News

Publication announcements from the five AAIG laboratories.

2026

Jun 1, 2026

SAIL paper accepted to Interspeech 2026

A SAIL paper was accepted to Interspeech 2026 as an oral presentation.

Interspeech 2026

May 1, 2026

SAIL paper accepted to ICML 2026

SAIL announced the acceptance of a paper to ICML 2026.

ICML 2026

Apr 1, 2026

SAIL paper accepted to Findings of ACL 2026

SAIL announced the acceptance of a paper to Findings of ACL 2026.

Findings of ACL 2026

Jan 1, 2026

Colla-Q: Toward Collaborative Experts in MoE Quantization via Minimax Precision Balancing

EMNLP 2026 publication from MMAI Lab.

EMNLP 2026

Jan 1, 2026

Layer-wise Curriculum Learning for Efficient LLM Compression

EMNLP 2026 publication from MMAI Lab.

EMNLP 2026

Jan 1, 2026

Re-calibrated Contrastive Loss for Transformation-Aware Prompt Conditioning in Vision-Language Models

BMVC 2026 publication from MMAI Lab.

BMVC 2026

Jan 1, 2026

Train Overcomplete, Deploy Compact: Scaling Recovery Capacity for Structured LLM Pruning

EMNLP 2026 publication from MMAI Lab.

EMNLP 2026

Jan 1, 2026

Disentangling Spurious Correlations in Vision-Language-Action Models via Predicting Domain-Invariant Latent Lookahead

Predicting domain-invariant latent lookahead to separate spurious correlations in vision-language-action models.

CoRL 2026

Jan 1, 2026

MicroVLA: Edge-Deployable Vision Language Action at 10M Parameters

An edge-deployable vision-language-action model for robot learning.

RSS Workshop 2026

Jan 1, 2026

Can Embodied Agents Remember What You Said? Evaluating Dialogue-Grounded Embodied Memory in 3D Environments

CVPR Workshop 2026 publication from HEI Lab.

CVPR Workshop 2026

Jan 1, 2026

Learning Sample-wise Rank-Aware Interpolation Weights for Composed Visual Data Retrieval

Rank-aware interpolation for composed visual data retrieval.

ECCV 2026

Jan 1, 2026

TextME: Bridging Unseen Modalities Through Text Descriptions

Text-guided representations that bridge unseen modalities.

ICML 2026

Jan 1, 2026

AI-Driven Quantitative Review of Mobility–Stability Trade-off in Oxide Semiconductors

Nano Convergence 2026 publication from iKnow Lab.

Nano Convergence 2026

Jan 1, 2026

ASSAY: Reconciling Stability and Validity in Reference-Free Scientific LLM Judges

Findings of EMNLP 2026 publication from iKnow Lab.

Findings of EMNLP 2026

Jan 1, 2026

CASCADE: Constraint-Aware Scaffolded Decomposition for Logical Anomaly Detection

ICDM 2026 publication from iKnow Lab.

ICDM 2026

Jan 1, 2026

Closed-Loop Solid-State Synthesis Planning for Materials Discovery With Large Language Models

Advanced Materials 2026 publication from iKnow Lab.

Advanced Materials 2026

Jan 1, 2026

Collaborative adaptation without forgetting in source-free domain adaptation

Pattern Recognition 2026 publication from iKnow Lab.

Pattern Recognition 2026

Jan 1, 2026

Filter by Quality, Stop by Difficulty: Confidence-Aware Self-Consistency with Adaptive Early Stopping

Findings of EMNLP 2026 publication from iKnow Lab.

Findings of EMNLP 2026

Jan 1, 2026

Dual-FreqDAE: Frequency-aware dual-branch transformer autoencoder for ECG denoising in mixed noise conditions

BSPC 2026 publication from LAMDA Lab.

BSPC 2026

Jan 1, 2026

NeuroNetFusion: enhanced EEG abnormality classification via multi-network TF-IDF feature selection

Sci Rep 2026 publication from LAMDA Lab.

Sci Rep 2026

Jan 1, 2026

Semi-Supervised Fatty Liver Classification Using Attention-Based Graph Neural Network Models

JKMS 2026 publication from LAMDA Lab.

JKMS 2026

Jan 1, 2026

AccentDrift: Real-time Streaming Accent Conversion via Sparse Speech Tokenization

Interspeech 2026 publication from SAIL.

