# Research Papers — 2026-02 · bundle page 40 of 210

> Full-text markdown of papers #1951–2000 of 10493 published in 2026-02, newest first. AI-readable mirrors of the full 10493-paper 2026-02 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-02/page/40
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/39.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/41.md)

### OrthoAI: A Neurosymbolic Framework for Evidence-Grounded Biomechanical Reasoning in Clear Aligner Orthodontics

Authors: Edouard Lansiaux, Margaux Leman, Mehdi Ammi
Published: 2026-02-23
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.00124v2

Automated clinical decision support for clear aligner orthodontics faces a key challenge: bridging geometric perception (3D tooth segmentation) with clinical reasoning (biomechanical feasibility). We address this with OrthOAI, introducing three methodological contributions. First, sparse-supervision segmentation: a landmark-to-point-cloud synthesis protocol enables training from sparse anatomical annotations (6-8 points per tooth) instead of dense labels, combined with a clinically stratified loss mixing label-smoothed cross-entropy and a batch-adaptive Dice term for class imbalance. Second, knowledge-grounded constraint inference: biomechanical feasibility is modeled as a Constraint Satisfaction Problem over a domain ontology of tooth movements, encoding evidence-based per-stage limits as soft and hard constraints. Third, multi-criteria treatment evaluation: treatment quality is scored through a formal Multi-Criteria Decision Analysis framework using a weighted Additive Value Function grounded in clinical priority theory. On landmark-reconstructed point clouds from 3DTeethLand (MICCAI 2024), segmentation reaches 81.4% Tooth Identification Rate with 60,705 parameters. Ablations quantify the impact of each design choice. End-to-end inference runs in under 4 seconds on CPU. We also outline the gap between the current prototype-trained on synthetic ellipsoidal approximations-and clinical deployment, with a roadmap for validation. Code and weights are released.

---

### CT-Flow: Orchestrating CT Interpretation Workflow with Model Context Protocol Servers

Authors: Yannian Gu, Xizhuo Zhang, Linjie Mu, Yongrui Yu, Zhongzhen Huang, Shaoting Zhang, Xiaofan Zhang
Published: 2026-02-23
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.00123v1

Recent advances in Large Vision-Language Models (LVLMs) have shown strong potential for multi-modal radiological reasoning, particularly in tasks like diagnostic visual question answering (VQA) and radiology report generation. However, most existing approaches for 3D CT analysis largely rely on static, single-pass inference. In practice, clinical interpretation is a dynamic, tool-mediated workflow where radiologists iteratively review slices and use measurement, radiomics, and segmentation tools to refine findings. To bridge this gap, we propose CT-Flow, an agentic framework designed for interoperable volumetric interpretation. By leveraging the Model Context Protocol (MCP), CT-Flow shifts from closed-box inference to an open, tool-aware paradigm. We curate CT-FlowBench, the first large-scale instruction-tuning benchmark tailored for 3D CT tool-use and multi-step reasoning. Built upon this, CT-Flow functions as a clinical orchestrator capable of decomposing complex natural language queries into automated tool-use sequences. Experimental evaluations on CT-FlowBench and standard 3D VQA datasets demonstrate that CT-Flow achieves state-of-the-art performance, surpassing baseline models by 41% in diagnostic accuracy and achieving a 95% success rate in autonomous tool invocation. This work provides a scalable foundation for integrating autonomous, agentic intelligence into real-world clinical radiology.

---

### NovaLAD: A Fast, CPU-Optimized Document Extraction Pipeline for Generative AI and Data Intelligence

Authors: Aman Ulla
Published: 2026-02-23
Categories: cs.CV, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2603.00122v1

Document extraction is an important step before retrieval-augmented generation (RAG), knowledge bases, and downstream generative AI can work. It turns unstructured documents like PDFs and scans into structured text and layout-aware representations. We introduce NovaLAD, a comprehensive document parsing system that integrates two concurrent YOLO object detection models - element detection and layout detection - with rule-based grouping and optional vision-language enhancement. When a page image is sent in, the first thing that happens is that it goes through both models at the same time. The element model finds semantic content like the title, header, text, table, image, and so on, and the layout model finds structural regions like layout_box, column_group, multi_column, row_group, and so on. A key design decision is to first send an image or figure through an image classifier (ViT) that decides whether it is relevant or not. Only useful images are then submitted to the Vision LLM for title, summary, and structured information, which cuts down on noise and costs. NovaLAD is built for speed: it works on CPU, employs parallel execution for detection, classification, OCR, and conversion, and generates several forms, including structured JSON, Markdown, RAG-ready texts, and knowledge graphs. We test on the DP-Bench benchmark (upstage/dp-bench) and get 96.49% TEDS and 98.51% NID, which is better than both commercial and open-source parsers. This paper explains how to extract data, how the architecture works, how data flows, and how to make NovaLAD both accurate and usable without needing a GPU.

