PaperHub

Xiangtai Li

~Xiangtai_Li1

23
论文总数
11.5
年均投稿
6.0
平均评分
接收情况18/23
会议分布
ICLR
11
NeurIPS
9
ICML
3

发表论文 (23 篇)

202516

4.2
5

MG-LLaVA: Towards Multi-Granularity Visual Instruction Tuning

ICLR 2025withdrawn
6.4
4

Conditional Panoramic Image Generation via Masked Autoregressive Modeling

NeurIPS 2025Poster
7.5
4

Both Ears Wide Open: Towards Language-Driven Spatial Audio Generation

ICLR 2025Spotlight
6.2
5

Towards Semantic Equivalence of Tokenization in Multimodal LLM

ICLR 2025Poster
4.0
4

MEDIC: Zero-shot Music Editing with Disentangled Inversion Control

ICLR 2025withdrawn
8.2
5

On Path to Multimodal Generalist: General-Level and General-Bench

ICML 2025Oral
5.0
4

PredFormer: Transformers Are Effective Spatial-Temporal Predictive Learners

ICLR 2025withdrawn
6.3
4

RobuRCDet: Enhancing Robustness of Radar-Camera Fusion in Bird's Eye View for 3D Object Detection

ICLR 2025Poster
5.5
4

Three-Dimensional Trajectory Prediction with 3DMoTraj Dataset

ICML 2025Poster
6.8
4

AdaVideoRAG: Omni-Contextual Adaptive Retrieval-Augmented Efficient Long Video Understanding

NeurIPS 2025Poster
6.4
4

VimoRAG: Video-based Retrieval-augmented 3D Motion Generation for Motion Language Models

NeurIPS 2025Poster
6.0
3

Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis

ICLR 2025Poster
4.3
4

RelationBooth: Towards Relation-Aware Customized Object Generation

ICLR 2025withdrawn
6.6
4

OmniAudio: Generating Spatial Audio from 360-Degree Video

ICML 2025Poster
7.5
4

RMP-SAM: Towards Real-Time Multi-Purpose Segment Anything

ICLR 2025Oral
7.8
4

MERIT: Multilingual Semantic Retrieval with Interleaved Multi-Condition Query

NeurIPS 2025Poster