Qualcomm

company

Verified

https://www.qualcomm.com/artificial-intelligence

AI & ML interests

We’re scaling AI to create new possibilities.

Recent Activity

qaihm-bot updated a model about 16 hours ago

qualcomm/Depth-Anything

qaihm-bot updated a model about 16 hours ago

qualcomm/Whisper-Small-Quantized

qaihm-bot updated a model about 16 hours ago

qualcomm/Llama3-TAIDE-LX-8B-Chat-Alpha1

View all activity

Papers

Efficient Training-Free Multi-Token Prediction via Embedding-Space Probing

Efficient Reasoning on the Edge

View all Papers

qualcomm 's Papers 13

Submitted by

Raghavv Goel

Efficient Training-Free Multi-Token Prediction via Embedding-Space Probing

qualcomm

Submitted by

taesiri

Efficient Reasoning on the Edge

qualcomm

Submitted by

Raghavv Goel

ConFu: Contemplate the Future for Better Speculative Sampling

qualcomm

Submitted by

Fabio Valerio Massoli

Reasoning as Compression: Unifying Budget Forcing via the Conditional Information Bottleneck

qualcomm

2

Submitted by

Raghavv Goel

Skip to the Good Part: Representation Structure & Inference-Time Layer Skipping in Diffusion vs. Autoregressive LLMs

qualcomm

Submitted by

M.Reza Ebrahimi

On the "Induction Bias" in Sequence Models

qualcomm

2

Submitted by

Amir Habibian

Multi-Scale Local Speculative Decoding for Image Generation

qualcomm

4

Submitted by

Amir Habibian

PyramidalWan: On Making Pretrained Video Model Pyramidal for Efficient Inference

qualcomm

3

Submitted by

Amir Habibian

ReHyAt: Recurrent Hybrid Attention for Video Diffusion Transformers

qualcomm

6

Submitted by

Julianna Piskorz

Masks Can Be Distracting: On Context Comprehension in Diffusion Language Models

qualcomm

2

Submitted by

Deepak Sridhar

Video Reasoning without Training

qualcomm

Attention Surgery: An Efficient Recipe to Linearize Your Video Diffusion Transformer

qualcomm

Submitted by

Thuan Nguyen Hoang

SwiftEdit: Lightning Fast Text-Guided Image Editing via One-Step Diffusion

qualcomm