Yufa Zhou

The Geometry of Reasoning: Flowing Logics in Representation Space

Fastcar: Cache Attentive Replay for Fast Auto-Regressive Video Generation on the Edge

Grounding and Enhancing Informativeness and Utility in Dataset Distillation

Efficient Reasoning with Hidden Thinking

Why Do Transformers Fail to Forecast Time Series In-Context?

Automating Structural Engineering Workflows with Large Language Model Agents

Strategic Generalization Without Interaction: Can Post-Training Alone Induce Multi-Agent Behavior?

DraftAttention: Fast Video Diffusion via Low-Resolution Attention Guidance

Fine-grained Attention I/O Complexity: Comprehensive Analysis for Backward Passes

Efficient Multi-modal Large Language Models via Progressive Consistency Distillation

Differential Privacy of Cross-Attention with Provable Guarantee

Beyond Linear Approximations: A Novel Pruning Approach for Attention Matrix

Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time

Tensor Attention Training: Provably Efficient Learning of Higher-order Transformers