Peng Xu

New Related-Key Impossible Differential Attack on MIBS-80

2016

MIBS is a lightweight block cipher designed by M. Izadi et al in 2009 for tiny computing devices, such as RFID tags and sensor network nodes. The cipher algorithm iterates a Feistel structure with SP …

A Novel Repetition Normalized Adversarial Reward for Headline Generation

2019

While reinforcement learning can effectively improve language generation models, it often suffers from generating incoherent and repetitive phrases [1]. In this paper, we propose a novel repetition normalized adversarial reward to mitigate these problems. Our …

Embedding-based Zero-shot Retrieval through Query Generation

2020 · arXiv (Cornell University)

Passage retrieval addresses the problem of locating relevant passages, usually from a large corpus, given a query. In practice, lexical term-matching algorithms like BM25 are popular choices for retrieval owing to their efficiency. However, term-based …

Geoscience Language Processing for Exploration

2021

Abstract Deep learning has recently been providing step-change capabilities, particularly using transformer models, for natural language processing applications such as question answering, query-based summarization, and language translation for general-purpose context. We have developed a geoscience-specific …

Multimodal Learning with Transformers: A Survey

2022 · arXiv (Cornell University)

Transformer is a promising neural network learner, and has achieved great success in various machine learning tasks. Thanks to the recent prevalence of multimodal applications and big data, Transformer-based multimodal learning has become a hot …

Microwave-activated quantum state transfer and entanglement generation among five to seven qubits

2025 · Laser Physics Letters

Abstract We propose a scheme for the rapid and high-fidelity transmission of quantum states and the generation of entanglement among at least five qubits in a circuit quantum electrodynamics system, based on optimized microwave-driven pulses. …

Do As I Can, Not As I Say: Grounding Language in Robotic Affordances

2022 · arXiv (Cornell University)

Large language models can encode a wealth of semantic knowledge about the world. Such knowledge could be extremely useful to robots aiming to act upon high-level, temporally extended instructions expressed in natural language. However, a …