---

### SIGMAS: Second-Order Interaction-based Grouping for Overlapping Multi-Agent Swarms

Authors: Minah Lee, Saibal Mukhopadhyay
Published: 2026-02-23
Categories: cs.MA, cs.AI
arXiv: https://arxiv.org/abs/2603.00120v1

Swarming systems, such as drone fleets and robotic teams, exhibit complex dynamics driven by both individual behaviors and emergent group-level interactions. Unlike traditional multi-agent domains such as pedestrian crowds or traffic systems, swarms typically consist of a few large groups with inherent and persistent memberships, making group identification essential for understanding fine-grained behavior. We introduce the novel task of group prediction in overlapping multi-agent swarms, where latent group structures must be inferred directly from agent trajectories without ground-truth supervision. To address this challenge, we propose SIGMAS (Second-order Interaction-based Grouping for Multi-Agent Swarms), a self-supervised framework that goes beyond direct pairwise interactions and model second-order interaction across agents. By capturing how similarly agents interact with others, SIGMAS enables robust group inference and adaptively balances individual and collective dynamics through a learnable gating mechanism for joint reasoning. Experiments across diverse synthetic swarm scenarios demonstrate that SIGMAS accurately recovers latent group structures and remains robust under simultaneously overlapping swarm dynamics, establishing both a new benchmark task and a principled modeling framework for swarm understanding.

---

### PACIFIER: Pacing Opinion Depolarization via a Unified Graph Learning Framework

Authors: Mingkai Liao, Zijun Zhang, Mingyang Zhou
Published: 2026-02-23
Categories: cs.SI, cs.LG
arXiv: https://arxiv.org/abs/2602.23390v4

Online social networks often form opposing echo chambers that reinforce opinion polarization. Under the Friedkin-Johnsen (FJ) model, ModerateInternal (MI) and ModerateExpressed (ME) reduce polarization by neutralizing selected users' internal or expressed opinions, but existing solutions are largely model-specific and learning-based depolarization remains underexplored. We study FJ-based moderation as feedback-free autoregressive sequential planning and propose PACIFIER, a unified graph-learning framework that constructs ordered intervention sequences from the initial graph-opinion instance without using recomputed post-intervention expressed opinions as intermediate feedback. PACIFIER combines history-aware node representations with Greedy and RL variants for immediate and long-horizon action scoring, and supports MI, ME, continuous opinions, cost-aware moderation, and node removal. We evaluate intervention trajectories by Accumulated Normalized Polarization (ANP). Trained only on synthetic graphs with fewer than 50 nodes, PACIFIER transfers to 15 real-world Twitter networks with up to 155,599 nodes. It improves over the strongest non-PACIFIER baseline by up to 35.3%, while PACIFIER-RL improves over PACIFIER-Greedy by up to 37.69%. Compared with oracle-style Greedy, PACIFIER retains 98.94% and 97.39% near-oracle quality on MI and ME, respectively, and is about 600x faster at the 450-node range. The source code is available at https://github.com/RickyYY-SZU/PACIFIER

---

### PACIFIER: Pacing Opinion Depolarization via a Unified Graph Learning Framework

Authors: Mingkai Liao
Published: 2026-02-23
Categories: cs.SI, cs.LG
arXiv: https://arxiv.org/abs/2602.23390v3

PACIFIER: Pacing Opinion Depolarization via a Unified Graph Learning Framework Opinion polarization moderation under the Friedkin-Johnsen (FJ) model is typically treated as an analytical optimization problem. Existing algorithms rely on linear steady-state analysis and repeated equilibrium recomputation, leading to poor scalability and limited adaptability to rich intervention regimes. This paper explores whether polarization moderation can be reformulated as a graph-based sequential planning problem. We propose PACIFIER, the first unified graph-learning and graph reinforcement learning framework for FJ-based intervention. It reformulates canonical MI and ME problems as ordered graph-intervention tasks evaluated by Accumulated Normalized Polarization (ANP). The framework includes PACIFIER-RL for long-horizon value learning and PACIFIER-Greedy for efficient myopic ranking, supporting cost-aware moderation, continuous opinions, and topology-altering node removal. The core challenge is small-to-large transfer. PACIFIER is trained on synthetic graphs with fewer than 50 nodes but must generalize to large real-world networks. To achieve this, we integrate four scale-compatible designs: a two-echo-chamber training distribution, anchor-and-mark history encoding, normalized global features, and residual-polarization rewards. These components make topology-preserving FJ moderation observable and learnable across graph scales. Experiments on 15 real-world Twitter networks (up to 155,599 nodes) show that PACIFIER matches analytical solvers in MI and consistently outperforms baselines in ME, continuous-ME, cost-ME, and node removal. PACIFIER-RL proves especially effective when long-horizon costs or structural consequences dominate immediate gains.

