Long Chen

Fast QR code detection

2017

Quick Response (QR) code is introduced by the Denso Wave in 1994 [7]. It can encode alphanumeric characters, a rich set of information can be made available through encoded URL addresses [2]. Nowadays, with the …

POEM+: Pricing Longer for Mobile Blockchain Computation Offloading with Edge Computing

2019

Blockchain as an effective security solution has been applied in many mobile devices. But due to the limits of storage and computational capacities, it is hard for mobile devices to run blockchain applications locally. To …

Shapley Counterfactual Credits for Multi-Agent Reinforcement Learning

2021

Centralized Training with Decentralized Execution (CTDE) has been a popular paradigm in cooperative Multi-Agent Reinforcement Learning (MARL) settings and is widely used in many real applications. One of the major challenges in the training process …

A Simple Weakly-Supervised Contrastive Learning Framework for Few-shot Sentiment Classification

2023 · Research Square

Abstract Most existing deep learning-based sentiment classification methods need large human-annotated data, but labeling large amounts of high-quality emotional texts is labor-intensive. Users on various social platforms generate massive amounts of tagged opinionated text (e.g., …

MEDOE: A Multi-Expert Decoder and Output Ensemble Framework for Long-tailed Semantic Segmentation

2023 · arXiv (Cornell University)

Long-tailed distribution of semantic categories, which has been often ignored in conventional methods, causes unsatisfactory performance in semantic segmentation on tail categories. In this paper, we focus on the problem of long-tailed semantic segmentation. Although …

RED: Unleashing Token-Level Rewards from Holistic Feedback via Reward Redistribution

2024 · arXiv (Cornell University)

Reinforcement learning from human feedback (RLHF) offers a promising approach to aligning large language models (LLMs) with human preferences. Typically, a reward model is trained or supplied to act as a proxy for humans in …

Cross Dense Feature Learning With Task Guidance for Few-Shot Classification

2024 · IEEE Transactions on Circuits and Systems for Video Technology

Few-shot classification aims to develop a classifier that adapts to new tasks using only a limited number of labeled images. To overcome the limitation of lacking training images in few-shot image classification, dense features have …

Neuromorphic Readout for Hadron Calorimeters

2025 · arXiv (Cornell University)

We simulate hadrons impinging on a homogeneous lead-tungstate (PbWO4) calorimeter to investigate how the resulting light yield and its temporal structure, as detected by an array of light-sensitive sensors, can be processed by a neuromorphic …

Short Paper: Decentralized Fair Exchange for Assets across Blockchain and the Internet

2025

In this brief announcement, we propose a protocol that enables Alice, who holds cryptocurrency assets maintained on a blockchain, and Bob, who holds traditional digital assets on the Internet secured by a trustworthy TLS service, …

ICPS: Real-Time Resource Configuration for Cloud Serverless Functions Considering Affinity

2025 · arXiv (Cornell University)

Serverless computing, with its operational simplicity and on-demand scalability, has become a preferred paradigm for deploying workflow applications. However, resource allocation for workflows, particularly those with branching structures, is complicated by cold starts and network …

Enhancing Diffusion Policies with Distribution-Matching Generator in Offline Reinforcement Learning

2026 · Proceedings of the AAAI Conference on Artificial Intelligence

Offline reinforcement learning (RL) can learn policies from pre-collected offline datasets without interacting with the environment, but it suffers from the issue of out-of-distribution (OOD). Recent methods use the generative adversarial paradigm to learn policies, …