PaperHub
影响力指数
96.69/100
前 0.2%
全站排名 #106
发表论文107 篇
平均评分5.5
年均产出35.7 篇/年

Yu Qiao

Principal Researcher@Shanghai Aritifcal Intelligence Laboratory·中国·OpenReview
研究方向

AI safety · Multimodal Large Models · foundation models · video action recognition and detection · face analysis and modeling

6.8
21

ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data

ICLR 2026Oral
6.7
23

CineTrans: Learning to Generate Videos with Cinematic Transitions via Masked Diffusion Models

ICLR 2026Poster
三作
6.5
16

VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling

ICLR 2026Poster
5.6
15

ExpVid: A Benchmark for Experiment Video Understanding & Reasoning

ICLR 2026Poster
5.5
13

MetaCaptioner: Towards Generalist Visual Captioning with Open-source Suites

ICLR 2026Poster
5.5
28

InternSVG: Towards Unified SVG Tasks with Multimodal Large Language Models

ICLR 2026Poster
5.5
12

InternSpatial: A Comprehensive Dataset for Spatial Reasoning in Vision-Language Models

ICLR 2026Poster
5.3
17

RRVF: Visual Reinforcement Learning with Reasoning, Rendering, and Visual Feedback

ICLR 2026Rejected
通讯
5.0
17

Lumina-OmniLV: A Unified Multimodal Framework for General Low-Level Vision

ICLR 2026Rejected
5.0
19

PICABench: How Far are We from Physical Realistic Image Editing?

ICLR 2026Poster
5.0
25

Vlaser: Vision-Language-Action Model with Synergistic Embodied Reasoning

ICLR 2026Poster
5.0
11

VisualPRM400K: An Effective Dataset for Training Multimodal Process Reward Models

ICLR 2026Poster
5.0
25

GDI-Bench: A Benchmark for General Document Intelligence with Vision and Reasoning Decoupling

ICLR 2026Rejected
通讯
5.0
24

IWR-Bench: Can LVLMs reconstruct interactive webpage from a user interaction video?

ICLR 2026Poster
4.5
20

GenExam: A Multidisciplinary Text-to-Image Exam

ICLR 2026Rejected
4.5
28

Learning Goal-Oriented Language-Guided Navigation with Self-Improving Demonstrations at Scale

ICLR 2026Rejected
4.5
29

RE-Searcher: Robust Agentic Search via Goal-oriented Planning and Self-reflection

ICLR 2026Rejected
通讯
4.4
6

ArtiMuse: Fine-Grained Image Aesthetics Assessment with Joint Scoring and Expert-Level Understanding

ICLR 2026Withdrawn
4.0
4

LIA-X: Interpretable Latent Portrait Animator

ICLR 2026Withdrawn
4.0
13

UniFork: Exploring Modality Alignment for Unified Multimodal Understanding and Generation

ICLR 2026Rejected
4.0
9

Benchmarking Visual Knowledge in Multimodal Large Language Models

ICLR 2026Withdrawn
4.0
5

Lightning Video: Building Compact Diffusion Transformers for High-Fidelity On-Device Video Generation

ICLR 2026Withdrawn
4.0
31

Truly Assessing Fluid Intelligence of Large Language Models through Dynamic Reasoning Evaluation

ICLR 2026Rejected
4.0
23

Learning on the Job: An Experience-Driven Self-Evolving Agent for Long-Horizon Tasks

ICLR 2026Rejected
4.0
4

MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning

ICLR 2026Withdrawn
4.0
11

Sequential Diffusion Language Models

ICLR 2026Rejected
3.3
4

ViCO: A Training Strategy towards Semantic Aware Dynamic High-Resolution

ICLR 2026Withdrawn
8.0
23

REEF: Representation Encoding Fingerprints for Large Language Models

ICLR 2025Oral
8.0
12

Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures

ICLR 2025Spotlight
7.8
21

ArchCAD-400K: A Large-Scale CAD drawings Dataset and New Baseline for Panoptic Symbol Spotting

NeurIPS 2025Poster
7.5
24

DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenes

ICLR 2025Spotlight
7.5
17

OS-ATLAS: Foundation Action Model for Generalist GUI Agents

ICLR 2025Spotlight
通讯
7.5
18

OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text

ICLR 2025Spotlight
7.3
24

ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models

NeurIPS 2025Poster
7.2
21

Lumina-T2X: Scalable Flow-based Large Diffusion Transformer for Flexible Resolution Generation

ICLR 2025Spotlight
6.8
19

VideoChat-R1.5: Visual Test-Time Scaling to Reinforce Multimodal Reasoning by Iterative Perception

NeurIPS 2025Poster
6.5
27

Bootstrapping Language-Guided Navigation Learning with Self-Refining Data Flywheel

ICLR 2025Poster
6.4
20

EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT

NeurIPS 2025Poster
通讯
6.3
26

An Intelligent Agentic System for Complex Image Restoration Problems

ICLR 2025Poster
6.3
19

DocGenome: A Large Benchmark for Multi-Modal Language Models in Real-World Academic Document Understanding

ICLR 2025Rejected
通讯
6.0
28

Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

ICLR 2025Rejected
6.0
19

Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning

ICLR 2025Poster
6.0
40

MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models

ICLR 2025Poster
6.0
13

Point or Line? Using Line-based Representation for Panoptic Symbol Spotting in CAD Drawings

NeurIPS 2025Poster
5.8
38

TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning

ICLR 2025Poster
5.8
24

Maintaining Structural Integrity in Parameter Spaces for Parameter Efficient Fine-tuning

ICLR 2025Poster
5.5
36

FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality

ICLR 2025Poster
5.3
21

Derail Yourself: Multi-turn LLM Jailbreak Attack through self-discovered clues

ICLR 2025Withdrawn
5.3
4

SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model

ICLR 2025Withdrawn
5.3
5

Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training

ICLR 2025Withdrawn
5.3
21

Towards Synergistic, Generalized, and Efficient Dual-System for Robotic Manipulation

ICLR 2025Rejected
通讯
5.2
41

Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation

ICLR 2025Rejected
5.0
12

VEnhancer: Generative Space-Time Enhancement for Video Generation

ICLR 2025Rejected
4.8
7

Linear Attention Sequence Parallelism

ICLR 2025Withdrawn
4.5
5

ToMiE: Towards Modular Growth in Enhanced SMPL Skeleton for 3D Human Gaussians with Animatable Garments

ICLR 2025Withdrawn
4.3
5

Diffusion Transformer Policy

ICLR 2025Withdrawn
4.3
10

OASIS: Open Agents Social Interaction Simulations on a Large Scale

ICLR 2025Rejected
4.0
5

Aligning Anything: Hierarchical Motion Estimation for Video Frame Interpolation

ICLR 2025Withdrawn
4.0
12

I-Lora: Iterative Merging of Routing-Tuned Low-Rank Adapters for Multi-task Learning

ICLR 2025Withdrawn
4.0
5

GMAI-VL & GMAI-VL-5.5M: A Large Vision-Language Model and A Comprehensive Multimodal Dataset Towards General Medical AI

ICLR 2025Withdrawn
3.4
6

SlideChat: A Large Vision-Language Assistant for Whole-Slide Pathology Image Understanding

ICLR 2025Withdrawn
合作者 (20)