Kye Gomez

kye's activity

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

upvoted 9 papers about 3 hours ago

FS-Researcher: Test-Time Scaling for Long-Horizon Research Tasks with File-System-Based Agents

Paper • 2602.01566 • Published 1 day ago • 38

VisionTrim: Unified Vision Token Compression for Training-Free MLLM Acceleration

Paper • 2601.22674 • Published 4 days ago • 3

Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry

Paper • 2601.22588 • Published 4 days ago • 3

LoopViT: Scaling Visual ARC with Looped Transformers

Paper • 2602.02156 • Published 1 day ago • 8

Toward Cognitive Supersensing in Multimodal Large Language Model

Paper • 2602.01541 • Published 1 day ago • 14

PixelGen: Pixel Diffusion Beats Latent Diffusion with Perceptual Loss

Paper • 2602.02493 • Published about 22 hours ago • 27

Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language Models

Paper • 2601.22060 • Published 5 days ago • 123

Kimi K2.5: Visual Agentic Intelligence

Paper • 2602.02276 • Published 1 day ago • 138

Green-VLA: Staged Vision-Language-Action Model for Generalist Robots

Paper • 2602.00919 • Published 3 days ago • 159

upvoted a paper about 18 hours ago

Do Reasoning Models Enhance Embedding Models?

Paper • 2601.21192 • Published 6 days ago • 23

upvoted 8 papers about 22 hours ago

Drive-JEPA: Video JEPA Meets Multimodal Trajectory Distillation for End-to-End Driving

Paper • 2601.22032 • Published 5 days ago • 3

DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understanding

Paper • 2601.23161 • Published 4 days ago • 10

Scaling Multiagent Systems with Process Rewards

Paper • 2601.23228 • Published 4 days ago • 7

NativeTok: Native Visual Tokenization for Improved Image Generation

Paper • 2601.22837 • Published 4 days ago • 9

DreamActor-M2: Universal Character Image Animation via Spatiotemporal In-Context Learning

Paper • 2601.21716 • Published 5 days ago • 12

DenseGRPO: From Sparse to Dense Reward for Flow Matching Model Alignment

Paper • 2601.20218 • Published 7 days ago • 14

FourierSampler: Unlocking Non-Autoregressive Potential in Diffusion Language Models via Frequency-Guided Generation

Paper • 2601.23182 • Published 4 days ago • 18

ASTRA: Automated Synthesis of agentic Trajectories and Reinforcement Arenas

Paper • 2601.21558 • Published 5 days ago • 53

upvoted 2 papers 2 days ago

Shaping capabilities with token-level data filtering

Paper • 2601.21571 • Published 5 days ago • 21

ConceptMoE: Adaptive Token-to-Concept Compression for Implicit Compute Allocation

Paper • 2601.21420 • Published 5 days ago • 40