Shilin Yan

WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs

Diffusion Language Model Knows the Answer Before It Decodes

Beyond Scattered Acceptance: Fast and Coherent Inference for DLMs via Longest Stable Prefixes

Jarvis: Towards Personalized AI Assistant via Personal KV-Cache Retrieval

CrossLMM: Decoupling Long Video Sequences from LMMs via Dual Cross-Attention Mechanisms

Adaptive Classifier-Free Guidance via Dynamic Low-Confidence Masking

T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT

UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens

A Sanity Check for AI-generated Image Detection

MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning

GoT: Unleashing Reasoning Capability of MLLM for Visual Generation and Editing

DynaPrompt: Dynamic Test-Time Prompt Tuning

General Compression Framework for Efficient Transformer Object Tracking

Closed-loop Scaling Up for Visual Object Tracking

111

xxxx