6 papers
DeskCraft: Benchmarking Desktop Agents on Professional Workflows and Human-in-the-Loop Collaboration
Wenkai Wang, Tao Xiong, Jingchen Ni +6
Real-world professional desktop workflows in specialized creative and engineering software unfold over long horizons and often require human-in-the-loop coordination, where agents…
Natural-Language Agent Harnesses
Linyue Pan, Lexiao Zou, Shuo Guo +2
Agent performance is strongly shaped by the surrounding harness: the external execution system around a model that organizes a task run. Yet this logic is usually buried in tightly…
SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture
Haiwen Diao, Penghao Wu, Hanming Deng +55
Recent large vision-language models (VLMs) remain fundamentally constrained by a persistent dichotomy: understanding and generation are treated as distinct problems, leading to fra…
Coffee: Controllable Diffusion Fine-tuning
Ziyao Zeng, Jingcheng Ni, Ruyi Liu +1
Text-to-image diffusion models can generate diverse content with flexible prompts, which makes them well-suited for customization through fine-tuning with a small amount of user-pr…
Iris: Integrating Language into Diffusion-based Monocular Depth Estimation
Ziyao Zeng, Jingcheng Ni, Daniel Wang +5
Traditional monocular depth estimation suffers from inherent ambiguity and visual nuisances. We demonstrate that language can enhance monocular depth estimation by providing an add…
HOMER: Homography-Based Efficient Multi-view 3D Object Removal
Jingcheng Ni, Weiguang Zhao, Daniel Wang +4
3D object removal is an important sub-task in 3D scene editing, with broad applications in scene understanding, augmented reality, and robotics. However, existing methods struggle…