---

### Optimized Disaster Recovery for Distributed Storage Systems: Lightweight Metadata Architectures to Overcome Cryptographic Hashing Bottleneck

Authors: Prasanna Kumar, Nishank Soni, Gaurang Munje
Published: 2026-02-23
Categories: cs.CR, cs.AI, cs.CE
arXiv: https://arxiv.org/abs/2602.22237v1

Distributed storage architectures are foundational to modern cloud-native infrastructure, yet a critical operational bottleneck persists within disaster recovery (DR) workflows: the dependence on content-based cryptographic hashing for data identification and synchronization. While hash-based deduplication is effective for storage efficiency in steady-state operation, it becomes a systemic liability during failover and failback events when hash indexes are stale, incomplete, or must be rebuilt following a crash. This paper precisely characterizes the operational conditions under which full or partial re-hashing becomes unavoidable. The paper also analyzes the downstream impact of cryptographic re-hashing on Recovery Time Objective (RTO) compliance, and proposes a generalized architectural shift toward deterministic, metadata-driven identification. The proposed framework assigns globally unique composite identifiers to data blocks at ingestion time-independent of content analysis enabling instantaneous delta computation during DR without any cryptographic overhead.

---

### CrossLLM-Mamba: Multimodal State Space Fusion of LLMs for RNA Interaction Prediction

Authors: Rabeya Tus Sadia, Qiang Ye, Qiang Cheng
Published: 2026-02-23
Categories: q-bio.GN, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.22236v1

Accurate prediction of RNA-associated interactions is essential for understanding cellular regulation and advancing drug discovery. While Biological Large Language Models (BioLLMs) such as ESM-2 and RiNALMo provide powerful sequence representations, existing methods rely on static fusion strategies that fail to capture the dynamic, context-dependent nature of molecular binding. We introduce CrossLLM-Mamba, a novel framework that reformulates interaction prediction as a state-space alignment problem. By leveraging bidirectional Mamba encoders, our approach enables deep ``crosstalk'' between modality-specific embeddings through hidden state propagation, modeling interactions as dynamic sequence transitions rather than static feature overlaps. The framework maintains linear computational complexity, making it scalable to high-dimensional BioLLM embeddings. We further incorporate Gaussian noise injection and Focal Loss to enhance robustness against hard-negative samples. Comprehensive experiments across three interaction categories, RNA-protein, RNA-small molecule, and RNA-RNA demonstrate that CrossLLM-Mamba achieves state-of-the-art performance. On the RPI1460 benchmark, our model attains an MCC of 0.892, surpassing the previous best by 5.2\%. For binding affinity prediction, we achieve Pearson correlations exceeding 0.95 on riboswitch and repeat RNA subtypes. These results establish state-space modeling as a powerful paradigm for multi-modal biological interaction prediction.

---

### Structured Prompt Language: Declarative Context Management for LLMs

Authors: Wen G. Gong
Published: 2026-02-23
Categories: cs.CL, cs.DB, cs.PL
arXiv: https://arxiv.org/abs/2602.21257v1

We present SPL (Structured Prompt Language), a declarative SQL-inspired language that treats large language models as generative knowledge bases and their context windows as constrained resources. SPL provides explicit WITH BUDGET/LIMIT token management, an automatic query optimizer, EXPLAIN transparency analogous to SQL's EXPLAIN ANALYZE, and native integration of retrieval-augmented generation (RAG) and persistent memory in a single declarative framework. SPL-flow extends SPL into resilient agentic pipelines with a three-tier provider fallback strategy (Ollama -> OpenRouter -> self-healing retry) fully transparent to the .spl script. Five extensions demonstrate the paradigm's breadth: (1) Text2SPL (multilingual NL->SPL translation); (2) Mixture-of-Models (MoM) routing that dispatches each PROMPT to a domain-specialist model at runtime; (3) Logical Chunking, an intelligent strategy for documents exceeding a single context window--expressed naturally through SPL's existing CTE syntax with no new constructs, decomposing a large query into a Map-Reduce pipeline that reduces attention cost from O(N^2) to O(N^2/k) and runs identically on cloud (parallel) or local hardware (sequential); (4) SPL-flow, a declarative agentic orchestration layer with resilient three-tier provider fallback; and (5) BENCHMARK for parallel multi-model comparison with automatic winner persistence. We provide a formal EBNF grammar, two pip-installable Python packages (spl-llm, spl-flow), and comparison against Prompty, DSPy, and LMQL. SPL reduces prompt boilerplate by 65% on average, surfaces a 68x cost spread across model tiers as a pre-execution signal, and runs the identical .spl script at $0.002 on OpenRouter or at zero marginal cost on a local Ollama instance--without modification.

