Samuel Stevens

samuelstevens's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 3 collections 17 days ago

LlaSMol

Collection

LLMs tuned on the SMolInstruct dataset for chemistry tasks. • 6 items • Updated Feb 4 • 2

AmpleGCG

Collection

Generative models to produce GCG-like adversarial suffixes • 7 items • Updated Feb 4 • 2

UGround

Collection

UGround: Universal GUI Visual Grounding for GUI Agents (ICLR'25 Oral) • 9 items • Updated 21 days ago • 4

upvoted a collection 26 days ago

SAE-V

Collection

SAEs for vision models like CLIP or DINOv2 • 3 items • Updated 17 days ago • 3

upvoted a paper 26 days ago

Sparse Autoencoders for Scientifically Rigorous Interpretation of Vision Models

Paper • 2502.06755 • Published 27 days ago • 7

upvoted 2 papers 5 months ago

ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery

Paper • 2410.05080 • Published Oct 7, 2024 • 21

Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents

Paper • 2410.05243 • Published Oct 7, 2024 • 19

upvoted a paper 10 months ago

Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization

Paper • 2405.15071 • Published May 23, 2024 • 40

upvoted a collection about 1 year ago

INaturalist-2021 Fine-tunes

Collection

Fine-tune experiments for various `timm` models on the INaturalist 2021 Challenge dataset (https://github.com/visipedia/inat_comp/tree/master/2021) • 5 items • Updated Oct 25, 2023 • 6

upvoted a paper over 1 year ago

MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning

Paper • 2309.05653 • Published Sep 11, 2023 • 10