Junlan Feng

DisCo_Speech: Controllable Zero-Shot Speech Generation with A Disentangled Speech Codec ACL 2026 Thinking-Based Non-Thinking: Solving the Reward Hacking Problem in Training Hybrid Reasoning Models via Reinforcement Learning ACL 2026 Self-Correction Distillation for Structured Data Question Answering AAAI 2026 Thinking Alignment of Scenario-Oriented User Simulation ACL 2026 Cognitive Alpha Mining via LLM-Driven Code-Based Evolution ACL 2026 Soft Orthogonal Low-Rank Adaptation for Knowledge Sharing in Large Language Model Continual Learning ACL 2026 Entriever: Energy-based Retriever for Knowledge-Grounded Dialog Systems ACL 2025 MoE-LPR: Multilingual Extension of Large Language Models Through Mixture-of-Experts with Language Priors Routing AAAI 2025 From Superficial to Deep: Integrating External Knowledge for Follow-up Question Generation Using Knowledge Graph and LLM COLING 2025 Palette of Language Models: A Solver for Controlled Text Generation NAACL 2025 Self-attention-based Graph-of-Thought for Math Problem Solving ACL 2025 Investigating and Scaling up Code-Switching for Multilingual Language Model Pre-Training ACL 2025 Understanding LLMs’ Cross-Lingual Context Retrieval: How Good It Is And Where It Comes From EMNLP 2025 MultiPL-MoE: Multi-Programming-Lingual Extension of Large Language Models through Hybrid Mixture-of-Experts EMNLP 2025 LOIRE: LifelOng learning on Incremental data via pre-trained language model gRowth Efficiently ICLR 2025 Large Language Models Are Cross-Lingual Knowledge-Free Reasoners NAACL 2025 Getting More from Less: Large Language Models are Good Spontaneous Multilingual Learners EMNLP 2024 MFSN: Multi-perspective Fusion Search Network For Pre-training Knowledge in Speech Emotion Recognition INTERSPEECH 2024 LLM as a metric critic for low resource relation identification EMNLP 2024 On Calibration of Speech Classification Models: Insights from Energy-Based Model Investigations INTERSPEECH 2024 GenDistiller: Distilling Pre-trained Language Models based on an Autoregressive Generative Model INTERSPEECH 2024 Exploring Energy-Based Models for Out-of-Distribution Detection in Dialect Identification INTERSPEECH 2024 CEC: A Noisy Label Detection Method for Speaker Recognition INTERSPEECH 2024 Multi-Action Dialog Policy Learning from Logged User Feedback AAAI 2023 Log-FGAER: Logic-Guided Fine-Grained Address Entity Recognition from Multi-Turn Spoken Dialogue EMNLP 2023 Learning to Leverage High-Order Medical Knowledge Graph for Joint Entity and Relation Extraction ACL 2023 Beyond Layout Embedding: Layout Attention with Gaussian Biases for Structured Document Understanding EMNLP 2023 Dynamic Perceiver for Efficient Visual Recognition ICCV 2023 Cascaded Multi-task Adaptive Learning Based on Neural Architecture Search INTERSPEECH 2023 Knowledge-Retrieval Task-Oriented Dialog Systems with Semi-Supervision INTERSPEECH 2023 “Think Before You Speak”: Improving Multi-Action Dialog Policy by Planning Single-Action Dialogs IJCAI 2022 Generalized Intent Discovery: Learning from Open World Dialogue System COLING 2022 PSSAT: A Perturbed Semantic Structure Awareness Transferring Method for Perturbation-Robust Slot Filling COLING 2022 CMCC: A Comprehensive and Large-Scale Human-Human Dataset for Dialogue Systems EMNLP 2022 State-Aware Adversarial Training for Utterance-Level Dialogue Generation EMNLP 2022 Information Extraction and Human-Robot Dialogue towards Real-life Tasks A Baseline Study with the MobileCS Dataset EMNLP 2022 A Generative User Simulator with GPT-based Architecture and Goal State Tracking for Reinforced Multi-Domain Dialog Systems EMNLP 2022 Curriculum-Based Self-Training Makes Better Few-Shot Learners for Data-to-Text Generation IJCAI 2022 Meta Auxiliary Learning for Low-resource Spoken Language Understanding INTERSPEECH 2022 Learning to Check Contract Inconsistencies AAAI 2021 Counterfactual Matters: Intrinsic Probing For Dialogue State Tracking EMNLP 2021 Meta-Reinforced Multi-Domain State Generator for Dialogue Systems ACL 2020 A structure-enhanced graph convolutional network for sentiment analysis EMNLP 2020 A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learning EMNLP 2020 Improved Learning of Word Embeddings with Word Definitions and Semantic Injection INTERSPEECH 2020 Towards Low-Resource Semi-Supervised Dialogue Generation with Meta-Learning EMNLP 2020 Code-Switching Sentence Generation by Bert and Generative Adversarial Networks INTERSPEECH 2019 Robust Sentiment Detection on Twitter from Biased and Noisy Data COLING 2010 Effects of Word Confusion Networks on Voice Search EACL 2009