# Research Papers — 2026-01 · bundle page 2 of 189

> Full-text markdown of papers #51–100 of 9403 published in 2026-01, newest first. AI-readable mirrors of the full 9403-paper 2026-01 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-01/page/2
[← Previous bundle](https://aipod.dev/papers/archive/2026-01.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/3.md)

### Synapse: Federated Tool Routing via Typed Compendium Artifacts

Authors: Abhijit Chakraborty, Yash Shah, Vivek Gupta
Published: 2026-01-31
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.00911v2

The unit of collaboration in federated learning determines what guarantees are even expressible. Flat units like weights, prompts, raw examples, carry no type signature on which privacy, conflict resolution, or cross-model transfer can dispatch as well-defined operations. We propose typed federated artifacts: schema validated objects whose declared field structure makes per field differential privacy, schema aware merging, and cross architectural transfer first-class operations rather than heuristic approximations. We instantiate this as SYNAPSE, a compendium for federated tool routing across clients with frozen, heterogeneous LLMs and no shared data or weights which is a setting flat units cannot handle without either leaking gradients or discarding structure. The compendium admits a typed merge operator with field wise conflict resolution, a formal DP guarantee on numeric metadata, and conditional retrieval distortion and routing-stability results empirically characterized on five distributions, including one where the contraction premise fails. A single compendium transfers across four LLM families (LLaMA 3.18B,LLaMA 3.2-3B, Mistral 7B, GPT 4o) with approximately 2 pt loss, a capability weight-sharing federation cannot provide without architectural matching.

---

### Efficient Deep Learning for Medical Imaging: Bridging the Gap Between High-Performance AI and Clinical Deployment

Authors: Cuong Manh Nguyen, Truong-Son Hy
Published: 2026-01-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.00910v1

Deep learning has revolutionized medical image analysis, playing a vital role in modern clinical applications. However, the deployment of large-scale models in real-world clinical settings remains challenging due to high computational costs, latency constraints, and patient data privacy concerns associated with cloud-based processing. To address these bottlenecks, this review provides a comprehensive synthesis of efficient and lightweight deep learning architectures specifically tailored for the medical domain. We categorize the landscape of modern efficient models into three primary streams: Convolutional Neural Networks (CNNs), Lightweight Transformers, and emerging Linear Complexity Models. Furthermore, we examine key model compression strategies (including pruning, quantization, knowledge distillation, and low-rank factorization) and evaluate their efficacy in maintaining diagnostic performance while reducing hardware requirements. By identifying current limitations and discussing the transition toward on-device intelligence, this review serves as a roadmap for researchers and practitioners aiming to bridge the gap between high-performance AI and resource-constrained clinical environments.

---

### PyGALAX: An Open-Source Python Toolkit for Advanced Explainable Geospatial Machine Learning

Authors: Pingping Wang, Yihong Yuan, Lingcheng Li, Yongmei Lu
Published: 2026-01-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.00907v1

PyGALAX is a Python package for geospatial analysis that integrates automated machine learning (AutoML) and explainable artificial intelligence (XAI) techniques to analyze spatial heterogeneity in both regression and classification tasks. It automatically selects and optimizes machine learning models for different geographic locations and contexts while maintaining interpretability through SHAP (SHapley Additive exPlanations) analysis. PyGALAX builds upon and improves the GALAX framework (Geospatial Analysis Leveraging AutoML and eXplainable AI), which has proven to outperform traditional geographically weighted regression (GWR) methods. Critical enhancements in PyGALAX from the original GALAX framework include automatic bandwidth selection and flexible kernel function selection, providing greater flexibility and robustness for spatial modeling across diverse datasets and research questions. PyGALAX not only inherits all the functionalities of the original GALAX framework but also packages them into an accessible, reproducible, and easily deployable Python toolkit while providing additional options for spatial modeling. It effectively addresses spatial non-stationarity and generates transparent insights into complex spatial relationships at both global and local scales, making advanced geospatial machine learning methods accessible to researchers and practitioners in geography, urban planning, environmental science, and related fields.

---

### Hallucination is a Consequence of Space-Optimality: A Rate-Distortion Theorem for Membership Testing

Authors: Anxin Guo, Jingwei Li
Published: 2026-01-31
Categories: cs.LG, cs.AI, cs.CL, cs.DS, cs.IT
arXiv: https://arxiv.org/abs/2602.00906v7

Large language models often hallucinate with high confidence on "random facts" that lack inferable patterns. We formalize the memorization of such facts as a membership testing problem, unifying the discrete error metrics of Bloom filters with the continuous log-loss of LLMs. By analyzing this problem in the regime where facts are sparse in the universe of plausible claims, we establish a rate-distortion theorem: the optimal memory efficiency is characterized by the minimum KL divergence between score distributions on facts and non-facts. This theoretical framework provides a distinctive explanation for hallucination under an idealized setting: even with optimal training, perfect data, and a simplified ``closed world'' setting, the information-theoretically optimal strategy under limited capacity is not to abstain or forget, but to assign high confidence to some non-facts, resulting in hallucination. We validate this theory empirically on both synthetic and real-world data, showing that hallucinations persist as a natural consequence of lossy compression. The same theorem recovers and sharpens classical space lower bounds for Bloom-type filters, pinning down an additive constant left open for two-sided filters.

---

### OCTOPUS: Enhancing the Spatial-Awareness of Vision SSMs with Multi-Dimensional Scans and Traversal Selection

Authors: Kunal Mahatha, Ali Bahri, Pierre Marza, Sahar Dastani, Maria Vakalopoulou, Stergios Christodoulidis, Jose Dolz, Christian Desrosiers
Published: 2026-01-31
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.00904v1

State space models (SSMs) have recently emerged as an alternative to transformers due to their unique ability of modeling global relationships in text with linear complexity. However, their success in vision tasks has been limited due to their causal formulation, which is suitable for sequential text but detrimental in the spatial domain where causality breaks the inherent spatial relationships among pixels or patches. As a result, standard SSMs fail to capture local spatial coherence, often linking non-adjacent patches while ignoring neighboring ones that are visually correlated. To address these limitations, we introduce OCTOPUS , a novel architecture that preserves both global context and local spatial structure within images, while maintaining the linear complexity of SSMs. OCTOPUS performs discrete reoccurrence along eight principal orientations, going forward or backward in the horizontal, vertical, and diagonal directions, allowing effective information exchange across all spatially connected regions while maintaining independence among unrelated patches. This design enables multi-directional recurrence, capturing both global context and local spatial structure with SSM-level efficiency. In our classification and segmentation benchmarks, OCTOPUS demonstrates notable improvements in boundary preservation and region consistency, as evident from the segmentation results, while maintaining relatively better classification accuracy compared to existing V-SSM based models. These results suggest that OCTOPUS appears as a foundation method for multi-directional recurrence as a scalable and effective mechanism for building spatially aware and computationally efficient vision architectures.

---

### Domain-Adaptive and Scalable Dense Retrieval for Content-Based Recommendation

Authors: Mritunjay Pandey
Published: 2026-01-31
Categories: cs.LG, cs.IR
arXiv: https://arxiv.org/abs/2602.00899v1

E-commerce recommendation and search commonly rely on sparse keyword matching (e.g., BM25), which breaks down under vocabulary mismatch when user intent has limited lexical overlap with product metadata. We cast content-based recommendation as recommendation-as-retrieval: given a natural-language intent signal (a query or review), retrieve the top-K most relevant items from a large catalog via semantic similarity. We present a scalable dense retrieval system based on a two-tower bi-encoder, fine-tuned on the Amazon Reviews 2023 (Fashion) subset using supervised contrastive learning with Multiple Negatives Ranking Loss. We construct training pairs from review text (as a query proxy) and item metadata (as the positive document) and fine-tune on 50,000 sampled interactions with a maximum sequence length of 500 tokens. For efficient serving, we combine FAISS HNSW indexing with an ONNX Runtime inference pipeline using INT8 dynamic quantization. On a review-to-title benchmark over 826,402 catalog items, our approach improves Recall@10 from 0.26 (BM25) to 0.66, while meeting practical latency and model-size constraints: 6.1 ms median CPU inference latency (batch size 1) and a 4x reduction in model size. Overall, we provide an end-to-end, reproducible blueprint for taking domain-adapted dense retrieval from offline training to CPU-efficient serving at catalog scale.

