Yunpu Ma

StreamingThinker: Large Language Models Can Think While Reading

MINED: Probing and Updating with Multimodal Time-Sensitive Knowledge for Large Multimodal Models

Beyond Magic Words: Sharpness-Aware Prompt Evolving for Robust Large Language Models with TARE

HiDrop: Hierarchical Vision Token Reduction in MLLMs via Late Injection, Concave Pyramid Pruning, and Early Exit

Reasoning Self-Evaluation via Trajectory Dynamics Modeling

The Few Govern the Many:Unveiling Few-Layer Dominance for Time Series Models

Enhancing LLM Steering through Sparse Autoencoder-Based Vector Refinement

GNPA-DIL: Unveiling the Vulnerability Genome Through Semantic Graph Distillation and Invariant Neural Reasoning

Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering

Supposedly Equivalent Facts That Aren’t? Entity Frequency in Pre-training Induces Asymmetry in LLMs

PERFT: Parameter-Efficient Routed Fine-Tuning for Mixture-of-Expert Model

DyGMamba: Efficiently Modeling Long-Term Temporal Dependency on Continuous-Time Dynamic Graphs with State Space Models

Quantum Architecture Search With Unsupervised Representation Learning