Felix Tuma

floom's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 1 day ago

Deep Researcher with Test-Time Diffusion

Paper • 2507.16075 • Published 8 days ago • 43

upvoted a paper 5 days ago

Group Sequence Policy Optimization

Paper • 2507.18071 • Published 6 days ago • 233

upvoted a paper 6 days ago

Beyond Context Limits: Subconscious Threads for Long-Horizon Reasoning

Paper • 2507.16784 • Published 7 days ago • 111

upvoted a paper 8 days ago

Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR

Paper • 2507.15778 • Published 9 days ago • 19

updated a collection 8 days ago

PotentialApplication

Collection

31 items • Updated 8 days ago

upvoted a paper 12 days ago

Seq vs Seq: An Open Suite of Paired Encoders and Decoders

Paper • 2507.11412 • Published 15 days ago • 25

upvoted 3 papers 16 days ago

Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data

Paper • 2507.07095 • Published 20 days ago • 53

MIRIX: Multi-Agent Memory System for LLM-Based Agents

Paper • 2507.07957 • Published 19 days ago • 59

Machine Bullshit: Characterizing the Emergent Disregard for Truth in Large Language Models

Paper • 2507.07484 • Published 20 days ago • 16

upvoted a paper 23 days ago

ZeCO: Zero Communication Overhead Sequence Parallelism for Linear Attention

Paper • 2507.01004 • Published 28 days ago • 10

updated a collection 23 days ago

PotentialApplication

Collection

31 items • Updated 8 days ago

upvoted a collection 23 days ago

Skywork-Reward-V2

Collection

Scaling preference data curation to the extreme • 9 items • Updated 26 days ago • 20

upvoted 3 papers 27 days ago

KnowRL: Exploring Knowledgeable Reinforcement Learning for Factuality

Paper • 2506.19807 • Published Jun 24 • 7

Orthogonal Finetuning Made Scalable

Paper • 2506.19847 • Published Jun 24 • 7

Can Large Language Models Capture Human Annotator Disagreements?

Paper • 2506.19467 • Published Jun 24 • 18

upvoted a paper about 1 month ago

EMLoC: Emulator-based Memory-efficient Fine-tuning with LoRA Correction

Paper • 2506.12015 • Published Jun 13 • 4

updated 2 collections about 1 month ago

ShowAndTell

Collection

66 items • Updated Jun 25

PotentialApplication

Collection

31 items • Updated 8 days ago

upvoted a paper about 1 month ago

ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models

Paper • 2505.24864 • Published May 30 • 133