activity
20192026
most citedPoint-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training

118 citations · 173 across the 21 of their papers we have counts for

collaborators

27 papers

cs.AI2026

The Verification Horizon: No Silver Bullet for Coding Agent Rewards

Binghai Wang, Chenlong Zhang, Dayiheng Liu +10

A classical intuition holds that verifying a solution is easier than producing one. For today's coding agents, this intuition is being inverted: as foundation models develop strong…

cs.CV2026

Unified Multimodal Autoregressive Modeling with Shared Context-Visual Tokenizer is Key to Unification

Wujian Peng, Lingchen Meng, Yuxuan Cai +7

Unified Multimodal Modeling aims to integrate visual understanding and generation within a single system. However, existing approaches typically rely on two disparate visual tokeni…

cs.CV2026

HomeWorld: A Unified Floorplan-to-Furnished Framework for Generating Controllable, Densely Interactive Whole-Home Scenes

Wenbo Li, Xiaoliang Ju, Zipeng Qin +2

Indoor scene generation is crucial for robot simulation and modern interior design. However, complex layouts together with scarce 3D scene data make learning-based generation chall…

cs.CV2025

DraCo: Draft as CoT for Text-to-Image Preview and Rare Concept Generation

Dongzhi Jiang, Renrui Zhang, Haodong Li +9

Recent unified multimodal large language models (MLLMs) have shown impressive capabilities, incorporating chain-of-thought (CoT) reasoning for enhanced text-to-image generation. Ho…

cs.CV2025★ 16 cited

Qwen3-VL Technical Report

Shuai Bai, Yuxuan Cai, Ruizhe Chen +61

We introduce Qwen3-VL, the most capable vision-language model in the Qwen series to date, achieving superior performance across a broad range of multimodal benchmarks. It natively…

cs.CV2025

MathCanvas: Intrinsic Visual Chain-of-Thought for Multimodal Mathematical Reasoning

Weikang Shi, Aldrich Yu, Rongyao Fang +11

While Large Language Models (LLMs) have excelled in textual reasoning, they struggle with mathematical domains like geometry that intrinsically rely on visual aids. Existing approa…