---

### A General Equilibrium Theory of Orchestrated AI Agent Systems

Authors: Jean-Philippe Garnier
Published: 2026-02-23
Categories: cs.GT, cs.AI, math.OC
arXiv: https://arxiv.org/abs/2602.21255v2

We establish a general equilibrium theory for systems of large language model (LLM) agents operating under centralized orchestration. The framework is a production economy in the sense of Arrow-Debreu (1954), extended to infinite-dimensional commodity spaces following Bewley (1972). Each LLM agent is modeled as a firm whose production set Y a $\subset$ H = L 2 ((0, T ), R R ) represents the feasible metric trajectories determined by its frozen model weights. The orchestrator is the consumer, choosing a routing policy over the agent DAG to maximize system welfare subject to a budget constraint evaluated at functional prices p $\in$ H A . These prices-elements of the Hilbert dual of the commodity space-assign a shadow value to each metric of each agent at each instant. We prove, via Brouwer's theorem applied to a finitedimensional approximation V K $\subset$ H, that every such economy admits at least one general equilibrium (p * , y * , $π$ * ). A functional Walras' law holds as a theorem: the value of functional excess demand is zero for all prices, as a consequence of the consumer's budget constraint-not by construction. We further establish Pareto optimality (First Welfare Theorem), decentralizability of Pareto optima (Second Welfare Theorem), and uniqueness with geometric convergence under a contraction condition (Banach). The orchestration dynamics constitute a Walrasian t{â}tonnement that converges globally under the contraction condition, unlike classical t{â}tonnement (Scarf, 1960). The framework admits a DSGE interpretation with SLO parameters as policy rates.

---

### GauS: Differentiable Scheduling Optimization via Gaussian Reparameterization

Authors: Yaohui Cai, Vesal Bakhtazad, Cunxi Yu, Zhiru Zhang
Published: 2026-02-23
Categories: cs.LG, cs.AR
arXiv: https://arxiv.org/abs/2602.20427v2

Efficient operator scheduling is a fundamental challenge in software compilation and hardware synthesis. While recent differentiable approaches have sought to replace traditional ones like exact solvers or heuristics with gradient-based search, they typically rely on categorical distributions that fail to capture the ordinal nature of time and suffer from a parameter space that scales poorly. In this paper, we propose a novel differentiable framework, GauS, that models operator scheduling as a stochastic relaxation using Gaussian distributions, which fully utilize modern parallel computing devices like GPUs. By representing schedules as continuous Gaussian variables, we successfully capture the ordinal nature of time and reduce the optimization space by orders of magnitude. Our method is highly flexible to represent various objectives and constraints, which provides the first differentiable formulation for the complex pipelined scheduling problem. We evaluate our method on a range of benchmarks, demonstrating that Gaus achieves Pareto-optimal results.

---

### Learning to Rewrite Tool Descriptions for Reliable LLM-Agent Tool Use

Authors: Ruocheng Guo, Kaiwen Dong, Xiang Gao, Kamalika Das
Published: 2026-02-23
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.20426v2

While most efforts to improve LLM-based tool-using agents focus on the agent itself - through larger models, better prompting, or fine-tuning - agent performance increasingly plateaus due to the quality of the tool interfaces these agents consume. Tool descriptions are often written for human developers and tolerate ambiguity that agents cannot resolve, particularly as the number of candidate tools grows. Existing approaches to improving tool interfaces (1) require re-running a multi-stage per-tool pipeline - synthesizing queries, executing an agent to collect trajectories, annotating trajectories, and prompting a strong LLM multiple times - for every API that enters the catalog, and (2) typically optimize each tool independently, limiting scalability and generalization to unseen tools. We propose Trace-Free+, a curriculum learning framework that progressively transfers supervision from trace-rich settings to trace-free deployment, encouraging the model to internalize reusable patterns of what makes a tool description effective. To support this approach, we construct a large-scale dataset of high-quality tool interfaces derived from real-world APIs through a principled data synthesis workflow. Experiments on widely adopted benchmarks show that Trace-Free+ improves robustness as tool catalogs scale to 150+ candidates - in scaling experiments, reducing accuracy degradation by 29.23% and improving average query-level success by 60.89% on StableToolBench - generalizes across domains without retraining, and provides complementary gains on top of agent fine-tuning.

---

### Implicit Intelligence -- Evaluating Agents on What Users Don't Say

Authors: Ved Sirdeshmukh, Marc Wetter
Published: 2026-02-23
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.20424v1

Real-world requests to AI agents are fundamentally underspecified. Natural human communication relies on shared context and unstated constraints that speakers expect listeners to infer. Current agentic benchmarks test explicit instruction-following but fail to evaluate whether agents can reason about implicit requirements spanning accessibility needs, privacy boundaries, catastrophic risks, and contextual constraints. We present Implicit Intelligence, an evaluation framework testing whether AI agents can move beyond prompt-following to become genuine goal-fulfillers, paired with Agent-as-a-World (AaW), a harness where interactive worlds are defined in human-readable YAML files and simulated by language models. Our scenarios feature apparent simplicity in user requests, hidden complexity in correct solutions, and discoverability of constraints through environmental exploration. Evaluating 16 frontier and open-weight models across 205 scenarios, we find that even the best-performing model achieves only 48.3% scenario pass rate, revealing substantial room for improvement in bridging the gap between literal instruction-following and human-like contextual reasoning.