---

### GAPNet: Plug-in Jointly Learning Task-Specific Graph for Dynamic Stock Relation

Authors: Yingjie Niu, Lanxin Lu, Changhong Jin, Ruihai Dong
Published: 2026-01-31
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.00888v1

The advent of the web has led to a paradigm shift in the financial relations, with the real-time dissemination of news, social discourse, and financial filings contributing significantly to the reshaping of financial forecasting. The existing methods rely on establishing relations a priori, i.e. predefining graphs to capture inter-stock relationships. However, the stock-related web signals are characterised by high levels of noise, asynchrony, and challenging to obtain, resulting in poor generalisability and non-alignment between the predefined graphs and the downstream tasks. To address this, we propose GAPNet, a Graph Adaptation Plug-in Network that jointly learns task-specific topology and representations in an end-to-end manner. GAPNet attaches to existing pairwise graph or hypergraph backbone models, enabling the dynamic adaptation and rewiring of edge topologies via two complementary components: a Spatial Perception Layer that captures short-term co-movements across assets, and a Temporal Perception Layer that maintains long-term dependency under distribution shift. Across two real-world stock datasets, GAPNet has been shown to consistently enhance the profitability and stability in comparision to the state-of-the-art models, yielding annualised cumulative returns of up to 0.47 for RT-GCN and 0.63 for CI-STHPAN, with peak Sharpe Ratio of 2.20 and 2.12 respectively. The plug-and-play design of GAPNet ensures its broad applicability to diverse GNN-based architectures. Our results underscore that jointly learning graph structures and representations is essential for task-specific relational modeling.

---

### EffGen: Enabling Small Language Models as Capable Autonomous Agents

Authors: Gaurav Srivastava, Aafiya Hussain, Chi Wang, Yingyan Celine Lin, Xuan Wang
Published: 2026-01-31
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.00887v2

Most existing language model agentic systems today are built and optimized for large language models (e.g., GPT, Claude, Gemini) via API calls; while powerful, this approach faces several limitations including high token costs and privacy concerns for sensitive applications. We introduce EffGen, an open-source agentic framework optimized for small language models (SLMs) that enables effective, efficient, and secure local deployment. EffGen makes four major contributions: (1) Enhanced tool-calling with prompt optimization that compresses input prompts by up to 70-80% (and 57% on average across our benchmarks) while preserving task semantics, (2) Intelligent task decomposition that breaks complex queries into parallel or sequential subtasks based on dependencies, (3) Complexity-based routing using five factors to make smart pre-execution decisions, and (4) Unified memory system combining short-term, long-term, and vector-based storage. Additionally, EffGen unifies multiple agent protocols (MCP, A2A, ACP) for cross-protocol communication. Results on 13 benchmarks show EffGen outperforms LangChain, AutoGen, and Smolagents with higher success rates, faster execution, and lower memory. Our results reveal that prompt optimization and complexity routing have complementary scaling behavior: optimization benefits SLMs more (11.2% gain at 1.5B vs 2.4% at 32B), while routing benefits large models more (3.6% at 1.5B vs 7.9% at 32B), providing consistent gains across all scales when combined. EffGen is released under the Apache 2.0 License, ensuring broad accessibility for research and commercial use, with the code available at https://github.com/ctrl-gaurav/effGen, the Python package at https://pypi.org/project/effgen/ (pip install effgen), and the project website and documentation at https://effgen.org/ and https://docs.effgen.org/.

---

### RoDiF: Robust Direct Fine-Tuning of Diffusion Policies with Corrupted Human Feedback

Authors: Amitesh Vatsa, Zhixian Xie, Wanxin Jin
Published: 2026-01-31
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2602.00886v1

Diffusion policies are a powerful paradigm for robotic control, but fine-tuning them with human preferences is fundamentally challenged by the multi-step structure of the denoising process. To overcome this, we introduce a Unified Markov Decision Process (MDP) formulation that coherently integrates the diffusion denoising chain with environmental dynamics, enabling reward-free Direct Preference Optimization (DPO) for diffusion policies. Building on this formulation, we propose RoDiF (Robust Direct Fine-Tuning), a method that explicitly addresses corrupted human preferences. RoDiF reinterprets the DPO objective through a geometric hypothesis-cutting perspective and employs a conservative cutting strategy to achieve robustness without assuming any specific noise distribution. Extensive experiments on long-horizon manipulation tasks show that RoDiF consistently outperforms state-of-the-art baselines, effectively steering pretrained diffusion policies of diverse architectures to human-preferred modes, while maintaining strong performance even under 30% corrupted preference labels.

---

### Reliability-Aware Determinantal Point Processes for Robust Informative Data Selection in Large Language Models

Authors: Ahmad Sarlak, Abolfazl Razi
Published: 2026-01-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.00885v1

Informative data selection is a key requirement for large language models (LLMs) to minimize the amount of data required for fine-tuning, network distillation, and token pruning, enabling fast and efficient deployment, especially under computational and communication constraints. Traditional subset selection methods, including those based on Determinantal Point Processes (DPP), focus on maximizing diversity but assume that selected data batches are always available error-free. This presumption prohibits their use under partial storage outage, imperfect communication, and stochastic access failures. Furthermore, we show that the original formulation collapses under such conditions. To address this gap, we introduce ProbDPP, a novel reliability-aware implementation of k-DPP that accounts for probabilistic data access by recasting the objective function with a regularization term that remains well-posed and decomposes into a geometric diversity term and unreliability cost. The resulting objective facilitates robust selection of diverse data batches under uncertainty. Furthermore, we frame this reliability-aware diversity maximization as a combinatorial semi-bandit problem and propose a UCB-style algorithm to efficiently learn the unknown reliability online. Theoretical analysis provides regret bounds for the proposed approach, ensuring performance guarantees.

---

### Test-time Generalization for Physics through Neural Operator Splitting

Authors: Louis Serrano, Jiequn Han, Edouard Oyallon, Shirley Ho, Rudy Morel
Published: 2026-01-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.00884v2

Neural operators have shown promise in learning solution maps of partial differential equations (PDEs), but they often struggle to generalize when test inputs lie outside the training distribution, such as novel initial conditions, unseen PDE coefficients or unseen physics. Prior works address this limitation with large-scale multiple physics pretraining followed by fine-tuning, but this still require examples from the new dynamics, falling short of true zero-shot generalization. In this work, we propose a method to enhance generalization at test time, i.e., without modifying pretrained weights. Building on DISCO, which provides a dictionary of neural operators trained across different dynamics, we introduce a neural operator splitting strategy that, at test time, searches over compositions of training operators to approximate unseen dynamics.On challenging out-of-distribution tasks including parameter extrapolation and novel combinations of physics phenomena, our approach achieves state-of-the-art zero-shot generalization results, while being able to recover the underlying PDE parameters. These results underscore test-time computation as a key avenue for building flexible, compositional, and generalizable neural operators.

