two-stage training

ActAvatar: Temporally-Aware Precise Action Control for Talking Avatars CVPR 2026 QiMeng-CRUX: Narrowing the Gap Between Natural Language and Verilog via Core Refined Understanding eXpression AAAI 2026 Reward Modeling for Scientific Writing Evaluation ACL 2026 STAGE: Storyboard-Anchored Generation for Cinematic Multi-shot Narrative CVPR 2026 UniLS: End-to-End Audio-Driven Avatars for Unified Listening and Speaking CVPR 2026 Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question Answering CVPR 2025 Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts ICML 2025 D$^3$epth: Distilling Diffusion Models For Efficient Depth Estimation Through A Two-Stage Approach ACML 2025 Faithful Transcription: Leveraging Bible Recordings to Improve ASR for Endangered Languages IJCNLP 2025 Met2Net: A Decoupled Two-Stage Spatio-Temporal Forecasting Model for Complex Meteorological Systems ICCV 2025 SelfRACG: Enabling LLMs to Self-Express and Retrieve for Code Generation EMNLP 2025 Task-Gated Multi-Expert Collaboration Network for Degraded Multi-Modal Image Fusion ICML 2025 VocalNet: Speech LLMs with Multi-Token Prediction for Faster and High-Quality Generation EMNLP 2025 Sing it, Narrate it: Quality Musical Lyrics Translation EMNLP 2024 SuperSVG: Superpixel-based Scalable Vector Graphics Synthesis CVPR 2024 Large-Scale and Multi-Perspective Opinion Summarization with Diverse Review Subsets EMNLP 2023 Complicate Then Simplify: A Novel Way to Explore Pre-trained Models for Text Classification COLING 2022 From Good to Best: Two-Stage Training for Cross-Lingual Machine Reading Comprehension AAAI 2022 Transn’s Submissions to the WMT22 Translation Suggestion Task EMNLP 2022 UniDS: A Unified Dialogue System for Chit-Chat and Task-oriented Dialogues ACL 2022 Just Train Twice: Improving Group Robustness without Training Group Information ICML 2021 X-net: A Joint Scale Down and Scale Up Method for Voice Call Interspeech 2021 Enhancing Neural Models with Vulnerability via Adversarial Attack COLING 2020