---

### MedCLIPSeg: Probabilistic Vision-Language Adaptation for Data-Efficient and Generalizable Medical Image Segmentation

Authors: Taha Koleilat, Hojat Asgariandehkordi, Omid Nejati Manzari, Berardino Barile, Yiming Xiao, Hassan Rivaz
Published: 2026-02-23
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2602.20423v1

Medical image segmentation remains challenging due to limited annotations for training, ambiguous anatomical features, and domain shifts. While vision-language models such as CLIP offer strong cross-modal representations, their potential for dense, text-guided medical image segmentation remains underexplored. We present MedCLIPSeg, a novel framework that adapts CLIP for robust, data-efficient, and uncertainty-aware medical image segmentation. Our approach leverages patch-level CLIP embeddings through probabilistic cross-modal attention, enabling bidirectional interaction between image and text tokens and explicit modeling of predictive uncertainty. Together with a soft patch-level contrastive loss that encourages more nuanced semantic learning across diverse textual prompts, MedCLIPSeg effectively improves data efficiency and domain generalizability. Extensive experiments across 16 datasets spanning five imaging modalities and six organs demonstrate that MedCLIPSeg outperforms prior methods in accuracy, efficiency, and robustness, while providing interpretable uncertainty maps that highlight local reliability of segmentation results. This work demonstrates the potential of probabilistic vision-language modeling for text-driven medical image segmentation.

---

### Diffusion Modulation via Environment Mechanism Modeling for Planning

Authors: Hanping Zhang, Yuhong Guo
Published: 2026-02-23
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.20422v1

Diffusion models have shown promising capabilities in trajectory generation for planning in offline reinforcement learning (RL). However, conventional diffusion-based planning methods often fail to account for the fact that generating trajectories in RL requires unique consistency between transitions to ensure coherence in real environments. This oversight can result in considerable discrepancies between the generated trajectories and the underlying mechanisms of a real environment. To address this problem, we propose a novel diffusion-based planning method, termed as Diffusion Modulation via Environment Mechanism Modeling (DMEMM). DMEMM modulates diffusion model training by incorporating key RL environment mechanisms, particularly transition dynamics and reward functions. Experimental results demonstrate that DMEMM achieves state-of-the-art performance for planning with offline reinforcement learning.

---

### CREDIT: Certified Ownership Verification of Deep Neural Networks Against Model Extraction Attacks

Authors: Bolin Shen, Zhan Cheng, Neil Zhenqiang Gong, Fan Yao, Yushun Dong
Published: 2026-02-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.20419v1

Machine Learning as a Service (MLaaS) has emerged as a widely adopted paradigm for providing access to deep neural network (DNN) models, enabling users to conveniently leverage these models through standardized APIs. However, such services are highly vulnerable to Model Extraction Attacks (MEAs), where an adversary repeatedly queries a target model to collect input-output pairs and uses them to train a surrogate model that closely replicates its functionality. While numerous defense strategies have been proposed, verifying the ownership of a suspicious model with strict theoretical guarantees remains a challenging task. To address this gap, we introduce CREDIT, a certified ownership verification against MEAs. Specifically, we employ mutual information to quantify the similarity between DNN models, propose a practical verification threshold, and provide rigorous theoretical guarantees for ownership verification based on this threshold. We extensively evaluate our approach on several mainstream datasets across different domains and tasks, achieving state-of-the-art performance. Our implementation is publicly available at: https://github.com/LabRAI/CREDIT.

---

### CITED: A Decision Boundary-Aware Signature for GNNs Towards Model Extraction Defense

Authors: Bolin Shen, Md Shamim Seraj, Zhan Cheng, Shayok Chakraborty, Yushun Dong
Published: 2026-02-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.20418v1

Graph neural networks (GNNs) have demonstrated superior performance in various applications, such as recommendation systems and financial risk management. However, deploying large-scale GNN models locally is particularly challenging for users, as it requires significant computational resources and extensive property data. Consequently, Machine Learning as a Service (MLaaS) has become increasingly popular, offering a convenient way to deploy and access various models, including GNNs. However, an emerging threat known as Model Extraction Attacks (MEAs) presents significant risks, as adversaries can readily obtain surrogate GNN models exhibiting similar functionality. Specifically, attackers repeatedly query the target model using subgraph inputs to collect corresponding responses. These input-output pairs are subsequently utilized to train their own surrogate models at minimal cost. Many techniques have been proposed to defend against MEAs, but most are limited to specific output levels (e.g., embedding or label) and suffer from inherent technical drawbacks. To address these limitations, we propose a novel ownership verification framework CITED which is a first-of-its-kind method to achieve ownership verification on both embedding and label levels. Moreover, CITED is a novel signature-based method that neither harms downstream performance nor introduces auxiliary models that reduce efficiency, while still outperforming all watermarking and fingerprinting approaches. Extensive experiments demonstrate the effectiveness and robustness of our CITED framework. Code is available at: https://github.com/LabRAI/CITED.

