4 papers
Where Reasoning Diverges: Localized Multi-Agent Debate for Multi-Hop Question Answering
Weijun Gao, Xiang Ding, Tiancheng Xing +1
Multi-agent debate commonly exchanges complete rationales even when disagreements concern only a few intermediate claims. We introduce Localized Multi-Agent Debate (LMAD), an infer…
Are LLMs Reliable Rankers? Rank Manipulation via Two-Stage Token Optimization
Tiancheng Xing, Jerry Li, Yixuan Du +1
Large language models (LLMs) are increasingly used as rerankers in information retrieval, yet their ranking behavior can be steered by small, natural-sounding prompts. To expose th…
SDiT: Semantic Region-Adaptive for Diffusion Transformers
Bowen Lin, Fanjiang Ye, Yihua Liu +7
Diffusion Transformers (DiTs) achieve state-of-the-art performance in text-to-image synthesis but remain computationally expensive due to the iterative nature of denoising and the…
Dataset Distillation via the Wasserstein Metric
Haoyang Liu, Yijiang Li, Tiancheng Xing +5
Dataset Distillation (DD) aims to generate a compact synthetic dataset that enables models to achieve performance comparable to training on the full large dataset, significantly re…