---

### DIAMOND: Directed Inference for Artifact Mitigation in Flow Matching Models

Authors: Alicja Polowczyk, Agnieszka Polowczyk, Piotr Borycki, Joanna Waczyńska, Jacek Tabor, Przemysław Spurek
Published: 2026-01-31
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.00883v1

Despite impressive results from recent text-to-image models like FLUX, visual and anatomical artifacts remain a significant hurdle for practical and professional use. Existing methods for artifact reduction, typically work in a post-hoc manner, consequently failing to intervene effectively during the core image formation process. Notably, current techniques require problematic and invasive modifications to the model weights, or depend on a computationally expensive and time-consuming process of regional refinement. To address these limitations, we propose DIAMOND, a training-free method that applies trajectory correction to mitigate artifacts during inference. By reconstructing an estimate of the clean sample at every step of the generative trajectory, DIAMOND actively steers the generation process away from latent states that lead to artifacts. Furthermore, we extend the proposed method to standard Diffusion Models, demonstrating that DIAMOND provides a robust, zero-shot path to high-fidelity, artifact-free image synthesis without the need for additional training or weight modifications in modern generative architectures. Code is available at https://gmum.github.io/DIAMOND/

---

### ILSIC: Corpora for Identifying Indian Legal Statutes from Queries by Laypeople

Authors: Shounak Paul, Raghav Dogra, Pawan Goyal, Saptarshi Ghosh
Published: 2026-01-31
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.00881v1

Legal Statute Identification (LSI) for a given situation is one of the most fundamental tasks in Legal NLP. This task has traditionally been modeled using facts from court judgments as input queries, due to their abundance. However, in practical settings, the input queries are likely to be informal and asked by laypersons, or non-professionals. While a few laypeople LSI datasets exist, there has been little research to explore the differences between court and laypeople data for LSI. In this work, we create ILSIC, a corpus of laypeople queries covering 500+ statutes from Indian law. Additionally, the corpus also contains court case judgements to enable researchers to effectively compare between court and laypeople data for LSI. We conducted extensive experiments on our corpus, including benchmarking over the laypeople dataset using zero and few-shot inference, retrieval-augmented generation and supervised fine-tuning. We observe that models trained purely on court judgements are ineffective during test on laypeople queries, while transfer learning from court to laypeople data can be beneficial in certain scenarios. We also conducted fine-grained analyses of our results in terms of categories of queries and frequency of statutes.

---

### Dynamic Expert Sharing: Decoupling Memory from Parallelism in Mixture-of-Experts Diffusion LLMs

Authors: Hao Mark Chen, Zhiwen Mo, Royson Lee, Qianzhou Wang, Da Li, Shell Xu Hu, Wayne Luk, Timothy Hospedales, Hongxiang Fan
Published: 2026-01-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.00879v1

Among parallel decoding paradigms, diffusion large language models (dLLMs) have emerged as a promising candidate that balances generation quality and throughput. However, their integration with Mixture-of-Experts (MoE) architectures is constrained by an expert explosion: as the number of tokens generated in parallel increases, the number of distinct experts activated grows nearly linearly. This results in substantial memory traffic that pushes inference into a memory-bound regime, negating the efficiency gains of both MoE and parallel decoding. To address this challenge, we propose Dynamic Expert Sharing (DES), a novel technique that shifts MoE optimization from token-centric pruning and conventional expert skipping methods to sequence-level coreset selection. To maximize expert reuse, DES identifies a compact, high-utility set of experts to satisfy the requirements of an entire parallel decoding block. We introduce two innovative selection strategies: (1) Intra-Sequence Sharing (DES-Seq), which adapts optimal allocation to the sequence level, and (2) Saliency-Aware Voting (DES-Vote), a novel mechanism that allows tokens to collectively elect a coreset based on aggregated router weights. Extensive experiments on MoE dLLMs demonstrate that DES reduces unique expert activations by over 55% and latency by up to 38%, while retaining 99% of vanilla accuracy, effectively decoupling memory overhead from the degree of parallelism.

---

### Sublinear Time Quantum Algorithm for Attention Approximation

Authors: Zhao Song, Jianfei Xue, Jiahao Zhang, Lichen Zhang
Published: 2026-01-31
Categories: quant-ph, cs.DS, cs.LG
arXiv: https://arxiv.org/abs/2602.00874v1

Given the query, key and value matrices $Q, K, V\in \mathbb{R}^{n\times d}$, the attention module is defined as $\mathrm{Att}(Q, K, V)=D^{-1}AV$ where $A=\exp(QK^\top/\sqrt{d})$ with $\exp(\cdot)$ applied entrywise, $D=\mathrm{diag}(A{\bf 1}_n)$. The attention module is the backbone of modern transformers and large language models, but explicitly forming the softmax matrix $D^{-1}A$ incurs $Ω(n^2)$ time, motivating numerous approximation schemes that reduce runtime to $\widetilde O(nd)$ via sparsity or low-rank factorization. We propose a quantum data structure that approximates any row of $\mathrm{Att}(Q, K, V)$ using only row queries to $Q, K, V$. Our algorithm preprocesses these matrices in $\widetilde{O}\left( ε^{-1} n^{0.5} \left( s_λ^{2.5} + s_λ^{1.5} d + α^{0.5} d \right) \right)$ time, where $ε$ is the target accuracy, $s_λ$ is the $λ$-statistical dimension of the exponential kernel defined by $Q$ and $K$, and $α$ measures the row distortion of $V$ that is at most $d/{\rm srank}(V)$, the stable rank of $V$. Each row query can be answered in $\widetilde{O}(s_λ^2 + s_λd)$ time. To our knowledge, this is the first quantum data structure that approximates rows of the attention matrix in sublinear time with respect to $n$. Our approach relies on a quantum Nyström approximation of the exponential kernel, quantum multivariate mean estimation for computing $D$, and quantum leverage score sampling for the multiplication with $V$.

---

### Learning Heat-based Equations in Self-similar variables

Authors: Shihao Wang, Qipeng Qian, Jingquan Wang
Published: 2026-01-31
Categories: cs.LG, math-ph
arXiv: https://arxiv.org/abs/2602.00872v2

We study solution learning for heat-based equations in self-similar variables (SSV). We develop an SSV training framework compatible with standard neural-operator training. We instantiate this framework on the two-dimensional incompressible Navier-Stokes equations and the one-dimensional viscous Burgers equation, and perform controlled comparisons between models trained in physical coordinates and in the corresponding self-similar coordinates using two simple fully connected architectures (standard multilayer perceptrons and a factorized fully connected network). Across both systems and both architectures, SSV-trained networks consistently deliver substantially more accurate and stable extrapolation beyond the training window and better capture qualitative long-time trends. These results suggest that self-similar coordinates provide a mathematically motivated inductive bias for learning the long-time dynamics of heat-based equations.

---

### Beyond Output Critique: Self-Correction via Task Distillation

Authors: Hossein A. Rahmani, Mengting Wan, Pei Zhou, Longqi Yang, Nick Craswell, Emine Yilmaz, Sujay Kumar Jauhar
Published: 2026-01-31
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.00871v1

Large language models (LLMs) have shown promising self-correction abilities, where iterative refinement improves the quality of generated responses. However, most existing approaches operate at the level of output critique, patching surface errors while often failing to correct deeper reasoning flaws. We propose SELF-THOUGHT, a framework that introduces an intermediate step of task abstraction before solution refinement. Given an input and an initial response, the model first distills the task into a structured template that captures key variables, constraints, and problem structure. This abstraction then guides solution instantiation, grounding subsequent responses in a clearer understanding of the task and reducing error propagation. Crucially, we show that these abstractions can be transferred across models: templates generated by larger models can serve as structured guides for smaller LLMs, which typically struggle with intrinsic self-correction. By reusing distilled task structures, smaller models achieve more reliable refinements without heavy fine-tuning or reliance on external verifiers. Experiments across diverse reasoning tasks demonstrate that SELF-THOUGHT improves accuracy, robustness, and generalization for both large and small models, offering a scalable path toward more reliable self-correcting language systems.

---

### Improving Flow Matching by Aligning Flow Divergence

Authors: Yuhao Huang, Taos Transue, Shih-Hsin Wang, William Feldman, Hong Zhang, Bao Wang
Published: 2026-01-31
Categories: cs.LG, cs.AI, math.NA
arXiv: https://arxiv.org/abs/2602.00869v1

Conditional flow matching (CFM) stands out as an efficient, simulation-free approach for training flow-based generative models, achieving remarkable performance for data generation. However, CFM is insufficient to ensure accuracy in learning probability paths. In this paper, we introduce a new partial differential equation characterization for the error between the learned and exact probability paths, along with its solution. We show that the total variation gap between the two probability paths is bounded above by a combination of the CFM loss and an associated divergence loss. This theoretical insight leads to the design of a new objective function that simultaneously matches the flow and its divergence. Our new approach improves the performance of the flow-based generative model by a noticeable margin without sacrificing generation efficiency. We showcase the advantages of this enhanced training approach over CFM on several important benchmark tasks, including generative modeling for dynamical systems, DNA sequences, and videos. Code is available at \href{https://github.com/Utah-Math-Data-Science/Flow_Div_Matching}{Utah-Math-Data-Science}.

---

### Foundation CAN LM: A Pretrained Language Model For Automotive CAN Data

Authors: Akiharu Esashi, Pawissanutt Lertpongrujikorn, Justin Makino, Yuibi Fujimoto, Mohsen Amini Salehi
Published: 2026-01-31
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.00866v1

The Controller Area Network (CAN) bus provides a rich source of vehicular signals increasingly leveraged for applications in automotive and auto insurance domains, including collision detection, predictive maintenance, and driver risk modeling. Despite this potential, existing pipelines largely train isolated task-specific models on raw CAN data, with only limited efforts exploring decoded signals. Such fragmentation prevents shared representation learning and limits cross-task generalization. By contrast, natural language processing (NLP) and computer vision (CV) have been transformed by the foundation model paradigm: large-scale pretraining followed by task-specific adaptation. In this work, we introduce the foundation CAN model that demonstrates multi-objective downstream generalization using a single pretrained backbone. Our approach treats CAN data as a language: we pretrain on large-scale, unlabeled decoded CAN signals and fine-tune across heterogeneous auto insurance tasks. To enable this, we propose a unified tokenization scheme for mixed discrete-continuous signals and address challenges of temporal complexity and trip-specific variability. Our results show that one pretrained CAN model can adapt effectively to diverse predictive tasks, validating that the foundation modeling paradigm, proven in NLP and CV, also holds for CAN data. This establishes a new direction for generalizable representation learning in automotive AI.

---

### Distill3R: A Pipeline for Democratizing 3D Foundation Models on Commodity Hardware

Authors: Brandon Leblanc, Charalambos Poullis
Published: 2026-01-31
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.00865v1

While multi-view 3D reconstruction has shifted toward large-scale foundation models capable of inferring globally consistent geometry, their reliance on massive computational clusters for training has created a significant barrier to entry for most academic laboratories. To bridge this compute divide, we introduce Distill3R, a framework designed to distill the geometric reasoning of 3D foundation models into compact students fully trainable on a single workstation. Our methodology centers on two primary innovations: (1) an offline caching pipeline that decouples heavy teacher inference from the training loop through compressed supervision signals, and (2) a confidence-aware distillation loss that leverages teacher uncertainty to enable training on commodity hardware. We propose a 72M-parameter student model which achieves a 9x reduction in parameters and a 5x inference speedup compared to its 650M-parameter teacher. The student is fully trainable in under 3 days on a single workstation, whereas its teacher requires massive GPU clusters for up to a week. We demonstrate that the student preserves the structural consistency and qualitative geometric understanding required for functional 3D awareness. By providing a reproducible, single-workstation training recipe, Distill3R serves as an exploratory entry point for democratized 3D vision research and efficient edge deployment. This work is not intended to compete with state-of-the-art foundation models, but to provide an accessible research baseline for laboratories without access to large-scale compute to train and specialize models on their own domain-specific data at minimal cost.

---

### Towards Multiscale Graph-based Protein Learning with Geometric Secondary Structural Motifs

Authors: Shih-Hsin Wang, Yuhao Huang, Taos Transue, Justin Baker, Jonathan Forstater, Thomas Strohmer, Bao Wang
Published: 2026-01-31
Categories: cs.LG, cs.AI, math.NA
arXiv: https://arxiv.org/abs/2602.00862v1

Graph neural networks (GNNs) have emerged as powerful tools for learning protein structures by capturing spatial relationships at the residue level. However, existing GNN-based methods often face challenges in learning multiscale representations and modeling long-range dependencies efficiently. In this work, we propose an efficient multiscale graph-based learning framework tailored to proteins. Our proposed framework contains two crucial components: (1) It constructs a hierarchical graph representation comprising a collection of fine-grained subgraphs, each corresponding to a secondary structure motif (e.g., $α$-helices, $β$-strands, loops), and a single coarse-grained graph that connects these motifs based on their spatial arrangement and relative orientation. (2) It employs two GNNs for feature learning: the first operates within individual secondary motifs to capture local interactions, and the second models higher-level structural relationships across motifs. Our modular framework allows a flexible choice of GNN in each stage. Theoretically, we show that our hierarchical framework preserves the desired maximal expressiveness, ensuring no loss of critical structural information. Empirically, we demonstrate that integrating baseline GNNs into our multiscale framework remarkably improves prediction accuracy and reduces computational cost across various benchmarks.

---

### Multi-Head Attention Is a Multi-Player Game

Authors: Kushal Chakrabarti, Nirmal Balachundar
Published: 2026-01-31
Categories: cs.AI, cs.CL, cs.GT, cs.LG
arXiv: https://arxiv.org/abs/2602.00861v1

Modern transformer attention is internally multi-agent -- heads compete and coordinate -- yet we train it as if it were a monolithic optimizer. We formalize this gap: cross-entropy training induces an implicit potential game among heads, and gradient descent converges to Nash equilibria with potentially unbounded inefficiency due to unpriced externalities (redundancy, correlated errors). Our main result bounds the Price of Anarchy by $Γ(G)$, the off-diagonal mass of a head interaction matrix capturing weight and gradient coupling. Under mild smoothness assumptions, we prove that both \emph{excess hallucination probability} and \emph{excess head redundancy} scale with PoA, unifying two distinct failure modes into a single mechanism. The bound is prescriptive: regularization that reduces $Γ(G)$ provably tightens PoA. We instantiate this as GAME-LoRA, combining Barlow Twins decorrelation with log-determinant coordination pressure. Experiments validate the theory: $Γ(G)$ predicts hallucination ($p{<}0.05$), emergent coalitions exhibit selective coordination, and GAME-LoRA achieves up to 18\% hallucination reduction (8\% average) with no knowledge degradation -- a Pareto improvement inaccessible to methods ignoring the game structure.

---

### Unifying Adversarial Robustness and Training Across Text Scoring Models

Authors: Manveer Singh Tamber, Hosna Oyarhoseini, Jimmy Lin
Published: 2026-01-31
Categories: cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2602.00857v1

Research on adversarial robustness in language models is currently fragmented across applications and attacks, obscuring shared vulnerabilities. In this work, we propose unifying the study of adversarial robustness in text scoring models spanning dense retrievers, rerankers, and reward models. This motivates adapting both attacks and adversarial training methods across model roles. Unlike open-ended generation, text scoring failures are directly testable: an attack succeeds when an irrelevant or rejected text outscores a relevant or chosen one. Using this principled lens of text scoring, we demonstrate that current adversarial training formulations for language models are often short-sighted, failing to effectively generalize across attacks. To address this, we introduce multiple adversarial training methods for text scoring models and show that combining complementary training methods can yield strong robustness while also improving task effectiveness. We also highlight the practical value of our approach for RLHF, showing that our adversarially trained reward models mitigate reward hacking and support the training of better-aligned LLMs. We provide our code and models for further study.

---

### Position: Human-Centric AI Requires a Minimum Viable Level of Human Understanding

Authors: Fangzhou Lin, Qianwen Ge, Lingyu Xu, Peiran Li, Xiangbo Gao, Shuo Xing, Kazunori Yamada, Ziming Zhang, Haichong Zhang, Zhengzhong Tu
Published: 2026-01-31
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.00854v1

AI systems increasingly produce fluent, correct, end-to-end outcomes. Over time, this erodes users' ability to explain, verify, or intervene. We define this divergence as the Capability-Comprehension Gap: a decoupling where assisted performance improves while users' internal models deteriorate. This paper argues that prevailing approaches to transparency, user control, literacy, and governance do not define the foundational understanding humans must retain for oversight under sustained AI delegation. To formalize this, we define the Cognitive Integrity Threshold (CIT) as the minimum comprehension required to preserve oversight, autonomy, and accountable participation under AI assistance. CIT does not require full reasoning reconstruction, nor does it constrain automation. It identifies the threshold beyond which oversight becomes procedural and contestability fails. We operatinalize CIT through three functional dimensions: (i) verification capacity, (ii) comprehension-preserving interaction, and (iii) institutional scaffolds for governance. This motivates a design and governance agenda that aligns human-AI interaction with cognitive sustainability in responsibility-critical settings.

---

### Investigating the Robustness of Subtask Distillation under Spurious Correlation

Authors: Pattarawat Chormai, Klaus-Robert Müller, Grégoire Montavon
Published: 2026-01-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.00852v1

Subtask distillation is an emerging paradigm in which compact, specialized models are extracted from large, general-purpose 'foundation models' for deployment in environments with limited resources or in standalone computer systems. Although distillation uses a teacher model, it still relies on a dataset that is often limited in size and may lack representativeness or exhibit spurious correlations. In this paper, we evaluate established distillation methods, as well as the recent SubDistill method, when using data with spurious correlations for distillation. As the strength of the correlations increases, we observe a widening gap between advanced methods, such as SubDistill, which remain fairly robust, and some baseline methods, which degrade to near-random performance. Overall, our study underscores the challenges of knowledge distillation when applied to imperfect, real-world datasets, particularly those with spurious correlations.

---

### Understanding Persuasion in Long-Running Agents

Authors: Hyejun Jeong, Amir Houmansadr, Shlomo Zilberstein, Eugene Bagdasarian
Published: 2026-01-31
Categories: cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2602.00851v3

Modern AI agents increasingly combine conversational interaction with autonomous task execution, such as coding and web research, raising a natural question: What happens when an agent engaged in long-horizon tasks is exposed to user persuasion? Yet studying this possibility is challenging because long-running agent behavior is noisy and costly to reproduce, and it remains unclear which unique challenges emerge only in extended task execution. We study how belief-level intervention can influence downstream task behavior, a phenomenon we name persuasion propagation. We introduce a behavior-centered evaluation framework that distinguishes between persuasion applied during or prior to task execution. Across web research and coding tasks, we find that on-the-fly persuasion induces weak and inconsistent behavioral effects. In contrast, when the belief state is explicitly specified at task time, belief-prefilled agents conduct on average 26.9% fewer searches and visit 16.9% fewer unique sources than neutral-prefilled agents. These results suggest that persuasion, even in prior interaction, can affect the agent's behavior, motivating behavior-level evaluation in agentic systems.

---

### RMFlow: Refined Mean Flow by a Noise-Injection Step for Multimodal Generation

Authors: Yuhao Huang, Shih-Hsin Wang, Andrea L. Bertozzi, Bao Wang
Published: 2026-01-31
Categories: cs.LG, cs.AI, math.NA
arXiv: https://arxiv.org/abs/2602.00849v1

Mean flow (MeanFlow) enables efficient, high-fidelity image generation, yet its single-function evaluation (1-NFE) generation often cannot yield compelling results. We address this issue by introducing RMFlow, an efficient multimodal generative model that integrates a coarse 1-NFE MeanFlow transport with a subsequent tailored noise-injection refinement step. RMFlow approximates the average velocity of the flow path using a neural network trained with a new loss function that balances minimizing the Wasserstein distance between probability paths and maximizing sample likelihood. RMFlow achieves near state-of-the-art results on text-to-image, context-to-molecule, and time-series generation using only 1-NFE, at a computational cost comparable to the baseline MeanFlows.

---

### Factuality on Demand: Controlling the Factuality-Informativeness Trade-off in Text Generation

Authors: Ziwei Gong, Yanda Chen, Julia Hirschberg, Chen Zhao, He He, Zhou Yu, Kathleen Mckeown
Published: 2026-01-31
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.00848v1

Large language models (LLMs) encode knowledge with varying degrees of confidence. When responding to queries, models face an inherent trade-off: they can generate responses that are less informative but highly factual, or more informative but potentially less accurate. Different applications demand different balances between informativeness and factuality. We introduce Factuality-Controlled Generation (FCG), a framework that enables users to specify factuality constraints alongside their queries. We propose to evaluate FCG performance on two dimensions: adherence to factuality constraints and response informativeness. We propose to train models on the FCG task using synthetic data, and show that our synthetic training significantly improves models' ability to both respect factuality requirements and maintain informativeness in their outputs.

---

### Omni-RRM: Advancing Omni Reward Modeling via Automatic Rubric-Grounded Preference Synthesis

Authors: Zicheng Kong, Dehua Ma, Zhenbo Xu, Alven Yang, Yiwei Ru, Haoran Wang, Zixuan Zhou, Fuqing Bie, Liuyu Xiang, Huijia Wu, Jian Zhao, Zhaofeng He
Published: 2026-01-31
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.00846v2

Multimodal large language models (MLLMs) struggle with alignment due to the limitations of existing reward models (RMs), which are predominantly vision-centric, dependent on costly human labels, and provide opaque scalar scores that fail to capture nuanced reasoning, leading to brittle alignment. We present Omni-RRM, an \textbf{Omni}-modal \textbf{R}ubric-grounded \textbf{R}eward \textbf{M}odel that generates multi-dimensional reward signals across text, image, video, and audio. To overcome the high cost and inherent inconsistency of human-centric evaluation in multi-dimensional reasoning, we introduce \textbf{Omni-Preference}, a high-quality dataset constructed via automatic rubric-grounded preference synthesis. In this pipeline, teacher models reconcile raw preferences into explicit justifications, ensuring that the synthesized supervision is both high-fidelity and interpretable. Omni-RRM is trained using a progressive SFT + GRPO regimen, specifically optimized to sharpen reward discrimination on low-margin, hard preference pairs. It achieves state-of-the-art accuracy on video (80.2\% on ShareGPT-Video) and audio benchmarks (66.8\% on Audio-HH-RLHF and 65.0\% on TA2T), yielding a five-benchmark Overall accuracy of 70.4\% and a +17.0\% relative gain over its backbone. Furthermore, Omni-RRM effectively guides Best-of-$N$ selection and exhibits robust transfer to text-only alignment. All resources, including the dataset, training and inference code, and model checkpoints are available at https://tmfk418.github.io/Omni-RRM.

---

### Optimizing Agentic Reasoning with Retrieval via Synthetic Semantic Information Gain Reward

Authors: Senkang Hu, Yong Dai, Yuzhi Zhao, Yihang Tao, Yu Guo, Zhengru Fang, Sam Tak Wu Kwong, Yuguang Fang
Published: 2026-01-31
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.00845v3

Agentic reasoning enables large reasoning models (LRMs) to dynamically acquire external knowledge, but yet optimizing the retrieval process remains challenging due to the lack of dense, principled reward signals. In this paper, we introduce InfoReasoner, a unified framework that incentivizes effective information seeking via a synthetic semantic information gain reward. Theoretically, we redefine information gain as uncertainty reduction over the model's belief states, establishing guarantees, including non-negativity, telescoping additivity, and channel monotonicity. Practically, to enable scalable optimization without manual retrieval annotations, we propose an output-aware intrinsic estimator that computes information gain directly from the model's output distributions using semantic clustering via bidirectional textual entailment. This intrinsic reward guides the policy to maximize epistemic progress, enabling efficient training via Group Relative Policy Optimization (GRPO). Experiments across seven question-answering benchmarks demonstrate that InfoReasoner consistently outperforms strong retrieval-augmented baselines, achieving up to 5.4% average accuracy improvement. Our work provides a theoretically grounded and scalable path toward agentic reasoning with retrieval. The code is available at https://github.com/dl-m9/InfoReasoner

---

### Multivariate Time Series Data Imputation via Distributionally Robust Regularization

Authors: Che-Yi Liao, Zheng Dong, Gian-Gabriel Garcia, Kamran Paynabar
Published: 2026-01-31
Categories: stat.ML, cs.LG, stat.AP
arXiv: https://arxiv.org/abs/2602.00844v2

Multivariate time series imputation is often compromised by mismatch between the observed and true data distributions, a bias induced by the combined effects of time-series non-stationarity and systematic missingness. Standard methods that encourage point-wise reconstruction or direct distributional alignment may overfit these biased observations. We propose the Distributionally Robust Regularized Imputer Objective (DRIO), which jointly minimizes reconstruction error and the worst-case divergence between the imputer distribution and data distributions within a Wasserstein ambiguity set. We derive a tractable upper-bound surrogate that reduces infinite-dimensional optimization over measures to adversarial search over sample trajectories, and develop an alternating learning algorithm compatible with modern deep learning backbones. Comprehensive experiments on diverse real-world datasets show that DRIO consistently provides robust imputation and suggests improved downstream forecasting under various missingness scenarios.

---

### NegaBent, No Regrets: Evolving Spectrally Flat Boolean Functions

Authors: Claude Carlet, Marko Ðurasevic, Ermes Franch, Domagoj Jakobovic, Luca Mariot, Stjepan Picek
Published: 2026-01-31
Categories: cs.NE, cs.CR
arXiv: https://arxiv.org/abs/2602.00843v1

Negabent Boolean functions are defined by having a flat magnitude spectrum under the nega-Hadamard transform. They exist in both even and odd dimensions, and the subclass of functions that are simultaneously bent and negabent (bent-negabent) has attracted interest due to the combined optimal periodic and negaperiodic spectral properties. In this work, we investigate how evolutionary algorithms can be used to evolve (bent-)negabent Boolean functions. Our experimental results indicate that evolutionary algorithms, especially genetic programming, are a suitable approach for evolving negabent Boolean functions, and we successfully evolve such functions in all dimensions we consider.

---

### Beyond First-Order: Learning Riemannian Geometries for Invariant Visual Place Recognition

Authors: Jintao Cheng, Weibin Li, Zhijian He, Jin Wu, Chi Man Vong, Wei Zhang
Published: 2026-01-31
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.00841v4

Visual Place Recognition (VPR) demands representations robust to drastic environmental and viewpoint shifts. Existing aggregation paradigms either depend on extensive supervised training or rely on first-order pooling, often struggling to preserve structural correlations under extreme shifts or incurring high adaptation costs. In this work, we propose Riemannian Invariant Aggregation (RIA), a unified geometric framework that explicitly models second-order scene structure on the Symmetric Positive Definite (SPD) manifold. By treating perturbations as tractable congruence transformations, RIA leverages geometry-aware Riemannian mappings to project covariance descriptors into a linearized Euclidean space, effectively preserving invariant structural components while suppressing noise. Extensive evaluations demonstrate that RIA achieves zero-shot performance comparable to supervised methods, and establishes state-of-the-art accuracy with simple fine-tuning, particularly in unstructured environments. The source code will be released.

---

### TransNormal: Dense Visual Semantics for Diffusion-based Transparent Object Normal Estimation

Authors: Mingwei Li, Hehe Fan, Yi Yang
Published: 2026-01-31
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.00839v1

Monocular normal estimation for transparent objects is critical for laboratory automation, yet it remains challenging due to complex light refraction and reflection. These optical properties often lead to catastrophic failures in conventional depth and normal sensors, hindering the deployment of embodied AI in scientific environments. We propose TransNormal, a novel framework that adapts pre-trained diffusion priors for single-step normal regression. To handle the lack of texture in transparent surfaces, TransNormal integrates dense visual semantics from DINOv3 via a cross-attention mechanism, providing strong geometric cues. Furthermore, we employ a multi-task learning objective and wavelet-based regularization to ensure the preservation of fine-grained structural details. To support this task, we introduce TransNormal-Synthetic, a physics-based dataset with high-fidelity normal maps for transparent labware. Extensive experiments demonstrate that TransNormal significantly outperforms state-of-the-art methods: on the ClearGrasp benchmark, it reduces mean error by 24.4% and improves 11.25° accuracy by 22.8%; on ClearPose, it achieves a 15.2% reduction in mean error. The code and dataset will be made publicly available at https://longxiang-ai.github.io/TransNormal.

---

### Exploration of Unary Arithmetic-Based Matrix Multiply Units for Low Precision DL Accelerators

Authors: Prabhu Vellaisamy, Harideep Nair, Di Wu, Shawn Blanton, John Paul Shen
Published: 2026-01-31
Categories: cs.AR, cs.AI
arXiv: https://arxiv.org/abs/2602.00838v1

General matrix multiplication (GEMM) is a fundamental operation in deep learning (DL). With DL moving increasingly toward low precision, recent works have proposed novel unary GEMM designs as an alternative to conventional binary GEMM hardware. A rigorous evaluation of recent unary and binary GEMM designs is needed to assess the potential of unary hardware for future DL compute. This paper focuses on unary GEMM designs for integer-based DL inference and performs a detailed evaluation of three latest unary design proposals, namely, uGEMM, tuGEMM and tubGEMM, by comparing them to a conventional binary GEMM. Rigorous post-synthesis evaluations beyond prior works are performed across varying bit-widths and matrix sizes to assess the designs' tradeoffs and determine optimal sweetspots. Further, we perform weight sparsity analysis across eight pretrained convolutional neural networks (CNNs) and the LLaMA2 large language model (LLM). In this work, we demonstrate how unary GEMM can be effectively used for energy-efficient compute in future edge AI accelerators.

---

### IDEM Enough? Evolving Highly Nonlinear Idempotent Boolean Functions

Authors: Claude Carlet, Marko Ðurasevic, Domagoj Jakobovic, Luca Mariot, Stjepan Picek
Published: 2026-01-31
Categories: cs.CR, cs.NE
arXiv: https://arxiv.org/abs/2602.00837v1

Idempotent Boolean functions form a highly structured subclass of Boolean functions that is closely related to rotation symmetry under a normal-basis representation and to invariance under a fixed linear map in a polynomial basis. These functions are attractive as candidates for cryptographic design, yet their additional algebraic constraints make the search for high nonlinearity substantially more difficult than in the unconstrained case. In this work, we investigate evolutionary methods for constructing highly nonlinear idempotent Boolean functions for dimensions $n=5$ up to $n=12$ using a polynomial basis representation with canonical primitive polynomials. Our results show that the problem of evolving idempotent functions is difficult due to the disruptive nature of crossover and mutation operators. Next, we show that idempotence can be enforced by encoding the truth table on orbits, yielding a compact genome of size equal to the number of distinct squaring orbits.

---

### Score-based Metropolis-Hastings for Fractional Langevin Algorithms

Authors: Ahmed Aloui, Junyi Liao, Ali Hasan, Jose Blanchet, Vahid Tarokh
Published: 2026-01-31
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2602.00835v1

Sampling from heavy-tailed and multimodal distributions is challenging when neither the target density nor the proposal density can be evaluated, as in $α$-stable Lévy-driven fractional Langevin algorithms. While the target distribution can be estimated from data via score-based or energy-based models, the $α$-stable proposal density and its score are generally unavailable, rendering classical density-based Metropolis--Hastings (MH) corrections impractical. Consequently, existing fractional Langevin methods operate in an unadjusted regime and can exhibit substantial finite-time errors and poor empirical control of tail behavior. We introduce the Metropolis-Adjusted Fractional Langevin Algorithm (MAFLA), an MH-inspired, fully score-based correction mechanism. MAFLA employs designed proxies for fractional proposal score gradients under isotropic symmetric $α$-stable noise and learns an acceptance function via Score Balance Matching. We empirically illustrate the strong performance of MAFLA on a series of tasks including combinatorial optimization problems where the method significantly improves finite time sampling accuracy over unadjusted fractional Langevin dynamics.

---

### A Minimum Variance Path Principle for Accurate and Stable Score-Based Density Ratio Estimation

Authors: Wei Chen, Jiacheng Li, Shigui Li, Zhiqi Lin, Junmei Yang, John Paisley, Delu Zeng
Published: 2026-01-31
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2602.00834v4

Score-based methods are powerful across machine learning, but they face a paradox: theoretically path-independent, yet practically path-dependent. We resolve this by proving that practical training objectives differ from the ideal, ground-truth objective by a crucial, overlooked term: the path variance of the score function. We propose the MVP (**M**imum **V**ariance **P**ath) Principle to minimize this path variance. Our key contribution is deriving a closed-form expression for the variance, making optimization tractable. By parameterizing the path with a flexible Kumaraswamy Mixture Model, our method learns data-adaptive, low-variance paths without heuristic manual selection. This principled optimization of the complete objective yields more accurate and stable estimators, establishing new state-of-the-art results on challenging benchmarks and providing a general framework for optimizing score-based interpolation. Our code can be found in https://github.com/Hoemr/OpenDRE.git.

---

### Over-Alignment vs Over-Fitting: The Role of Feature Learning Strength in Generalization

Authors: Taesun Yeom, Taehyeok Ha, Jaeho Lee
Published: 2026-01-31
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2602.00827v2

Feature learning strength (FLS), i.e., the inverse of the effective output scaling of a model, plays a critical role in shaping the optimization dynamics of neural nets. While its impact has been extensively studied under the asymptotic regimes -- both in training time and FLS -- existing theory offers limited insight into how FLS affects generalization in practical settings, such as when training is stopped upon reaching a target training risk. In this work, we investigate the impact of FLS on generalization in deep networks under such practical conditions. Through empirical studies, we first uncover the emergence of an $\textit{optimal FLS}$ -- neither too small nor too large -- that yields substantial generalization gains. This finding runs counter to the prevailing intuition that stronger feature learning universally improves generalization. To explain this phenomenon, we develop a theoretical analysis of gradient flow dynamics in two-layer ReLU nets trained with logistic loss, where FLS is controlled via initialization scale. Our main theoretical result establishes the existence of an optimal FLS arising from a trade-off between two competing effects: An excessively large FLS induces an $\textit{over-alignment}$ phenomenon that degrades generalization, while an overly small FLS leads to $\textit{over-fitting}$.

---

### Harmful Overfitting in Sobolev Spaces

Authors: Kedar Karhadkar, Alexander Sietsema, Deanna Needell, Guido Montufar
Published: 2026-01-31
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2602.00825v1

Motivated by recent work on benign overfitting in overparameterized machine learning, we study the generalization behavior of functions in Sobolev spaces $W^{k, p}(\mathbb{R}^d)$ that perfectly fit a noisy training data set. Under assumptions of label noise and sufficient regularity in the data distribution, we show that approximately norm-minimizing interpolators, which are canonical solutions selected by smoothness bias, exhibit harmful overfitting: even as the training sample size $n \to \infty$, the generalization error remains bounded below by a positive constant with high probability. Our results hold for arbitrary values of $p \in (1, \infty)$, in contrast to prior results studying the Hilbert space case ($p = 2$) using kernel methods. Our proof uses a geometric argument which identifies harmful neighborhoods of the training data using Sobolev inequalities.

---

### Safety-Efficacy Trade Off: Robustness against Data-Poisoning

Authors: Diego Granziol
Published: 2026-01-31
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2602.00822v1

Backdoor and data poisoning attacks can achieve high attack success while evading existing spectral and optimisation based defences. We show that this behaviour is not incidental, but arises from a fundamental geometric mechanism in input space. Using kernel ridge regression as an exact model of wide neural networks, we prove that clustered dirty label poisons induce a rank one spike in the input Hessian whose magnitude scales quadratically with attack efficacy. Crucially, for nonlinear kernels we identify a near clone regime in which poison efficacy remains order one while the induced input curvature vanishes, making the attack provably spectrally undetectable. We further show that input gradient regularisation contracts poison aligned Fisher and Hessian eigenmodes under gradient flow, yielding an explicit and unavoidable safety efficacy trade off by reducing data fitting capacity. For exponential kernels, this defence admits a precise interpretation as an anisotropic high pass filter that increases the effective length scale and suppresses near clone poisons. Extensive experiments on linear models and deep convolutional networks across MNIST and CIFAR 10 and CIFAR 100 validate the theory, demonstrating consistent lags between attack success and spectral visibility, and showing that regularisation and data augmentation jointly suppress poisoning. Our results establish when backdoors are inherently invisible, and provide the first end to end characterisation of poisoning, detectability, and defence through input space curvature.

---

### Zero-Shot Generative De-identification: Inversion-Free Flow for Privacy-Preserving Skin Image Analysis

Authors: Konstantinos Moutselos, Ilias Maglogiannis
Published: 2026-01-31
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.00821v2

The secure analysis of dermatological images in clinical environments is fundamentally restricted by the critical trade-off between patient privacy and the preservation of diagnostic fidelity. Traditional de-identification techniques often degrade essential pathological markers, while state-of-the-art generative approaches typically require computationally intensive inversion processes or extensive task-specific fine-tuning, limiting their feasibility for real-time deployment. This study introduces a zero-shot generative de-identification framework that utilizes an inversion-free pipeline for privacy-preserving medical image analysis. By leveraging Rectified Flow Transformers (FlowEdit), the proposed method achieves high-fidelity identity transformation in less than 20 seconds without requiring pathology-specific training or labeled datasets. We introduce a novel "segment-by-synthesis" mechanism that generates counterfactual "healthy" and "pathological" digital twin pairs to isolate clinical signals from biometric identifiers in a zero-shot manner. Our approach specifically utilizes the CIELAB color space to decouple erythema-related pathological signals from semantic noise and individual skin characteristics. Pilot validation on high-resolution clinical samples demonstrates robust stability in preserving pathological features, achieving an Intersection over Union (IoU) stability exceeding 0.67, while ensuring rigorous de-identification. These results suggest that the proposed zero-shot, inversion-free approach provides a scalable and efficient solution for secure data sharing and collaborative biomedical research, bypassing the need for large-scale annotated medical datasets while aligning with data protection standards.

---

### Hessian Spectral Analysis at Foundation Model Scale

Authors: Diego Granziol, Khurshid Juarev
Published: 2026-01-31
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2602.00816v1

Accurate Hessian spectra of foundation models have remained out of reach, leading most prior work to rely on small models or strong structural approximations. We show that faithful spectral analysis of the true Hessian is tractable at frontier scale. Using shard-local finite-difference Hessian vector products compatible with Fully Sharded Data Parallelism, we perform stochastic Lanczos quadrature on open-source language models with up to 100B parameters, producing the first large-scale spectral density estimates beyond the sub-10B regime. We characterize the numerical behavior of this pipeline, including finite-difference bias, floating-point noise amplification, and their effect on Krylov stability in fp32 and bf16, and derive practical operating regimes that are validated empirically. We further provide end-to-end runtime and memory scaling laws, showing that full-operator spectral probing incurs only a modest constant-factor overhead over first-order training. Crucially, direct access to the Hessian reveals that widely used block-diagonal curvature approximations can fail catastrophically, exhibiting order-one relative error and poor directional alignment even in mid-scale LLMs. Together, our results demonstrate that foundation-model Hessian spectra are both computable and qualitatively misrepresented by prevailing approximations, opening the door to principled curvature-based analysis at scale.

---

### Resource-Efficient Reinforcement for Reasoning Large Language Models via Dynamic One-Shot Policy Refinement

Authors: Yunjian Zhang, Sudong Wang, Yang Li, Peiran Xu, Conghao Zhou, Xiaoyue Ma, Jianing Li, Yao Zhu
Published: 2026-01-31
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.00815v2

Large language models (LLMs) have exhibited remarkable performance on complex reasoning tasks, with reinforcement learning under verifiable rewards (RLVR) emerging as a principled framework for aligning model behavior with reasoning chains. Despite its promise, RLVR remains prohibitively resource-intensive, requiring extensive reward signals and incurring substantial rollout costs during training. In this work, we revisit the fundamental question of data and compute efficiency in RLVR. We first establish a theoretical lower bound on the sample complexity required to unlock reasoning capabilities, and empirically validate that strong performance can be achieved with a surprisingly small number of training instances. To tackle the computational burden, we propose Dynamic One-Shot Policy Refinement (DoPR), an uncertainty-aware RL strategy that dynamically selects a single informative training sample per batch for policy updates, guided by reward volatility and exploration-driven acquisition. DoPR reduces rollout overhead by nearly an order of magnitude while preserving competitive reasoning accuracy, offering a scalable and resource-efficient solution for LLM post-training. This approach offers a practical path toward more efficient and accessible RL-based training for reasoning-intensive LLM applications.

---

### SyNeT: Synthetic Negatives for Traversability Learning

Authors: Bomena Kim, Hojun Lee, Younsoo Park, Yaoyu Hu, Sebastian Scherer, Inwook Shim
Published: 2026-01-31
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2602.00814v2

Reliable traversability estimation is crucial for autonomous robots to navigate complex outdoor environments safely. Existing self-supervised learning frameworks primarily rely on positive and unlabeled data; however, the lack of explicit negative data remains a critical limitation, hindering the model's ability to accurately identify diverse non-traversable regions. To address this issue, we introduce a method to explicitly construct synthetic negatives, representing plausible but non-traversable, and integrate them into vision-based traversability learning. Our approach is formulated as a training strategy that can be seamlessly integrated into both Positive-Unlabeled (PU) and Positive-Negative (PN) frameworks without modifying inference architectures. Complementing standard pixel-wise metrics, we introduce an object-centric FPR evaluation approach that analyzes predictions in regions where synthetic negatives are inserted. This evaluation provides an indirect measure of the model's ability to consistently identify non-traversable regions without additional manual labeling. Extensive experiments on both public and self-collected datasets demonstrate that our approach significantly enhances robustness and generalization across diverse environments. The source code and demonstration videos will be publicly available.

---

### Generating a Paracosm for Training-Free Zero-Shot Composed Image Retrieval

Authors: Tong Wang, Yunhan Zhao, Shu Kong
Published: 2026-01-31
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.00813v6

Composed Image Retrieval (CIR) is the task of retrieving a target image from a database using a multimodal query, which consists of a reference image and a modification text. The text specifies how to alter the reference image to form a ''mental image'', based on which CIR should find the target image in the database. The fundamental challenge of CIR is that this ''mental image'' is not physically available and is only implicitly defined by the query. The contemporary literature pursues zero-shot methods and uses a Large Multimodal Model (LMM) to generate a textual description for a given multimodal query, and then employs a Vision-Language Model (VLM) for textual-visual matching to search for the target image. In contrast, we address CIR from first principles by directly generating the ''mental image'' for more accurate matching. Particularly, we prompt an LMM to generate a ''mental image'' for a given multimodal query and propose to use this ''mental image'' to search for the target image. As the ''mental image'' has a synthetic-to-real domain gap with real images, we also generate a synthetic counterpart for each real image in the database to facilitate matching. In this sense, our method uses LMM to construct a ``paracosm'', where it matches the multimodal query and database images. Hence, we call this method Paracosm. Notably, Paracosm is a training-free zero-shot CIR method. It significantly outperforms existing zero-shot methods on challenging benchmarks, achieving state-of-the-art performance for zero-shot CIR.

---

### MissMAC-Bench: Building Solid Benchmark for Missing Modality Issue in Robust Multimodal Affective Computing

Authors: Ronghao Lin, Honghao Lu, Ruixing Wu, Aolin Xiong, Qinggong Chu, Qiaolin He, Sijie Mai, Haifeng Hu
Published: 2026-01-31
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.00811v1

As a knowledge discovery task over heterogeneous data sources, current Multimodal Affective Computing (MAC) heavily rely on the completeness of multiple modalities to accurately understand human's affective state. However, in real-world scenarios, the availability of modality data is often dynamic and uncertain, leading to substantial performance fluctuations due to the distribution shifts and semantic deficiencies of the incomplete multimodal inputs. Known as the missing modality issue, this challenge poses a critical barrier to the robustness and practical deployment of MAC models. To systematically quantify this issue, we introduce MissMAC-Bench, a comprehensive benchmark designed to establish fair and unified evaluation standards from the perspective of cross-modal synergy. Two guiding principles are proposed, including no missing prior during training, and one single model capable of handling both complete and incomplete modality scenarios, thereby ensuring better generalization. Moreover, to bridge the gap between academic research and real-world applications, our benchmark integrates evaluation protocols with both fixed and random missing patterns at the dataset and instance levels. Extensive experiments conducted on 3 widely-used language models across 4 datasets validate the effectiveness of diverse MAC approaches in tackling the missing modality issue. Our benchmark provides a solid foundation for advancing robust multimodal affective computing and promotes the development of multimedia data mining.

---

### VVLoc: Prior-free 3-DoF Vehicle Visual Localization

Authors: Ze Huang, Zhongyang Xiao, Mingliang Song, Longan Yang, Hongyuan Yuan, Li Sun
Published: 2026-01-31
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2602.00810v1

Localization is a critical technology in autonomous driving, encompassing both topological localization, which identifies the most similar map keyframe to the current observation, and metric localization, which provides precise spatial coordinates. Conventional methods typically address these tasks independently, rely on single-camera setups, and often require additional 3D semantic or pose priors, while lacking mechanisms to quantify the confidence of localization results, making them less feasible for real industrial applications. In this paper, we propose VVLoc, a unified pipeline that employs a single neural network to concurrently achieve topological and metric vehicle localization using multi-camera system. VVLoc first evaluates the geo-proximity between visual observations, then estimates their relative metric poses using a matching strategy, while also providing a confidence measure. Additionally, the training process for VVLoc is highly efficient, requiring only pairs of visual data and corresponding ground-truth poses, eliminating the need for complex supplementary data. We evaluate VVLoc not only on the publicly available datasets, but also on a more challenging self-collected dataset, demonstrating its ability to deliver state-of-the-art localization accuracy across a wide range of localization tasks.

---

### Mobile Exergames: Activity Recognition Based on Smartphone Sensors

Authors: David Craveiro, Hugo Silva
Published: 2026-01-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.00809v1

Smartphone sensors can be extremely useful in providing information on the activities and behaviors of persons. Human activity recognition is increasingly used for games, medical, or surveillance. In this paper, we propose a proof-of-concept 2D endless game called Duck Catch & Fit, which implements a detailed activity recognition system that uses a smartphone accelerometer, gyroscope, and magnetometer sensors. The system applies feature extraction and learning mechanism to detect human activities like staying, side movements, and fake side movements. In addition, a voice recognition system is combined to recognize the word "fire" and raise the game's complexity. The results show that it is possible to use machine learning techniques to recognize human activity with high recognition levels. Also, the combination of movement-based and voice-based integrations contributes to a more immersive gameplay.

---

### Any3D-VLA: Enhancing VLA Robustness via Diverse Point Clouds

Authors: Xianzhe Fan, Shengliang Deng, Xiaoyang Wu, Yuxiang Lu, Zhuoling Li, Mi Yan, Yujia Zhang, Zhizheng Zhang, He Wang, Hengshuang Zhao
Published: 2026-01-31
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2602.00807v2

Existing Vision-Language-Action (VLA) models typically take 2D images as visual input, which limits their spatial understanding in complex scenes. How can we incorporate 3D information to enhance VLA capabilities? We conduct a pilot study across different observation spaces and visual representations. The results show that explicitly lifting visual input into point clouds yields representations that better complement their corresponding 2D representations. To address the challenges of (1) scarce 3D data and (2) the domain gap induced by cross-environment differences and depth-scale biases, we propose Any3D-VLA. It unifies the simulator, sensor, and model-estimated point clouds within a training pipeline, constructs diverse inputs, and learns domain-agnostic 3D representations that are fused with the corresponding 2D representations. Simulation and real-world experiments demonstrate Any3D-VLA's advantages in improving performance and mitigating the domain gap. Our project homepage is available at https://xianzhefan.github.io/Any3D-VLA.github.io.

---