---

### gQIR: Generative Quanta Image Reconstruction

Authors: Aryan Garg, Sizhuo Ma, Mohit Gupta
Published: 2026-02-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.20417v1

Capturing high-quality images from only a few detected photons is a fundamental challenge in computational imaging. Single-photon avalanche diode (SPAD) sensors promise high-quality imaging in regimes where conventional cameras fail, but raw \emph{quanta frames} contain only sparse, noisy, binary photon detections. Recovering a coherent image from a burst of such frames requires handling alignment, denoising, and demosaicing (for color) under noise statistics far outside those assumed by standard restoration pipelines or modern generative models. We present an approach that adapts large text-to-image latent diffusion models to the photon-limited domain of quanta burst imaging. Our method leverages the structural and semantic priors of internet-scale diffusion models while introducing mechanisms to handle Bernoulli photon statistics. By integrating latent-space restoration with burst-level spatio-temporal reasoning, our approach produces reconstructions that are both photometrically faithful and perceptually pleasing, even under high-speed motion. We evaluate the method on synthetic benchmarks and new real-world datasets, including the first color SPAD burst dataset and a challenging \textit{Deforming (XD)} video benchmark. Across all settings, the approach substantially improves perceptual quality over classical and modern learning-based baselines, demonstrating the promise of adapting large generative priors to extreme photon-limited sensing. Code at \href{https://github.com/Aryan-Garg/gQIR}{https://github.com/Aryan-Garg/gQIR}.

---

### SimLBR: Learning to Detect Fake Images by Learning to Detect Real Images

Authors: Aayush Dhakal, Subash Khanal, Srikumar Sastry, Jacob Arndt, Philipe Ambrozio Dias, Dalton Lunga, Nathan Jacobs
Published: 2026-02-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.20412v1

The rapid advancement of generative models has made the detection of AI-generated images a critical challenge for both research and society. Recent works have shown that most state-of-the-art fake image detection methods overfit to their training data and catastrophically fail when evaluated on curated hard test sets with strong distribution shifts. In this work, we argue that it is more principled to learn a tight decision boundary around the real image distribution and treat the fake category as a sink class. To this end, we propose SimLBR, a simple and efficient framework for fake image detection using Latent Blending Regularization (LBR). Our method significantly improves cross-generator generalization, achieving up to +24.85\% accuracy and +69.62\% recall on the challenging Chameleon benchmark. SimLBR is also highly efficient, training orders of magnitude faster than existing approaches. Furthermore, we emphasize the need for reliability-oriented evaluation in fake image detection, introducing risk-adjusted metrics and worst-case estimates to better assess model robustness. All code and models will be released on HuggingFace and GitHub.

---

### CLIPoint3D: Language-Grounded Few-Shot Unsupervised 3D Point Cloud Domain Adaptation

Authors: Mainak Singha, Sarthak Mehrotra, Paolo Casari, Subhasis Chaudhuri, Elisa Ricci, Biplab Banerjee
Published: 2026-02-23
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.20409v2

Recent vision-language models (VLMs) such as CLIP demonstrate impressive cross-modal reasoning, extending beyond images to 3D perception. Yet, these models remain fragile under domain shifts, especially when adapting from synthetic to real-world point clouds. Conventional 3D domain adaptation approaches rely on heavy trainable encoders, yielding strong accuracy but at the cost of efficiency. We introduce CLIPoint3D, the first framework for few-shot unsupervised 3D point cloud domain adaptation built upon CLIP. Our approach projects 3D samples into multiple depth maps and exploits the frozen CLIP backbone, refined through a knowledge-driven prompt tuning scheme that integrates high-level language priors with geometric cues from a lightweight 3D encoder. To adapt task-specific features effectively, we apply parameter-efficient fine-tuning to CLIP's encoders and design an entropy-guided view sampling strategy for selecting confident projections. Furthermore, an optimal transport-based alignment loss and an uncertainty-aware prototype alignment loss collaboratively bridge source-target distribution gaps while maintaining class separability. Extensive experiments on PointDA-10 and GraspNetPC-10 benchmarks show that CLIPoint3D achieves consistent 3-16% accuracy gains over both CLIP-based and conventional encoder-based baselines. Project page: https://sarthakm320.github.io/CLIPoint3D.

---

### Examining and Addressing Barriers to Diversity in LLM-Generated Ideas

Authors: Yuting Deng, Melanie Brucks, Olivier Toubia
Published: 2026-02-23
Categories: cs.CY, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2602.20408v1

Ideas generated by independent samples of humans tend to be more diverse than ideas generated from independent LLM samples, raising concerns that widespread reliance on LLMs could homogenize ideation and undermine innovation at a societal level. Drawing on cognitive psychology, we identify (both theoretically and empirically) two mechanisms undermining LLM idea diversity. First, at the individual level, LLMs exhibit fixation just as humans do, where early outputs constrain subsequent ideation. Second, at the collective level, LLMs aggregate knowledge into a unified distribution rather than exhibiting the knowledge partitioning inherent to human populations, where each person occupies a distinct region of the knowledge space. Through four studies, we demonstrate that targeted prompting interventions can address each mechanism independently: Chain-of-Thought (CoT) prompting reduces fixation by encouraging structured reasoning (only in LLMs, not humans), while ordinary personas (versus "creative entrepreneurs" such as Steve Jobs) improve knowledge partitioning by serving as diverse sampling cues, anchoring generation in distinct regions of the semantic space. Combining both approaches produces the highest idea diversity, outperforming humans. These findings offer a theoretically grounded framework for understanding LLM idea diversity and practical strategies for human-AI collaborations that leverage AI's efficiency without compromising the diversity essential to a healthy innovation ecosystem.

