collaborators

7 papers

cs.AI2026

Multi-Adapter Representation Interventions via Energy Calibration

Manjiang Yu, Hongji Li, Junwei Chen +4

Representation intervention has emerged as a promising paradigm for aligning large language models toward desired behaviors without modifying model weights. Existing methods typica…

cs.AI2026

Tail-Aware HiFloat4: W4A4 Post-Training Quantization for Wan2.2

Zhanfeng Feng, Shuai Guo, Xin Di +3

This report describes Tail-Aware HiFloat4, our submission to the low-bit text-to-video generation quantization challenge. Our method adapts the public ViDiT-Q post-training quantiz…

cs.IR2026

Memento: Personalized RAG-Style Long-Retention Data Scaling for META Ads Recommendation

Xiaoyu Chen, Ruichen Wang, Jieming Di +21

Modeling of long history data suffers from long-context window attention dilution, system efficiency and catastrophic forgetting problems, where naive linear scaling approach like…

cs.CR2026

SLIM: Stealthy Low-Coverage Black-Box Watermarking via Latent-Space Confusion Zones

Hengyu Wu, Yang Cao

Training data is a critical and often proprietary asset in Large Language Model (LLM) development, motivating the use of data watermarking to embed model-transferable signals for u…

cs.LG2026

Null-Space Filtering for Data-Free Continual Model Merging: Preserving Stability, Promoting Plasticity

Zihuan Qiu, Lei Wang, Yang Cao +7

Data-free continual model merging (DFCMM) aims to fuse independently fine-tuned models into a single backbone that evolves with incoming tasks without accessing task data. This pap…

cs.DC2025

Staggered Batch Scheduling: Co-optimizing Time-to-First-Token and Throughput for High-Efficiency LLM Inference

Jian Tian, Shuailong Li, Yang Cao +8

The evolution of Large Language Model (LLM) serving towards complex, distributed architectures--specifically the P/D-separated, large-scale DP+EP paradigm--introduces distinct sche…