Papers6

#fine-tuning

Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics

The paper shows that three popular ways to control language models—fine-tuning a few weights, LoRA, and activation steering—are actually the same kind of action: a dynamic weight update driven by a control knob.

#language model steering#dynamic weight updates#activation steering

Not triaged yet

Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models

Beginner

Zengbin Wang, Xuecai Hu et al.Jan 28arXiv

Text-to-image models draw pretty pictures, but often put things in the wrong places or miss how objects interact.

#text-to-image#spatial intelligence#occlusion

Not triaged yet

EEG Foundation Models: Progresses, Benchmarking, and Open Problems

Intermediate

Dingkun Liu, Yuheng Chen et al.Jan 25arXiv

This paper builds a fair, big playground (a benchmark) to test many EEG foundation models side-by-side on the same rules.

#EEG foundation models#brain-computer interface#self-supervised learning

Not triaged yet

Privacy Collapse: Benign Fine-Tuning Can Break Contextual Privacy in Language Models

Intermediate

Anmol Goel, Cornelius Emde et al.Jan 21arXiv

Benign fine-tuning meant to make language models more helpful can accidentally make them overshare private information.

#contextual privacy#privacy collapse#fine-tuning

Not triaged yet

NitroGen: An Open Foundation Model for Generalist Gaming Agents

Intermediate

Loïc Magne, Anas Awadalla et al.Jan 4arXiv

NitroGen is a vision-to-action AI that learns to play many video games by watching 40,000 hours of gameplay videos from over 1,000 titles with on-screen controller overlays.

#NitroGen#generalist gaming agent#behavior cloning

Not triaged yet

Adaptation of Agentic AI

Intermediate

Pengcheng Jiang, Jiacheng Lin et al.Dec 18arXiv

This paper organizes how AI agents learn and improve into one simple map with four roads: A1, A2, T1, and T2.

#agentic AI#adaptation#A1 A2 T1 T2

Not triaged yet