Minghua (Richardo) He 👋

WeDLM is a diffusion language model framework built on standard causal attention via Topological Reordering, enabling prefix-cache compatibility and streaming parallel decoding. It achieves up to 3× speedup on reasoning benchmarks and 10× in low-entropy regimes compared to vLLM-served AR baselines—the first DLLM to outperform industrial AR engines in wall-clock speed.

ExeCoder enhances LLM-based code translation by incorporating executability representations like syntax and semantics.

We propose Chimera, an end-to-end framework that unifies anomaly detection and root cause localization through interactive multi-task learning and bidirectional knowledge transfer.

We propose MIDLog, a weakly-supervised method using multi-instance learning to enable log anomaly detection with inexact, bag-level labels instead of fine-grained annotation.

WeDLM is a diffusion language model framework built on standard causal attention via Topological Reordering, enabling prefix-cache compatibility and streaming parallel decoding. It achieves up to 3× speedup on reasoning benchmarks and 10× in low-entropy regimes compared to vLLM-served AR baselines—the first DLLM to outperform industrial AR engines in wall-clock speed.

We propose d-TreeRPO, a reliable RL framework for diffusion LLMs that leverages tree-structured rollouts and bottom-up advantage computation with verifiable rewards, achieving significant gains on reasoning benchmarks.

A comprehensive survey of parallel text generation techniques, from parallel decoding to the latest diffusion language models.

We introduce MicroRemed, the first benchmark for evaluating LLMs in end-to-end microservice remediation, from diagnosis reports directly to executable Ansible playbooks.

We present CodeAD, a novel framework that automatically synthesizes lightweight Python rule functions for LogAD using LLMs, achieving 3.6% F1 improvement while processing datasets 4x faster at a fraction of the cost.

We propose DUET, a closed-loop framework for joint exploration of user-item textual profiles in recommendation systems. It distills raw data into concise cues, expands them into rich profiles via self-prompt construction, and optimizes profiles jointly with reinforcement learning using downstream recommendation feedback, while enabling interpretable LLM-compatible representations.

We propose Support Vector Regularization (SVR) to control optimization trajectory drift in contrastive language-audio pretraining by using an auxiliary support vector to harness rich information from negative samples while improving training stability.

Inspired by how human SREs operate, we introduce RCLAgent, a multi-agent recursion-of-thought framework that accurately localizes the root cause of failures in microservice systems using only a single request.

We propose WarriorMath, a defect-aware framework that improves LLM mathematical reasoning through targeted data synthesis and progressive training.

FusionLog routes unlabeled target logs by semantic similarity, applies meta-learned small models to general logs, and distills LLM-guided pseudo labels for proprietary logs to fuse knowledge without target labels.

GeneralLog collaborates LLMs and small models at the knowledge level, routing proprietary logs to LLMs and general logs to small models to reach 90%+ F1 under fully zero-label settings.

We propose LogAction, a framework that integrates transfer and active learning to achieve high-performance cross-system anomaly detection with minimal labeling effort.

We propose CoorLog, a framework using an adaptive coordinator for efficient and generalizable log anomaly detection, especially in evolving software systems.

We propose Chimera, an end-to-end framework that unifies anomaly detection and root cause localization through interactive multi-task learning and bidirectional knowledge transfer.

We introduce 'diagnostic faithfulness' as a key metric and propose FaithLog, a system that enhances model trustworthiness via a causality-guided attention mechanism.

ExeCoder enhances LLM-based code translation by incorporating executability representations like syntax and semantics.

We introduce ZeroLog, a framework for zero-label, generalizable cross-system anomaly detection using logs.

CSLParser presents a collaborative framework where small and large language models work together for efficient log parsing.

We propose FreeLog, a system-agnostic meta-learning approach for cross-system log anomaly detection that requires no labeled data from the target system.

We propose VISTA, a variable-centric strategy that improves the efficiency and reduces the cost of LLM-based log parsing through novel sampling, caching, and ICL techniques.

We propose CLSLog, a collaborative scheme combining LLM generalization and small model efficiency to effectively handle evolutionary logs in anomaly detection.

We propose MIDLog, a weakly-supervised method using multi-instance learning to enable log anomaly detection with inexact, bag-level labels instead of fine-grained annotation.

We propose LLMeLog, which leverages LLMs to enrich log event semantics and fine-tunes a BERT model on the enriched data, significantly boosting anomaly detection accuracy.