Ehsan Abbasnejad

Venues

Frequent coauthors

Papers

1. Certified but Fooled! Breaking Certified Defenses with Ghost Certificates
   AAAI 2026 ·

   Viet Quoc Vo

   DBLP profile ↗ORCID search ↗
2. Truth as a Trajectory: What Internal Representations Reveal About Large Language Model Reasoning
   ACL 2026 ·

   Hamed Damirchi

   DBLP profile ↗ORCID search ↗
3. Bayesian Low-Rank Learning (Bella): A Practical Approach to Bayesian Neural Networks
   AAAI 2025 ·

   Bao Gia Doan

   DBLP profile ↗ORCID search ↗
4. Do Deep Neural Network Solutions Form a Star Domain?
   ICLR 2025 ·

   Ankit Sonthalia

   DBLP profile ↗ORCID search ↗
5. Do We Always Need the Simplicity Bias? Looking for Optimal Inductive Biases in the Wild
   CVPR 2025 ·

   Damien Teney

   DBLP profile ↗ORCID search ↗
6. Geometry-Aware Collaborative Multi-Solutions Optimizer for Model Fine-Tuning with Parameter Efficiency
   NeurIPS 2025 ·

   Van-Anh Nguyen

   DBLP profile ↗ORCID search ↗
7. Mysteries of the Deep: Role of Intermediate Representations in Out of Distribution Detection
   NeurIPS 2025 ·

   Ignacio Meza De La Jara

   DBLP profile ↗ORCID search ↗
8. RandLoRA: Full rank parameter-efficient fine-tuning of large models
   ICLR 2025 ·

   Paul Albert

   DBLP profile ↗ORCID search ↗
9. Synergy and Diversity in CLIP: Enhancing Performance Through Adaptive Backbone Ensembling
   ICLR 2025 ·

   Cristian Rodriguez Opazo

   DBLP profile ↗ORCID search ↗
10. Towards Higher Effective Rank in Parameter-Efficient Fine-Tuning Using Khatri-Rao Product
    ICCV 2025 ·

    Paul Albert

    DBLP profile ↗ORCID search ↗
11. BLURD: Benchmarking and Learning using a Unified Rendering and Diffusion Model
    NeurIPS 2024 ·

    Boris Repasky

    DBLP profile ↗ORCID search ↗
12. Brusleattack: a Query-Efficient Score- based Black-Box Sparse Adversarial Attack
    ICLR 2024 ·

    Viet Quoc Vo

    DBLP profile ↗ORCID search ↗
13. Knowledge Composition using Task Vectors with Learned Anisotropic Scaling
    NeurIPS 2024 ·

    Frederic Z. Zhang

    DBLP profile ↗ORCID search ↗
14. Neural Redshift: Random Networks are not Random Functions
    CVPR 2024 ·

    Damien Teney

    DBLP profile ↗ORCID search ↗
15. Selective Mixup Helps with Distribution Shifts, But Not (Only) because of Mixup
    ICML 2024 ·

    Damien Teney

    DBLP profile ↗ORCID search ↗