LAS @ ETH Zurich

https://las.inf.ethz.ch

AI & ML interests

None defined yet.

Recent Activity

rikelue authored a paper 14 days ago

Apertus 1.5: From Open Text Models to Open Multimodal Reasoners

rikelue authored a paper 14 days ago

Reinforcement Learning via Self-Distillation

rikelue authored a paper 14 days ago

Apertus: Democratizing Open and Compliant LLMs for Global Language Environments

View all activity

Papers

Aligning Language Models from User Interactions

Reinforcement Learning via Self-Distillation

View all Papers

authored 3 papers 14 days ago

Apertus 1.5: From Open Text Models to Open Multimodal Reasoners

Paper • 2610.15542 • Published 26 days ago • 40

Reinforcement Learning via Self-Distillation

Paper • 2601.20802 • Published Jan 28 • 52

Apertus: Democratizing Open and Compliant LLMs for Global Language Environments

Paper • 2509.14233 • Published Sep 17, 2025 • 25

authored a paper 4 months ago

Partition, Prompt, Aggregate: Statistical Self-Consistency in Language Models

Paper • 2607.15277 • Published Jul 16 • 5

submitted a paper to Daily Papers 4 months ago

Partition, Prompt, Aggregate: Statistical Self-Consistency in Language Models

Paper • 2607.15277 • Published Jul 16 • 5

authored a paper 8 months ago

Aligning Language Models from User Interactions

Paper • 2603.12273 • Published Feb 18

updated a collection 8 months ago

Self-Distillation

3 items • Updated Mar 17 • 1

authored a paper 8 months ago

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

Paper • 2602.21320 • Published Feb 24 • 12

authored 2 papers 9 months ago

Post-hoc Probabilistic Vision-Language Models

Paper • 2412.06014 • Published Dec 8, 2024 • 1

Reinforcement Learning via Self-Distillation

Paper • 2601.20802 • Published Jan 28 • 52

authored a paper 9 months ago

Self-Distillation Enables Continual Learning

Paper • 2601.19897 • Published Jan 27 • 40

updated a collection 9 months ago

Self-Distillation

3 items • Updated Mar 17 • 1

authored a paper 9 months ago

Reinforcement Learning via Self-Distillation

Paper • 2601.20802 • Published Jan 28 • 52

submitted a paper to Daily Papers 9 months ago

Reinforcement Learning via Self-Distillation

Paper • 2601.20802 • Published Jan 28 • 52

in lasgroup/verifiable-corpus about 1 year ago

Improve dataset card: Add HF paper link, GitHub link, task categories, tags, sample usage, and citation

#2 opened about 1 year ago by

authored a paper about 1 year ago

Learning on the Job: Test-Time Curricula for Targeted Reinforcement Learning

Paper • 2510.04786 • Published Oct 6, 2025 • 3

updated a dataset about 1 year ago

lasgroup/verifiable-corpus

Viewer • Updated Oct 9, 2025 • 90.7k • 164 • 2

updated a collection about 1 year ago

Test-Time Curricula for Targeted RL

6 items • Updated Oct 7, 2025

updated a collection about 1 year ago

Test-Time Curricula for Targeted RL (Qwen3-8B)

8 items • Updated Oct 3, 2025