Technical University of Munich

university

Verified

https://www.tum.de/

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

KristianS7 submitted a paper 1 day ago

Depth-adaptive Inference of Looped Language Models via Continuous Depth Batching

shaghayegh submitted a paper 28 days ago

ContextBias: Controlled Evaluation of Bias Persistence Under Context Shift in Text-to-Image Models

Amr-Hegazy submitted a paper about 1 month ago

Gated Recurrent Transformers: Expressive Depth through Recurrent Modulation

View all activity

Papers

Depth-adaptive Inference of Looped Language Models via Continuous Depth Batching

ContextBias: Controlled Evaluation of Bias Persistence Under Context Shift in Text-to-Image Models

View all Papers

TUM 's papers 23

Submitted by

Kristian Schwethelm

Depth-adaptive Inference of Looped Language Models via Continuous Depth Batching

TUM

Technical University of Munich

Submitted by

kolli

ContextBias: Controlled Evaluation of Bias Persistence Under Context Shift in Text-to-Image Models

TUM

Technical University of Munich

Submitted by

Amr Hegazy

Gated Recurrent Transformers: Expressive Depth through Recurrent Modulation

TUM

Technical University of Munich

Submitted by

kolli

StylisticBias: A Few Human Visual Cues Drive Most Social Biases in MLLMs

TUM

Technical University of Munich

RAM: Reachability Across Morphologies

TUM

Technical University of Munich

Submitted by

Ganlin Zhang

BA-T: An Iterative Transformer for Two-View Bundle Adjustment

TUM

Technical University of Munich

Submitted by

Simon Weber

Functional Attention: From Pairwise Affinities to Functional Correspondences

TUM

Technical University of Munich

GRASP: Gated Regression-Aware Skill Proposer for Self-Improving LLM Agents

TUM

Technical University of Munich

Submitted by

JZPeterPan

RealICU: Do LLM Agents Understand Long-Context ICU Data? A Benchmark Beyond Behavior Imitation

TUM

Technical University of Munich

Submitted by

Zheyu Zhang

Active Tabular Augmentation via Policy-Guided Diffusion Inpainting

TUM

Technical University of Munich

1

Submitted by

Sai Niranjan

Trees to Flows and Back: Unifying Decision Trees and Diffusion Models

TUM

Technical University of Munich

2

Submitted by

Kristian Schwethelm

How Much Is One Recurrence Worth? Iso-Depth Scaling Laws for Looped Language Models

TUM

Technical University of Munich