Finn Reyes

finnreyes's activity

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

upvoted 2 papers about 2 hours ago

YOLO-PEFT: Parameter-Efficient Fine-Tuning on YOLO Family

Paper • 2608.07051 • Published 5 days ago • 20

Characterizing the Quality Profile of AI-Generated C++ in Production

Paper • 2608.06640 • Published 6 days ago • 10

upvoted 6 papers 1 day ago

EffectLearner: World-Aware Object-Effect Reasoning for Real-World Video Object Removal

Paper • 2608.05565 • Published 6 days ago • 22

GaussianSelector: Lightweight Human-Guided Object Selection in 3D Gaussian Splatting with Graph Optimization

Paper • 2608.01492 • Published 10 days ago • 12

FactorJEPA: Factorizing Monolithic Futures into Layout-Agent-Interaction Channels for Crowded and Chaotic Global South Urban Worlds

Paper • 2608.01049 • Published 10 days ago • 13

PaDoc: Layout-Grounded Parallel Decoding for Document Parsing

Paper • 2608.06146 • Published 6 days ago • 24

Teaching Nemotron Greek: Mining a Corpus, Adapting Retrieval, and Grounding Generation for Modern Greek across Specialist Domains

Paper • 2608.05138 • Published 7 days ago • 31

SmartMage: Dynamic Modality Orchestration for 3D Scene Understanding

Paper • 2608.05137 • Published 2 days ago • 27

upvoted 6 papers 2 days ago

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks

Paper • 2608.03764 • Published 8 days ago • 27

Resume Means Resume: A Machine-Checked Conformance Contract for Checkpoint, Interrupt, and Resume Semantics in Workflow Persistence Layers

Paper • 2608.03836 • Published 4 days ago • 4

K-EXAONE 2.0 Technical Report

Paper • 2608.04505 • Published 7 days ago • 25

Lossless Tensor Compression as Program Synthesis

Paper • 2608.02162 • Published 9 days ago • 15

The Personalization Mirage: How LLMs Fabricate User Profiles, and Why Self-Monitoring Misleads

Paper • 2608.04570 • Published 7 days ago • 40

Recursive Synthesis for Long-Horizon Terminal Tasks

Paper • 2608.05466 • Published 5 days ago • 238

upvoted 5 papers 3 days ago

SG-WAM: Self-Guided World Modeling in Geometry-Aware Policy Space

Paper • 2608.01397 • Published 10 days ago • 10

DAPD: Dual-Anchored Policy Distillation

Paper • 2608.01735 • Published 9 days ago • 129

Memory for Large Language Models

Paper • 2607.25380 • Published 15 days ago • 15

Progressive Agent Skill Generation via Reinforcement Learning

Paper • 2608.01678 • Published 9 days ago • 58

VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System

Paper • 2607.27380 • Published 14 days ago • 71

upvoted a paper 4 days ago

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks

Paper • 2608.02023 • Published 9 days ago • 155