Finn Reyes

finnreyes's activity

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

upvoted 4 papers about 4 hours ago

IDEAgent: Agentic Quality-Diversity Search for Research Idea Generation

Paper • 2607.22375 • Published 5 days ago • 8

LAMAR: An Open Language-Aware Multilingual Alignment Reranker

Paper • 2607.22042 • Published 5 days ago • 13

VisCo: Leveraging Large Language Models as Intrinsic Encoders for Visual Token Compression

Paper • 2607.12756 • Published 15 days ago • 3

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills

Paper • 2607.22529 • Published 5 days ago • 38

upvoted 2 papers 1 day ago

Beyond Relevance-Centric Retrieval: Rubric-Oriented Document Set Selection and Ranking

Paper • 2607.19747 • Published 7 days ago • 31

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD

Paper • 2607.20145 • Published 7 days ago • 70

upvoted 2 papers 2 days ago

Two-Level Meta-Rubrics for Evaluating Open-Ended Generation: GAMUT, a Benchmark for Factual Completeness

Paper • 2607.19322 • Published 8 days ago • 9

Trajectory-aware Cross-view Geo-localization with Sequential Observations

Paper • 2607.15491 • Published 13 days ago • 8

upvoted 3 papers 3 days ago

KnowAct-GUIClaw: Know Deeply, Act Perfectly, Personal GUI Assistant with Self-Evolving Memory and Skill

Paper • 2607.12625 • Published 14 days ago • 80

DiffGI: Differentiable Geometry Images for High-Fidelity Thin-Shell 3D Generation

Paper • 2607.13365 • Published 14 days ago • 20

ISO: An RLVR-Native Optimization Stack

Paper • 2607.19331 • Published 8 days ago • 8

upvoted 4 papers 4 days ago

MetaView: Monocular Novel View Synthesis with Scale-Aware Implicit Geometry Priors

Paper • 2607.12000 • Published 16 days ago • 39

TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs

Paper • 2607.17423 • Published 10 days ago • 165

Hallo4D: Multi-Modal Hallucination Mitigation for Consistent Spatio-Temporal Generation

Paper • 2607.12752 • Published 14 days ago • 20

ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU

Paper • 2607.19191 • Published 8 days ago • 302

upvoted 3 papers 6 days ago

VideoRAE: Taming Video Foundation Models for Generative Modeling via Representation Autoencoders

Paper • 2607.14088 • Published 14 days ago • 14

Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectories

Paper • 2607.15330 • Published 13 days ago • 70

On-Policy Delta Distillation

Paper • 2607.15161 • Published 13 days ago • 38

upvoted 2 papers 7 days ago

xHC: Expanded Hyper-Connections

Paper • 2607.14530 • Published 13 days ago • 56

RAGU: A Multi-Step GraphRAG Engine with a Compact Domain-Adapted LLM

Paper • 2607.11683 • Published 16 days ago • 146