Search Results for author: Xiwen Zhang

Found 13 papers, 8 papers with code

Minimalist Softmax Attention Provably Learns Constrained Boolean Functions

no code implementations26 May 2025 Jerry Yao-Chieh Hu, Xiwen Zhang, Maojiang Su, Zhao Song, Han Liu

We study the computational limits of learning $k$-bit Boolean functions (specifically, $\mathrm{AND}$, $\mathrm{OR}$, and their noisy variants), using a minimalist single-head softmax-attention mechanism, where $k=\Theta(d)$ relevant bits are selected from $d$ inputs.

On the Perception Bottleneck of VLMs for Chart Understanding

1 code implementation24 Mar 2025 Junteng Liu, Weihao Zeng, Xiwen Zhang, Yijun Wang, Zifei Shan, Junxian He

Chart understanding requires models to effectively analyze and reason about numerical data, textual elements, and complex visual components.

Chart Understanding Contrastive Learning

A LSTM-Transformer Model for pulsation control of pVADs

no code implementations10 Mar 2025 Chaoran E, Chenghan Chen, Yuyang Shi, Haiyun Wang, Peixin Hua, Xiwen Zhang

(2)The pulsation time characteristic points predicted by the LSTM-Transformer Model shows a maximum prediction error of 1. 78ms, which is significantly lower than other methods.

Diving into Self-Evolving Training for Multimodal Reasoning

no code implementations23 Dec 2024 Wei Liu, Junlong Li, Xiwen Zhang, Fan Zhou, Yu Cheng, Junxian He

Our analysis leads to a set of best practices for each factor, aimed at optimizing multimodal reasoning.

Multimodal Reasoning

Small Language Models: Survey, Measurements, and Insights

1 code implementation24 Sep 2024 Zhenyan Lu, Xiang Li, Dongqi Cai, Rongjie Yi, Fangming Liu, Xiwen Zhang, Nicholas D. Lane, Mengwei Xu

Small language models (SLMs), despite their widespread adoption in modern smart devices, have received significantly less academic attention compared to their large language model (LLM) counterparts, which are predominantly deployed in data centers and cloud environments.

Benchmarking Decoder +5

DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving

1 code implementation18 Jun 2024 Yuxuan Tong, Xiwen Zhang, Rui Wang, Ruidong Wu, Junxian He

Solving mathematical problems requires advanced reasoning abilities and presents notable challenges for large language models.

Ranked #4 on Natural Questions on TheoremQA (using extra training data)

Arithmetic Reasoning Math +3

InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation

2 code implementations12 Sep 2023 Xingchao Liu, Xiwen Zhang, Jianzhu Ma, Jian Peng, Qiang Liu

Leveraging our new pipeline, we create, to the best of our knowledge, the first one-step diffusion-based text-to-image generator with SD-level image quality, achieving an FID (Frechet Inception Distance) of $23. 3$ on MS COCO 2017-5k, surpassing the previous state-of-the-art technique, progressive distillation, by a significant margin ($37. 2$ $\rightarrow$ $23. 3$ in FID).

Text to Image Generation Text-to-Image Generation

Deep Learning for Frame Error Prediction using a DARPA Spectrum Collaboration Challenge (SC2) Dataset

1 code implementation22 Mar 2020 Abu Shafin Mohammad Mahdee Jameel, Ahmed P. Mohamed, Xiwen Zhang, Aly El Gamal

We demonstrate a first example for employing deep learning in predicting frame errors for a Collaborative Intelligent Radio Network (CIRN) using a dataset collected during participation in the final scrimmages of the DARPA SC2 challenge.

Deep Learning

Efficient Training of Deep Classifiers for Wireless Source Identification using Test SNR Estimates

no code implementations26 Dec 2019 Xingchen Wang, Shengtai Ju, Xiwen Zhang, Sharan Ramjee, Aly El Gamal

We study efficient deep learning training algorithms that process received wireless signals, if a test Signal to Noise Ratio (SNR) estimate is available.

Benchmarking

Approximate Query Service on Autonomous IoT Cameras

no code implementations2 Sep 2019 Mengwei Xu, Xiwen Zhang, Yunxin Liu, Gang Huang, Xuanzhe Liu, Felix Xiaozhu Lin

Elf is a runtime for an energy-constrained camera to continuously summarize video scenes as approximate object counts.

Databases

Deep Learning for Interference Identification: Band, Training SNR, and Sample Selection

1 code implementation16 May 2019 Xiwen Zhang, Tolunay Seyfi, Shengtai Ju, Sharan Ramjee, Aly El Gamal, Yonina C. Eldar

We study the problem of interference source identification, through the lens of recognizing one of 15 different channels that belong to 3 different wireless technologies: Bluetooth, Zigbee, and WiFi.

Classification Deep Learning +1

Cannot find the paper you are looking for? You can Submit a new open access paper.