Tom Goldstein
- Papers
- 48
Cite
Notes
Only stored in your browser.
Authored papers
48Image Generation with a Sphere Encoder
arXiv 2026
BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset
arXiv 2025
The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text
arXiv 2025
LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation
arXiv 2025
Zero-Shot Vision Encoder Grafting via LLM Surrogates
ICCV 2025
Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence
arXiv 2025
Gemstones: A Model Suite for Multi-Faceted Scaling Laws
arXiv 2025
Zebra-CoT: A Dataset for Interleaved Vision Language Reasoning
arXiv 2025
ARGUS: Hallucination and Omission Evaluation in Video-LLMs
ICCV 2025
MORSE-500: A Programmatically Controllable Video Benchmark to Stress-Test Multimodal Reasoning
arXiv 2025
Has My System Prompt Been Used? Large Language Model Prompt Membership Inference
arXiv 2025
DynaGuard: A Dynamic Guardrail Model With User-Defined Policies
arXiv 2025
When Can You Get Away with Low Memory Adam?
arXiv 2025
Exploiting Sparsity for Long Context Inference: Million Token Contexts on Commodity GPUs
arXiv 2025
LiveBench: A Challenging, Contamination-Limited LLM Benchmark
arXiv 2024
Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text
arXiv 2024
Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models
arXiv 2024
Coercing LLMs to do and reveal (almost) anything
arXiv 2024
What do we learn from inverting CLIP models?
arXiv 2024
The CLRS-Text Algorithmic Reasoning Language Benchmark
arXiv 2024
Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs
arXiv 2024
WAVES: Benchmarking the Robustness of Image Watermarks
arXiv 2024
Transformers Can Do Arithmetic with the Right Embeddings
arXiv 2024
Measuring Style Similarity in Diffusion Models
arXiv 2024
Generating Potent Poisons and Backdoors from Scratch with Guided Diffusion
arXiv 2024
Benchmarking ChatGPT on Algorithmic Reasoning
arXiv 2024
NEFTune: Noisy Embeddings Improve Instruction Finetuning
arXiv 2023
On the Reliability of Watermarks for Large Language Models
arXiv 2023
Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks
NeurIPS 2023 11
Understanding and Mitigating Copying in Diffusion Models
understanding-and-mitigating-copying-in
Bring Your Own Data! Self-Supervised Evaluation for Large Language Models
arXiv 2023
On the Exploitability of Instruction Tuning
on-the-exploitability-of-instruction-tuning
Universal Guidance for Diffusion Models
arXiv 2023
Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery
hard-prompts-made-easy-gradient-based
Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robust
arXiv 2023
InstructZero: Efficient Instruction Optimization for Black-Box Large Language Models
arXiv 2023
Object Recognition as Next Token Prediction
CVPR 2024 1
Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise
cold-diffusion-inverting-arbitrary-image
Cramming: Training a Language Model on a Single GPU in One Day
arXiv 2022
Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries
arXiv 2022
Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models
arXiv 2022
What do Vision Transformers Learn? A Visual Exploration
arXiv 2022
Plug-In Inversion: Model-Agnostic Inversion for Vision with Data Augmentations
plug-in-inversion-model-agnostic-inversion
Stochastic Training is Not Necessary for Generalization
stochastic-training-is-not-necessary-for-1
Datasets for Studying Generalization from Easy to Hard Examples
arXiv 2021
SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training
saint-improved-neural-networks-for-tabular-1
Does your graph need a confidence boost? Convergent boosted smoothing on graphs with tabular node features
arXiv 2021
Visualizing the Loss Landscape of Neural Nets
visualizing-the-loss-landscape-of-neural-nets-1
Affiliations
Frequent co-authors
10from 48 papers