Shang-Wen Li

In Pursuit of Pixel Supervision for Visual Pre-training CVPR 2026 TV2TV: A Unified Framework for Interleaved Language and Video Generation CVPR 2026 Demystifying Synthetic Data in LLM Pre-training: A Systematic Study of Scaling Laws, Benefits, and Pitfalls EMNLP 2025 SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Models ICML 2025 Altogether: Image Captioning via Re-aligning Alt-text EMNLP 2024 Demystifying CLIP Data ICLR 2024 GSQA: An End-to-End Model for Generative Spoken Question Answering Interspeech 2024 MoDE: CLIP Data Experts via Clustering CVPR 2024 VoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wild ACL 2024 Expand, Rerank, and Retrieve: Query Reranking for Open-Domain Question Answering ACL 2023 Improving Textless Spoken Language Understanding with Discrete Units as Intermediate Target Interspeech 2023 Introducing Semantics into Speech Encoders ACL 2023 MAViL: Masked Audio-Video Learners NeurIPS 2023 ML-SUPERB: Multilingual Speech Universal PERformance Benchmark Interspeech 2023 Syllable Discovery and Cross-Lingual Generalization in a Visually Grounded, Self-Supervised Speech Model Interspeech 2023 An Exploration of Prompt Tuning on Generative Spoken Language Model for Speech Processing Tasks Interspeech 2022 Cooperative Self-training of Machine Reading Comprehension NAACL 2022 DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings NAACL 2022 DUAL: Discrete Spoken Unit Adaptive Learning for Textless Spoken Question Answering Interspeech 2022 Lifelong Pretraining: Continually Adapting Language Models to Emerging Corpora ACL 2022 Lifelong Pretraining: Continually Adapting Language Models to Emerging Corpora NAACL 2022 Listen, Adapt, Better WER: Source-free Single-utterance Test-time Adaptation for Automatic Speech Recognition Interspeech 2022 Meta Learning for Natural Language Processing: A Survey NAACL 2022 Self-supervised Representation Learning for Speech Processing NAACL 2022 SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities ACL 2022 Joint Retrieval-Extraction Training for Evidence-Aware Dialog Response Selection Interspeech 2021 Meta Learning and Its Applications to Natural Language Processing ACL 2021 Mitigating Biases in Toxic Language Detection through Invariant Rationalization ACL 2021 Pairwise Supervised Contrastive Learning of Sentence Representations EMNLP 2021 SUPERB: Speech Processing Universal PERformance Benchmark Interspeech 2021 Supporting Clustering with Contrastive Learning NAACL 2021 Zero-shot Generalization in Dialog State Tracking through Generative Question Answering EACL 2021 Knowledge Grounded Conversational Symptom Detection with Graph Memory Networks EMNLP 2020 Prototypical Q Networks for Automatic Conversational Diagnosis and Few-Shot New Disease Adaption Interspeech 2020 Style Attuned Pre-Training and Parameter Efficient Fine-Tuning for Spoken Language Understanding Interspeech 2020