SenseNova

company

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

pufanyi authored a paper about 3 hours ago

Senses Wide Shut: A Representation-Action Gap in Omnimodal LLMs

weiyukun new activity about 21 hours ago

sensenova/SenseNova-U1.5-8B-MoT-LoRAs:8-step LoRA for the image2image pipeline

weiyukun new activity about 21 hours ago

sensenova/SenseNova-U1.5-8B-MoT-LoRAs:为什么我用这个lora不行呢？

View all activity

Papers

Vision as Unified Multimodal Generation

SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture

View all Papers

Articles

NEO-unify: Building Native Multimodal Unified Models End to End

sensenova 's papers 8

Submitted by

Xuanke Shi

Vision as Unified Multimodal Generation

sensenova

Submitted by

Haiwen Diao

SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture

sensenova

Submitted by

taesiri

Demystifing Video Reasoning

sensenova

Submitted by

Wenwen Tong

SenseNova-MARS: Empowering Multimodal Agentic Reasoning and Search via Reinforcement Learning

sensenova

ConsistCompose: Unified Multimodal Layout Control for Image Composition

sensenova

Submitted by

Zhongang Cai

Scaling Spatial Intelligence with Multimodal Foundation Models

sensenova

Submitted by

yl-1993

Phased DMD: Few-step Distribution Matching Distillation via Score Matching within Subintervals

sensenova

Submitted by

Zhongang Cai

Has GPT-5 Achieved Spatial Intelligence? An Empirical Study

sensenova