Ahmed Imtiaz Humayun

12 papers · 2018–2025 · 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 ↓

+4 more ↓

🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (23) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🐣 Hot Topic Early Bird

👑 Triple Crown 🗃️ Keyword Collector (64) ❓ The Questioner (2) 💎 Century Club · Bronze

Venues

ICLR (4) CVPR (2) ICML (2) COLING (1) ICCV (1) Interspeech (1) NeurIPS (1)

Top co-authors

Richard Baraniuk (5) Randall Balestriero (5) Negar Rostamzadeh (2) Deepak Ramachandran (2) Ibtihel Amara (2) Cristina Nader Vasconcelos (2) Guha Balakrishnan (2) Mohammad Havaei (2) Junfeng He (2) Richard G. Baraniuk (2)

Research topics

Machine Learning (9) Deep Learning (8) Models (6) Artificial Intelligence (5) Core AI (5) Core Methods (5) Optimization & Theory (4) Architectures (3) Learning Types (2) Computer Science (1) Healthcare & Medicine (1) Speech & Audio (1) Analysis (1) Application Areas (1) Applications (1)

Keywords

generative model (3) variational autoencoder (2) piecewise linear (2) image generation (2) transfer learning (2) uniform sampling (1) model safety (1) representation learning (1) text-to-image generation (1) natural language processing (1) feature learning (1) network visualization (1) robustness (1) distribution shift (1) singular value decomposition (1) ensemble learning (1) implicit neural representation (1) semi-supervised learning (1) support vector machine (1) neural network pruning (1)

Papers

Erasing More Than Intended? How Concept Erasure Degrades the Generation of Non-Target Concepts ICCV 2025 MITIGATING OVER-EXPLORATION IN LATENT SPACE OPTIMIZATION USING LES ICML 2025 The Journey Matters: Average Parameter Count over Pre-training Unifies Sparse and Dense Scaling Laws ICLR 2025 What Secrets Do Your Manifolds Hold? Understanding the Local Geometry of Generative Models ICLR 2025 Deep Networks Always Grok and Here is Why ICML 2024 Learning Transferable Features for Implicit Neural Representations NeurIPS 2024 Self-Consuming Generative Models Go MAD ICLR 2024 Unicode Normalization and Grapheme Parsing of Indic Languages COLING 2024 SplineCam: Exact Visualization and Characterization of Deep Network Geometry and Decision Boundaries CVPR 2023 MaGNET: Uniform Sampling from Deep Generative Network Manifolds Without Retraining ICLR 2022 Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values CVPR 2022 An Ensemble of Transfer, Semi-supervised and Supervised Learning Methods for Pathological Heart Sound Classification Interspeech 2018