---

### $κ$-Explorer: A Unified Framework for Active Model Estimation in MDPs

Authors: Xihe Gu, Urbashi Mitra, Tara Javidi
Published: 2026-02-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.20404v1

In tabular Markov decision processes (MDPs) with perfect state observability, each trajectory provides active samples from the transition distributions conditioned on state-action pairs. Consequently, accurate model estimation depends on how the exploration policy allocates visitation frequencies in accordance with the intrinsic complexity of each transition distribution. Building on recent work on coverage-based exploration, we introduce a parameterized family of decomposable and concave objective functions $U_κ$ that explicitly incorporate both intrinsic estimation complexity and extrinsic visitation frequency. Moreover, the curvature $κ$ provides a unified treatment of various global objectives, such as the average-case and worst-case estimation error objectives. Using the closed-form characterization of the gradient of $U_κ$, we propose $κ$-Explorer, an active exploration algorithm that performs Frank-Wolfe-style optimization over state-action occupancy measures. The diminishing-returns structure of $U_κ$ naturally prioritizes underexplored and high-variance transitions, while preserving smoothness properties that enable efficient optimization. We establish tight regret guarantees for $κ$-Explorer and further introduce a fully online and computationally efficient surrogate algorithm for practical use. Experiments on benchmark MDPs demonstrate that $κ$-Explorer provides superior performance compared to existing exploration strategies.

---

### Risk-Averse Wasserstein Distributionally Robust Online Learning

Authors: Guixian Chen, Salar Fattahi, Soroosh Shafiee
Published: 2026-02-23
Categories: cs.LG, math.OC, stat.ML
arXiv: https://arxiv.org/abs/2602.20403v2

We study distributionally robust online learning, where a risk-averse learner updates decisions sequentially to guard against worst-case distributions drawn from a Wasserstein ambiguity set centered at past observations. While this paradigm is well understood in the offline setting through Wasserstein Distributionally Robust Optimization (DRO), its online extension poses significant challenges in convergence. In this paper, we formulate the problem as an online saddle-point stochastic game between a decision maker and an adversary selecting worst-case distributions, and propose a general framework that converges to a robust Nash equilibrium coinciding with the solution of the corresponding offline Wasserstein DRO problem.

---

### Wasserstein Distributionally Robust Online Learning

Authors: Guixian Chen, Salar Fattahi, Soroosh Shafiee
Published: 2026-02-23
Categories: cs.LG, math.OC, stat.ML
arXiv: https://arxiv.org/abs/2602.20403v1

We study distributionally robust online learning, where a risk-averse learner updates decisions sequentially to guard against worst-case distributions drawn from a Wasserstein ambiguity set centered at past observations. While this paradigm is well understood in the offline setting through Wasserstein Distributionally Robust Optimization (DRO), its online extension poses significant challenges in both convergence and computation. In this paper, we address these challenges. First, we formulate the problem as an online saddle-point stochastic game between a decision maker and an adversary selecting worst-case distributions, and propose a general framework that converges to a robust Nash equilibrium coinciding with the solution of the corresponding offline Wasserstein DRO problem. Second, we address the main computational bottleneck, which is the repeated solution of worst-case expectation problems. For the important class of piecewise concave loss functions, we propose a tailored algorithm that exploits problem geometry to achieve substantial speedups over state-of-the-art solvers such as Gurobi. The key insight is a novel connection between the worst-case expectation problem, an inherently infinite-dimensional optimization problem, and a classical and tractable budget allocation problem, which is of independent interest.

---

### Three Concrete Challenges and Two Hopes for the Safety of Unsupervised Elicitation

Authors: Callum Canavan, Aditya Shrivastava, Allison Qi, Jonathan Michala, Fabien Roger
Published: 2026-02-23
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.20400v1

To steer language models towards truthful outputs on tasks which are beyond human capability, previous work has suggested training models on easy tasks to steer them on harder ones (easy-to-hard generalization), or using unsupervised training algorithms to steer models with no external labels at all (unsupervised elicitation). Although techniques from both paradigms have been shown to improve model accuracy on a wide variety of tasks, we argue that the datasets used for these evaluations could cause overoptimistic evaluation results. Unlike many real-world datasets, they often (1) have no features with more salience than truthfulness, (2) have balanced training sets, and (3) contain only data points to which the model can give a well-defined answer. We construct datasets that lack each of these properties to stress-test a range of standard unsupervised elicitation and easy-to-hard generalization techniques. We find that no technique reliably performs well on any of these challenges. We also study ensembling and combining easy-to-hard and unsupervised techniques, and find they only partially mitigate performance degradation due to these challenges. We believe that overcoming these challenges should be a priority for future work on unsupervised elicitation.

