Shusen Liu

Akshay Kulkarni, Tsui-Wei Weng, Vivek Narayanaswamy et al.

Sparse autoencoders (SAEs) promise a unified approach for mechanistic interpretability, concept discovery, and model steering in LLMs and LVLMs. However, realizing this potential requires that the learned features be both interpretable and steerable. To that end, we introduce two new computationally inexpensive interpretability and steerability metrics and conduct a systematic analysis on LVLMs. Our analysis uncovers two observations; (i) a majority of SAE neurons exhibit either low interpretability or low steerability or both, rendering them ineffective for downstream use; and (ii) due to the unsupervised nature of SAEs, user-desired concepts are often absent in the learned dictionary, thus limiting their practical utility. To address these limitations, we propose Concept Bottleneck Sparse Autoencoders (CB-SAE) - a novel post-hoc framework that prunes low-utility neurons and augments the latent space with a lightweight concept bottleneck aligned to a user-defined concept set. The resulting CB-SAE improves interpretability by +32.1% and steerability by +14.5% across LVLMs and image generation tasks. We will make our code and model weights available.

Yeping Hu, Ruben Glatt, Shusen Liu

Graph-based surrogate models provide fast alternatives to high-fidelity CFD solvers, but their opaque latent spaces and limited controllability restrict use in safety-critical settings. A key failure mode in oscillatory flows is phase drift, where predictions remain qualitatively correct but gradually lose temporal alignment with observations, limiting use in digital twins and closed-loop control. Correcting this through retraining is expensive and impractical during deployment. We ask whether phase drift can instead be corrected post hoc by manipulating the latent space of a frozen surrogate. We propose a phase-steering framework for pretrained graph-based CFD models that combines the right representation with the right intervention mechanism. To obtain disentangled representation for effective steering, we use sparse autoencoders (SAEs) on frozen MeshGraphNet embeddings. To steer dynamics, we move beyond static per-feature interventions such as scaling or clamping, and introduce a temporally coherent, phase-aware method. Specifically, we identify oscillatory feature pairs with Hilbert analysis, project spatial fields into low-rank temporal coefficients via SVD, and apply smooth time-varying rotations to advance or delay periodic modes while preserving amplitude-phase structure. Using a representation-agnostic setup, we compare SAE-based steering with PCA and raw embedding spaces under the same intervention pipeline. Results show that sparse, disentangled representations outperform dense or entangled ones, while static interventions fail in this dynamical setting. Overall, this work shows that latent-space steering can be extended from semantic domains to time-dependent physical systems when interventions respect the underlying dynamics, and that the same sparse features used for interpretability can also serve as physically meaningful control axes.

Kuangshi Ai, Haichao Miao, Zhimin Li et al.

Recent advances in multi-modal large language models (MLLMs) have enabled increasingly sophisticated autonomous visualization agents capable of translating user intentions into data visualizations. However, measuring progress and comparing different agents remains challenging, particularly in scientific visualization (SciVis), due to the absence of comprehensive, large-scale benchmarks for evaluating real-world capabilities. This position paper examines the various types of evaluation required for SciVis agents, outlines the associated challenges, provides a simple proof-of-concept evaluation example, and discusses how evaluation benchmarks can facilitate agent self-improvement. We advocate for a broader collaboration to develop a SciVis agentic evaluation benchmark that would not only assess existing capabilities but also drive innovation and stimulate future development in the field.

Shubham Mohole, Hongjun Choi, Shusen Liu et al.

Retrieval-augmented generation (RAG) systems are increasingly adopted in clinical decision support, yet they remain methodologically blind-they retrieve evidence but cannot vet its scientific quality. A paper claiming "Antioxidant proteins decreased after alloferon treatment" and a rigorous multi-laboratory replication study will be treated as equally credible, even if the former lacked scientific rigor or was even retracted. To address this challenge, we introduce VERIRAG, a framework that makes three notable contributions: (i) the Veritable, an 11-point checklist that evaluates each source for methodological rigor, including data integrity and statistical validity; (ii) a Hard-to-Vary (HV) Score, a quantitative aggregator that weights evidence by its quality and diversity; and (iii) a Dynamic Acceptance Threshold, which calibrates the required evidence based on how extraordinary a claim is. Across four datasets-comprising retracted, conflicting, comprehensive, and settled science corpora-the VERIRAG approach consistently outperforms all baselines, achieving absolute F1 scores ranging from 0.53 to 0.65, representing a 10 to 14 point improvement over the next-best method in each respective dataset. We will release all materials necessary for reproducing our results.

Shusen Liu, Bhavya Kailkhura, Jize Zhang et al.

The scientific community has been increasingly interested in harnessing the power of deep learning to solve various domain challenges. However, despite the effectiveness in building predictive models, fundamental challenges exist in extracting actionable knowledge from deep neural networks due to their opaque nature. In this work, we propose techniques for exploring the behavior of deep learning models by injecting domain-specific actionable attributes as tunable "knobs" in the analysis pipeline. By incorporating the domain knowledge in a generative modeling framework, we are not only able to better understand the behavior of these black-box models, but also provide scientists with actionable insights that can potentially lead to fundamental discoveries.