0

Haodong Li

Papers
19

Cite

Notes

Only stored in your browser.

Attribution

Affiliations & profile
Semantic Scholar
Attribution policy →
19papers

Authored papers

19

Auto-Rubric as Reward: From Implicit Preferences to Explicit Multimodal Generative Criteria

arXiv 2026

2026

DVD: Deterministic Video Depth Estimation with Generative Priors

arXiv 2026

2026

Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion

arXiv 2026

2026

SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments

arXiv 2026

2026

Proact-VL: A Proactive VideoLLM for Real-Time AI Companions

arXiv 2026

2026

UniM: A Unified Any-to-Any Interleaved Multimodal Benchmark

arXiv 2026

2026

WebVR: Benchmarking Multimodal LLMs for WebPage Recreation from Videos via Human-Aligned Visual Rubrics

arXiv 2026

2026

GEBench: Benchmarking Image Generation Models as GUI Environments

arXiv 2026

2026

PEARL: Personalized Streaming Video Understanding Model

arXiv 2026

2026

GENIUS: Generative Fluid Intelligence Evaluation Suite

arXiv 2026

2026

CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation

arXiv 2026

2026

How Well Do Models Follow Visual Instructions? VIBE: A Systematic Benchmark for Visual Instruction-Driven Image Editing

arXiv 2026

2026

Chain of Mindset: Reasoning with Adaptive Cognitive Modes

arXiv 2026

2026

Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation

arXiv 2025

2025

Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model

arXiv 2025

2025

DA^2: Depth Anything in Any Direction

arXiv 2025

2025

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

arXiv 2025

2025

Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction

arXiv 2024

2024

LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching

CVPR 2024 1

2023

Affiliations

No known affiliations.

Frequent co-authors

10

from 19 papers