Search Results for author:
Found 6 papers, 1 papers with code
Does it Really Generalize Well on Unseen Data? Systematic Evaluation of Relational Triple Extraction Methods
To keep a knowledge graph up-to-date, an extractor needs not only the ability to recall the triples it encountered during training, but also the ability to extract the new triples from the context that it has never seen before.
No Token Left Behind: Reliable KV Cache Compression via Importance-Aware Mixed Precision Quantization
Key-Value (KV) Caching has become an essential technique for accelerating the inference speed and throughput of generative Large Language Models~(LLMs).
Saliency Grafting: Innocuous Attribution-Guided Mixup with Calibrated Label Mixing
However, they now suffer from lack of sample diversification as they always deterministically select regions with maximum saliency, injecting bias into the augmented data.
Fighting Fire with Fire: Contrastive Debiasing without Bias-free Data via Generative Bias-transformation
Deep neural networks (DNNs), despite their impressive ability to generalize over-capacity networks, often rely heavily on malignant bias as shortcuts instead of task-related information for discriminative tasks.
Stop just recalling memorized relations: Extracting Unseen Relational Triples from the context
In this paper, we show that although existing extraction models are able to memorize and recall already seen triples, they cannot generalize effectively for unseen triples.
Attribution Preservation in Network Compression for Reliable Network Interpretation
Neural networks embedded in safety-sensitive applications such as self-driving cars and wearable health monitors rely on two important techniques: input attribution for hindsight analysis and network compression to reduce its size for edge-computing.
