Travis King's picture

Travis King

travisking

·

AI & ML interests

have you heard of generative AI?

Recent Activity

upvoted a collection about 12 hours ago

Skywork-Reward-V2

upvoted a collection about 12 hours ago

Reward Models 10-2025

liked a Space about 12 hours ago

ScalerLab/JudgeBench

View all activity

Organizations

None yet

upvoted 2 collections about 12 hours ago

Skywork-Reward-V2

Scaling preference data curation to the extreme • 9 items • Updated Jul 4 • 24

Reward Models 10-2025

A collection of great reward models for research and production • 7 items • Updated about 6 hours ago • 9

upvoted a collection 10 days ago

Olmo 3 Pre-training

All artifacts related to Olmo 3 pre-training • 10 items • Updated 5 days ago • 25

upvoted a paper 14 days ago

Mitigating Label Length Bias in Large Language Models

Paper • 2511.14385 • Published 16 days ago • 6

upvoted an article 15 days ago

Article

ViDoRe V3: a comprehensive evaluation of retrieval for enterprise use-cases

29 days ago

•

52

upvoted a collection 15 days ago

Nemotron RAG

11 items • Updated about 6 hours ago • 47

upvoted a paper 15 days ago

OlmoEarth: Stable Latent Image Modeling for Multimodal Earth Observation

Paper • 2511.13655 • Published 17 days ago • 9

upvoted 3 articles 16 days ago

Article

🌳 QAT: The Art of Growing a Bonsai Model

24 days ago

•

15

Article

The Heterogeneous Feature of RoPE-based Attention in Long-Context LLMs

19 days ago

•

11

Article

Why Did MiniMax M2 End Up as a Full Attention Model?

Oct 30

•

65

upvoted a paper 17 days ago

DoPE: Denoising Rotary Position Embedding

Paper • 2511.09146 • Published 22 days ago • 92

upvoted 2 papers 20 days ago

LoopTool: Closing the Data-Training Loop for Robust LLM Tool Calls

Paper • 2511.09148 • Published 22 days ago • 16

Motif 2 12.7B technical report

Paper • 2511.07464 • Published 27 days ago • 38

upvoted a paper 22 days ago

Routing Manifold Alignment Improves Generalization of Mixture-of-Experts LLMs

Paper • 2511.07419 • Published 24 days ago • 25

upvoted a paper 23 days ago

Too Good to be Bad: On the Failure of LLMs to Role-Play Villains

Paper • 2511.04962 • Published 27 days ago • 52

upvoted 2 collections 23 days ago

SYNTH

Fully generalist synthetic dataset and SOTA small reasoners • 3 items • Updated 24 days ago • 10

Common Pile v0.1

All resources related to Common Pile v0.1, an 8TB dataset of public domain and openly licensed text • 4 items • Updated Jun 6 • 37

upvoted a paper 30 days ago

Trove: A Flexible Toolkit for Dense Retrieval

Paper • 2511.01857 • Published about 1 month ago • 10

upvoted a changelog about 1 month ago

Changelog

Cleaner Collection URLs

Oct 23

• 78

upvoted a paper about 1 month ago

Model Merging with Functional Dual Anchors

Paper • 2510.21223 • Published Oct 24 • 12