Hao Xue

The paper proposes SafeDIG, a robust safety steering framework that adapts Diffusion Transformers for text-to-image generation by treating safety control as position-aware sparse feature transfer, ensuring reliable safety across different risk domains.

The paper introduces StreamSynth, a sequential setting for synthetic data generation, and proposes SynLearner, a framework that enables LLMs to improve synthesis performance by accumulating and transferring experience across a stream of tasks.

The paper introduces EvoXXLTraffic, an ultra-large, sensor-evolving dataset that simulates real-world road network growth, demonstrating that existing state-of-the-art traffic forecasting models fail when faced with such dynamic network changes.

The paper introduces ConsisGuard, a framework that addresses the 'deliberation-to-enforcement gap' in LLM guardrails by ensuring that the reasoning process is faithfully and consistently translated into the final safety decision.

This paper introduces KGERMAR, a framework that constructs dynamic, context-specific knowledge graphs during inference for long-context language modeling, achieving lower perplexity and better memory efficiency than memory-augmented baselines.

This paper proposes CrossPool, a serving engine for cold Machine Learning Models (LLMs) that separates weights and KV-cache into two GPU memory pools to improve GPU memory utilization and long-context support.

The paper proposes CODA, an algorithm-hardware co-designed architecture for deploying Video Diffusion Models on edge devices, achieving up to 1.80x speedup and 1.74x energy efficiency.

This paper proposes a domain-generalized training framework for pixel-level image tampering detection in modern vision-language models, improving robustness and out-of-distribution performance.