PPaperPicks

Soheil Feizi

University of Maryland (UMD), Reliable AI Lab, College Park, MD, USA

31 papers at tracked venues · 23 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0003-0944-8242 ↗Google Scholar ↗Homepage ↗

Venues

ICLR ×7NeurIPS ×7EMNLP ×5ACL ×4AAAI ×2EACL ×2ICML ×2CVPR ×1PerCom ×1

Frequent coauthors

Samyadeep Basu
DBLP profile ↗ORCID search ↗
×5
Sriram Balasubramanian
DBLP profile ↗ORCID search ↗
×3
Yize Cheng
DBLP profile ↗ORCID search ↗
×3
Vinu Sankar Sadasivan
DBLP profile ↗ORCID search ↗
×2
Shoumik Saha
DBLP profile ↗ORCID search ↗
×2
Arman Zarei
DBLP profile ↗ORCID search ↗
×2
Mazda Moayeri
DBLP profile ↗ORCID search ↗
×2
Neha Mukund Kalibhat
DBLP profile ↗ORCID search ↗
×2
Ming Li
DBLP profile ↗ORCID search ↗
×1
Mucong Ding
DBLP profile ↗ORCID search ↗
×1
Samuel Audia
DBLP profile ↗ORCID search ↗
×1
Atoosa Malemir Chegini
DBLP profile ↗ORCID search ↗
×1

Papers

  1. Attacker's Noise Can Manipulate Your Audio-based LLM in the Real World
    EACL 2026 ·
    Vinu Sankar Sadasivan
    DBLP profile ↗ORCID search ↗
  2. Decomposition-Enhanced Training for Post-Hoc Attributions in Language Models
    EACL 2026 ·
    Sriram Balasubramanian
    DBLP profile ↗ORCID search ↗
  3. Schoenfeld's Anatomy of Mathematical Reasoning by Language Models
    ACL 2026 ·
    Ming Li
    DBLP profile ↗ORCID search ↗
  4. Your LLM Agents are Temporally Blind: The Misalignment Between Tool Use Decisions and Human Time Perception
    ACL 2026 ·
    Yize Cheng
    DBLP profile ↗ORCID search ↗
  5. A Closer Look at Bias and Chain-of-Thought Faithfulness of Large (Vision) Language Models
    EMNLP 2025 ·
    Sriram Balasubramanian
    DBLP profile ↗ORCID search ↗
  6. A Technical Report on "Erasing the Invisible": The 2024 NeurIPS Competition on Stress Testing Image Watermarks
    NeurIPS 2025 ·
    Mucong Ding
    DBLP profile ↗ORCID search ↗
  7. Adversarial Paraphrasing: A Universal Attack for Humanizing AI-Generated Text
    NeurIPS 2025 ·
    Yize Cheng
    DBLP profile ↗ORCID search ↗
  8. Almost AI, Almost Human: The Challenge of Detecting AI-Polished Writing
    ACL 2025 ·
    Shoumik Saha
    DBLP profile ↗ORCID search ↗
  9. DyePack: Provably Flagging Test Set Contamination in LLMs Using Backdoors
    EMNLP 2025 ·
    Yize Cheng
    DBLP profile ↗ORCID search ↗
  10. How Learnable Grids Recover Fine Detail in Low Dimensions: A Neural Tangent Kernel Analysis of Multigrid Parametric Encodings
    ICLR 2025 ·
    Samuel Audia
    DBLP profile ↗ORCID search ↗
  11. Localizing Knowledge in Diffusion Transformers
    NeurIPS 2025 ·
    Arman Zarei
    DBLP profile ↗ORCID search ↗
  12. Mitigating Compositional Failures in Text-to-Image Models with Causal Text Embedding Refinement
    PerCom 2025 ·
    Arman Zarei
    DBLP profile ↗ORCID search ↗
  13. RePanda: Pandas-powered Tabular Verification and Reasoning
    ACL 2025 ·
    Atoosa Malemir Chegini
    DBLP profile ↗ORCID search ↗
  14. Rethinking Artistic Copyright Infringements In the Era Of Text-to-Image Generative Models
    ICLR 2025 ·
    Mazda Moayeri
    DBLP profile ↗ORCID search ↗
  15. Tool Preferences in Agentic LLMs are Unreliable
    EMNLP 2025 ·
    Kazem Faghih
    DBLP profile ↗ORCID search ↗
  16. Understanding the Effect of using Semantically Meaningful Tokens for Visual Representation Learning
    CVPR 2025 ·
    Neha Mukund Kalibhat
    DBLP profile ↗ORCID search ↗
  17. Unearthing Skill-level Insights for Understanding Trade-offs of Foundation Models
    ICLR 2025 ·
    Mazda Moayeri
    DBLP profile ↗ORCID search ↗
  18. DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified Robustness
    ICLR 2024 ·
    Shoumik Saha
    DBLP profile ↗ORCID search ↗
  19. Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP
    NeurIPS 2024 ·
    Sriram Balasubramanian
    DBLP profile ↗ORCID search ↗
  20. Distilling Knowledge from Text-to-Image Generative Models Improves Visio-Linguistic Reasoning in CLIP
    EMNLP 2024 ·
    Samyadeep Basu
    DBLP profile ↗ORCID search ↗
  21. Fast Adversarial Attacks on Language Models In One GPU Minute
    ICML 2024 ·
    Vinu Sankar Sadasivan
    DBLP profile ↗ORCID search ↗
  22. IntCoOp: Interpretability-Aware Vision-Language Prompt Tuning
    EMNLP 2024 ·
    Soumya Suvra Ghosal
    DBLP profile ↗ORCID search ↗
  23. LLM-Check: Investigating Detection of Hallucinations in Large Language Models
    NeurIPS 2024 ·
    Gaurang Sriramanan
    DBLP profile ↗ORCID search ↗
  24. Localizing and Editing Knowledge In Text-to-Image Generative Models
    ICLR 2024 ·
    Samyadeep Basu
    DBLP profile ↗ORCID search ↗
  25. Loki: Low-rank Keys for Efficient Sparse Attention
    NeurIPS 2024 ·
    Prajwal Singhania
    DBLP profile ↗ORCID search ↗
  26. Measuring Self-Supervised Representation Quality for Downstream Classification Using Discriminative Features
    AAAI 2024 ·
    Neha Mukund Kalibhat
    DBLP profile ↗ORCID search ↗
  27. On Mechanistic Knowledge Localization in Text-to-Image Generative Models
    ICML 2024 ·
    Samyadeep Basu
    DBLP profile ↗ORCID search ↗
  28. PRIME: Prioritizing Interpretability in Failure Mode Extraction
    ICLR 2024 ·
    Keivan Rezaei
    DBLP profile ↗ORCID search ↗
  29. Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks
    ICLR 2024 ·
    Mehrdad Saberi
    DBLP profile ↗ORCID search ↗
  30. Strong Baselines for Parameter-Efficient Few-Shot Fine-Tuning
    AAAI 2024 ·
    Samyadeep Basu
    DBLP profile ↗ORCID search ↗
  31. Understanding Information Storage and Transfer in Multi-Modal Large Language Models
    NeurIPS 2024 ·
    Samyadeep Basu
    DBLP profile ↗ORCID search ↗