Tom Goldstein
~Tom_Goldstein1
38
论文总数
19.0
年均投稿
平均评分
接收情况17/38
会议分布
ICLR
25
NeurIPS
9
COLM
4
发表论文 (38 篇)
202521 篇
4
Quantifying Cross-Modality Memorization in Vision-Language Models
NeurIPS 2025Poster
5
LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation
COLM 2025Poster
4
What do we learn from inverting CLIP models?
ICLR 2025withdrawn
5
Has My System Prompt Been Used? Large Language Model Prompt Membership Inference
ICLR 2025Rejected
3
Data Brittleness Estimation with Self-Supervised Features
ICLR 2025withdrawn
4
Dense Backpropagation Improves Training for Sparse Mixture-of-Experts
NeurIPS 2025Poster
3
A Simple Baseline for Predicting Future Events with Auto-Regressive Tabular Transformers
ICLR 2025Rejected
5
Gradient-based Optimization of Dataset Mixtures
ICLR 2025withdrawn
4
GenQA: An Instruction Dataset of LLM Generated Questions and Answers
ICLR 2025withdrawn
5
OPTune: Efficient Online Preference Tuning
ICLR 2025withdrawn
3
CinePile: A Long Video Question Answering Dataset and Benchmark
ICLR 2025Rejected
4
Dense Backpropagation Improves Routing for Sparsely-Gated Mixture-of-Experts
ICLR 2025Rejected
-
Extracting Parameter Counts from Fine-Tuning APIs
ICLR 2025withdrawn
5
Gemstones: A Model Suite for Multi-Faceted Scaling Laws
NeurIPS 2025Poster
4
LLMs Boost the Performance of Decision Trees on Tabular Data across Sample Sizes
ICLR 2025Rejected
3
Running Huge Context Windows On Tiny GPUs
ICLR 2025Rejected
5
Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models
ICLR 2025Rejected
4
Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models
COLM 2025Poster
4
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
NeurIPS 2025Spotlight
5
From Pixels to Prose: A Large Dataset of Dense Image Captions
ICLR 2025withdrawn
3
LiveBench: A Challenging, Contamination-Limited LLM Benchmark
ICLR 2025Spotlight
202417 篇
3
InstructZero: Efficient Instruction Optimization for Black-Box Large Language Models
ICLR 2024Rejected
4
A Simple and Efficient Baseline for Data Attribution on Images
ICLR 2024withdrawn
4
CALVIN: Improved Contextual Video Captioning via Instruction Tuning
NeurIPS 2024Poster
4
Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models
NeurIPS 2024Poster
4
LMD3: Language Model Data Density Dependence
COLM 2024Poster
4
Universal Guidance for Diffusion Models
ICLR 2024Poster
4
Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models
NeurIPS 2024Poster
4
What do vision transformers learn? A visual exploration
ICLR 2024Rejected
4
Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text
ICLR 2024Rejected
4
Bring Your Own Data! Self-Sensitivity Evaluation for Large Language Models
COLM 2024Poster
4
Bring Your Own Data! Self-Supervised Evaluation for Large Language Models
ICLR 2024withdrawn
4
Baseline Defenses for Adversarial Attacks Against Aligned Language Models
ICLR 2024Rejected
3
On the Reliability of Watermarks for Large Language Models
ICLR 2024Poster
3
Transformers Can Do Arithmetic with the Right Embeddings
NeurIPS 2024Poster
4
Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs
NeurIPS 2024Poster
4
Algorithm Design for Learned Algorithms
ICLR 2024withdrawn
4
NEFTune: Noisy Embeddings Improve Instruction Finetuning
ICLR 2024Poster