Robin Williams's picture

Robin Williams PRO

bfuzzy1

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 12 days ago

DDT: Decoupled Diffusion Transformer

updated a collection 26 days ago

upvoted a paper 26 days ago

LogQuant: Log-Distributed 2-Bit Quantization of KV Cache with Superior Accuracy Preservation

View all activity

Organizations

None yet

bfuzzy1's activity

upvoted a paper 12 days ago

DDT: Decoupled Diffusion Transformer

Paper • 2504.05741 • Published 15 days ago • 73

updated a collection 26 days ago

Nifty

32 items • Updated 26 days ago

upvoted a paper 26 days ago

LogQuant: Log-Distributed 2-Bit Quantization of KV Cache with Superior Accuracy Preservation

Paper • 2503.19950 • Published 29 days ago • 11

updated a collection 28 days ago

Nifty

32 items • Updated 26 days ago

upvoted a paper 28 days ago

I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders

Paper • 2503.18878 • Published 30 days ago • 117

upvoted a paper about 1 month ago

START: Self-taught Reasoner with Tools

Paper • 2503.04625 • Published Mar 6 • 110

updated a collection about 1 month ago

Nifty

32 items • Updated 26 days ago

upvoted a paper about 1 month ago

MeshPad: Interactive Sketch Conditioned Artistic-designed Mesh Generation and Editing

Paper • 2503.01425 • Published Mar 3 • 14

updated a collection about 2 months ago

Nifty

32 items • Updated 26 days ago

upvoted 2 papers about 2 months ago

Linguistic Generalizability of Test-Time Scaling in Mathematical Reasoning

Paper • 2502.17407 • Published Feb 24 • 26

Slamming: Training a Speech Language Model on One GPU in a Day

Paper • 2502.15814 • Published Feb 19 • 69

updated a collection 2 months ago

Nifty

32 items • Updated 26 days ago

upvoted a paper 2 months ago

Building A Proof-Oriented Programmer That Is 64% Better Than GPT-4o Under Data Scarsity

Paper • 2502.11901 • Published Feb 17 • 6

updated a collection 2 months ago

Nifty

32 items • Updated 26 days ago

upvoted 4 papers 2 months ago

Dyve: Thinking Fast and Slow for Dynamic Process Verification

Paper • 2502.11157 • Published Feb 16 • 7

CRANE: Reasoning with constrained LLM generation

Paper • 2502.09061 • Published Feb 13 • 19

How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training

Paper • 2502.11196 • Published Feb 16 • 22

SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?

Paper • 2502.12115 • Published Feb 17 • 45

updated a collection 2 months ago

Nifty

32 items • Updated 26 days ago