2025
Understanding the RoPE Extensions of Long-Context LLMs: An Attention Perspective.
Proceedings of the 31st International Conference on Computational Linguistics, 2025
ZigZagKV: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty.
Proceedings of the 31st International Conference on Computational Linguistics, 2025
2024
On Elastic Language Models.
ACM Trans. Inf. Syst., November, 2024
NaturalSpeech: End-to-End Text-to-Speech Synthesis With Human-Level Quality.
,
,
,
,
,
,
,
,
,
,
,
,
,
IEEE Trans. Pattern Anal. Mach. Intell., June, 2024
Intrusion detection for Industrial Internet of Things based on deep learning.
Neurocomputing, January, 2024
SDMuse: Stochastic Differential Music Editing and Generation via Hybrid Representation.
IEEE Trans. Multim., 2024
RefXVC: Cross-Lingual Voice Conversion With Enhanced Reference Leveraging.
IEEE ACM Trans. Audio Speech Lang. Process., 2024
Overview of the Tenth Dialog System Technology Challenge: DSTC10.
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
IEEE ACM Trans. Audio Speech Lang. Process., 2024
VoiceBench: Benchmarking LLM-Based Voice Assistants.
CoRR, 2024
MoDification: Mixture of Depths Made Easy.
,
,
,
,
,
,
,
,
,
,
CoRR, 2024
MimicTalk: Mimicking a personalized and expressive 3D talking face in minutes.
,
,
,
,
,
,
,
,
,
,
,
,
CoRR, 2024
Aligning Language Models Using Follow-up Likelihood as Reward Signal.
CoRR, 2024
LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via Hybrid Architecture.
CoRR, 2024
MulliVC: Multi-lingual Voice Conversion With Cycle Consistency.
CoRR, 2024
Beyond the Speculative Game: A Survey of Speculative Execution in Large Language Models.
CoRR, 2024
MimicTalk: Mimicking a personalized and expressive 3D talking face in minutes.
,
,
,
,
,
,
,
,
,
,
,
,
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024
Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis.
,
,
,
,
,
,
,
,
,
,
,
,
,
Proceedings of the Twelfth International Conference on Learning Representations, 2024
Mega-TTS 2: Boosting Prompting Mechanisms for Zero-Shot Speech Synthesis.
,
,
,
,
,
,
,
,
,
,
,
,
Proceedings of the Twelfth International Conference on Learning Representations, 2024
Unlocking the Potential of Model Merging for Low-Resource Languages.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024
DynaThink: Fast or Slow? A Dynamic Decision-Making Framework for Large Language Models.
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024
Beyond Single-Audio: Advancing Multi-Audio Processing in Audio Large Language Models.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024
TS-Align: A Teacher-Student Collaborative Framework for Scalable Iterative Finetuning of Large Language Models.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024
Eliminating Contextual Bias in Aspect-Based Sentiment Analysis.
Proceedings of the Advances in Information Retrieval, 2024
Minimal Distillation Schedule for Extreme Language Model Compression.
Proceedings of the Findings of the Association for Computational Linguistics: EACL 2024, 2024
Task-agnostic Distillation of Encoder-Decoder Language Models.
Proceedings of the 2024 Joint International Conference on Computational Linguistics, 2024
CrossTune: Black-Box Few-Shot Classification with Label Enhancement.
Proceedings of the 2024 Joint International Conference on Computational Linguistics, 2024
How Speculative Can Speculative Decoding Be?
Proceedings of the 2024 Joint International Conference on Computational Linguistics, 2024
Unveiling the Achilles' Heel of NLG Evaluators: A Unified Adversarial Framework Driven by Large Language Models.
Proceedings of the Findings of the Association for Computational Linguistics, 2024
A Comprehensive Analysis of the Effectiveness of Large Language Models as Automatic Dialogue Evaluators.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024
2023
Stance-level Sarcasm Detection with BERT and Stance-centered Graph Attention Networks.
ACM Trans. Internet Techn., 2023
PoE: A Panel of Experts for Generalized Automatic Dialogue Assessment.
IEEE ACM Trans. Audio Speech Lang. Process., 2023
Towards the Law of Capacity Gap in Distilling Language Models.
CoRR, 2023
Sparse Contrastive Learning of Sentence Embeddings.
CoRR, 2023
C2G2: Controllable Co-speech Gesture Generation with Latent Diffusion Model.
CoRR, 2023
Mega-TTS 2: Zero-Shot Text-to-Speech with Arbitrary Length Speech Prompts.
,
,
,
,
,
,
,
,
,
,
CoRR, 2023
Overview of Robust and Multilingual Automatic Evaluation Metrics for Open-Domain Dialogue Systems at DSTC 11 Track 4.
CoRR, 2023
Mega-TTS: Zero-Shot Text-to-Speech at Scale with Intrinsic Inductive Bias.
,
,
,
,
,
,
,
,
,
,
,
CoRR, 2023
Ada-TTA: Towards Adaptive High-Quality Text-to-Talking Avatar Synthesis.
CoRR, 2023
Make-An-Audio 2: Temporal-Enhanced Text-to-Audio Generation.
CoRR, 2023
Enhancing Black-Box Few-Shot Text Classification with Prompt-Based Data Augmentation.
CoRR, 2023
Task-agnostic Distillation of Encoder-Decoder Language Models.
CoRR, 2023
SongDriver2: Real-time Emotion-based Music Arrangement with Soft Transition.
CoRR, 2023
Phoenix: Democratizing ChatGPT across Languages.
,
,
,
,
,
,
,
,
,
,
,
,
,
CoRR, 2023
Modular Retrieval for Generalization and Interpretation.
