Kye Gomez

kye's activity

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

upvoted 8 papers about 4 hours ago

Towards Pixel-Level VLM Perception via Simple Points Prediction

Paper • 2601.19228 • Published 2 days ago • 5

Revisiting Parameter Server in LLM Post-Training

Paper • 2601.19362 • Published 1 day ago • 4

Selective Steering: Norm-Preserving Control Through Discriminative Layer Selection

Paper • 2601.19375 • Published 1 day ago • 5

Post-LayerNorm Is Back: Stable, ExpressivE, and Deep

Paper • 2601.19895 • Published 1 day ago • 8

Visual Generation Unlocks Human-Like Reasoning through Multimodal World Models

Paper • 2601.19834 • Published 1 day ago • 19

AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking

Paper • 2601.17645 • Published 4 days ago • 19

A Pragmatic VLA Foundation Model

Paper • 2601.18692 • Published 2 days ago • 26

AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security

Paper • 2601.18491 • Published 2 days ago • 60

upvoted 12 papers 1 day ago

One Adapts to Any: Meta Reward Modeling for Personalized LLM Alignment

Paper • 2601.18731 • Published 2 days ago • 6

IVRA: Improving Visual-Token Relations for Robot Action Policy with Training-Free Hint-Based Guidance

Paper • 2601.16207 • Published 6 days ago • 7

Least-Loaded Expert Parallelism: Load Balancing An Imbalanced Mixture-of-Experts

Paper • 2601.17111 • Published 5 days ago • 5

SkyReels-V3 Technique Report

Paper • 2601.17323 • Published 5 days ago • 7

DRPG (Decompose, Retrieve, Plan, Generate): An Agentic Framework for Academic Rebuttal

Paper • 2601.18081 • Published 3 days ago • 7

Agentic Very Long Video Understanding

Paper • 2601.18157 • Published 3 days ago • 9

AR-Omni: A Unified Autoregressive Model for Any-to-Any Generation

Paper • 2601.17761 • Published 4 days ago • 9

CGPT: Cluster-Guided Partial Tables with LLM-Generated Supervision for Table Retrieval

Paper • 2601.15849 • Published 7 days ago • 12

iFSQ: Improving FSQ for Image Generation with 1 Line of Code

Paper • 2601.17124 • Published 5 days ago • 29

Elastic Attention: Test-time Adaptive Sparsity Ratios for Efficient Transformers

Paper • 2601.17367 • Published 5 days ago • 29

The Script is All You Need: An Agentic Framework for Long-Horizon Dialogue-to-Cinematic Video Generation

Paper • 2601.17737 • Published 4 days ago • 48

daVinci-Dev: Agent-native Mid-training for Software Engineering

Paper • 2601.18418 • Published 3 days ago • 114