Joe Mama

JoeMama123123123's activity

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

upvoted 8 papers about 8 hours ago

Learning to Act with World Models by Valuing What Comes Next

Paper • 2611.12200 • Published 2 days ago • 3

EVAThink: Evidence Sufficiency-Guided Training for Adaptive Thinking in Video Understanding

Paper • 2611.13907 • Published 1 day ago • 2

Tree-Ising: Repairing Language Models with Bit-Level Ising Edits

Paper • 2611.14210 • Published 1 day ago • 58

Shortcuts and Boundaries: Verifiable RL Misalignment and Contextual Safety Learning

Paper • 2611.12865 • Published 3 days ago • 3

Are Dense Rewards Worth Their Tokens in GRPO?

Paper • 2611.13560 • Published 1 day ago • 3

EarthRecord: From Pixels to Land Change with Multimodal Agents over Four Decades of Satellite Imagery

Paper • 2611.12934 • Published 6 days ago • 4

Market-Conditioned JEPA: Learning from Unpredictable Market Shocks

Paper • 2611.13572 • Published 1 day ago • 4

ProTEUS: A mutation-resolved world model for closed-loop protein evolution

Paper • 2611.13348 • Published 3 days ago • 9

upvoted a paper about 9 hours ago

MMDM: Measuring Massive Multitask Decision Making

Paper • 2611.14309 • Published 1 day ago • 25

upvoted 5 papers about 11 hours ago

Predictive Surprise as Self-Grounding Concept Bottleneck for Interpretable Time Series

Paper • 2611.12955 • Published 5 days ago • 3

DepthGraft: Structural Regularization through Hierarchical Cross-Layer KV Reconstruction

Paper • 2611.03142 • Published 10 days ago • 12

ExRL: Sample-Efficient Online Adaptation of Long-Chunk Policies via Execution Length Control

Paper • 2611.13482 • Published 1 day ago • 4

Few-Step Streaming Video Generation via Condition Shifting

Paper • 2611.14033 • Published 1 day ago • 42

dNaViT: Discrete Codes are General-Purpose Visual Representations

Paper • 2611.12426 • Published 3 days ago • 32

upvoted 3 papers about 13 hours ago

AutoVend: Benchmarking LLM Agents on Long-Horizon Autonomous Vending Operations

Paper • 2610.36980 • Published 15 days ago • 8

InfraRSI: Harnessing Recursive Self-Improvement for Training Infrastructure

Paper • 2611.11558 • Published 3 days ago • 28

Longtail-SWE: High-Quality SWE Tasks for Underrepresented Languages

Paper • 2611.10304 • Published 5 days ago • 20

upvoted 3 papers 1 day ago

Training Vision Transformers to Focus: Emergence of Spatial Attention Head Specialization

Paper • 2611.11890 • Published 3 days ago • 4

InstantHMR : Real-Time Human Mesh Recovery on Your Phone

Paper • 2611.09195 • Published 5 days ago • 2

Stochastic Deep Supervision for Gallery-Consistent Early-Exit Face Recognition

Paper • 2611.09987 • Published 10 days ago • 2