Ke Wang

14

Papers

252

Total Citations

Papers (14)

Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification

LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging

Review-Enhanced Hierarchical Contrastive Learning for Recommendation

StreamingFlow: Streaming Occupancy Forecasting with Asynchronous Multi-modal Data Streams via Neural Ordinary Differential Equation

Beyond Spatial Domain: Cross-domain Promoted Fourier Convolution Helps Single Image Dehazing

Adaptive Markup Language Generation for Contextually-Grounded Visual Document Understanding

Learning from Failure: Improving Meeting Summarization without Good Samples

Vision Transformers Beat WideResNets on Small Scale Datasets Adversarial Robustness

Aligning Logits Generatively for Principled Black-Box Knowledge Distillation

Semantically-Shifted Incremental Adapter-Tuning is A Continual ViTransformer

NegRefine: Refining Negative Label-Based Zero-Shot OOD Detection

Scaling and Taming Adversarial Training with Synthetic Data

Pi-DUAL: Using privileged information to distinguish clean from noisy labels

Localizing Task Information for Improved Model Merging and Compression