Ömer Kaya's picture

10 130

Ömer Kaya

andthattoo

·

https://twitter.com/andthatto

AI & ML interests

Synthetic data, verifiable information retrieval

Recent Activity

updated a model 4 days ago

driaforall/Tiny-Agent-a-1.5B

liked a model 4 days ago

microsoft/OmniParser-v2.0

reacted to Kseniase's post with 🔥 5 days ago

8 New Applications of Test-Time Scaling We've noticed a huge interest in test-time scaling (TTS), so we decided to explore this concept further. Test-time compute (TTC) refers to the amount of computational power used by an AI model when generating a response. Many researchers are now focused on scaling TTC, as it enables slow, deep "thinking" and step-by-step reasoning, which improves overall models' performance. Here are 8 fresh studies on test-time scaling: 1. https://huggingface.co/papers/2502.05171 Introduces an LM that scales TTC by reasoning in latent space instead of generating more tokens with no special training. Here, a recurrent block to processes information iteratively. 2. https://huggingface.co/papers/2502.04728 Shows how TTS is applied to enhance model's Planning Domain Definition Language (PDDL) reasoning capabilities, which can be used to generate a symbolic world model. 3. https://huggingface.co/papers/2502.06703 Analyzes optimal TTS strategies and shows how small models can outperform much larger ones. 4. https://huggingface.co/papers/2502.04128 Shows how TTS improves expressiveness, timbre consistency and accuracy in speech synthesis with Llasa framework. It also dives into benefits of scaling train-time compute. 5. https://huggingface.co/papers/2502.07154 Suggests a modified training loss for better reasoning of LLMs when scaling TTC. 6. https://huggingface.co/papers/2502.05078 Unifies the strengths of chain, tree, and graph paradigms into one framework that expands reasoning only on necessary subproblems. 7. https://huggingface.co/papers/2502.01839 Explores scaling trends of self-verification and how to improve its capabilities with TTC. 8. https://huggingface.co/papers/2501.14723 Explores how scaling serial compute (iterations) and parallel compute (trajectories), can improve accuracy in real-world software engineering issues. Also, explore our article about TTS for more -> https://huggingface.co/blog/Kseniase/testtimecompute

View all activity

Organizations

andthattoo's activity

upvoted a paper 9 days ago

Competitive Programming with Large Reasoning Models

Paper • 2502.06807 • Published 18 days ago • 60

upvoted a paper 14 days ago

SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model

Paper • 2502.02737 • Published 17 days ago • 187

upvoted an article 17 days ago

Article

DABStep: Data Agent Benchmark for Multi-step Reasoning

18 days ago

• 48

upvoted a paper 17 days ago

SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training

Paper • 2501.17161 • Published 24 days ago • 106

upvoted a paper 27 days ago

ComplexFuncBench: Exploring Multi-Step and Constrained Function Calling under Long-Context Scenario

Paper • 2501.10132 • Published Jan 17 • 19

upvoted a paper 30 days ago

Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training

Paper • 2501.11425 • Published Jan 20 • 91

upvoted a paper 8 months ago

Scaling Synthetic Data Creation with 1,000,000,000 Personas

Paper • 2406.20094 • Published Jun 28, 2024 • 97

upvoted a collection 9 months ago

Function Calling v3

Models fine-tuned for function-calling • 14 items • Updated Apr 27, 2024 • 21

upvoted a paper 9 months ago

RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content

Paper • 2403.13031 • Published Mar 19, 2024 • 1

upvoted a paper about 1 year ago

RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval

Paper • 2401.18059 • Published Jan 31, 2024 • 37