Kaipeng Zhang

Perception or Prejudice: Can MLLMs Go Beyond First Impressions of Personality?

arXiv 2026

LongCLI-Bench: A Preliminary Benchmark and Study for Long-horizon Agentic Programming in Command-Line Interfaces

arXiv 2026

MeepleLM: A Virtual Playtester Simulating Diverse Subjective Experiences

arXiv 2026

World Craft: Agentic Framework to Create Visualizable Worlds via Text

arXiv 2026

WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG

arXiv 2026

PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference

arXiv 2026

PyVision-RL: Forging Open Agentic Vision Models via RL

arXiv 2026

InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

arXiv 2025

Sekai: A Video Dataset towards World Exploration

arXiv 2025

Think or Not Think: A Study of Explicit Thinking in Rule-Based Visual Reinforcement Fine-Tuning

arXiv 2025

Enhance-A-Video: Better Generated Video for Free

arXiv 2025

Yume-1.5: A Text-Controlled Interactive World Generation Model

arXiv 2025

InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

arXiv 2025

Neural-Driven Image Editing

arXiv 2025

OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling

arXiv 2025

PyVision: Agentic Vision with Dynamic Tooling

arXiv 2025

TIR-Bench: A Comprehensive Benchmark for Agentic Thinking-with-Images Reasoning

arXiv 2025

Symbolic Graphics Programming with Large Language Models

arXiv 2025

REPA Works Until It Doesn't: Early-Stopped, Holistic Alignment Supercharges Diffusion Training

arXiv 2025

InMind: Evaluating LLMs in Capturing and Applying Individual Human Reasoning Styles

arXiv 2025

SVBench: Evaluation of Video Generation Models on Social Reasoning

arXiv 2025

Improving Autoregressive Image Generation through Coarse-to-Fine Token Prediction

arXiv 2025

ARMOR v0.1: Empowering Autoregressive Multimodal Understanding Model with Interleaved Multimodal Generation via Asymmetric Synergy

arXiv 2025

LeX-Art: Rethinking Text Generation via Scalable High-Quality Data Synthesis

arXiv 2025

Neighboring Autoregressive Modeling for Efficient Visual Generation

ICCV 2025

MDK12-Bench: A Multi-Discipline Benchmark for Evaluating Reasoning in Multimodal Large Language Models

mdk12-bench-a-multi-discipline-benchmark-for

ProJudge: A Multi-Modal Multi-Discipline Benchmark and Instruction-Tuning Dataset for MLLM-based Process Judges

ICCV 2025

Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiT

arXiv 2024

Needle In A Multimodal Haystack

arXiv 2024

EfficientQAT: Efficient Quantization-Aware Training for Large Language Models

arXiv 2024

SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models

arXiv 2024

OpenING: A Comprehensive Benchmark for Judging Open-ended Interleaved Image-Text Generation

CVPR 2025 1

T3M: Text Guided 3D Human Motion Synthesis from Speech

arXiv 2024

DiffAgent: Fast and Accurate Text-to-Image API Selection with Large Language Model

CVPR 2024 1

BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation

arXiv 2024

Dynamic Multimodal Evaluation with Flexible Complexity by Vision-Language Bootstrapping

arXiv 2024

Rethinking Human Evaluation Protocol for Text-to-Video Models: Enhancing Reliability,Reproducibility, and Practicality

arXiv 2024

ChartAssisstant: A Universal Chart Multimodal Language Model via Chart-to-Table Pre-training and Multitask Instruction Tuning

arXiv 2024

Diffree: Text-Guided Shape Free Object Inpainting with Diffusion Model

arXiv 2024

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

arXiv 2024

ZipAR: Accelerating Auto-regressive Image Generation through Spatial Locality

arXiv 2024

Adapting LLaMA Decoder to Vision Transformer

arXiv 2024

HRVMamba: High-Resolution Visual State Space Model for Dense Prediction

arXiv 2024

ImageBind-LLM: Multi-modality Instruction Tuning

arXiv 2023

Meta-Transformer: A Unified Framework for Multimodal Learning

arXiv 2023

Towards Lossless Dataset Distillation via Difficulty-Aligned Trajectory Matching

arXiv 2023

MLLMs-Augmented Visual-Language Representation Learning

arXiv 2023

OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models

arXiv 2023

DiffRate : Differentiable Compression Rate for Efficient Vision Transformers

ICCV 2023 1

OneLLM: One Framework to Align All Modalities with Language

CVPR 2024 1