Finn Reyes

finnreyes's activity

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

upvoted 2 papers about 3 hours ago

MUON-RT Reusing the Teacher's Trajectory for Momentum-Free Muon for LLM Self-Distillation

Paper • 2610.41104 • Published 10 days ago • 23

StreamDuo: A Live Commentator and a Research Agent for Unseen Games

Paper • 2611.01120 • Published 9 days ago • 26

upvoted 6 papers 1 day ago

On the Generalization Limitation of On-Policy Distillation for Post-RL Consolidation

Paper • 2611.05609 • Published 6 days ago • 25

Order-Only On-Policy Distillation

Paper • 2611.02112 • Published 8 days ago • 36

From Fragmentation to Fusion: A Survey and Roadmap for Omnimodal Embeddings

Paper • 2611.00172 • Published 10 days ago • 25

Think Less, Locally: Local Preference Learning for Reasoning Compression

Paper • 2611.04814 • Published 6 days ago • 63

Lost in Recovery: Demystifying Recovery Behavior of Computer-Use Agents via Goal-Oriented Action Replay

Paper • 2610.27954 • Published 20 days ago • 37

DreamX: Video Diffusion Model is a Universal Latent Action Learner

Paper • 2611.05377 • Published 6 days ago • 58

upvoted 7 papers 2 days ago

WebHarbor: Docking Real Websites for Evolving GUI Agent Environments

Paper • 2611.03634 • Published 7 days ago • 29

Route Anything: A Study of Model and Policy Routing for General-Purpose AI Systems

Paper • 2611.05275 • Published 6 days ago • 81

Training Foundation Models with a Single Algorithm

Paper • 2610.40564 • Published 11 days ago • 15

Venus-DefakerOne2: A Vision-Forensics Foundation Model with Broader Coverage

Paper • 2610.37918 • Published 13 days ago • 25

Turns Matter: Advancing Streaming Video RL via Turn-Level Credit

Paper • 2611.06728 • Published 5 days ago • 91

Latent Reasoning in Continuous Space for Unified Multimodal Models

Paper • 2610.42149 • Published 10 days ago • 46

AnchorComplete: Recovering Complete Scene Meshes from Partial Point Clouds

Paper • 2611.03228 • Published 7 days ago • 12

upvoted 4 papers 3 days ago

SleuthVLM: Do We Really Need Audio-in-Video for Omni Video Understanding?

Paper • 2611.06083 • Published 5 days ago • 8

Human-to-Robot Transfer via Bridging Representation and Action Space in VLAs

Paper • 2611.04391 • Published 6 days ago • 17

PyRUA-DataFarm: LLM Agent as a Cost-Efficient Teleoperator for Real-Ready Robot Data

Paper • 2611.05320 • Published 5 days ago • 27

GameVerse: A Minute-Scale Gameplay Dataset for Long-Horizon Interactive World Modeling

Paper • 2610.37257 • Published 9 days ago • 38

upvoted a paper 4 days ago

PhotoGuider: Composition-Aware Cropping and 360^{circ} View Framing with Explainable Photographic Assessments

Paper • 2611.02897 • Published 7 days ago • 39