Andreas Stöffelbauer

andreasskyscanner's activity

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

upvoted a paper 3 days ago

The Embedder's Dilemma: LLMs Are Better, but at What Cost?

Paper • 2608.12875 • Published 14 days ago • 14

upvoted a paper 10 days ago

Self-Supervised Visual On-Policy Distillation

Paper • 2608.14144 • Published 13 days ago • 169

upvoted a paper 12 days ago

DarwinX: Evolving Agent Harnesses Through Natural Selection

Paper • 2608.07545 • Published 27 days ago • 113

upvoted a paper 14 days ago

On-Policy Self-Distillation without Any Supervision

Paper • 2608.06296 • Published 18 days ago • 217

upvoted a paper 21 days ago

Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes

Paper • 2608.05000 • Published 21 days ago • 62

upvoted a paper 23 days ago

From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement

Paper • 2607.23802 • Published Jul 26 • 106

upvoted 4 papers about 1 month ago

NVIDIA-labs OO Agents: Native Python Object-Oriented Agents

Paper • 2607.20709 • Published Jul 22 • 35

Two-Level Meta-Rubrics for Evaluating Open-Ended Generation: GAMUT, a Benchmark for Factual Completeness

Paper • 2607.19322 • Published Jul 21 • 11

Understanding Reasoning from Pretraining to Post-Training

Paper • 2607.16097 • Published Jul 17 • 29

Linear Attention Architectures: Mechanisms, Trade-offs, and Cross-Layer Routing

Paper • 2607.07953 • Published Jul 8 • 16

upvoted 2 papers about 2 months ago

Quantifying and Expanding the Theoretical Capacity of Late-Interaction Retrieval Models

Paper • 2607.05803 • Published Jul 7 • 10

LLM-as-a-Verifier: A General-Purpose Verification Framework

Paper • 2607.05391 • Published Jul 6 • 18

upvoted 2 papers 2 months ago

Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients

Paper • 2606.18216 • Published Jun 16 • 65

Prompt-Level Distillation: A Non-Parametric Alternative to Model Fine-Tuning for Efficient Reasoning

Paper • 2602.21103 • Published Jun 2 • 9

upvoted 6 papers 3 months ago

Trajectory-Refined Distillation

Paper • 2606.08432 • Published Jun 7 • 7

CORE: Contrastive Reflection Enables Rapid Improvements in Reasoning

Paper • 2605.28742 • Published May 27 • 4

Reinforcement Learning from Rich Feedback with Distributional DAgger

Paper • 2606.05152 • Published Jun 3 • 3

On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters

Paper • 2606.02437 • Published Jun 1 • 243

Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention

Paper • 2605.29548 • Published May 28 • 13

Your Embedding Model is SMARTer Than You Think

Paper • 2605.24938 • Published May 24 • 25