Author name cluster

Hui Su

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

12 papers

2 author rows

AAAI Conference 2026 Conference Paper

Efficient Forecasting of Geostationary Infrared Brightness Temperature Sequences: A Benchmark and a Lightweight Model

Kuai Dai
Hui Su
Xutao Li
Chengxing Zhai

Forecasting geostationary infrared brightness temperature sequences from historical observations is a significant and challenging task. By analyzing these predictions, cloud evolution, convective activity, and atmospheric radiative states can be revealed in advance, offering high potential value in domains such as weather nowcasting, energy management, and disaster monitoring. Recently, artificial intelligence techniques have provided valuable insights into this task. However, as a nascent research area, the lack of a standardized, high-quality benchmark has significantly impeded progress. Moreover, training existing deep learning models for this task remains computationally expensive due to the complexity of their network architectures and modeling mechanisms. To address these challenges, we introduce a new benchmark, FY4ABT, and propose a lightweight prediction model, WavePredNet. Specifically, FY4ABT comprises three sub-datasets designed to respectively evaluate prediction performance under short-term, medium-term, and long-term scenarios. Meanwhile, WavePredNet effectively captures multi-scale dynamics, including both low- and high-frequency components with low computational costs while delivering exceptional performance.

PDF Details DOI

AAAI Conference 2026 Conference Paper

SatSolarCast: A Flexible Framework for Multimodal Solar Irradiance Forecasting via Memory-Alignment Learning

Kuai Dai
Hui Su
Chengxing Zhai
Huiwei Lin
Mingliang Bai

Solar irradiance forecast aims to accurately estimate future solar irradiance based on historical data, playing a vital role in energy production and grid management. While ground-based station measurements provide local accuracy, geostationary satellites offer much broader environmental contexts, such as cloud coverage, which serves as a key factor for accurate forecasting. However, effectively integrating these multimodal observations remains a challenge, with existing methods suffering from inflexibility and high computational costs. To address this problem, we propose SatSolarCast, a flexible and efficient multimodal framework that introduces a memory alignment learning mechanism to integrate geostationary satellite data and historical irradiance observations. By preserving and recalling long-term spatiotemporal patterns from a specialized satellite memory bank, SatSolarCast enables effective guidance for both short- and long-term prediction. Additionally, SatSolarCast offers plug-and-play compatibility and can be incorporated into various forecasting architectures. Extensive experiments across four ground stations demonstrate that SatSolarCast substantially improves forecasting performance compared to prior methods with much lower computational costs.

PDF Details DOI

ICML Conference 2025 Conference Paper

SkipGPT: Each Token is One of a Kind

Anhao Zhao
Fanghua Ye 0001
Yingqi Fan
Junlong Tong
Jing Xiong
Zhiwei Fei
Hui Su
Xiaoyu Shen 0001

Large language models (LLMs) achieve remarkable performance across tasks but incur substantial computational costs due to their deep, multi-layered architectures. Layer pruning has emerged as a strategy to alleviate these inefficiencies, but conventional static pruning methods overlook two critical dynamics inherent to LLM inference: (1) horizontal dynamics, where token-level heterogeneity demands context-aware pruning decisions, and (2) vertical dynamics, where the distinct functional roles of MLP and self-attention layers necessitate component-specific pruning policies. We introduce SkipGPT, a dynamic layer pruning framework designed to optimize computational resource allocation through two core innovations: (1) global token-aware routing to prioritize critical tokens and (2) decoupled pruning policies for MLP and self-attention components. To mitigate training instability, we propose a two-stage optimization paradigm: first, a disentangled training phase that learns routing strategies via soft parameterization to avoid premature pruning decisions, followed by parameter-efficient LoRA fine-tuning to restore performance impacted by layer removal. Extensive experiments demonstrate that SkipGPT reduces over 40% model parameters while matching or exceeding the performance of the original dense model across benchmarks. By harmonizing dynamic efficiency with preserved expressivity, SkipGPT advances the practical deployment of scalable, resource-aware LLMs. Our code is publicly available at: https: //github. com/EIT-NLP/SkipGPT.

Details

IJCAI Conference 2020 Conference Paper

BlueMemo: Depression Analysis through Twitter Posts

Pengwei Hu
Chenhao Lin
Hui Su
Shaochun Li
Xue Han
Yuan Zhang
Jing Mei

The use of social media runs through our lives, and users' emotions are also affected by it. Previous studies have reported social organizations and psychologists using social media to find depressed patients. However, due to the variety of content published by users, it isn't effortless for the system to consider the text, image, and even the hidden information behind the image. To address this problem, we proposed a new system for social media screening of depressed patients named BlueMemo. We collected real-time posts from Twitter. Based on the posts, learned text features, image features, and visual attributes were extracted as three modalities and were fed into a multi-modal fusion and classification model to implement our system. The proposed BlueMemo has the power to help physicians and clinicians quickly and accurately identify users at potential risk for depression.

PDF Details DOI

NeurIPS Conference 2019 Conference Paper

Deep Structured Prediction for Facial Landmark Detection

Lisha Chen
Hui Su
Qiang Ji

Existing deep learning based facial landmark detection methods have achieved excellent performance. These methods, however, do not explicitly embed the structural dependencies among landmark points. They hence cannot preserve the geometric relationships between landmark points or generalize well to challenging conditions or unseen data. This paper proposes a method for deep structured facial landmark detection based on combining a deep Convolutional Network with a Conditional Random Field. We demonstrate its superior performance to existing state-of-the-art techniques in facial landmark detection, especially a better generalization ability on challenging datasets that include large pose and occlusion.