CoRR, 2023
Bag of Tricks for Unsupervised Text-to-Speech.
Proceedings of the Eleventh International Conference on Learning Representations, 2023
LeanSpeech: The Microsoft Lightweight Speech Synthesis System for Limmits Challenge 2023.
Proceedings of the IEEE International Conference on Acoustics, 2023
xDial-Eval: A Multilingual Open-Domain Dialogue Evaluation Benchmark.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2023, 2023
Lifting the Curse of Capacity Gap in Distilling Language Models.
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023
VideoDubber: Machine Translation with Speech-Aware Length Control for Video Dubbing.
Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023
2022
A Focused Study on Sequence Length for Dialogue Summarization.
CoRR, 2022
AutoDisc: Automatic Distillation Schedule for Large Language Model Compression.
CoRR, 2022
Making Pre-trained Language Models Good Long-tailed Learners.
CoRR, 2022
Report from the NSF Future Directions Workshop on Automatic Evaluation of Dialog: Research Directions and Challenges.
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
CoRR, 2022
S3T: Self-Supervised Pre-training with Swin Transformer for Music Classification.
CoRR, 2022
Adaptable Text Matching via Meta-Weight Regulator.
Proceedings of the SIGIR '22: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, Madrid, Spain, July 11, 2022
Current Problems and Solutions of Industrial Control Network Intrusion Detection: A Brief Survey.
Proceedings of the IEEE International Conference on Real-time Computing and Robotics, 2022
Doge Tickets: Uncovering Domain-General Language Models by Playing Lottery Tickets.
Proceedings of the Natural Language Processing and Chinese Computing, 2022
Aspect-Specific Context Modeling for Aspect-Based Sentiment Analysis.
Proceedings of the Natural Language Processing and Chinese Computing, 2022
Towards Effective Multi-Modal Interchanges in Zero-Resource Sounding Object Localization.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022
ReLyMe: Improving Lyric-to-Melody Generation by Incorporating Lyric-Melody Relationships.
Proceedings of the MM '22: The 30th ACM International Conference on Multimedia, Lisboa, Portugal, October 10, 2022
SongDriver: Real-time Music Accompaniment Generation without Logical Latency nor Exposure Bias.
,
,
,
,
,
,
,
,
,
,
Proceedings of the MM '22: The 30th ACM International Conference on Multimedia, Lisboa, Portugal, October 10, 2022
PDAugment: Data Augmentation by Pitch and Duration Adjustments for Automatic Lyrics Transcription.
Proceedings of the 23rd International Society for Music Information Retrieval Conference, 2022
S3T: Self-Supervised Pre-Training with Swin Transformer For Music Classification.
Proceedings of the IEEE International Conference on Acoustics, 2022
Making Pretrained Language Models Good Long-tailed Learners.
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022
FineD-Eval: Fine-grained Automatic Dialogue-Level Evaluation.
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022
Sparse Teachers Can Be Dense with Knowledge.
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022
Analyzing and Evaluating Faithfulness in Dialogue Summarization.
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022
XPrompt: Exploring the Extreme of Prompt Tuning.
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022
TeleMelody: Lyric-to-Melody Generation with a Template-Based Two-Stage Method.
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022
Structural Bias for Aspect Sentiment Triplet Extraction.
Proceedings of the 29th International Conference on Computational Linguistics, 2022
Automatic Song Translation for Tonal Languages.
Proceedings of the Findings of the Association for Computational Linguistics: ACL 2022, 2022
MDD-Eval: Self-Training on Augmented Data for Multi-Domain Dialogue Evaluation.
Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022
2021
D-Score: Holistic Dialogue Evaluation Without Reference.
IEEE ACM Trans. Audio Speech Lang. Process., 2021
Automatic Evaluation and Moderation of Open-domain Dialogue Systems.
CoRR, 2021
A Simple Baseline for Cross-Domain Few-Shot Text Classification.
Proceedings of the Natural Language Processing and Chinese Computing, 2021
Investigating the Impact of Pre-trained Language Models on Dialog Evaluation.
Proceedings of the Conversational AI for Natural Human-Centric Interaction, 2021
Denoispeech: Denoising Text to Speech with Frame-Level Noise Modeling.
Proceedings of the IEEE International Conference on Acoustics, 2021
Revisiting Self-training for Few-shot Learning of Language Model.
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021
DynaEval: Unifying Turn and Dialogue Level Evaluation.
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, 2021
Exploiting Position Bias for Robust Aspect Sentiment Classification.
Proceedings of the Findings of the Association for Computational Linguistics: ACL/IJCNLP 2021, 2021
UWSpeech: Speech to Speech Translation for Unwritten Languages.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021
2020
End-to-end Emotion-Cause Pair Extraction via Learning to Link.
CoRR, 2020
FastLR: Non-Autoregressive Lipreading Model with Integrate-and-Fire.
Proceedings of the MM '20: The 28th ACM International Conference on Multimedia, 2020
Deep AM-FM: Toolkit for Automatic Dialogue Evaluation.
Proceedings of the Conversational Dialogue Systems for the Next Decade, 2020
Task-Level Curriculum Learning for Non-Autoregressive Neural Machine Translation.
Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, 2020
A Multi-task Learning Framework for Opinion Triplet Extraction.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2020, 2020
SimulSpeech: End-to-End Simultaneous Speech to Text Translation.
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020
2019
Syntax-Aware Aspect-Level Sentiment Classification with Proximity-Weighted Convolution Network.
Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, 2019
Discriminative and Correlative Partial Multi-Label Learning.
Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, 2019
Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks.
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, 2019