Burny's picture

Burny

BurnyCoder

·

https://burnyverse.com/

AI & ML interests

deep learning, LLMs, interpretability, science, physics

Recent Activity

liked a model about 19 hours ago

Qwen/Qwen2.5-0.5B-Instruct

upvoted a collection about 19 hours ago

upvoted a collection about 19 hours ago

View all activity

Organizations

upvoted 2 collections about 19 hours ago

SmolLM3

12 items • Updated Jul 9, 2025 • 8

🪐 SmolLM

A series of smol LLMs: 135M, 360M and 1.7B. We release base and Instruct models as well as the training corpus and some WebGPU demos • 12 items • Updated May 5, 2025 • 251

upvoted a paper 7 days ago

Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs

Paper • 2605.09063 • Published 11 days ago • 77

upvoted a paper 12 days ago

Recursive Multi-Agent Systems

Paper • 2604.25917 • Published 22 days ago • 270

upvoted a paper 13 days ago

Personalizable Long-Context Symbolic Music Infilling with MIDI-RWKV

Paper • 2506.13001 • Published Jun 16, 2025 • 2

upvoted a collection 25 days ago

DeepSeek-V4

4 items • Updated 25 days ago • 646

upvoted a paper about 1 month ago

In-the-Flow Agentic System Optimization for Effective Planning and Tool Use

Paper • 2510.05592 • Published Oct 7, 2025 • 111

upvoted 2 collections 2 months ago

The Well

A 15TB collection of physics simulation datasets. • 18 items • Updated Mar 24, 2025 • 52

DLM-Scope

Sparse Autoencoders of Diffusion Language Models (Dream-7B, LLaDA-8B) and Large Language Models (Qwen-2.5-7B, LLaMA-3-8B) • 6 items • Updated Feb 5 • 7

upvoted a paper 2 months ago

Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero Data

Paper • 2602.21320 • Published Feb 24 • 12

upvoted a collection 2 months ago

Tool-R0

Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero Data (https://arxiv.org/pdf/2602.21320) • 5 items • Updated Mar 3 • 2

upvoted an article 3 months ago

Article

Uncensor any LLM with abliteration

mlabonne

•

Jun 13, 2024

• 853

upvoted an article 4 months ago

Article

How We Use Claude Code Skills to Run 1,000+ ML Experiments a Day

sionic-ai

•

Dec 8, 2025

• 57

upvoted 2 collections 4 months ago

Waypoint-1

The first real time diffusion world model designed for consumer hardware • 3 items • Updated Jan 30 • 8

Trinity-Large

8 items • Updated Mar 30 • 42

upvoted 2 papers 4 months ago

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models

Paper • 2601.14004 • Published Jan 20 • 48

Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs

Paper • 2402.14740 • Published Feb 22, 2024 • 18

upvoted a collection 5 months ago

Activation Oracles

12 items • Updated Dec 26, 2025 • 18

upvoted a collection 6 months ago

ThinkPRM

Process Reward Models that Think -- https://arxiv.org/abs/2504.16828 • 8 items • Updated Jul 29, 2025 • 6

upvoted a paper 6 months ago

Less is More: Recursive Reasoning with Tiny Networks

Paper • 2510.04871 • Published Oct 6, 2025 • 514