Kye Gomez

kye's activity

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

upvoted 5 papers about 15 hours ago

Training Agents to Evolve with Their Harness: TaoLive Digital Avatar Agent Technical Report

Paper • 2608.15763 • Published 7 days ago • 43

VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning

Paper • 2608.26105 • Published 3 days ago • 247

TTPO: Test-Time Policy Optimization

Paper • 2608.27448 • Published 2 days ago • 65

PILOT in the Loop: Live Self-Improvement for Long-Horizon Agents

Paper • 2608.26530 • Published 2 days ago • 25

GameWAM: A World Action Model for Video Games

Paper • 2608.26200 • Published 4 days ago • 38

upvoted 2 papers 1 day ago

MA-VLA: Multi-Arm Vision-Language-Action Model for Collaboration and Compositional Generalization

Paper • 2608.25864 • Published 3 days ago • 9

JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution

Paper • 2608.25593 • Published 3 days ago • 107

upvoted 3 papers 3 days ago

GigaBrain-0.7: Scaling Embodied Foundation Models to Emergent Capabilities with a Three-System Architecture

Paper • 2608.15875 • Published 13 days ago • 98

Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMs

Paper • 2608.20492 • Published 9 days ago • 102

TileMix: Tile-Centric Mixed-Precision Attention for LLM Inference Acceleration

Paper • 2608.17336 • Published 11 days ago • 5

upvoted 8 papers 4 days ago

From Generation to Simulation: How Far Are World Models from Being True Simulators?

Paper • 2608.23070 • Published 5 days ago • 4

AutoResearch: Insight In, Hallucination Out

Paper • 2608.17906 • Published 6 days ago • 9

Task-CoEvolve: Efficient Harness Optimization via Adaptive Validation Task Selection

Paper • 2608.20169 • Published 5 days ago • 11

Towards a Densing Law for User Representation Learning at Billion-Scale Capacity

Paper • 2608.23392 • Published 5 days ago • 27

Prime Agent: A Self-Improving RLM Harness

Paper • 2608.23552 • Published 5 days ago • 43

TLive-Omni: An Omni-Modal Understanding Model for E-Commerce Live Streaming

Paper • 2608.20958 • Published 8 days ago • 58

EchoWM: Open and Enterable Omnimodal World Models

Paper • 2608.23189 • Published 5 days ago • 74

Apodex 1.1: Scaling Agentic Intelligence for Complex Work

Paper • 2608.23283 • Published 5 days ago • 200

upvoted 2 papers 6 days ago

EXIMO: VLM Guided Exploration of VLA Policies

Paper • 2608.19891 • Published 9 days ago • 16

Hierarchical Self-Improvement: A Framework for Task-Specific Evolvable Agent Harnesses

Paper • 2608.08466 • Published 20 days ago • 12