7 956 633

Kye Gomez

kye

https://discord.gg/qUtxnK2NMf

kyegomezb

AI & ML interests

Neuroscience, Behavior Science, Anti-Matter, Anti-Gravity propulsion,

Recent Activity

upvoted a paper about 1 hour ago

OTTER: A Vision-Language-Action Model with Text-Aware Visual Feature Extraction

upvoted a paper about 1 hour ago

Mixture of Experts Made Intrinsically Interpretable

upvoted a paper about 1 hour ago

"Principal Components" Enable A New Language of Images

View all activity

Organizations

kye's activity

upvoted 4 papers about 1 hour ago

upvoted 10 papers about 18 hours ago

Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia

Paper • 2503.07920 • Published 2 days ago • 74

MagicInfinite: Generating Infinite Talking Videos with Your Words and Voice

Paper • 2503.05978 • Published 5 days ago • 29

Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning

Paper • 2503.07572 • Published 2 days ago • 20

Evaluating Intelligence via Trial and Error

Paper • 2502.18858 • Published 15 days ago • 4

OmniMamba: Efficient and Unified Multimodal Understanding and Generation via State Space Models

Paper • 2503.08686 • Published 1 day ago • 13

Gemini Embedding: Generalizable Embeddings from Gemini

Paper • 2503.07891 • Published 2 days ago • 19

LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL

Paper • 2503.07536 • Published 2 days ago • 56

SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories

Paper • 2503.08625 • Published 1 day ago • 22

UniF^2ace: Fine-grained Face Understanding and Generation with Unified Multimodal Models

Paper • 2503.08120 • Published 1 day ago • 25

YuE: Scaling Open Foundation Models for Long-Form Music Generation

Paper • 2503.08638 • Published 1 day ago • 48

upvoted 4 papers 1 day ago

Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models

Paper • 2503.06749 • Published 3 days ago • 20

Automated Movie Generation via Multi-Agent CoT Planning

Paper • 2503.07314 • Published 2 days ago • 32

MM-Eureka: Exploring Visual Aha Moment with Rule-based Large-scale Reinforcement Learning

Paper • 2503.07365 • Published 2 days ago • 51

SEAP: Training-free Sparse Expert Activation Pruning Unlock the Brainpower of Large Language Models

Paper • 2503.07605 • Published 2 days ago • 61

upvoted 2 papers 2 days ago

Linear-MoE: Linear Sequence Modeling Meets Mixture-of-Experts

Paper • 2503.05447 • Published 5 days ago • 7

R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model

Paper • 2503.05132 • Published 6 days ago • 42