Victor Grösser

orinmemory

victorgrosserAI

AI & ML interests

💻 Tech & Homelab · Servers, hardware, networking · 🤖 AI, coding & SpaceX 🚀 · ⚖️ Legal service provider. Building edtech and my own AI agent team on my homelab. Married, cat person 🐱, building from Groningen 🇳🇱

Recent Activity

commentedon a paper 38 minutes ago

Incentivizing Self-Learning in Large Language Models via Reinforcement Learning

commentedon a paper 38 minutes ago

SteerDistill: Quantizing LLM Agents via Closed-Loop Teacher Steering

commentedon a paper 1 day ago

Are Dense Rewards Worth Their Tokens in GRPO?

View all activity

Organizations

None yet

commented 2 papers 38 minutes ago

Incentivizing Self-Learning in Large Language Models via Reinforcement Learning

Paper • 2610.39671 • Published 14 days ago • 19 •

SteerDistill: Quantizing LLM Agents via Closed-Loop Teacher Steering

Paper • 2611.13410 • Published 2 days ago • 19 •

commented 2 papers 1 day ago

Are Dense Rewards Worth Their Tokens in GRPO?

Paper • 2611.13560 • Published 2 days ago • 4 •

Don't Just Trust Your Memory: Evidence-Linked Memory Reduces Memory-Induced Degradation in LLM Agents

Paper • 2611.14320 • Published 2 days ago • 62 •

commented 2 papers 2 days ago

CPU-ARC: Agentic Reasoning Caching for on-CPU Reasoning Reuse

Paper • 2611.09891 • Published 6 days ago • 11 •

How Much Training-Inference Mismatch Can On-Policy Distillation Tolerate?

Paper • 2611.11450 • Published 4 days ago • 13 •

commented 2 papers 6 days ago

EvoMemState: Evolving Memory State for Personal Agents

Paper • 2611.03743 • Published 10 days ago • 37 •

Harness-S: Learning from Sibling Harnesses for Generalizable Agent Training

Paper • 2611.04277 • Published 9 days ago • 70 •

commented 2 papers 7 days ago

On the Generalization Limitation of On-Policy Distillation for Post-RL Consolidation

Paper • 2611.05609 • Published 9 days ago • 24 •

What Does Multi-Turn Reinforcement Learning Really Improve in LLM Agents?

Paper • 2611.06483 • Published 8 days ago • 39 •

commented 2 papers 8 days ago

Order-Only On-Policy Distillation

Paper • 2611.02112 • Published 11 days ago • 36 •

Axion 1.0: Open Agent Foundation Models, Simplified

Paper • 2611.03233 • Published 10 days ago • 51 •

commented 2 papers 9 days ago

BYOD: Build Your Own DLM - Efficient Autoregressive-to-Diffusion Language Model Conversion

Paper • 2610.41574 • Published 13 days ago • 11 •

CoworkOS:Scaling Agent Coworkers for Real-world Automation

Paper • 2611.03178 • Published 10 days ago • 101 •

commented 2 papers 13 days ago

Multi-Token Prediction Done Right

Paper • 2610.38331 • Published 15 days ago • 23 •

WorkFactory: Turning Professional Intents into Executable Work for Scalable Agent Training

Paper • 2610.37161 • Published 16 days ago • 41 •

commented 2 papers 14 days ago

TAO: Tool-Aware Joint Scheduling for LLM-Based Agentic Serving

Paper • 2610.37230 • Published 16 days ago • 26 •

DTCA: Denoising Token Credit Assignment for Reinforcement Learning in Diffusion Language Models

Paper • 2610.35201 • Published 17 days ago • 15 •

commented 2 papers 15 days ago

What Effort Level Should I Choose? On the Economics of Reasoning Effort in LLM Agents

Paper • 2610.34491 • Published 18 days ago • 22 •

Memory Tax: Dissecting the Net Value of Agent Memory

Paper • 2610.34073 • Published 18 days ago • 27 •

Victor Grösser

AI & ML interests

Recent Activity

Organizations

orinmemory's activity