Interactive demo
Weekly curation
We do not pretend every paper is revolutionary. Here is a transparent slice of this week: top selections versus near-misses and why they did not make the shortlist.
Selected (sample)
- 93
- 90
- 87
- 86
- 82
- 80
- 78
- 75
Near misses
- 47
METTA: Memory-Enhanced Test-Time Adaptation for Meta-Reinforcement Learning
Below top cut for this week’s automated tranche
- 47
Sensorimotor Alignment: A Platonic Proxy for Embodied Policy Success
Below top cut for this week’s automated tranche
- 45
Direct Pass@$k$ Optimization for Thought Pruning: Balancing Quality and Diversity in Test-Time Reasoning
Below top cut for this week’s automated tranche
- 44
Point-Level Refinable Semantic Mapping for Spatial Understanding
Below top cut for this week’s automated tranche
- 43
Reading, Writing, Sharing, and Interacting with the World through Video
Below top cut for this week’s automated tranche
- 43
What does quantum parameter estimation estimate? A no-go result for true quantity values
Below top cut for this week’s automated tranche
- 43
SCOPE: Scene-graph Construction Optimized by Plan Error-correction for Robot Long-term Planning Datasets
Below top cut for this week’s automated tranche
- 42
Fluctuation-free Quantum Battery Charging Enabled by Bell-like Entangled and Separable Charger States
Below top cut for this week’s automated tranche
- 1Discover — arXiv queries per hot topic
- 2Score — five-factor disruptiveness model
- 3Select — top ~20 + near-miss transparency
- 4Explain — fixed article skeleton for humans
- 5Serve — free HTML + x402 JSON for agents