0

Xin Jin

Papers
41

Cite

Notes

Only stored in your browser.

Attribution

Affiliations & profile
Semantic Scholar
Attribution policy →
41papers

Authored papers

41

D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models

arXiv 2026

2026

LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs

arXiv 2026

2026

VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model

arXiv 2026

2026

Disentangled Robot Learning via Separate Forward and Inverse Dynamics Pretraining

arXiv 2026

2026

ANTS: Adaptive Negative Textual Space Shaping for OOD Detection via Test-Time MLLM Understanding and Reasoning

arXiv 2026

2026

RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-Evolution

arXiv 2026

2026

Speak While Watching: Unleashing TRUE Real-Time Video Understanding Capability of Multimodal Large Language Models

arXiv 2026

2026

SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation

arXiv 2025

2025

Bridging Past and Future: End-to-End Autonomous Driving with Historical Prediction and Planning

CVPR 2025 1

2025

Multi-Layer Visual Feature Fusion in Multimodal LLMs: Methods, Analysis, and Best Practices

CVPR 2025 1

2025

ORV: 4D Occupancy-centric Robot Video Generation

arXiv 2025

2025

Reasoning in Space via Grounding in the World

arXiv 2025

2025

InteractComp: Evaluating Search Agents With Ambiguous Queries

arXiv 2025

2025

DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolution

ICCV 2025

2025

Adaptive Data Exploitation in Deep Reinforcement Learning

arXiv 2025

2025

Distribution Matching Distillation Meets Reinforcement Learning

arXiv 2025

2025

Decoupled DMD: CFG Augmentation as the Spear, Distribution Matching as the Shield

arXiv 2025

2025

Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer

arXiv 2025

2025

DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge

dreamvla-a-vision-language-action-model

2025

OmniNWM: Omniscient Driving Navigation World Models

arXiv 2025

2025

Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance for Self-supervised Monocular Depth Estimation

arXiv 2025

2025

Perceptual Decoupling for Scalable Multi-modal Reasoning via Reward-Optimized Captioning

arXiv 2025

2025

Taming LLMs by Scaling Learning Rates with Gradient Grouping

arXiv 2025

2025

Examining the Source of Defects from a Mechanical Perspective for 3D Anomaly Detection

arXiv 2025

2025

UniScene: Unified Occupancy-centric Driving Scene Generation

CVPR 2025 1

2024

Towards RAW Object Detection in Diverse Conditions

CVPR 2025 1

2024

MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs

arXiv 2024

2024

DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving

arXiv 2024

2024

SUMix: Mixup with Semantic and Uncertain Information

arXiv 2024

2024

A Survey of Resource-efficient LLM and Multimodal Foundation Models

arXiv 2024

2024

Lighting Every Darkness with 3DGS: Fast Training and Real-Time Rendering for HDR View Synthesis

arXiv 2024

2024

A Survey on Mixup Augmentations and Beyond

arXiv 2024

2024

DreamLIP: Language-Image Pre-training with Long Captions

arXiv 2024

2024

MotionBank: A Large-scale Video Motion Benchmark with Disentangled Rule-based Annotations

arXiv 2024

2024

Inpaint Anything: Segment Anything Meets Image Inpainting

arXiv 2023

2023

Automatic Intrinsic Reward Shaping for Exploration in Deep Reinforcement Learning

arXiv 2023

2023

Make Explicit Calibration Implicit: Calibrate Denoiser Instead of the Noise Model

ICCV 2023 1

2023

Generalized Lightness Adaptation with Channel Selective Normalization

ICCV 2023 1

2023

Learning Distortion Invariant Representation for Image Restoration from A Causality Perspective

CVPR 2023 1

2023

NaviNeRF: NeRF-based 3D Representation Disentanglement by Latent Semantic Navigation

ICCV 2023 1

2023

Region Normalization for Image Inpainting

arXiv 2019

2019

Affiliations

No known affiliations.

Frequent co-authors

10

from 41 papers