collaborators

10 papers

cs.DC2026

Libra: Taming Attention Workload Skew in Long-Context LLM Training with Bounded Sequence Pool

Yan Wang, Xiulong Yuan, Kaiming Yang +16

Long-context LLM training suffers from a load-balancing problem that sequence packing does not solve. Packing samples into fixed-token sequences balances memory and linear-cost ope…

cs.CL2026

Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling

Xiang Hu, Xinyu Wei, Hao Gu +10

Scaling modern large language models (LLMs) to long contexts is limited by the quadratic computation cost, and poor length extrapolation of dense attention. Chunk-wise sparse atten…

cs.AI2026

From Context-Aware to Conflict-Aware: Generalizing Contrastive Decoding for Knowledge Conflict in LLMs

Runze Jiang, Taiqiang Wu, Yan Wang +2

When large language models generate from retrieved or augmented contexts, conflicts between external context and parametric priors remain a central reliability bottleneck. Existing…

cs.LG2026

FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention

Yan Wang, Qifan Zhang, Jiachen Yu +12

Conventional LLMs keep the full KV cache loaded during decoding, causing a severe GPU memory bottleneck for ultra-long context serving. In this report, we propose \textbf{Lookahead…

cs.CL2026

AlignFed: Alignment-Aware Asynchronous Federated Fine-Tuning for Large Language Models in Heterogeneous Edge Environments

Yan Wang, Ziyi Gao, Rui Wang

Large Language Models (LLMs) have significantly propelled the advancement of edge intelligence and have been widely deployed across various scenarios, including autonomous driving,…

cs.RO2026

Planning-aligned Token Compression for Long-Context Autonomous Driving

Zhixuan Liang, Yuxiao Chen, Yurong You +12

Monolithic vision-action models represent an emerging paradigm in autonomous driving. However, this architecture produces token sequences that quickly exceed real-time computationa…