Starstrek

Stars321123's activity

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

upvoted a paper about 9 hours ago

Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction

Paper • 2605.05242 • Published 8 days ago • 79

upvoted a paper 1 day ago

Audio-Visual Intelligence in Large Foundation Models

Paper • 2605.04045 • Published 6 days ago • 26

upvoted an article 2 days ago

view article

Article

Introducing SyGra Studio

• 

Feb 5

•

27

upvoted 5 papers 2 days ago

Continuous-Time Distribution Matching for Few-Step Diffusion Distillation

Paper • 2605.06376 • Published 4 days ago • 24

Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning

Paper • 2605.06130 • Published 4 days ago • 64

When to Trust Imagination: Adaptive Action Execution for World Action Models

Paper • 2605.06222 • Published 4 days ago • 37

The Granularity Axis: A Micro-to-Macro Latent Direction for Social Roles in Language Models

Paper • 2605.06196 • Published 4 days ago • 5

MARBLE: Multi-Aspect Reward Balance for Diffusion RL

Paper • 2605.06507 • Published 4 days ago • 35

upvoted a collection 2 days ago

WTF GENIUS PAPERS

Collection

Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models. • 124 items • Updated about 22 hours ago • 19

upvoted 2 papers 2 days ago

Continuous Latent Diffusion Language Model

Paper • 2605.06548 • Published 4 days ago • 62

SkillOS: Learning Skill Curation for Self-Evolving Agents

Paper • 2605.06614 • Published 4 days ago • 33

upvoted 2 papers 3 days ago

MiA-Signature: Approximating Global Activation for Long-Context Understanding

Paper • 2605.06416 • Published 4 days ago • 49

Stream-R1: Reliability-Perplexity Aware Reward Distillation for Streaming Video Generation

Paper • 2605.03849 • Published 6 days ago • 117

upvoted a collection 3 days ago

RLDX-1

Collection

RLDX-1 : General-purpose robotics foundation model for dexterous manipulation. • 11 items • Updated 4 days ago • 17

upvoted a paper 3 days ago

RLDX-1 Technical Report

Paper • 2605.03269 • Published 6 days ago • 105

upvoted 2 collections 3 days ago

Fine tuning

Collection

25 items • Updated 8 days ago • 2

Reasoning

Collection

109 items • Updated 3 days ago • 3

upvoted 2 papers 3 days ago

Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems

Paper • 2605.04018 • Published 6 days ago • 31

HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation

Paper • 2604.28196 • Published 11 days ago • 70

upvoted an article 4 days ago

view article

Article

Make and publish your Reachy Mini App

• 

Dec 3, 2025

•

42