ekellbuch (Kelly Buchanan)

upvoted 6 papers 3 months ago

upvoted an article 3 months ago

Article

SmolLM - blazingly fast and remarkably powerful

Jul 16, 2024

•

428

upvoted 2 articles 4 months ago

Article

SmolLM3: smol, multilingual, long-context reasoner

Jul 8

•

732

Article

Reachy Mini - The Open-Source Robot for Today's and Tomorrow's AI Builders

Jul 9

•

720

upvoted 2 papers 8 months ago

Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation

Paper • 2503.16430 • Published Mar 20 • 34

Kimi k1.5: Scaling Reinforcement Learning with LLMs

Paper • 2501.12599 • Published Jan 22 • 125

upvoted 2 papers 9 months ago

Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models

Paper • 2503.09573 • Published Mar 12 • 73

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Paper • 2502.06703 • Published Feb 10 • 153

upvoted an article over 1 year ago

Article

Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth

Jul 29, 2024

•

364

upvoted 2 papers over 1 year ago

FeatUp: A Model-Agnostic Framework for Features at Any Resolution

Paper • 2403.10516 • Published Mar 15, 2024 • 16

EMO: Emote Portrait Alive - Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions

Paper • 2402.17485 • Published Feb 27, 2024 • 196

Kelly Buchanan

AI & ML interests

Organizations

Pathologies of Predictive Diversity in Deep Ensembles

Archon: An Architecture Search Framework for Inference-Time Techniques

Brain-to-Text Benchmark '24: Lessons Learned

Shrinking the Generation-Verification Gap with Weak Verifiers

Emergence of Segmentation with Minimalistic White-Box Transformers

What's in a Prior? Learned Proximal Networks for Inverse Problems

SmolLM - blazingly fast and remarkably powerful

SmolLM3: smol, multilingual, long-context reasoner

Reachy Mini - The Open-Source Robot for Today's and Tomorrow's AI Builders

Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation

Kimi k1.5: Scaling Reinforcement Learning with LLMs

Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth

FeatUp: A Model-Agnostic Framework for Features at Any Resolution

EMO: Emote Portrait Alive - Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions

Kelly Buchanan

AI & ML interests

Organizations

ekellbuch's activity

SmolLM - blazingly fast and remarkably powerful

SmolLM3: smol, multilingual, long-context reasoner

Reachy Mini - The Open-Source Robot for Today's and Tomorrow's AI Builders

Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth