Research
Papers and datasets worth knowing, ranked by significance and community attention.
FearCaut-Qwen: Affective Steering in a Vision-Language Model Shifts the Decision Criterion for Hazard Assessment
Vision-language models (VLMs) show great potential for damage assessment after a disaster, but a recurring deficiency is that they are reluctant to declare a hazard; that is, recall is low even when overall accuracy appears adequate.
U-Space: Uncovering When and Why Uncertainty Arises in Language Models
Large language models are informing decisions with ever-higher stakes.
Marformer: A Transformer for Predicting Missing Data Distributions
We present the Marformer, a Transformer trained to directly predict conditional marginals given any set of observed values.
asdex: Automatic Sparse Differentiation in JAX
Automatic sparse differentiation (ASD) exploits this structure in four steps: detection of the input-agnostic sparsity pattern, coloring of a graph to group columns or rows that can share an AD pass, compressed differentiation to compute a compressed derivative matrix with one AD pass per color, and finally decompression into the original sparsity pattern.
RouterInterp: Understanding Superposed Specialisation in Mixture of Experts Routing
Leveraging the SSH, we introduce RouterInterp, a method for interpreting expert routing that identifies Sparse Autoencoder features most predictive of routing decisions and produces unified natural language explanations.
MotherTree: Meta-learning on synthetic data improves decision tree training
We introduce MotherTree, a tabular transformer that meta-learns decision tree induction: given a training set for a new task, it outputs a hard, axis-aligned decision tree, equivalent in form to classically trained trees, in a single forward pass.
Rubric-CEPR: Self-Evolving Image Editing via Reward-Verified Self-Distillation
To this end, we propose a self-evolving framework, named Rubric-CEPR, that verifies the editor's own samples with its internal representations through a rubric-augmented Contrastive Edit-Preservation Reward (CEPR).
Dissecting Representation Structure in Vision Transformers: A Rigorous Architectural Study
Representation structure is crucial for understanding Vision Transformer (ViT) architectures and their generalization behavior.
Is In-Domain Training Enough for Fine-Grained Industrial Anomaly Understanding?
A single multimodal large language model (MLLM) struggles to excel simultaneously at detection, localization, description, and reasoning in multimodal industrial anomaly understanding (MM-IAU).
An Interpretable Approach to PDE Solution Discovery via Structural Experience Distillation
PDE solution discovery aims to identify explicit symbolic expressions for unknown physical fields from observations under known physical constraints.
DSReg: Provably Recovering Individual World Latents without Reconstruction
Methods that recover individual latent variables of the world, from nonlinear ICA to dictionary learning and causal representation learning, anchor the latents to observations through reconstruction, auxiliary supervision, or distributional asymmetries such as non-Gaussianity.
Memorization and Malign Generalization in Conditional Diffusion Models with Random Features
Conditional diffusion models generate diverse, novel, and high-quality samples under prescribed conditions.
Attributing HOW, Not Just WHICH: Counterfactual Response Trajectories for Diffusion Models
Diffusion models have achieved remarkable success in image generation, yet tracing their outputs to individual training examples remains challenging.
Rethinking Contrastive Loss in CLIP Post-training: A Complementary Framework with Frozen Text Encoder
Building on this finding, we propose ComCLIP, a lightweight single-epoch post-training recipe that freezes CLIP's text encoder---so the refined vision encoder is a drop-in replacement with unchanged architecture and inference cost---and trains the vision encoder with a properly-tempered contrastive loss, an MSE anchoring loss against the original CLIP, and a relational distillation loss from DINOv2.
How Do Transformers Learn to Represent Symmetries?
Training Transformer-based architectures with finite data augmentation has become an increasingly popular approach in geometric machine learning.
CARE: Constrained Attention Refinement for Fine-Grained Visual Classification via Teacher-Student Distillation
To address this problem, we propose CARE, a constrained attention refinement framework for interpretable fine-grained recognition via teacher-student distillation.
MiniVer-V: Identifying Minimal Sufficient Evidence for Short Video Verification
We introduce MiniVer-V, a benchmark of 195 short videos with three-way verdict annotations (supported, refuted, insufficient) and 5,510 multimodal evidence units spanning visual keyframes, speech transcripts, and web-retrieved external sources.
Chaos in the Text: Revealing the Modality Preference in Mixed-Modality Retrievers
Dense retrievers have made significant progress on text and image corpora, but whether these capabilities extend reliably to mixed corpora containing text, image, and fused text-image documents remains unclear.
Softmax Attention on Gaussian Mixtures: Linear When It Can, Selective When It Must
This work studies the infinite-prompt limit of softmax attention on Gaussian mixtures, which retain the tractability of Gaussian data while introducing latent structure, multimodality, and nonlinear dependencies.
Correlational Training of Morphological Neural Networks
In this work, we propose a novel weight update method for morphological neural networks inspired from the Multiplicative Weights Update (MWU) scheme.
Fully Interpretable Minimal Transformers: From Geometry to Algorithm
We present a framework for building and interpreting minimal transformer models.
SV-TAD: Native Sparse Convs for Efficient Temporal Action Detection
To adapt billion-parameter Vision Transformers for long-video understanding, recent methods freeze the backbone and train lightweight convolutional modules.
RIFT: Relative Isolation From Trees For Anomaly Detection
Inspired by the geometric interpretation of this formula, we introduce RIFT (Relative Isolation From Trees), a deterministic anomaly detection method that generates the minimum spanning tree and scores each point by the sum of the apparent sizes of tree edges as viewed from that point.
When Citations Mislead? A Claim-Level Benchmark for Legal Hallucination Detection
We introduce PARCEL, a benchmark for checking whether a legal claim is supported by the underlying authority.
The Polytopal Neural Network
We propose Polytopal Neural Networks (PNNs), a framework that extracts distinct layer-wise aspects by enforcing a polytope-based structure that is used directly in subsequent information processing.
Leaner Transformers Can Easily Learn to Cluster
Recent work shows that transformers can exactly perform Lloyd's algorithm for $k$-means clustering with $n$ points in $d$ dimensions with an embedding size $d{\textsf{emb}} = d+k$ (thus, requiring attention projection matrices of size $(d+k)^2$).
Is Real-World Training Data Necessary for Generalist Graph Anomaly Detection?
Generalist graph anomaly detection (GAD) aims to build a foundation model that detects anomalies on arbitrary unseen graphs without retraining or fine-tuning.
Causal-fate dynamics of unrealized influence
Here we formulate causal-fate dynamics, in which generated influence may be realized, remain latent, or be transformed by subsequent dynamics, and give an exact finite-transport representation when the relevant maps are specified.
Healthy Counterfactual Generation via Diffusion Inpainting for Mammography Classification
To address this issue, we propose a counterfactual data augmentation strategy that generates healthy mammograms by "erasing" lesions from anomalous images, thereby enriching the training distribution.
Revisiting Identity and Spectra Dispersion in Media-Bridged Time Series Forecasting: Linking Multivariate Signals and Narrative Flows
To explore this, we propose the Multimedia Identity-Aware Prism Network (MIDAPN), a unified spatiotemporal forecasting backbone based on media-general graph adaptation and automatic temporal learning: (1) Following media pre-alignment, our Multimedia Identity-Aware Graph (MIDAG) revisits identity through static essence, dynamic behavior, and latent commonality, inducing affinities that extend variable-specific dependencies across media.
AutoAdapt: Automatic Domain Discovery Enables Low-Cost Extensibility
We present AutoAdapt, a modular framework that incorporates new domains and data via targeted single-adapter training without modifying other adapters.
Temporal transformer CAN encoder with federated lightweight heads for anomaly detection
Motivated by this gap, we present a privacy-preserving framework for anomaly detection in in-vehicle networks, based on a Temporal Transformer CAN Encoder with Federated Lightweight Heads, to better capture these irregularities.