Interspeech 2026

Jan 1, 2026

Hierarchical Representation Alignment Learning of Diffusion Transformers for Neural Audio Codec

ACL 2026 publication from SAIL.

ACL 2026

Jan 1, 2026

ReGen: Hierarchical Multi-Prompt Representation Generation for Efficient Waveform Diffusion Models

ICML 2026 publication from SAIL.

ICML 2026

2025

Jun 1, 2025

Do Your Best and Get Enough Rest for Continual Learning

CVPR 2025 publication update from MMAI Lab.

CVPR 2025

Jun 1, 2025

CLIP-RT: Learning Language-Conditioned Robotic Policies from Natural Language Supervision

Language-supervised robotic policies that make collecting robot demonstrations more accessible.

RSS 2025

Jan 1, 2025

Channel Propagation Networks for Refreshable Vision Transformer

WACV 2025 publication update from MMAI Lab.

WACV 2025

Jan 1, 2025

Enriching Local Patterns with Multi-Token Attention for Broad-Sight Neural Networks

WACV 2025 publication update from MMAI Lab.

WACV 2025

Jan 1, 2025

Continual Vision-and-Language Navigation

A continual learning formulation for vision-and-language navigation agents adapting to new scene domains.

BMVC 2025

Jan 1, 2025

Socratic Planner: Self-QA-Based Zero-Shot Planning for Embodied Instruction Following

ICRA 2025 publication from HEI Lab.

ICRA 2025

Jan 1, 2025

FLEX: Expert-level False-Less EXecution Metric for Reliable Text-to-SQL Benchmark

An execution metric for assessing reliable Text-to-SQL systems.

NAACL 2025

Jan 1, 2025

Data Augmentation for Improving Convergence Speed in Federated Sequential Recommendation System

IEEE Access 2025 publication from iKnow Lab.

IEEE Access 2025

Jan 1, 2025

DCC: Differentiable Cardinality Constraints for Partial Index Tracking

AAAI 2025 publication from iKnow Lab.

AAAI 2025

Jan 1, 2025

Exploring the Side-information Fusion for Sequential Recommendation

IEEE Access 2025 publication from iKnow Lab.

IEEE Access 2025

Jan 1, 2025

Machine learning-based prediction of aerodynamic performance in arformoterol-lactose dry powder inhaler formulations using surface roughness features

Int J Pharm 2025 publication from iKnow Lab.

Int J Pharm 2025

Jan 1, 2025

Rethinking the Training Paradigm of Discrete Token-Based Multimodal LLMs: An Analysis of Text-Centric Bias

CIKM 2025 publication from iKnow Lab.

CIKM 2025

Jan 1, 2025

Towards Fully-Automated Materials Discovery via Large-Scale Synthesis Dataset and Expert-Level LLM-as-a-Judge

CIKM 2025 publication from iKnow Lab.

CIKM 2025

Jan 1, 2025

Evaluation of Multi-Agent LLMs in Multidisciplinary Team Decision-Making for Challenging Cancer Cases

MLHC 2025 publication from LAMDA Lab.

MLHC 2025

Jan 1, 2025

CoreaSpeech: Korean Speech Corpus via JAMO-based Coreset Selection for Efficient and Robust Korean Speech Generation

NeurIPS 2025 publication from SAIL.

NeurIPS 2025

Jan 1, 2025

DurFlex-EVC: Duration-Flexible Emotional Voice Conversion with Parallel Generation

IEEE TAC 2025 publication from SAIL.

IEEE TAC 2025

Jan 1, 2025

HiddenSinger: High-Quality Singing Voice Synthesis via Neural Audio Codec and Latent Diffusion Models

Neural Networks 2025 publication from SAIL.

Neural Networks 2025

Jan 1, 2025

HierSpeech++: Bridging the Gap between Semantic and Acoustic Representation by Hierarchical Variational Inference for Zero-shot Speech Synthesis

IEEE TNNLS 2025 publication from SAIL.

IEEE TNNLS 2025

Jan 1, 2025

Parameter-Efficient Fine-Tuning for Low-Resource Text-to-Speech via Cross-Lingual Continual Learning

Interspeech 2025 publication from SAIL.

Interspeech 2025

Jan 1, 2025

PeriodWave: Multi-Period Flow Matching for High-Fidelity Waveform Generation

ICLR 2025 publication from SAIL.

ICLR 2025

Jan 1, 2025

Personalized and Controllable Voice Style Transfer with Speech Diffusion Transformer

IEEE TASLP 2025 publication from SAIL.

