Skip to content
conftrace_

Guangzhi Sun

21 papers · 2022–2026 · 6 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 ↓
+7 more ↓ πŸ—ΊοΈ Taxonomy Completionist (45) πŸŒ‰ Interdisciplinary Bridge Β· Silver 🌍 Conference Polyglot Β· Silver 🐣 Hot Topic Early Bird 🀝 Dynamic Duo (14)
🀝 Dynamic Duo (14) πŸ—ƒοΈ Keyword Collector (110) πŸ”₯ Unstoppable Β· Bronze ❓ The Questioner (3) ⚑ Prolific Year Β· Productive 🌈 Renaissance Researcher (5) πŸ’Ž Century Club Β· Bronze

Venues

Interspeech (7) ACL (5) ICML (4) EMNLP (2) ICLR (2) NAACL (1)

Top co-authors

Chao Zhang (14) Zejun Ma (6) Changli Tang (6) Wei Li (6) Phil Woodland (6) Wenyi Yu (4) Xiao Zhan (3) Potsawee Manakul (3) Yudong Yang (3) Yixuan Li (3)

Research topics

Artificial Intelligence (13) Core AI (13) Deep Learning (9) Machine Learning (9) Speech & Audio (9) Natural Language Processing (8) Recognition (6) Application Areas (5) Resources & Methods (5) Applications (3) Core Methods (3) Learning Types (3) Techniques (3) Analysis (2) Architectures (2)

Keywords

large language model (6) speech recognition (4) low-rank adaptation (3) audio-language model (3) video understanding (3) automatic speech recognition (3) speech translation (2) pointer generator (2) speech understanding (2) sound source localization (1) text generation (1) text classification (1) audio-visual learning (1) zero-shot learning (1) speech synthesis (1) direct preference optimization (1) bayesian inference (1) speaker embedding (1) speaker verification (1) machine unlearning (1)

Papers

Protecting Bystander Privacy via Selective Hearing in Audio LLMs ACL 2026 Audio-centric Video Understanding Benchmark without Text Shortcut EMNLP 2025 Bayesian WeakS-to-Strong from Text Classification to Generation ICLR 2025 CASE-Bench: Context-Aware SafEty Benchmark for Large Language Models ICML 2025 Enhancing Low-Resource Language and Instruction Following Capabilities of Audio Language Models Interspeech 2025 Improving LLM Video Understanding with 16 Frames Per Second ICML 2025 SkillAggregation: Reference-free LLM-Dependent Aggregation ACL 2025 Unlearning vs. Obfuscation: Are We Truly Removing Knowledge? EMNLP 2025 video-SALMONN-o1: Reasoning-enhanced Audio-visual Large Language Model ICML 2025 Wav2Prompt: End-to-End Speech Prompt Learning and Task-based Fine-tuning for Text-based LLMs NAACL 2025 Can Large Language Models Understand Spatial Audio? Interspeech 2024 M3AV: A Multimodal, Multigenre, and Multipurpose Audio-Visual Academic Lecture Dataset ACL 2024 SALMONN: Towards Generic Hearing Abilities for Large Language Models ICLR 2024 SAML: Speaker Adaptive Mixture of LoRA Experts for End-to-End ASR Interspeech 2024 SOT Triggered Neural Clustering for Speaker Attributed ASR Interspeech 2024 Speech-based Slot Filling using Large Language Models ACL 2024 video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models ICML 2024 Whisper-PMFA: Partial Multi-Scale Feature Aggregation for Speaker Verification using Whisper Models Interspeech 2024 Can Contextual Biasing Remain Effective with Whisper and GPT-2? Interspeech 2023 Cross-Utterance Conditioned VAE for Non-Autoregressive Text-to-Speech ACL 2022 Tree-constrained Pointer Generator with Graph Neural Network Encodings for Contextual Speech Recognition Interspeech 2022