Finn Reyes

finnreyes's activity

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

upvoted 6 papers about 13 hours ago

Human-in-the-Loop Signature Bootstrapping for UAV Hyperspectral PFM-1 Mine Detection

Paper • 2607.25310 • Published 5 days ago • 3

Agentic Context Management: Solving Agent Memory and Cost by Treating Them as Lifecycle and Architecture Problems

Paper • 2607.21503 • Published 10 days ago • 25

PerceptionBench: Evaluating Atomic Visual Perception in Multimodal Large Language Models

Paper • 2607.24957 • Published 6 days ago • 15

Reasoning Denoiser: Denoising Reasoning Traces for Hallucination Detection in Large Reasoning Models

Paper • 2607.22098 • Published 9 days ago • 8

Robostral Navigate

Paper • 2607.20785 • Published 11 days ago • 11

Data Pyramid for Embodied Manipulation

Paper • 2607.24744 • Published 6 days ago • 36

upvoted 2 papers 1 day ago

Pass the Baton: Trajectory-Relayed On-Policy Distillation

Paper • 2607.26057 • Published 5 days ago • 29

A New Role for Relevance: Guiding Corpus Interaction in Agentic Search

Paper • 2607.24223 • Published 6 days ago • 91

upvoted 2 papers 2 days ago

From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Search

Paper • 2607.24280 • Published 6 days ago • 81

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published 6 days ago • 423

upvoted 4 papers 4 days ago

IDEAgent: Agentic Quality-Diversity Search for Research Idea Generation

Paper • 2607.22375 • Published 9 days ago • 9

LAMAR: An Open Language-Aware Multilingual Alignment Reranker

Paper • 2607.22042 • Published 9 days ago • 16

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

Paper • 2607.12756 • Published 19 days ago • 5

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

Paper • 2607.22529 • Published 9 days ago • 47

upvoted 2 papers 5 days ago

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

Paper • 2607.19747 • Published 11 days ago • 31

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

Paper • 2607.20145 • Published 11 days ago • 72

upvoted 4 papers 6 days ago

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

Paper • 2607.19322 • Published 12 days ago • 9

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

Paper • 2607.15491 • Published 17 days ago • 8

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

Paper • 2607.12625 • Published 18 days ago • 80

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

Paper • 2607.13365 • Published 18 days ago • 20