Jing Jiang

9

Papers

43

Total Citations

Papers (9)

Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates

Personalized Federated Collaborative Filtering: A Variational AutoEncoder Approach

WALL-E: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents

Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld

GliDe with a CaPE: A Low-Hassle Method to Accelerate Speculative Decoding

DPC: Dual-Prompt Collaboration for Tuning Vision-Language Models

Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast

Bridge Then Begin Anew: Generating Target-Relevant Intermediate Model for Source-Free Visual Emotion Adaptation

Federated Foundation Models on Heterogeneous Time Series