Christos Thrampoulidis

Venues

Frequent coauthors

Papers

1. For-Value: Efficient Forward-Only Data Valuation for finetuning LLMs and VLMs
   ACL 2026 ·

   Wenlong Deng

   DBLP profile ↗ORCID search ↗
2. DARE the Extreme: Revisiting Delta-Parameter Pruning For Fine-Tuned Models
   ICLR 2025 ·

   Wenlong Deng

   DBLP profile ↗ORCID search ↗
3. Implicit Bias of Spectal Descent and Muon on Multiclass Separable Data
   NeurIPS 2025 ·

   Chen Fan

   DBLP profile ↗ORCID search ↗
4. Leveraging Online Olympiad-Level Math Problems for LLMs Training and Contamination-Resistant Evaluation
   ICML 2025 ·

   Sadegh Mahdavi

   DBLP profile ↗ORCID search ↗
5. On the Effect of Negative Gradient in Group Relative Deep Reinforcement Optimization
   NeurIPS 2025 ·

   Wenlong Deng

   DBLP profile ↗ORCID search ↗
6. Sharper Guarantees for Learning Neural Network Classifiers with Gradient Methods
   ICLR 2025 ·

   Hossein Taheri

   DBLP profile ↗ORCID search ↗
7. Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining
   NeurIPS 2025 ·

   Nathan Stromberg

   DBLP profile ↗ORCID search ↗
8. Class-Attribute Priors: Adapting Optimization to Heterogeneity and Fairness Objective
   AAAI 2024 ·

   Xuechen Zhang

   DBLP profile ↗ORCID search ↗
9. Engineering the Neural Collapse Geometry of Supervised-Contrastive Loss (Student Abstract)
   AAAI 2024 ·

   Jaidev Gill

   DBLP profile ↗ORCID search ↗
10. Implicit Optimization Bias of Next-token Prediction in Linear Models
    NeurIPS 2024 · Christos Thrampoulidis
11. Memorization Capacity of Multi-Head Attention in Transformers
    ICLR 2024 ·

    Sadegh Mahdavi

    DBLP profile ↗ORCID search ↗
12. Symmetric Neural-Collapse Representations with Supervised Contrastive Loss: The Impact of ReLU and Batching
    ICLR 2024 ·

    Ganesh Ramachandra Kini

    DBLP profile ↗ORCID search ↗
13. Unlocking the Potential of Prompt-Tuning in Bridging Generalized and Personalized Federated Learning
    CVPR 2024 ·

    Wenlong Deng

    DBLP profile ↗ORCID search ↗