Kye Gomez

kye's activity

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

upvoted 5 papers 1 day ago

EmbeddingGemma 2: Unified and Efficient Multimodal Representations

Paper • 2610.37364 • Published 3 days ago • 27

Harness-Model Collaboration for Long-Horizon Continual Learning

Paper • 2610.34724 • Published 4 days ago • 13

SearchHorizonBench: A Benchmark for Search Value in AI Agents

Paper • 2610.34714 • Published 4 days ago • 10

What Effort Level Should I Choose? On the Economics of Reasoning Effort in LLM Agents

Paper • 2610.34491 • Published 5 days ago • 30

Multiscale Policy Optimization for Long-Horizon LLM Agents

Paper • 2610.35013 • Published 4 days ago • 381

upvoted 6 papers 2 days ago

Nested Sparsity for Scalable Pretraining and Continual Learning

Paper • 2610.31818 • Published 8 days ago • 15

Thinking-in-Bets at Test Time Reduces Sycophantic Revisions in LLM Agents

Paper • 2610.34654 • Published 4 days ago • 19

Continual Learning Exam: Benchmarking Long-Horizon RSI and Experiential Learning in LLM Agents

Paper • 2610.33956 • Published 5 days ago • 62

Work Agents: Systems, Capabilities, and Optimization

Paper • 2610.35845 • Published 4 days ago • 119

DynaFlow: Learning Free-Form Multi-Agent Orchestration

Paper • 2610.34467 • Published 5 days ago • 143

Trajectory2Gym: Decision-Grounded Compositional Interaction Synthesis for Tool-Use Agents

Paper • 2610.33568 • Published 6 days ago • 368

upvoted 6 papers 3 days ago

RoboJudge: Multimodal Language Models as Judges for Embodied Video Generation

Paper • 2610.27782 • Published 10 days ago • 7

DuoLM: Fast and Effective Personalized Recommendation with Language Models

Paper • 2610.24481 • Published 10 days ago • 13

MMVistaReason: Toward Open-Data and Post-Training Recipes for Multimodal Reasoning

Paper • 2610.01352 • Published 8 days ago • 16

MultiAgent-OPD: End-to-End Training of Hierarchical Multi-Agent Systems with On-Policy Distillation

Paper • 2610.23234 • Published 10 days ago • 13

DraMaze: A Multi-Agent Pipeline with Future-Aware Memory for Diverse Microdrama Script Generation

Paper • 2610.32002 • Published 8 days ago • 20

RSIHub: A Composable Framework for Agent-Evolution Methods

Paper • 2610.32253 • Published 7 days ago • 49

upvoted 3 papers 6 days ago

MambaAct: Efficient Mamba Action Experts for Flow-Matching Vision-Language-Action Models

Paper • 2610.22951 • Published 14 days ago • 17

RTAformer: Relation-Transition-Aware Transformer for Video Scene Graph Generation

Paper • 2610.20091 • Published 16 days ago • 19

WeVisOne-VL: Unified Visual Perception from Objects to Pixels

Paper • 2610.31329 • Published 8 days ago • 259