works on

From the 1 of 11 linked papers with an AI index.

activity
20242026
collaborators

11 papers

cs.CV2026

Fast and Accurate Image Restoration and Generation with Rank Enhanced Linear Attention

Yuang Ai

The paper proposes Rank Enhanced Linear Attention (RELA), which adds a lightweight depthwise convolution to linear attention to improve image restoration performance, and builds LA…

cs.AI2026

Benchmark Everything Everywhere All at Once

Shiyun Xiong, Dongming Wu, Peiwen Sun +5

Benchmarks are fundamental for evaluating and advancing LLMs and MLLMs by providing standardized and explicit measures of performance. However, their construction is labor-intensiv…

cs.CL2026

BitLM: Unlocking Multi-Token Language Generation with Bitwise Continuous Diffusion

Shaobin Zhuang, Yuang Ai, Jiaming Han +7

Autoregressive language models generate text one token at a time, yet natural language is inherently structured in multi-token units, including phrases, n-grams, and collocations t…

cs.CV2026

BitDance: Scaling Autoregressive Generative Models with Binary Tokens

Yuang Ai, Jiaming Han, Shaobin Zhuang +8

We present BitDance, a scalable autoregressive (AR) image generator that predicts binary visual tokens instead of codebook indices. With high-entropy binary latents, BitDance lets…

cs.CV2026

UniWeTok: An Unified Binary Tokenizer with Codebook Size for Unified Multimodal Large Language Model

Shaobin Zhuang, Yuang Ai, Jiaming Han +12

Unified Multimodal Large Language Models (MLLMs) require a visual representation that simultaneously supports high-fidelity reconstruction, complex semantic extraction, and generat…

cs.CV2026

Random Wins All: Rethinking Grouping Strategies for Vision Tokens

Qihang Fan, Yuang Ai, Huaibo Huang +1

Since Transformers are introduced into vision architectures, their quadratic complexity has always been a significant issue that many research efforts aim to address. A representat…