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 3 hours ago

qualcomm/IBM-Granite-v3.1-8B-Instruct

qaihm-bot updated a model about 3 hours ago

qualcomm/Distil-Bert-Base-Uncased-Hf

qaihm-bot updated a model about 3 hours ago

qualcomm/Falcon3-7B-Instruct

View all activity

Papers

On Locality and Length Generalization in Visual Reasoning

When Cloud Agents Meet Device Agents: Lessons from Hybrid Multi-Agent Systems

View all Papers

qualcomm 's papers 16

Submitted by

M.Reza Ebrahimi

On Locality and Length Generalization in Visual Reasoning

qualcomm

2

Submitted by

Corrado Rainone

When Cloud Agents Meet Device Agents: Lessons from Hybrid Multi-Agent Systems

qualcomm

Submitted by

Fabio Valerio Massoli

Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models

qualcomm

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