IEEE TASLP 2025

Jan 1, 2025

StreamFlow: Streaming Audio Generation from Discrete Tokens via Streaming Flow Matching

NeurIPS 2025 publication from SAIL.

NeurIPS 2025

2024

Dec 29, 2024

Style-KD : Class-Imbalanced Medical Image Classification via Style Knowledge Distillation

BSPC 2024 publication update from MMAI Lab.

BSPC 2024

Dec 1, 2024

Generative Self-Supervised Learning for Medical Image Classification

ACCV 2024 publication update from MMAI Lab.

ACCV 2024

Dec 1, 2024

Neural Substitution for Branch-level Network Re-parameterization

ACCV 2024 publication update from MMAI Lab.

ACCV 2024

Nov 25, 2024

Unsupervised Hashing Network with Hyper Quantization Tree

BMVC 2024 publication update from MMAI Lab.

BMVC 2024

Oct 4, 2024

Spatial Bias for Attention-free Non-local Neural Networks

ESWA 2024 publication update from MMAI Lab.

ESWA 2024

Apr 21, 2024

Attentional Decoder Networks for Chest X-ray Image Recognition on High-resolution Features

CMPB 2024 publication update from MMAI Lab.

CMPB 2024

Apr 16, 2024

Analyzing to Discover Origins of CNNs and ViT Architectures in Medical Images

Sci Rep 2024 publication update from MMAI Lab.

Sci Rep 2024

Jan 1, 2024

Towards long-tailed, multi-label disease classification from chest X-ray: Overview of the CXR-LT challenge

MedIA 2024 publication update from MMAI Lab.

MedIA 2024

Jan 1, 2024

Fine-Grained Self-Supervised Learning with Jigsaw puzzles for medical image classification

CBM 2024 publication update from MMAI Lab.

CBM 2024

Jan 1, 2024

PGA: Personalizing Grasping Agents with Single Human-Robot Interaction

IROS 2024 publication from HEI Lab.

IROS 2024

Jan 1, 2024

PROGrasp: Pragmatic Human-Robot Communication for Object Grasping

ICRA 2024 publication from HEI Lab.

ICRA 2024

Jan 1, 2024

Can Large Language Models be Good Emotional Supporter? Mitigating Preference Bias on Emotional Support Conversation

ACL 2024 publication from iKnow Lab.

ACL 2024

Jan 1, 2024

Cross-Modal Dynamic Transfer Learning for Multimodal Emotion Recognition

IEEE Access 2024 publication from iKnow Lab.

IEEE Access 2024

Jan 1, 2024

Multi-intent-aware Session-based Recommendation

SIGIR 2024 publication from iKnow Lab.

SIGIR 2024

Jan 1, 2024

OmniStitch: Depth-Aware Stitching Framework for Omnidirectional Vision with Multiple Cameras

ACM MM 2024 publication from iKnow Lab.

ACM MM 2024

Jan 1, 2024

Regularization Using Noise Samples Identified by the Feature Norm for Face Recognition

IEEE Access 2024 publication from LAMDA Lab.

IEEE Access 2024

Jan 1, 2024

Text-free diffusion inpainting using reference images for enhanced visual fidelity

Pattern Recognition 2024 publication from LAMDA Lab.

Pattern Recognition 2024

Jan 1, 2024

Audio Super-resolution with Robust Speech Representation Learning of Masked Autoencoder

IEEE TASLP 2024 publication from SAIL.

IEEE TASLP 2024

Jan 1, 2024

Cross-lingual Text-to-Speech via Hierarchical Style Transfer

ICASSP Workshop 2024 publication from SAIL.

ICASSP Workshop 2024

Jan 1, 2024

DDDM-VC: Decoupled Denoising Diffusion Models with Disentangled Representation and Prior Mixup for Verified Robust Voice Conversion

AAAI 2024 publication from SAIL.

AAAI 2024

Jan 1, 2024

DiffProsody: Diffusion-based Latent Prosody Generation for Expressive Speech Synthesis with Prosody Conditional Adversarial Training

IEEE TASLP 2024 publication from SAIL.

IEEE TASLP 2024

Jan 1, 2024

MIDI-Voice: Expressive Zero-shot Singing Voice Synthesis via MIDI-driven Priors

ICASSP 2024 publication from SAIL.

