Qi Su

The paper proposes a unified framework that maps the geometry of games to effective solver dynamics, suggesting that solvability is governed by continuous structural properties rather than discrete classifications.

The paper proposes Preference Delta Aggregation (PDA), a framework that aggregates multiple weak preference signals derived from smaller model pairs using LoRA merging to significantly boost the performance of a strong large language model.

The paper introduces SPIRE, a multi-agent framework designed to extend LLM research capabilities to the humanities by enabling evidence-grounded interpretive reasoning over primary sources.

Proposed EnerInfer framework manages energy efficiency, throughput, and thermal comfort for on-device LLM inference, improving energy efficiency up to 65% without QoE violation.

This paper introduces MMEE, a multilingual and multi-emotion corpus for emphasis detection, and evaluates two state-of-the-art models under various settings.