AI.info

Zhiqiang Shen

Explore Zhiqiang Shen on AI.info.

• Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs
• AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design
• Simple Domain Generalization for Strong Pixel-Level Image Tampering Detection in Modern VLMs
• BiGain: Unified Token Compression for Joint Generation and Classification
• Pushing the Frontier of Black-Box LVLM Attacks via Fine-Grained Detail Targeting
• Sink-Aware Pruning for Diffusion Language Models
• ShapeCond: Fast Shapelet-Guided Dataset Condensation for Time Series Classification
• Hard Labels In! Rethinking the Role of Hard Labels in Mitigating Local Semantic Drift
• RAGFort: Dual-Path Defense Against Proprietary Knowledge Base Extraction in Retrieval-Augmented Generation
• Attention Is All You Need for KV Cache in Diffusion LLMs
• MosaicDiff: Training-free Structural Pruning for Diffusion Model Acceleration Reflecting Pretraining Dynamics
• Prompting Test-Time Scaling Is A Strong LLM Reasoning Data Augmentation