Zhonghao Chen — accepted AI-conference papers

2026

Causally-Grounded Dual-Path Attention Intervention for Object Hallucination Mitigation in LVLMs

Liu Yu, Zhonghao Chen, Ping Kuang, Zhikun Feng, Fan Zhou, Lan Wang +1

AAAI 2026technical

Object hallucination remains a critical challenge in Large Vision-Language Models (LVLMs), where models generate content inconsistent with visual inputs. Existing language-decoder based mitigation approaches often regulate visual or textual attention independently, overlooking their interaction as t

Cited by 0 Source ↗PDF ↗Scholar ↗

2026

SPARe: Stacked Parallelism with Adaptive Reordering for Fault-Tolerant LLM Pretraining Systems with 100k+ GPUs

Jin Lee, Zhonghao Chen, Xuhang He, Robert Underwood, Bogdan Nicolae, Franck Cappello +3

ICML 2026poster

In large-scale LLM pretraining systems with $100\mathrm{k}+$ GPUs, failures become the norm rather than the exception, and restart costs can dominate wall-clock training time. However, existing fault-tolerance mechanisms are largely unprepared for this restart-dominant regime. To address this challe…

Cited by 0 Source ↗Scholar ↗