Jie Zhou

UME-R1: Exploring Reasoning-Driven Generative Multimodal Embeddings

Exploring Specular Reflection Inconsistency for Generalizable Face Forgery Detection

SpaceR: Reinforcing MLLMs in Video Spatial Reasoning

DeepRAG: Thinking to Retrieve Step by Step for Large Language Models

RewardAnything: Generalizable Principle-Following Reward Models

LaCo: Efficient Layer-wise Compression of Visual Tokens for Multimodal Large Language Models

Continuous Autoregressive Language Models

Improving Multi-step RAG with Hypergraph-based Memory

Beyond Next Token Prediction: Patch-Level Training for Large Language Models

Efficient Speech Language Modeling via Energy Distance in Continuous Latent Space

DelTA: An Online Document-Level Translation Agent Based on Multi-Level Memory

MiniPLM: Knowledge Distillation for Pre-training Language Models

Continuous Visual Autoregressive Generation via Score Maximization

AVG-LLaVA: A Large Multimodal Model with Adaptive Visual Granularity

MaskMamba: A Hybrid Mamba-Transformer Model for Masked Image Generation

DynST: Large-Scale Spatial-Temporal Dataset for Transferable Traffic Forecasting with Dynamic Road Networks

POINTS: Improving Your Vision-language Model with Affordable Strategies

Bridging the Reality Gap: A Benchmark for Physical Reasoning in General World Models with Various Physical Phenomena beyond Mechanics

The Stochastic Parrot on LLM’s Shoulder: A Summative Assessment of Physical Concept Understanding

Comprehensive Artistic Style Representation for Quantitative Evaluation