLMs can autonomously achieve recursive self-improvement by learning and refining explicit, executable world models from interaction data.

A self-learning agent autonomously refines X-ray diffraction analysis skills, surpassing expert performance on challenging real-world and simulated data without LLM retraining.

Even-odd perturbations of Boussinesq solitary waves exhibit a strict dichotomy: they either scatter globally or blow up in finite time.

JewelTry is proposed, a mask-free diffusion framework for scale-aware jewelry VTON that incorporates a scale adapter that encodes product dimensions into a scale token, enabling the model to learn scale relationships between jewelry items and surrounding human anatomy in-context.

Restoration processes can inadvertently suppress defect detection, but SafeRestore offers a robust framework to audibly assess when to trust automated image transformations.

R²-MAD not only corrects misconceptions in multi-agent debates but also intelligently weighs agent contributions based on past performance, leading to more accurate outcomes.

Transcript-only self-reflection is mathematically incapable of guaranteed improvement without external verification, but grounding reflective updates in environment risk turns multi-agent memory optimization into a provably convergent game.

LLMs can achieve a 7.5x performance boost in web search and extraction by using a bi-level multi-agent architecture with iterative refinement and shared memory.

Forget rigid multi-agent pipelines: this framework lets you build self-organizing AI "companies" that dynamically recruit talent and adapt to tasks on the fly.