Technical University of Munich

Technical University of Munich on Hugging Face Daily Papers: 15 papers, 0 in the top 3 of their day, 0 paper of the day.

  1. Depth-adaptive Inference of Looped Language Models via Continuous Depth Batching 12 upvotes, #17 of 2026-09-28
  2. ContextBias: Controlled Evaluation of Bias Persistence Under Context Shift in Text-to-Image Models 5 upvotes, #30 of 2026-09-01
  3. Gated Recurrent Transformers: Expressive Depth through Recurrent Modulation in Transformers 10 upvotes, #21 of 2026-08-27
  4. StylisticBias: A Few Human Visual Cues Drive Most Social Biases in MLLMs 3 upvotes, #10 of 2026-06-22
  5. Functional Attention: From Pairwise Affinities to Functional Correspondences 2 upvotes, #50 of 2026-06-04
  6. BA-T: An Iterative Transformer for Two-View Bundle Adjustment 2 upvotes, #39 of 2026-06-03
  7. Active Tabular Augmentation via Policy-Guided Diffusion Inpainting 0 upvotes, #55 of 2026-05-14
  8. RealICU: Do LLM Agents Understand Long-Context ICU Data? A Benchmark Beyond Behavior Imitation 8 upvotes, #22 of 2026-05-14
  9. Trees to Flows and Back: Unifying Decision Trees and Diffusion Models 7 upvotes, #13 of 2026-05-04
  10. How Much Is One Recurrence Worth? Iso-Depth Scaling Laws for Looped Language Models 9 upvotes, #12 of 2026-04-28
  11. KV Packet: Recomputation-Free Context-Independent KV Caching for LLMs 10 upvotes, #12 of 2026-04-17
  12. MedOpenClaw: Auditable Medical Imaging Agents Reasoning over Uncurated Full Studies 31 upvotes, #6 of 2026-03-30
  13. FINER: MLLMs Hallucinate under Fine-grained Negative Queries 3 upvotes, #25 of 2026-03-19
  14. sebis at ArchEHR-QA 2026: How Much Can You Do Locally? Evaluating Grounded EHR QA on a Single Notebook 0 upvotes, #45 of 2026-03-17
  15. CLARE: Continual Learning for Vision-Language-Action Models via Autonomous Adapter Routing and Expansion 4 upvotes, #11 of 2026-01-20

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.