New Lower Bound and Upper Bounds on the Regret for Online Sparse Linear Regression
We study online sparse linear regression (OSLR) where any algorithm is restricted to accessing only $b$ out of $d$ attributes per instance for prediction and $b0\geq 0$ additional attributes after prediction, which was proved to be NP-hard.
A Stevens's Power Law Check-up of GPT-5.5's Implicit Reading of Visual Encoding
We adapt Stevens's power law to measure the implicit ability of AI models to read visualizations, which can reveal the built-in perceptual mechanisms of algorithmic models.
Embedding-Bias in Conditional Independence Testing
To test conditional independence of $X$ and $Y$ given a text or an image $Z$, one conditions on an embedding $ψ(Z)$ in place of $Z$.
Less from More: Reinforcing Sparse Video Reasoning from Dense References
We propose SAVER, a dense-to-sparse post-training framework that uses dense video views as training-time references for sparse-frame inference.
SAGE: Sink-Aware Guided Emphasis for Visual Grounding in Vision-Language Decoders
Building on this insight, we propose SAGE (Sink-Aware Guided Emphasis), a lightweight intervention that steers decoder attention away from PIS and toward query-dependent regions of interest (ROIs) using token-aligned ROI masks derived from standard vision backbones such as CLIP, ViT, and DINOv3.
Nobody Truly Agrees on Sentiment: Humans, Bespoke Tools, and LLMs Struggle with Social Media Texts
In this study, we evaluate the inter-rater reliability of three bespoke sentiment analysis tools (TextBlob, VADER, and Twitter-roBERTa-base) and three large language models (LLMs: Qwen3-32B, GPT-OSS-120B, Llama-4-Maverick-17B) against six human raters across 100 tweets.
Beyond Distributional Fidelity: Causal-Penalized Diffusion for Synthetic Tabular Data
In this paper, we study whether causal fidelity can be improved directly within a fully generative tabular model.
Adaptive Adversarial Augmentation for Controllable Face Synthesis
We propose Ensemble Feedback Controllable Synthesis (EFCS), a guided framework that generates diverse and challenging samples while preserving visual realism.
When to Unpair: Regulating Pairing Dependence in Medical Visual In-Context Learning
Visual in-context learning (ICL), well suited to label-scarce medical imaging, uses support image-label pairs to demonstrate input-output mappings, while the labels collectively indicate the requested task.
Efficient Multi-Granularity Knowledge Transfer for Radiology Report Generation
Radiology report generation can automatically generate clinical descriptions from X-ray images, thereby significantly improving the efficiency of radiologists.
HAND: A Biologically-Inspired Activation Function that Improves Generalisation and Sample Efficiency in Image Classification
We incorporate a biologically-inspired inductive bias into a new activation function, HAND (Homeostasis, Accelerating Nonlinearity, and Divisive-nomalisation), and show its effectiveness with CNNs trained on image classification.
Optimization Encoders: Rethinking Second-Order Meta-Learning for Neural Fields
Guided by this view, we introduce Attentive Latent Fields (MetaLF), an equivariant transformer-based neural field that contextualizes a latent pointcloud through self-attention.
Similar Predictive Fit but Different Latent Dynamics: Characterizing Learned Dynamical Structure in Personalized Models of Brain Disorders
We investigate whether personalized latent dynamics reveal clinically associated differences even when predictive fit is similar.
Shared Gaussianization: What Gaussian Regularizers Certify About Contrastive Learning, and What They Miss
What can a distribution-matching regularizer such as SIGReg in LeJEPA certify about contrastive learning?
What can linear attention learn from nonlinear teachers in-context?
Linear attention is a tractable model for understanding the mechanisms governing in-context learning in transformers.
MSU Team at the Explainable Deepfake Detection Challenge 2026: Grounded Artifact Evidence for Deepfake Detection
In this paper, we present our solution to the Explainable Deepfake Detection Challenge [2] on the XPlainVerse dataset [1], where systems are required to predict whether an image is real or fake and generate both complex and simple explanations grounded in visible forensic cues.