Skip to content

Author

Xueqi Cheng

We have 14 of 129 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Nov 2026

CLEAR: Structured Specifications for Controllable Long-Horizon ML Research Engineering

Large language model (LLM) agents are increasingly being used to automate machine learning research workflows, ranging from code development and experiment execution to research reproduction and scientific discovery, suggesting a shift from automating individual research tasks toward automating long-horizon workflows t...

Xin Liu, Hong-Ru Song, Ru-Qing Zhang et al. · 0 citations
Preprint Nov 2026

Learning When to Think Aloud in Latent Reasoning

VITAL is an importance-guided hybrid reasoning framework that selectively verbalizes informative tokens as reasoning anchors while keeping most computation latent, and achieves higher reasoning accuracy with substantially shorter reasoning trajectories on Qwen3-1.7B.

Zhe-Hao Zhou, Tong Su, Sheng-Yu Zhu et al. · 1 citation

How Do LLM-Generated Texts Impact Term-Based Retrieval Models?

This paper investigates the influence of LLM-generated content on term-based retrieval models, and reveals that LLM-generated texts exhibit smoother high-frequency and steeper low-frequency Zipf slopes, higher term specificity, and greater document-level diversity.

Wei Huang, Ke-Ping Bi, Yin-Qiong Cai et al. · 1 citation
#machine learning Preprint Oct 2026

Capability Scaling-Down Laws for LLM Compression

LLM compression reduces inference costs and memory requirements, but selecting a method and configuration remains largely empirical because comparable resource reductions can produce different capability losses. We systematically investigate capability scaling-down laws for LLM compression across pruning, quantization,...

Xue-Qi Cheng, Liang Wu, Kelly Wan et al. · 0 citations
#natural language process... Preprint Sep 2026

Shared Experience, Separate Learning: Companion Confidence Calibration for LLMs

CoCal is introduced, which trains a lightweight companion from rollout hidden states and verifier-derived correctness supervision while leaving task optimization unchanged, and shows that CoCal improves confidence estimation without sacrificing task performance, outperforming both RL-based concurrent methods and matche...

Shi-Yu Ni, Ke-Ping Bi, Jia-Feng Guo et al. · 0 citations
#artificial intelligence Conference Jan 2026

Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agents

Temporal Semantic Memory is proposed, a memory framework that models semantic time for point-wise memory and supports the construction and utilization of durative memory and incorporates the query's temporal intent on the semantic timeline.

Miao Su, Yu-Can Guo, Zhong-Ni Hou et al. · 12 citations

CLIPure: Purification in Latent Space via CLIP for Adversarially Robust Zero-Shot Classification

An adversarially robust zero-shot image classifier that boosts the SOTA robustness by a large margin and is the first purification method in multi-modal latent space and CLIPure-Cos is the first purification method that is not based on generative models, which substantially improves defense efficiency.

Ming-Kun Zhang, Keping Bi, Wei Chen et al. · 14 citations · ⚡1
Preprint Aug 2026

HiDiffTIR: Hierarchical Difficulty-Aware Policy Optimization for Multi-Turn Tool-Integrated Reasoning

HiDiffTIR is proposed, a Hierarchical Difficulty-aware policy optimization framework for multi-turn TIR that consistently improves multi-turn TIR performance and tool invocation accuracy over strong RL baselines, highlighting the necessity of difficulty-aware credit assignment for effective policy optimization in tool-...

Yu-Can Guo, Xiao-Han Wang, Miao Su et al. · 0 citations
#natural language process... Preprint May 2025

Popular but Wrong: Understanding and Mitigating LLM Overconfidence through Knowledge Popularity

It is shown that popularity-related signals can mitigate overconfidence and improve overall confidence estimation, and incorporate knowledge popularity reduces average confidence on incorrect answers and improves overall confidence estimation.

Shiyu Ni, Keping Bi, Jiafeng Guo et al. · 6 citations

DeepRepro: State-Aware Subplanning for Paper-to-Code Reproduction in Evolving Repositories

DeepRepro dynamically transforms evolving repository states and runtime feedback into fine-grained implementation subplans, keeping planning aligned with execution throughout repository construction, and consistently outperforms strong scientific and commercial code-agent baselines.

Hong-Ru Song, Ru-Qing Zhang, Jia-Feng Guo et al. · 1 citation
Preprint Jul 2026

Token-Flow Firewall: Semantic Runtime Auditing for Persistent AI Agents

TokenWall is proposed, a runtime defense framework that acts as a semantic firewall over agent token flows, demonstrating that semantic runtime containment can achieve a practical security-utility trade-off for persistent AI agents.

Puji Wang, Yingchen Zhang, Ruqing Zhang et al. · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.