ICASSP 2024

Jan 1, 2024

TranSentence: Speech-to-Speech Translation via Language-agnostic Sentence-level Speech Encoding without Language-parallel Data

ICASSP 2024 publication from SAIL.

ICASSP 2024

2023

Dec 1, 2023

Deep Learning Using Computed Tomography to Identify High-Risk Patients for Acute Small Bowel Obstruction: Development and Validation of a Prediction Model: A Retrospective Cohort Study

IJS 2023 publication update from MMAI Lab.

IJS 2023

Aug 10, 2023

Robust Asymmetric Loss for Multi-Label Long-Tailed Learning

ICCVW 2023 publication update from MMAI Lab.

ICCVW 2023

Jan 1, 2023

GVCCI: Lifelong Learning of Visual Grounding for Language-Guided Robotic Manipulation

IROS 2023 publication from HEI Lab.

IROS 2023

Jan 1, 2023

The Dialog Must Go On: Improving Visual Dialog via Generative Self-Training

CVPR 2023 publication from HEI Lab.

CVPR 2023

Jan 1, 2023

GTA: Gated Toxicity Avoidance for LM Performance Preservation

Findings of EMNLP 2023 publication from iKnow Lab.

Findings of EMNLP 2023

Jan 1, 2023

Outlier-aware Cross-Market Product Recommendation

BigComp 2023 publication from iKnow Lab.

BigComp 2023

Jan 1, 2023

Diff-HierVC: Diffusion-based Hierarchical Voice Conversion with Robust Pitch Generation and Masked Prior for Zero-shot Speaker Adaptation

Interspeech 2023 publication from SAIL.

Interspeech 2023

Jan 1, 2023

HierVST: Hierarchical Adaptive Zero-shot Voice Style Transfer

Interspeech 2023 publication from SAIL.

Interspeech 2023

Jan 1, 2023

PauseSpeech: Natural Speech Synthesis via Pre-trained Language Model and Pause-based Prosody Modeling

ACPR 2023 publication from SAIL.

ACPR 2023

2022

Jan 1, 2022

FPAdaMetric: False-positive-aware Adaptive Metric Learning for Session-based Recommendation

AAAI 2022 publication from iKnow Lab.

AAAI 2022

Jan 1, 2022

Duration Controllable Voice Conversion via Phoneme-based Information Bottleneck

IEEE TASLP 2022 publication from SAIL.

IEEE TASLP 2022

Jan 1, 2022

EmoQ-TTS: Emotion Intensity Quantization for Fine-Grained Controllable Emotional Text-to-Speech

ICASSP 2022 publication from SAIL.

ICASSP 2022

Jan 1, 2022

Fre-GAN 2: Fast and Efficient Frequency-consistent Audio Synthesis

ICASSP 2022 publication from SAIL.

ICASSP 2022

Jan 1, 2022

HierSpeech: Bridging the Gap between Text and Speech by Hierarchical Variational Inference using Self-supervised Representations for Speech Synthesis

NeurIPS 2022 publication from SAIL.

NeurIPS 2022

Jan 1, 2022

PVAE-TTS: Progressively Style Adaptive Text-to-Speech via Progressive Variaional Autoencoder

ICASSP 2022 publication from SAIL.

ICASSP 2022

Jan 1, 2022

StyleVC: Non-Parallel Voice Conversion with Adversarial Style Generalization

ICPR 2022 publication from SAIL.

ICPR 2022

2021

Jan 1, 2021

Dual Aggregated Feature Pyramid Network for Multi Label Classification

Pattern Recognition 2021 publication from MMAI Lab.

Pattern Recognition 2021

Jan 1, 2021

Unsupervised Feature Learning for Self-Tuning Neural Networks

Neural Networks 2021 publication from MMAI Lab.

Neural Networks 2021

Jan 1, 2021

Attend What You Need: Motion-Appearance Synergistic Networks for Video Question Answering

ACL 2021 publication from HEI Lab.

ACL 2021

Jan 1, 2021

Reasoning Visual Dialog with Sparse Graph Learning and Knowledge Transfer

EMNLP 2021 publication from HEI Lab.

EMNLP 2021

Jan 1, 2021

One-Step Pixel-Level Perturbation-Based Saliency Detector

BMVC 2021 publication from iKnow Lab.

BMVC 2021

Jan 1, 2021

Self-Supervised Multimodal Opinion Summarization

ACL 2021 publication from iKnow Lab.

ACL 2021

Jan 1, 2021

Fre-GAN: Adversarial Frequency-consistent Audio Synthesis

Interspeech 2021 publication from SAIL.

