Jason Li

11 papers · 2019–2026 · 5 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

+4 more ↓

🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (25) 🏃 Academic Marathon · Sprint 💎 Century Club · Bronze

🗃️ Keyword Collector (50) ❓ The Questioner ⚡ Prolific Year · Productive 🌈 Renaissance Researcher (5)

Venues

Interspeech (5) AAAI (3) CVPR (1) EMNLP (1) NAACL (1)

Top co-authors

Boris Ginsburg (4) Edresson Casanova (4) Subhankar Ghosh (4) Paarth Neekhara (4) Shehzeen Hussain (3) Xuesong Yang (3) Ryan Langman (2) Nan Duan (1) Lauren Yraola (1) Junshi Huang (1)

Research topics

Artificial Intelligence (7) Core AI (7) Speech & Audio (6) Deep Learning (4) Machine Learning (3) Architectures (3) Synthesis (3) Processing (2) Computer Vision (1) Natural Language Processing (1) Reinforcement Learning (1) Analysis (1) Applications (1) Core Methods (1) Learning Types (1)

Keywords

large language model (3) speech synthesis (2) speech language model (2) autoregressive model (2) convolutional neural network (1) automatic speech recognition (1) human pose estimation (1) multi-objective optimization (1) video understanding (1) acoustic model (1) classifier-free guidance (1) language model (1) vision-language model (1) multimodal large language model (1) hybrid action space (1) connectionist temporal classification (1) audio codec (1) reasoning ability (1) multimodal model (1) prompt engineering (1)

Papers

Advancing Safe Mechanical Ventilation Using Offline RL with Hybrid Actions and Clinically Aligned Rewards AAAI 2026 Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation CVPR 2026 UM-Text: A Unified Multimodal Model for Image Understanding and Visual Text Editing AAAI 2026 Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model Interspeech 2025 Error Reflection Prompting: Can Large Language Models Successfully Understand Errors? NAACL 2025 HiFiTTS-2: A Large-Scale High Bandwidth Speech Dataset Interspeech 2025 Koel-TTS: Enhancing LLM based Speech Generation with Preference Alignment and Classifier Free Guidance EMNLP 2025 NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference Interspeech 2025 Improving Robustness of LLM-based Speech Synthesis by Learning Monotonic Alignment Interspeech 2024 Segment-Then-Rank: Non-Factoid Question Answering on Instructional Videos AAAI 2020 Jasper: An End-to-End Convolutional Neural Acoustic Model Interspeech 2019