SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement
Paper
•
2504.07934
•
Published
•
21
Kelly Buchanan PRO
ekellbuch
AI & ML interests
Robustness, Computational Neuroscience.
Recent Activity
published
a dataset
4 months ago
ekellbuch/sentido_fisico
updated
a dataset
4 months ago
ekellbuch/0izbaj2i
Organizations
upvoted
a
paper
1 day ago
upvoted
6
papers
4 months ago
Pathologies of Predictive Diversity in Deep Ensembles
Paper
•
2302.00704
•
Published
•
1
Archon: An Architecture Search Framework for Inference-Time Techniques
Paper
•
2409.15254
•
Published
•
1
Brain-to-Text Benchmark '24: Lessons Learned
Paper
•
2412.17227
•
Published
•
1
Shrinking the Generation-Verification Gap with Weak Verifiers
Paper
•
2506.18203
•
Published
•
2
Emergence of Segmentation with Minimalistic White-Box Transformers
Paper
•
2308.16271
•
Published
•
16
What's in a Prior? Learned Proximal Networks for Inverse Problems
Paper
•
2310.14344
•
Published
•
2
upvoted
3
articles
5 months ago
Article
SmolLM - blazingly fast and remarkably powerful
- +1
•
438
Article
SmolLM3: smol, multilingual, long-context reasoner
- +21
•
746
Article
Reachy Mini - The Open-Source Robot for Today's and Tomorrow's AI Builders
•
759
upvoted
3
papers
10 months ago
Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation
Paper
•
2503.16430
•
Published
•
34
Kimi k1.5: Scaling Reinforcement Learning with LLMs
Paper
•
2501.12599
•
Published
•
126
Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models
Paper
•
2503.09573
•
Published
•
74
upvoted
a
paper
11 months ago
upvoted
an
article
over 1 year ago
Article
Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth
•
365