activity
20242026
collaborators

6 papers

cs.CL2026

Unveiling Downstream Performance Scaling of LLMs: A Clustering-Based Perspective

Chengyin Xu, Kaiyuan Chen, Xiao Li +2

The escalating scale and cost of Large Language Models (LLMs) training necessitate accurate pre-training prediction of downstream task performance for comprehensive understanding o…

cs.CV2026

Revealing and Enhancing Core Visual Regions: Harnessing Internal Attention Dynamics for Hallucination Mitigation in LVLMs

Guangtao Lyu, Qi Liu, Chenghao Xu +5

LVLMs have achieved strong multimodal reasoning capabilities but remain prone to hallucinations, producing outputs inconsistent with visual inputs or user instructions. Existing tr…

cs.LG2025

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss

Yunrui Yu, Hang Su, Cheng-zhong Xu +2

Gradient-based adversarial attacks using the Cross-Entropy (CE) loss often suffer from overestimation due to relative errors in gradient computation induced by floating-point arith…

cs.LG2025

HGCA: Hybrid GPU-CPU Attention for Long Context LLM Inference

Weishu Deng, Yujie Yang, Peiran Du +6

Scaling inference for large language models (LLMs) is increasingly constrained by limited GPU memory, especially due to growing key-value (KV) caches required for long-context gene…

cs.LG2025

Scalable Complexity Control Facilitates Reasoning Ability of LLMs

Liangkai Hang, Junjie Yao, Zhiwei Bai +17

The reasoning ability of large language models (LLMs) has been rapidly advancing in recent years, attracting interest in more fundamental approaches that can reliably enhance their…

cs.CV2024

Faster Multi-GPU Training with PPLL: A Pipeline Parallelism Framework Leveraging Local Learning

Xiuyuan Guo, Chengqi Xu, Guinan Guo +6

Currently, training large-scale deep learning models is typically achieved through parallel training across multiple GPUs. However, due to the inherent communication overhead and s…