collaborators

6 papers

cs.CL2026

Periodic RoPE for Infinite Context LLMs

Simin Huo

The ability to process ultra-long contexts is crucial for large language models (LLMs) to perform long-horizon tasks. While recent efforts have extended context windows to 1M and b…

cs.CV2026

TTF: Temporal Token Fusion for Efficient Video-Language Model

Simin Huo, Ning LI

Video-language models (VLMs) face rapid inference costs as visual token counts scale with video length. For example, 32 frames at resolution already yield >8,000 v…

cs.CV2026

MaMe & MaRe: Matrix-Based Token Merging and Restoration for Efficient Visual Perception and Synthesis

Simin Huo, Ning Li

Token compression is crucial for mitigating the quadratic complexity of self-attention mechanisms in Vision Transformers (ViTs), which often involve numerous input tokens. Existing…

cs.CV2025

Iwin Transformer: Hierarchical Vision Transformer using Interleaved Windows

Simin Huo, Ning Li

Vision Transformers (ViTs) face two limitations: the rigid resolution dependency of positional embeddings, which complicates cross-resolution fine-tuning, and the quadratic complex…

cs.LG2025

ULU: A Unified Activation Function

Simin Huo

We propose \textbf{ULU}, a novel non-monotonic, piecewise activation function defined as , where . ULU treats po…

cs.CV2025

Single Domain Generalization for Few-Shot Counting via Universal Representation Matching

Xianing Chen, Si Huo, Borui Jiang +2

Few-shot counting estimates the number of target objects in an image using only a few annotated exemplars. However, domain shift severely hinders existing methods to generalize to…