papers

Publications (17)

cs.CL2023

Enhancing Document-level Event Argument Extraction with Contextual Clues and Role Relevance

Wanlong Liu, Shaohuan Cheng, Dingyi Zeng +1

Document-level event argument extraction poses new challenges of long input and cross-sentence inference compared to its sentence-level counterpart. However, most prior works focus…

cs.CV2026

Vision SmolMamba: Spike-Guided Token Pruning for Energy-Efficient Spiking State-Space Vision Models

Dewei Bai, Hongxiang Peng, Yunyun Zeng +3

Spiking Transformers have shown strong potential for long-range visual modeling through spike-driven self-attention. However, their quadratic token interactions remain fundamentall…

cs.CL2020

Improving Readability for Automatic Speech Recognition Transcription

Junwei Liao, Sefik Emre Eskimez, Liyang Lu +5

Modern Automatic Speech Recognition (ASR) systems can achieve high performance in terms of recognition accuracy. However, a perfectly accurate transcript still can be challenging t…

cs.AI2021

Self-Annotated Training for Controllable Image Captioning

Zhangzi Zhu, Tianlei Wang, Hong Qu

The Controllable Image Captioning (CIC) task aims to generate captions conditioned on designated control signals. Several structure-related control signals are proposed to control…

cs.NE2020

Rectified Linear Postsynaptic Potential Function for Backpropagation in Deep Spiking Neural Networks

Malu Zhang, Jiadong Wang, Burin Amornpaisannon +8

Spiking Neural Networks (SNNs) use spatio-temporal spike patterns to represent and transmit information, which is not only biologically realistic but also suitable for ultra-low-po…

cs.CL2024

MLPs Compass: What is learned when MLPs are combined with PLMs?

Li Zhou, Wenyu Chen, Yong Cao +3

While Transformer-based pre-trained language models and their variants exhibit strong semantic representation capabilities, the question of comprehending the information gain deriv…

cs.CL2021

Generating Human Readable Transcript for Automatic Speech Recognition with Pre-trained Language Model

Junwei Liao, Yu Shi, Ming Gong +5

Modern Automatic Speech Recognition (ASR) systems can achieve high performance in terms of recognition accuracy. However, a perfectly accurate transcript still can be challenging t…

cs.LG2026

Congestion-Aware Dynamic Axonal Delay for Spiking Neural Networks

Dewei Bai, Hongxiang Peng, Yunyun Zeng +2

The paper introduces a congestion‑aware dynamic axonal delay mechanism for spiking neural networks that combines a static base delay with an activity‑conditioned shift, improving t…

#spiking neural networks#dynamic delay#temporal processing#speech recognition
cs.CV2026

QB-LIF: Learnable-Scale Quantized Burst Neurons for Efficient SNNs

Dewei Bai, Hongxiang Peng, Jiajun Mei +4

Binary spike coding enables sparse and event-driven computation in spiking neural networks (SNNs), yet its 1-bit-per-timestep representation fundamentally limits information throug…

cs.CL2020

KINNEWS and KIRNEWS: Benchmarking Cross-Lingual Text Classification for Kinyarwanda and Kirundi

Rubungo Andre Niyongabo, Hong Qu, Julia Kreutzer +1

Recent progress in text classification has been focused on high-resource languages such as English and Chinese. For low-resource languages, amongst them most African languages, the…

cs.CV2025

HybridReg: Robust 3D Point Cloud Registration with Hybrid Motions

Keyu Du, Hao Xu, Haipeng Li +3

Scene-level point cloud registration is very challenging when considering dynamic foregrounds. Existing indoor datasets mostly assume rigid motions, so the trained models cannot ro…

cs.LG2022

Double Thompson Sampling in Finite stochastic Games

Shuqing Shi, Xiaobin Wang, Zhiyou Yang +2

We consider the trade-off problem between exploration and exploitation under finite discounted Markov Decision Process, where the state transition matrix of the underlying environm…

cs.CV2026

BSViT: A Burst Spiking Vision Transformer for Expressive and Efficient Visual Representation Learning

Hongxiang Peng, Dewei Bai, Hong Qu

Spiking Vision Transformers (S-ViTs) offer a promising framework for energy-efficient visual learning. However, existing designs remain limited by two fundamental issues: the restr…

cs.LG2024

DPGNN: Dual-Perception Graph Neural Network for Representation Learning

Li Zhou, Wenyu Chen, Dingyi Zeng +4

Graph neural networks (GNNs) have drawn increasing attention in recent years and achieved remarkable performance in many graph-based tasks, especially in semi-supervised learning o…

cs.CV2023

Improving Image Captioning with Control Signal of Sentence Quality

Zhangzi Zhu, Hong Qu

In the dataset of image captioning, each image is aligned with several descriptions. Despite the fact that the quality of these descriptions varies, existing captioning models trea…

cs.CL2021

Improving Zero-shot Neural Machine Translation on Language-specific Encoders-Decoders

Junwei Liao, Yu Shi, Ming Gong +3

Recently, universal neural machine translation (NMT) with shared encoder-decoder gained good performance on zero-shot translation. Unlike universal NMT, jointly trained language-sp…

cs.CV2021

Macroscopic Control of Text Generation for Image Captioning

Zhangzi Zhu, Tianlei Wang, Hong Qu

Despite the fact that image captioning models have been able to generate impressive descriptions for a given image, challenges remain: (1) the controllability and diversity of exis…