Poly Arti

polyarti's activity

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

commented 9 papers about 13 hours ago

e-means: outperforming k-means (in one-tenth the epochs)

Paper • 2611.09501 • Published 5 days ago • 5 •

3

MotionGraphicsBench: Evaluating Motion Graphics Generation with Programmatic Verification

Paper • 2611.10592 • Published 4 days ago • 12 •

3

Creative Priming: Decoupling Process from Product to Escape the Creative Paradox

Paper • 2611.11740 • Published 2 days ago • 2 •

3

All Quiet on the Neural Front: Language Models Do Not Report Injected Pain States

Paper • 2611.10123 • Published 5 days ago • 7 •

5

ReproBridge: Building Reproducibility into ML Research Artifacts

Paper • 2611.08452 • Published 6 days ago • 32 •

3

LCM-Promo: An LLM-Based Uplift Model for Promotion Allocation

Paper • 2610.37570 • Published 15 days ago • 4 •

3

Spatial Harness: Grounding Spatial Reasoning in Executable World States with Physics Engines

Paper • 2611.11344 • Published 3 days ago • 2 •

3

FraudBench: A Legal Evaluation of AI Deception

Paper • 2611.12167 • Published 2 days ago • 2 •

3

onóna: Twin Embeddings with Tied Unembeddings

Paper • 2611.10556 • Published 4 days ago • 3 •

6

commented a paper about 14 hours ago

FlyHash for LLM Agent Memory: An Empirical Validation and a New Application

Paper • 2611.05791 • Published 7 days ago • 5 •

6

commented 8 papers about 16 hours ago

How Many Exposures Does a World Model Need? Learning Unseen Game Mechanics at Test Time

Paper • 2611.12324 • Published 2 days ago • 15 •

3

SkinMind: Equipping Agentic RAG with Human-Inspired Graph Probing for Reliable Dermatology AI

Paper • 2611.08935 • Published 5 days ago • 4 •

3

Toward the Era of Agentic Embodied Intelligence

Paper • 2611.09124 • Published 5 days ago • 50 •

3

Flide: Accelerating Decision Inference with Exact State Forking

Paper • 2610.42148 • Published 12 days ago • 34 •

3

TRIO: Task Refinement with Individual Optimization for Retrieval-Augmented Generation

Paper • 2611.02810 • Published 9 days ago • 9 •

4

Auriga Technical Report: A Task-Agnostic Agent Harness for Zero-Shot Embodied Manipulation

Paper • 2611.01112 • Published 11 days ago • 4 •

3

RidgeFill: Training-Free Late-Layer Cache Fill for Faster Prefill

Paper • 2611.09709 • Published 5 days ago • 2 •

3

onóna: Twin Embeddings with Tied Unembeddings

Paper • 2611.10556 • Published 4 days ago • 3 •

6

commented a paper about 17 hours ago

Static Recovery Is Not Dynamic Stability: Dynamics-Aware Benchmarking of Protein Motif Scaffolding

Paper • 2611.07723 • Published 6 days ago • 2 •

5

commented a paper about 19 hours ago

InfraRSI: Harnessing Recursive Self-Improvement for Training Infrastructure

Paper • 2611.11558 • Published 3 days ago • 27 •

5