Hamid Alinejad-Rokny

SC-Arena: A Natural Language Benchmark for Single-Cell Reasoning with Knowledge-Augmented Evaluation

EVADE-Bench: Multimodal Benchmark for Evasive Content Detection in E-Commerce Applications

IPBench: Benchmarking the Knowledge of Large Language Models in Intellectual Property

One Model to Critique Them All: Rewarding Agentic Tool-Use via Efficient Reasoning

Structuring Reasoning for Complex Rules Beyond Flat Representations

DEEM: Diffusion models serve as the eyes of large language models for image perception

OpenOmni: Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Alignment and Real-time Emotional Speech Synthesis

LIME: LESS IS MORE FOR MLLM EVALUATION