collaborators

9 papers

cs.CV2026

ET-Prune: Evidence-Aware Dynamic Budgeting for Visual Token Pruning in Text-Rich MLLMs

Zizhong Ding, Junxian Li, Kai Liu +4

Visual token pruning reduces the inference cost of multimodal large language models, but a fixed token ratio is poorly matched to text-rich inputs. In OCR-centric tasks, decisive e…

cs.LG2026

WorldDynCache: Risk-Controlled Latent Dynamics Approximation for Diffusion World Model

Leyang Chen, Junyi Wu, Shaoqiu Zhang +1

Diffusion world models generate high-quality futures, but re- peated transformer evaluations make inference prohibitively slow. Existing caches reuse intermediate features, selecti…

cs.CV2026

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers

Maohua Li, Qirui Li, Yanke Zhou +10

Modern text-to-image diffusion transformers (DiTs) generate images through joint attention, in which text and image tokens interact directly within a single sequence. In large-scal…

cs.CV2026

Rethinking Cross-Layer Information Routing in Diffusion Transformers

Chao Xu, Maohua Li, Qirui Li +9

Diffusion Transformers (DiTs) have become a de facto backbone of modern visual generation, and nearly every major axis of their design -- tokenization, attention, conditioning, obj…

cs.LG2026

EdgeRazor: A Lightweight Framework for Large Language Models via Mixed-Precision Quantization-Aware Distillation

Shu-Hao Zhang, Le-Tong Huang, Xiang-Sheng Deng +5

Quantization has emerged as a mainstream approach for deploying Large Language Models (LLMs) on resource-constrained devices, yet compressing precision below 4-bit typically causes…

cs.LG2026

Elastic-dLLM: Position Preserving Context Compression and Augmentation of Diffusion LLMs

Junyi Wu, Tianchen Zhao, Shaoqiu Zhang +3

Unlike autoregressive models, which generate one token at a time, dLLMs denoise a chunk of [MASK] tokens jointly and sample one or more tokens per step; despite enabling parallel d…