Qualcomm

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

1. On Locality and Length Generalization in Visual Reasoning 4 upvotes, #29 of 2026-07-17
2. When Cloud Agents Meet Device Agents: Lessons from Hybrid Multi-Agent Systems 15 upvotes, #25 of 2026-05-29
3. Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models 29 upvotes, #10 of 2026-05-12
4. Reasoning as Compression: Unifying Budget Forcing via the Conditional Information Bottleneck 21 upvotes, #9 of 2026-03-23
5. Efficient Training-Free Multi-Token Prediction via Embedding-Space Probing 7 upvotes, #21 of 2026-03-19
6. Efficient Reasoning on the Edge 17 upvotes, #20 of 2026-03-18
7. ConFu: Contemplate the Future for Better Speculative Sampling 1 upvotes, #22 of 2026-03-11
8. Skip to the Good Part: Representation Structure & Inference-Time Layer Skipping in Diffusion vs. Autoregressive LLMs 3 upvotes, #30 of 2026-03-10
9. On the "Induction Bias" in Sequence Models 4 upvotes, #18 of 2026-02-24
10. PyramidalWan: On Making Pretrained Video Model Pyramidal for Efficient Inference 2 upvotes, #22 of 2026-01-09
11. Multi-Scale Local Speculative Decoding for Image Generation 2 upvotes, #22 of 2026-01-09
12. ReHyAt: Recurrent Hybrid Attention for Video Diffusion Transformers 3 upvotes, #20 of 2026-01-09
13. Masks Can Be Distracting: On Context Comprehension in Diffusion Language Models 1 upvotes, #41 of 2025-12-03
14. Video Reasoning without Training 7 upvotes, #21 of 2025-10-22
15. SwiftEdit: Lightning Fast Text-Guided Image Editing via One-Step Diffusion 30 upvotes, #6 of 2024-12-09

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.