PPaperPicks

Tom Goldstein

University of Maryland, Department of Computer Science, College Park, MD, USA

33 papers at tracked venues · 28 at CORE A* · active 2024–2025

DBLP profile ↗ORCID 0000-0003-1660-9307 ↗Google Scholar ↗Homepage ↗

Venues

NeurIPS ×13CVPR ×4ICLR ×4ICML ×4ICCV ×2NAACL ×2AAAI ×1AAMAS ×1ECCV ×1ICRA ×1

Frequent coauthors

Mucong Ding
DBLP profile ↗ORCID search ↗
×2
Sean McLeish
DBLP profile ↗ORCID search ↗
×2
Alex Hanson
DBLP profile ↗ORCID search ↗
×2
Yuxin Wen
DBLP profile ↗ORCID search ↗
×2
Kaiyu Yue
DBLP profile ↗ORCID search ↗
×2
Abhimanyu Hans
DBLP profile ↗ORCID search ↗
×2
Gowthami Somepalli
DBLP profile ↗ORCID search ↗
×2
Lichang Chen
DBLP profile ↗ORCID search ↗
×2
Ruchit Rawal
DBLP profile ↗ORCID search ↗
×1
Michael-Andrei Panaitescu-Liess
DBLP profile ↗ORCID search ↗
×1
Ashwinee Panda
DBLP profile ↗ORCID search ↗
×1
Reza Shirkavand
DBLP profile ↗ORCID search ↗
×1

Papers

  1. A Technical Report on "Erasing the Invisible": The 2024 NeurIPS Competition on Stress Testing Image Watermarks
    NeurIPS 2025 ·
    Mucong Ding
    DBLP profile ↗ORCID search ↗
  2. ARGUS: Hallucination and Omission Evaluation in Video-LLMs
    ICCV 2025 ·
    Ruchit Rawal
    DBLP profile ↗ORCID search ↗
  3. Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?
    AAAI 2025 ·
    Michael-Andrei Panaitescu-Liess
    DBLP profile ↗ORCID search ↗
  4. Dense Backpropagation Improves Training for Sparse Mixture-of-Experts
    NeurIPS 2025 ·
    Ashwinee Panda
    DBLP profile ↗ORCID search ↗
  5. Efficient Fine-Tuning and Concept Suppression for Pruned Diffusion Models
    CVPR 2025 ·
    Reza Shirkavand
    DBLP profile ↗ORCID search ↗
  6. Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement
    NAACL 2025 ·
    Xiyao Wang
    DBLP profile ↗ORCID search ↗
  7. FineGRAIN: Evaluating Failure Modes of Text-to-Image Models with Vision Language Model Judges
    NeurIPS 2025 ·
    Kevin David Hayes
    DBLP profile ↗ORCID search ↗
  8. Gemstones: A Model Suite for Multi-Faceted Scaling Laws
    NeurIPS 2025 ·
    Sean McLeish
    DBLP profile ↗ORCID search ↗
  9. LLM-Generated Passphrases That Are Secure and Easy to Remember
    NAACL 2025 ·
    Jie S. Li
    DBLP profile ↗ORCID search ↗
  10. LiveBench: A Challenging, Contamination-Limited LLM Benchmark
    ICLR 2025 ·
    Colin White
    DBLP profile ↗ORCID search ↗
  11. Multimodal Agentic Model Predictive Control
    AAMAS 2025 ·
    Saptarashmi Bandyopadhyay
    DBLP profile ↗ORCID search ↗
  12. PUP 3D-GS: Principled Uncertainty Pruning for 3D Gaussian Splatting
    CVPR 2025 ·
    Alex Hanson
    DBLP profile ↗ORCID search ↗
  13. Quantifying Cross-Modality Memorization in Vision-Language Models
    NeurIPS 2025 ·
    Yuxin Wen
    DBLP profile ↗ORCID search ↗
  14. Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
    NeurIPS 2025 ·
    Jonas Geiping
    DBLP profile ↗ORCID search ↗
  15. Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives
    CVPR 2025 ·
    Alex Hanson
    DBLP profile ↗ORCID search ↗
  16. The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text
    NeurIPS 2025 ·
    Nikhil Kandpal
    DBLP profile ↗ORCID search ↗
  17. Zero-Shot Vision Encoder Grafting via LLM Surrogates
    ICCV 2025 ·
    Kaiyu Yue
    DBLP profile ↗ORCID search ↗
  18. Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs
    NeurIPS 2024 ·
    Abhimanyu Hans
    DBLP profile ↗ORCID search ↗
  19. CALVIN: Improved Contextual Video Captioning via Instruction Tuning
    NeurIPS 2024 ·
    Gowthami Somepalli
    DBLP profile ↗ORCID search ↗
  20. Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization
    NeurIPS 2024 ·
    Mucong Ding
    DBLP profile ↗ORCID search ↗
  21. Hierarchical Point Attention for Indoor 3D Object Detection
    ICRA 2024 ·
    Manli Shu
    DBLP profile ↗ORCID search ↗
  22. InstructZero: Efficient Instruction Optimization for Black-Box Large Language Models
    ICML 2024 ·
    Lichang Chen
    DBLP profile ↗ORCID search ↗
  23. Investigating Style Similarity in Diffusion Models
    ECCV 2024 ·
    Gowthami Somepalli
    DBLP profile ↗ORCID search ↗
  24. NEFTune: Noisy Embeddings Improve Instruction Finetuning
    ICLR 2024 ·
    Neel Jain
    DBLP profile ↗ORCID search ↗
  25. ODIN: Disentangled Reward Mitigates Hacking in RLHF
    ICML 2024 ·
    Lichang Chen
    DBLP profile ↗ORCID search ↗
  26. Object Recognition as Next Token Prediction
    CVPR 2024 ·
    Kaiyu Yue
    DBLP profile ↗ORCID search ↗
  27. On the Reliability of Watermarks for Large Language Models
    ICLR 2024 ·
    John Kirchenbauer
    DBLP profile ↗ORCID search ↗
  28. Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models
    NeurIPS 2024 ·
    Yuxin Wen
    DBLP profile ↗ORCID search ↗
  29. Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models
    NeurIPS 2024 ·
    Yuancheng Xu
    DBLP profile ↗ORCID search ↗
  30. Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text
    ICML 2024 ·
    Abhimanyu Hans
    DBLP profile ↗ORCID search ↗
  31. Transformers Can Do Arithmetic with the Right Embeddings
    NeurIPS 2024 ·
    Sean McLeish
    DBLP profile ↗ORCID search ↗
  32. Universal Guidance for Diffusion Models
    ICLR 2024 ·
    Arpit Bansal
    DBLP profile ↗ORCID search ↗
  33. WAVES: Benchmarking the Robustness of Image Watermarks
    ICML 2024 ·
    Bang An
    DBLP profile ↗ORCID search ↗