Jie Jiang

14

Papers

47

Total Citations

Papers (14)

STEM: Unleashing the Power of Embeddings for Multi-Task Recommendation

Scaling Laws for Floating–Point Quantization Training

Decoupled Training: Return of Frustratingly Easy Multi-Domain Learning

From Feature Interaction to Feature Generation: A Generative Paradigm of CTR Prediction Models

PointCFormer: A Relation-Based Progressive Feature Extraction Network for Point Cloud Completion

MRFS: Mutually Reinforcing Image Fusion and Segmentation

On the Embedding Collapse when Scaling up Recommendation Models

Seeing What You Miss: Vision-Language Pre-Training With Semantic Completion Learning

VLPD: Context-Aware Pedestrian Detection via Vision-Language Semantic Self-Supervision

Scaling Mesh Generation via Compressive Tokenization

Unleashing Vecset Diffusion Model for Fast Shape Generation

RomanTex: Decoupling 3D-aware Rotary Positional Embedded Multi-Attention Network for Texture Synthesis

MaterialMVP: Illumination-Invariant Material Generation via Multi-view PBR Diffusion

ForkMerge: Mitigating Negative Transfer in Auxiliary-Task Learning