collaborators

10 papers

cs.CL2026

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry

Yehan Yang, Junyuan Shang, Yang Li +3

Long-context LLM inference is bottlenecked by quadratic attention computation and growing KV-cache costs. Existing sparse attention and KV-compression methods typically decide whic…

cs.CL2026

ConSA: Controllable Sparsity in Hybrid Attention via Learnable Allocation

Yao Chen, Yinqi Yang, Junyuan Shang +6

Hybrid architectures combining full attention (FA) and sliding-window attention (SWA) are a promising paradigm for efficient LLM inference. However, existing methods typically rely…

cs.CV2026

PP-OCRv6: From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks

Yubo Zhang, Xueqing Wang, Manhui Lin +13

Vision-Language Models (VLMs) have achieved impressive results on general vision-language tasks, yet they suffer from hallucination, imprecise localization, and prohibitive computa…

cs.LG2026

AdaGC: Enhancing LLM Pretraining Stability via Adaptive Gradient Clipping

Guoxia Wang, Shuai Li, Congliang Chen +5

Loss spikes remain a persistent obstacle in large-scale language model pretraining. While previous research has attempted to identify the root cause of loss spikes by investigating…

cs.LG2026

Sparse Layer Sharpness-Aware Minimization for Efficient Fine-Tuning

Yifei Cheng, Xianglin Yang, Guoxia Wang +5

Sharpness-aware minimization (SAM) seeks the minima with a flat loss landscape to improve the generalization performance in machine learning tasks, including fine-tuning. However,…

cs.CL2026

RRAttention: Dynamic Block Sparse Attention via Per-Head Round-Robin Shifts for Long-Context Inference

Siran Liu, Guoxia Wang, Sa Wang +7

The quadratic complexity of attention mechanisms poses a critical bottleneck for large language models processing long contexts. While dynamic sparse attention methods offer input-…