Zhifeng Kong

12 papers · 2020–2026 · 7 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 ↓

+5 more ↓

🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (24)

🏆 Grand Slam 🧬 Topic Evolution 🗃️ Keyword Collector (67) 💎 Century Club · Bronze 🔥 Unstoppable · Bronze

Venues

ICLR (4) ICML (3) AAAI (1) AISTATS (1) CVPR (1) Interspeech (1) NeurIPS (1)

Top co-authors

Bryan Catanzaro (7) Rafael Valle (5) Wei Ping (5) Arushi Goel (4) Sang-gil Lee (3) Zhaoyang Lyu (2) rohan badlani (2) Dinesh Manocha (2) Kamalika Chaudhuri (2) Sungwon Kim (2)

Research topics

Artificial Intelligence (7) Deep Learning (7) Core AI (7) Models (5) Machine Learning (4) Architectures (3) Natural Language Processing (2) Speech & Audio (2) Application Areas (2) Learning Paradigms (2) Optimization & Theory (2) Synthesis (2) Computer Vision (1) Analysis (1) Applications (1)

Keywords

diffusion model (3) audio-language model (2) adversarial robustness (1) variational inference (1) curriculum learning (1) data augmentation (1) speech synthesis (1) audio classification (1) audio-visual learning (1) instruction following (1) flow matching (1) theoretical analysis (1) convex relaxation (1) linear programming (1) temporal alignment (1) in-context learning (1) expressive power (1) adversarial attack (1) generative model (1) few-shot learning (1)

Papers

Benchmarking Single-Factor Physical Video-to-Audio Generation CVPR 2026 Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities ICML 2025 ETTA: Elucidating the Design Space of Text-to-Audio Models ICML 2025 Fugatto 1: Foundational Generative Audio Transformer Opus 1 ICLR 2025 Synthio: Augmenting Small-Scale Audio Classification Datasets with Synthetic Data ICLR 2025 Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities ICML 2024 CleanUNet 2: A Hybrid Speech Denoising Model on Waveform and Spectrogram Interspeech 2023 A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion ICLR 2022 DiffWave: A Versatile Diffusion Model for Audio Synthesis ICLR 2021 Understanding Instance-based Interpretability of Variational Auto-Encoders NeurIPS 2021 Fastened CROWN: Tightened Neural Network Robustness Certificates AAAI 2020 The Expressive Power of a Class of Normalizing Flow Models AISTATS 2020