Tianyu Zhang

On The Surprising Effectiveness of a Single Global Merging in Decentralized Learning

Discrete Compositional Generation via General Soft Operators and Robust Reinforcement Learning

Chronological Thinking in Full-Duplex Spoken Dialogue Language Models

Metadata-Agnostic Decentralized Learning

SCOPE: Selective Cross-modal Orchestration of Visual Perception Experts

Improving GUI Grounding with Explicit Position-to-Coordinate Mapping

Advantage Alignment Algorithms

AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Document Understanding

VCR: A Task for Pixel-Level Complex Reasoning in Vision Language Models via Restoring Occluded Text

AI for Global Climate Cooperation: Modeling Global Climate Negotiations, Agreements, and Long-Term Cooperation in RICE-N

MuPT: A Generative Symbolic Music Pretrained Transformer

MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic Approximation

BigDocs: An Open Dataset for Training Multimodal Models on Document and Code Tasks