Author name cluster

Xiaofeng Hou

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.

4 papers

2 author rows

AAAI Conference 2026 Conference Paper

AdaReason: Progressive Training of Multi-LoRA Adapters for Budget-Adaptive Language Reasoning Models

Jiacheng Wang
Tianle Chen
Pengyu Cheng
Xiaofeng Hou
Jiacheng Liu

Large reasoning models (LRMs) have demonstrated remarkable capabilities in solving complex problems through extended chain-of-thought reasoning. However, existing approaches face a fundamental trade-off between computational efficiency and reasoning accuracy. Current methods either lack support for user-specified computational budgets or require maintaining multiple independent models, leading to significant resource overhead. In this paper, we present AdaReason, a unified framework that trains a single base model to support arbitrary user-defined computational budgets through dynamic adapter composition. Our approach introduces three key innovations: (1) a length-adaptive step reward function that stabilizes training across diverse budget constraints, (2) a progressive training strategy that gradually tightens computational bounds while maintaining model performance, and (3) a runtime adapter merging mechanism that dynamically interpolates between different computational preferences. Unlike existing methods that suffer from training instability in large context windows, AdaReason achieves stable convergence through careful reward shaping and progressive constraint tightening. Additionally, we provide a rigorous theoretical analysis, establishing a performance bound for our merged model. Experiments on different reasoning benchmarks demonstrate that AdaReason establishes a new state-of-the-art in the performance-efficiency trade-off and enables flexible runtime budget adaptation.

PDF Details DOI

AAAI Conference 2026 Conference Paper

DesireKV: Decoupling Sensitivity and Importance for Reasoning-Aware KV Cache Compression

Pengyu Cheng
Jiacheng Wang
Tianle Chen
Bei Liu
Xiaofeng Hou
Jiacheng Liu

Large language models performing chain-of-thought (CoT) reasoning generate extensive intermediate sequences that consume substantial memory through key-value (KV) cache storage. Unlike conventional text generation, reasoning sequences exhibit unique characteristics, including repetitive logic patterns and low information density, making existing KV cache compression methods suboptimal. We propose DesireKV, a novel compression framework that first constructs a two-dimensional coordinate system based on attention-derived importance and outlier-based quantization sensitivity. It then applies a dedicated protection mechanism for tokens critical to the reasoning process itself. Our approach makes differentiated compression decisions: retaining important and sensitive tokens, quantizing important but insensitive tokens, and evicting unimportant tokens. Through comprehensive evaluation on reasoning benchmarks, we demonstrate that DesireKV achieves up to 2.93× throughput improvement while maintaining nearly 99% of original reasoning accuracy.

PDF Details DOI

ECAI Conference 2023 Conference Paper

Label Aggregation with Self-Supervision Enhanced Graph Transformer

Jiacheng Liu 0001
Feilong Tang 0001
Xiaofeng Hou

Aggregating noisy labels produced by the crowd of workers to generate true labels is a challenging problem in crowdsourcing. The key behind label aggregation is to effectively utilize the hidden information (e. g. , characteristics of workers and questions which are often missing) in the labeling process. Existing methods mainly generated aggregation models based on the complicated Bayesian model or some strong assumptions. Recently, deep learning-based methods attempt to automate label aggregation but need various labels. These all make them hard to deploy to real-world applications. In fact, abundant information in the process of crowdsourcing itself can be extremely helpful to aggregate the labels. In this paper, we propose ATHENA (lAbel aggregaTion witH sElf-supervision eNhanced grAph transformer) to aggregate labels by utilizing the self-supervision signals in crowdsourcing. Firstly, we propose a transformer-based graph neural network that can learn from the crowdsourcing topology and features. Then, we use self-supervision signals inherently included in the dataset to help to aggregate the labels. To be specific, we identify the answer-based self-supervision signal that can predict the answer of any user given to different tasks. In our evaluations, we compare the proposed ATHENA with the other 11 representative methods on 10 datasets. Our experimental results demonstrate that ATHENA is highly effective in aggregating labels and obtains much better performance than existing methods.

Details

AAAI Conference 2020 Conference Paper

Fine-Grained Machine Teaching with Attention Modeling

Jiacheng Liu
Xiaofeng Hou
Feilong Tang

The state-of-the-art machine teaching techniques overestimate the ability of learners in grasping a complex concept. On one side, since a complicated concept always contains multiple ﬁne-grained concepts, students can only grasp parts of them during a practical teaching process. On the other side, because a single teaching sample contains unequal information in terms of various ﬁne-grained concepts, learners accept them at different levels. Thus, with more and more complicated dataset, it is challenging for us to rethink the machine teaching frameworks. In this work, we propose a new machine teaching framework called Attentive Machine Teaching (AMT). Specifically, we argue that a complicated concept always consists of multiple features, which we call ﬁne-grained concepts. We deﬁne attention to represent the learning level of a learner in studying a ﬁne-grained concept. Afterwards, we propose AMT, an adaptive teaching framework to construct the personalized optimal teaching dataset for learners. During each iteration, we estimate the workers’ ability with Graph Neural Network (GNN) and select the best sample using a pool-based searching approach. For corroborating our theoretical ﬁndings, we conduct extensive experiments with both synthetic datasets and real datasets. Our experimental results verify the effectiveness of AMT algorithms.

PDF Details