Chenyu You

CSRv2: Unlocking Ultra-Sparse Embeddings

The Chosen Few: Sparse Adaptation for Large Models

Scaling Attention via Feature Sparsity

SPROUT: Training-free Nuclear Instance Segmentation with Automatic Prompting

Don’t Scale It All: Training-Free Localized Test-Time Scaling for Diffusion Models

Route Experts by Sequence, Not by Token

A Unified Perspective and Review on Tree Search for LLMs Test-Time Scaling

Plug-and-Play Global Memory via Test-Time Registers

Enabling Thinking, Reflecting and Chain-of-Thought Reasoning with Biological Sequences

QuantAgent: Price-Driven Multi-Agent LLMs for High-Frequency Trading

Paper2Slide: A Multi-Agent Framework for Automatic Scientific Slide Generation

TCMAgent: A Multi-Agent Framework for General Traditional Chinese Medicine

Test-Time Layer Recurrence Enables Ultra-Deep Thinking in LLMs Without Chain-of-Thought

A Stitch in Time Forecasts Nine: Towards End-to-End Agentic Time Series Forecasting

VCoT-Pro: Advancing Visual Reasoning with a Large-scale Comprehensive Visual Chain-of-Thought Dataset

Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation

Buckle Up: Robustifying LLMs at Every Customization Stage via Data Curation

Robust Multi-modal Learning with Shifted Feature Reweighting Against Spurious Correlations