Felix Tuma

floom

AI & ML interests

NLP

Recent Activity

updated a collection 1 day ago

PotentialApplication

liked a model 4 days ago

Salesforce/Llama-xLAM-2-70b-fc-r

updated a collection 5 days ago

PotentialApplication

View all activity

Organizations

None yet

floom's activity

upvoted a paper 5 days ago

ATLAS: Learning to Optimally Memorize the Context at Test Time

Paper • 2505.23735 • Published 9 days ago • 22

upvoted 2 papers 6 days ago

The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models

Paper • 2505.22617 • Published 10 days ago • 116

On-Policy RL with Optimal Reward Baseline

Paper • 2505.23585 • Published 9 days ago • 14

upvoted a paper 12 days ago

Quartet: Native FP4 Training Can Be Optimal for Large Language Models

Paper • 2505.14669 • Published 18 days ago • 73

upvoted 2 papers 14 days ago

The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning

Paper • 2505.15134 • Published 17 days ago • 6

Reinforcement Learning Finetunes Small Subnetworks in Large Language Models

Paper • 2505.11711 • Published 21 days ago • 10

upvoted a paper 24 days ago

Learning Dynamics in Continual Pre-Training for Large Language Models

Paper • 2505.07796 • Published 26 days ago • 19

upvoted 3 papers 30 days ago

upvoted a paper about 1 month ago

Beyond One-Size-Fits-All: Inversion Learning for Highly Effective NLG Evaluation Prompts

Paper • 2504.21117 • Published Apr 29 • 25

upvoted 4 papers about 2 months ago

Do PhD-level LLMs Truly Grasp Elementary Addition? Probing Rule Learning vs. Memorization in Large Language Models

Paper • 2504.05262 • Published Apr 7 • 11

Reasoning Models Can Be Effective Without Thinking

Paper • 2504.09858 • Published Apr 14 • 11

xVerify: Efficient Answer Verifier for Reasoning Model Evaluations

Paper • 2504.10481 • Published Apr 14 • 84

Heimdall: test-time scaling on the generative verification

Paper • 2504.10337 • Published Apr 14 • 33

upvoted a paper 2 months ago

Agentic Knowledgeable Self-awareness

Paper • 2504.03553 • Published Apr 4 • 28

upvoted 2 papers 3 months ago

Temporal Consistency for LLM Reasoning Process Error Identification

Paper • 2503.14495 • Published Mar 18 • 10

NeoBERT: A Next-Generation BERT

Paper • 2502.19587 • Published Feb 26 • 39

upvoted 2 papers 4 months ago

LIMO: Less is More for Reasoning

Paper • 2502.03387 • Published Feb 5 • 61

APE: Faster and Longer Context-Augmented Generation via Adaptive Parallel Encoding

Paper • 2502.05431 • Published Feb 8 • 6