Skip to content

Author

Li-Jie Hu

We have 7 of 43 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.

#artificial intelligence Preprint Oct 2026

How Do Agentic LLMs Decide to Call Tools? A Tool-Call Vector Shaped by Suppression

This work proposes a method that converts complex agentic prompts into minimal contrastive pairs in which a single request verb determines the tool-call decision, and traces the decision to a vector, $\mu_\Delta$, that is both causally necessary and sufficient and generalizes beyond the discovery prompts to native mult...

X. Gong, Ting-Xu Han, Jia-Hao Zhang et al. · 0 citations
#artificial intelligence Preprint Sep 2026

D-Scope: Decomposing and Steering Diffusion Transformers with Sparse Autoencoders

Sparse autoencoders (SAEs) reveal visual structure in diffusion transformers (DiTs), but interpreting a feature does not establish whether it can be used to control generation. We introduce D-Scope (Diffusion Scope), a framework that connects feature interpretation to generation control through shared visual evidence....

Xinyue Xu, Jiahao Zhang, Li-Jie Hu et al. · 1 citation
#machine learning Preprint Sep 2026

RolloutFaith: Auditing Persistent Internal Interventions in Visual World Model

Interpretability methods such as probes, activation patches and learned editors are designed to reveal or modify a model's current computation. World models pose a harder requirement: because their predictions become inputs to later predictions, a useful internal correction must survive after editing stops. We therefor...

Jun-Chi Yao, Zi-Yi Wang, You-Ling Huang et al. · 0 citations
#natural language process... Preprint Sep 2026

The Answer-Basin Representation Hypothesis: We Are Not Probing or Steering Concepts

Linear probing and activation steering use linear directions to predict and control behavior-level concepts such as correctness, safety, and social bias in question answering. We call these \emph{behavior-level concept directions}. Drawing on the Linear Representation Hypothesis (LRH) and circuit studies, these directi...

Man-Jiang Yu, Hong-Ji Li, Zi-Han Wang et al. · 0 citations
#artificial intelligence Preprint Jul 2026

CleanVideo: Adaptive Concept Erasure for Text-to-Video Diffusion Models

Experiments show that CleanVideo effectively erases target concepts while maintaining visual fidelity and temporal coherence, outperforming existing baselines under frame-level and video-level evaluations and under concept-recovery attacks when the protected pipeline remains intact.

Jun-Hui Liao, Hongji Li, Wen-Rui Zhou et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Concept-Grounded Reasoning with Prompt-Driven Localization for Interpretable Structured Report Generation

Experiments on BUS-CoT and IU X-ray datasets demonstrate consistent improvements in diagnostic accuracy, concept consistency, and report quality over strong general-purpose and medical MLLMs, indicating that concept-grounded reasoning better aligns generation with clinical decision processes.

Xin-Yue Xu, Hong-Bin Lin, Juan-Gui Xu et al. · 0 citations
#machine learning Preprint Sep 2026

SharedSAE: One Feature Dictionary Across Language Models

This work shows that a single shared SAE can replace a collection of dedicated per-model SAEs, and combines a shared dictionary with model-specific encoder-decoder pairs to achieve near-dedicated-SAE reconstruction quality.

Daniil A. Ognev, Célian Vasson, Li-Jie Hu et al. · 0 citations

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