Interspeech 2021

Jan 1, 2021

GC-TTS: Few-shot Speaker Adaptation with Geometric Constraints

SMC 2021 publication from SAIL.

SMC 2021

Jan 1, 2021

Multi-SpectroGAN: High-Diversity and High-Fidelity Spectrogram Generation with Adversarial Style Combination for Speech Synthesis

AAAI 2021 publication from SAIL.

AAAI 2021

Jan 1, 2021

Reinforce-Aligner: Reinforcement Alignment Search for Robust End-to-End Text-to-Speech

Interspeech 2021 publication from SAIL.

Interspeech 2021

Jan 1, 2021

VoiceMixer: Adversarial Voice Style Mixup

NeurIPS 2021 publication from SAIL.

NeurIPS 2021

2020

Jan 1, 2020

Deep Learning Algorithms for Detecting and Visualising Intussusception on Plain Abdominal Radiography in Children: A Retrospective Multicenter Study

Sci Rep 2020 publication from MMAI Lab.

Sci Rep 2020

Jan 1, 2020

Label Propagation Adaptive Resonance Theory for Semi-Supervised Continuous Learning

ICASSP 2020 publication from HEI Lab.

ICASSP 2020

Jan 1, 2020

CITIES: Contextual Inference of Tail-item Embeddings for Sequential Recommendation

ICDM 2020 publication from iKnow Lab.

ICDM 2020

Jan 1, 2020

SQuAD2-CR: Semi-supervised Annotation for Cause and Rationales for Unanswerability in SQuAD 2.0

LREC 2020 publication from iKnow Lab.

LREC 2020

Jan 1, 2020

Audio Dequantization for High Fidelity Audio Generation in Flow-based Neural Vocoder

Interspeech 2020 publication from SAIL.

Interspeech 2020

2019

Jan 1, 2019

Dual Attention Networks for Visual Reference Resolution in Visual Dialog

EMNLP 2019 publication from HEI Lab.

EMNLP 2019

Jan 1, 2019

MeLU: Meta-Learned User Preference Estimator for Cold-start Recommendation

KDD 2019 publication from iKnow Lab.

KDD 2019

Jan 1, 2019

Learning Machines Can Curl - Adaptive deep reinforcement learning enables the robot Curly to win against human players in an icy world

NeurIPS 2019 publication from SAIL.

NeurIPS 2019

2018

Jan 1, 2018

Machine-Translated Knowledge Transfer for Commonsense Causal Reasoning

AAAI 2018 publication from iKnow Lab.

AAAI 2018

Jan 1, 2018

PREFER: PREdiction Model for Financial Entity Relation

FEIII Workshop 2018 publication from iKnow Lab.

FEIII Workshop 2018

Jan 1, 2018

Visual Choice of Plausible Alternatives: An Evaluation of Image-based Commonsense Causal Reasoning

LREC 2018 publication from iKnow Lab.

LREC 2018

2017

Jan 1, 2017

Gradable Adjective Embedding for Commonsense Knowledge

PAKDD 2017 publication from iKnow Lab.

PAKDD 2017

Jan 1, 2017

Multimodal KB Harvesting for Emerging Spatial Entities

TKDE 2017 publication from iKnow Lab.

TKDE 2017

Jan 1, 2017

Understanding Relations using Concepts and Semantics

FEIII Workshop 2017 publication from iKnow Lab.

FEIII Workshop 2017

2016

Jan 1, 2016

ECO: Entity-level Captioning in Context

ASONAM 2016 publication from iKnow Lab.

ASONAM 2016

Jan 1, 2016

Event Grounding from Multimodal Social Network Fusion

ICDM 2016 publication from iKnow Lab.

ICDM 2016

2014

Jan 1, 2014

Skill Ontology-based Model for Quality Assurance in Crowdsourcing

DASFAA Workshop 2014 publication from iKnow Lab.

DASFAA Workshop 2014

2013

Jan 1, 2013

Hybrid Entity Clustering using crowds and data

VLDB 2013 publication from iKnow Lab.

VLDB 2013

Jan 1, 2013

Toward Scalable Indexing for Top-k Queries

TKDE 2013 publication from iKnow Lab.

TKDE 2013

2012

Jan 1, 2012

Efficient Dual-Resolution Layer Indexing for Top-k Queries

ICDE 2012 publication from iKnow Lab.

ICDE 2012