Xin Chen

This paper analyzes the Solana Rug Pull ecosystem by creating a large-scale, manually verified dataset of fraudulent tokens, identifying three key behavioral patterns, and characterizing the resulting economic and behavioral dynamics.

VertMark introduces a novel, unified, and training-free framework to embed robust watermarks into vertical domain pre-trained language models (VPLMs) for copyright protection across multiple specialized domains.

The paper introduces PlanAudio, a unified LLM-based framework that directly synthesizes natural, composite audio containing speech and sounds from unconstrained free-form text prompts, outperforming existing methods.

The paper introduces OmniMatBench, a comprehensive, human-calibrated multimodal reasoning benchmark covering 19 materials science subfields, revealing that current multimodal language models (MLLMs) have significant gaps in complex materials-science reasoning.

The paper introduces PARL, a framework that learns personalized evaluation rubrics directly from raw user interaction histories to accurately assess how well LLM outputs align with subjective, user-specific preferences.

The paper introduces GenPT, a Generative Projective Testing framework, which demonstrates superior reliability and resistance to social-desirability bias compared to traditional self-report questionnaires when assessing LLM psychological states.

The paper proposes DAG-MoE, a novel sparse Mixture-of-Experts framework that replaces standard weighted-sum aggregation with structural aggregation to enhance model performance and enable multi-step reasoning.

FLARE is a systematic conversion framework that enables a single checkpoint to support both autoregressive (AR) and diffusion-style parallel decoding for hybrid-attention large language models, achieving competitive performance and throughput gains.