PDF Details

IJCAI Conference 2019 Conference Paper

Embodied Conversational AI Agents in a Multi-modal Multi-agent Competitive Dialogue

Rahul R. Divekar
Xiangyang Mou
Lisha Chen
Maíra Gatti de Bayser
Melina Alberio Guerra
Hui Su

In a setting where two AI agents embodied as animated humanoid avatars are engaged in a conversation with one human and each other, we see two challenges. One, determination by the AI agents about which one of them is being addressed. Two, determination by the AI agents if they may/could/should speak at the end of a turn. In this work we bring these two challenges together and explore the participation of AI agents in multi-party conversations. Particularly, we show two embodied AI shopkeeper agents who sell similar items aiming to get the business of a user by competing with each other on the price. In this scenario, we solve the first challenge by using headpose (estimated by deep learning techniques) to determine who the user is talking to. For the second challenge we use deontic logic to model rules of a negotiation conversation.

PDF Details

IJCAI Conference 2019 Conference Paper

Reagent: Converting Ordinary Webpages into Interactive Software Agents

Matthew Peveler
Jeffrey O. Kephart
Hui Su

We introduce Reagent, a technology that can be used in conjunction with automated speech recognition to allow users to query and manipulate ordinary webpages via speech and pointing. Reagent can be used out-of-the-box with third-party websites, as it requires neither special instrumentation from website developers nor special domain knowledge to capture semantically-meaningful mouse interactions with structured elements such as tables and plots. When it is unable to infer mappings between domain vocabulary and visible webpage content on its own, Reagent proactively seeks help by engaging in a voice-based interaction with the user.

PDF Details

AAAI Conference 2019 System Paper

The Rensselaer Mandarin Project — A Cognitive and Immersive Language Learning Environment

David Allen
Rahul R. Divekar
Jaimie Drozdal
Lilit Balagyozyan
Shuyue Zheng
Ziyi Song
Huang Zou
Jeramey Tyler

The Rensselaer Mandarin Project enables a group of foreign language students to improve functional understanding, pronunciation and vocabulary in Mandarin Chinese through authentic speaking situations in a virtual visit to China. Students use speech, gestures, and combinations thereof to navigate an immersive, mixed reality, stylized realism game experience through interaction with AI agents, immersive technologies, and game mechanics. The environment was developed in a black box theater equipped with a human-scale 360◦ panoramic screen (140 h, 200 r), arrays of markerless motion tracking sensors, and speakers for spatial audio.

PDF Details

UAI Conference 2018 Conference Paper

A Cost-Effective Framework for Preference Elicitation and Aggregation

Zhibing Zhao
Haoming Li 0002
Junming Wang
Jeffrey O. Kephart
Nicholas Mattei
Hui Su
Lirong Xia

We propose a cost-effective framework for preference elicitation and aggregation under the Plackett-Luce model with features. Given a budget, our framework iteratively computes the most cost-effective elicitation questions in order to help the agents make a better group decision. We illustrate the viability of the framework with experiments on Amazon Mechanical Turk, which we use to estimate the cost of answering different types of elicitation questions. We compare the prediction accuracy of our framework when adopting various information criteria that evaluate the expected information gain from a question. Our experiments show carefully designed information criteria are much more efficient, i. e. , they arrive at the correct answer using fewer queries, than randomly asking questions given the budget constraint.

Details

AAAI Conference 2018 Short Paper

Dialogue Generation With GAN

Hui Su
Xiaoyu Shen
Pengwei Hu
Wenjie Li
Yun Chen

This paper presents a Generative Adversarial Network (GAN) to model multi-turn dialogue generation, which trains a latent hierarchical recurrent encoder-decoder simultaneously with a discriminative classiﬁer that make the prior approximate to the posterior. Experiments show that our model achieves better results.

PDF Details

AAAI Conference 2018 Conference Paper

Improving Variational Encoder-Decoders in Dialogue Generation

Xiaoyu Shen
Hui Su
Shuzi Niu
Vera Demberg

Variational encoder-decoders (VEDs) have shown promising results in dialogue generation. However, the latent variable distributions are usually approximated by a much simpler model than the powerful RNN structure used for encoding and decoding, yielding the KL-vanishing problem and inconsistent training objective. In this paper, we separate the training step into two phases: The ﬁrst phase learns to autoencode discrete texts into continuous embeddings, from which the second phase learns to generalize latent representations by reconstructing the encoded embedding. In this case, latent variables are sampled by transforming Gaussian noise through multi-layer perceptrons and are trained with a separate VED model, which has the potential of realizing a much more ﬂexible distribution. We compare our model with current popular models and the experiment demonstrates substantial improvement in both metric-based and human evaluations.

PDF Details

AAAI Conference 2018 Short Paper

Towards Better Variational Encoder-Decoders in Seq2Seq Tasks

Xiaoyu Shen
Hui Su

Variational encoder-decoders have shown promising results in seq2seq tasks. However, the training process is known difﬁcult to be controlled because latent variables tend to be ignored while decoding. In this paper, we thoroughly analyze the reason behind this training difﬁculty, compare different ways of alleviating it and propose a new framework that helps signiﬁcantly improve the overall performance.

PDF Details