---

### GeoPT: Scaling Physics Simulation via Lifted Geometric Pre-Training

Authors: Haixu Wu, Minghao Guo, Zongyi Li, Zhiyang Dou, Mingsheng Long, Kaiming He, Wojciech Matusik
Published: 2026-02-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.20399v2

Neural simulators promise efficient surrogates for physics simulation, but scaling them is bottlenecked by the prohibitive cost of generating high-fidelity training data. Pre-training on abundant off-the-shelf geometries offers a natural alternative, yet faces a fundamental gap: supervision on static geometry alone ignores dynamics and can lead to negative transfer on physics tasks. We present GeoPT, a unified pre-trained model for general physics simulation based on lifted geometric pre-training. The core idea is to augment geometry with synthetic dynamics, enabling dynamics-aware self-supervision without physics labels. Pre-trained on over one million samples, GeoPT consistently improves industrial-fidelity benchmarks spanning fluid mechanics for cars, aircraft, and ships, and solid mechanics in crash simulation, reducing labeled data requirements by 20-60% and accelerating convergence by 2$\times$. These results show that lifting with synthetic dynamics bridges the geometry-physics gap, unlocking a scalable path for neural simulation and potentially beyond. Code is available at https://github.com/Physics-Scaling/GeoPT.

---

### cc-Shapley: Measuring Multivariate Feature Importance Needs Causal Context

Authors: Jörg Martin, Stefan Haufe
Published: 2026-02-23
Categories: cs.LG, stat.ME
arXiv: https://arxiv.org/abs/2602.20396v3

Explainable artificial intelligence promises to yield insights into relevant features, thereby enabling humans to examine and scrutinize machine learning models or even facilitating scientific discovery. Considering the widespread technique of Shapley values, we find that purely data-driven operationalization of multivariate feature importance is unsuitable for such purposes. Even for simple problems with two features, spurious associations due to collider bias and suppression arise from considering one feature only in the observational context of the other, which can lead to misinterpretations. Causal knowledge about the data-generating process is required to identify and correct such misleading feature attributions. We propose cc-Shapley (causal context Shapley), an interventional modification of conventional observational Shapley values leveraging knowledge of the data's causal structure, thereby analyzing the relevance of a feature in the causal context of the remaining features. We show theoretically that this eradicates spurious association induced by collider bias. We compare the behavior of Shapley and cc-Shapley values on various, synthetic, and real-world datasets. We observe nullification or reversal of associations compared to univariate feature importance when moving from observational to cc-Shapley.

---

### Selecting Optimal Variable Order in Autoregressive Ising Models

Authors: Shiba Biswal, Marc Vuffray, Andrey Y. Lokhov
Published: 2026-02-23
Categories: stat.ML, cond-mat.stat-mech, cs.LG
arXiv: https://arxiv.org/abs/2602.20394v2

Autoregressive models enable tractable sampling from learned probability distributions, but their performance critically depends on the variable ordering used in the factorization via complexities of the resulting conditional distributions. We propose to learn the Markov random field describing the underlying data, and use the inferred graphical model structure to construct optimized variable orderings. We illustrate our approach on two-dimensional image-like models where a structure-aware ordering leads to restricted conditioning sets, thereby reducing model complexity. Numerical experiments on Ising models with discrete data demonstrate that graph-informed orderings yield higher-fidelity generated samples compared to naive variable orderings.

---

### Detecting and Mitigating Group Bias in Heterogeneous Treatment Effects

Authors: Joel Persson, Jurriën Bakker, Dennis Bohle, Stefan Feuerriegel, Florian von Wangenheim
Published: 2026-02-23
Categories: stat.ME, cs.LG, econ.EM
arXiv: https://arxiv.org/abs/2602.20383v1

Heterogeneous treatment effects (HTEs) are increasingly estimated using machine learning models that produce highly personalized predictions of treatment effects. In practice, however, predicted treatment effects are rarely interpreted, reported, or audited at the individual level but, instead, are often aggregated to broader subgroups, such as demographic segments, risk strata, or markets. We show that such aggregation can induce systematic bias of the group-level causal effect: even when models for predicting the individual-level conditional average treatment effect (CATE) are correctly specified and trained on data from randomized experiments, aggregating the predicted CATEs up to the group level does not, in general, recover the corresponding group average treatment effect (GATE). We develop a unified statistical framework to detect and mitigate this form of group bias in randomized experiments. We first define group bias as the discrepancy between the model-implied and experimentally identified GATEs, derive an asymptotically normal estimator, and then provide a simple-to-implement statistical test. For mitigation, we propose a shrinkage-based bias-correction, and show that the theoretically optimal and empirically feasible solutions have closed-form expressions. The framework is fully general, imposes minimal assumptions, and only requires computing sample moments. We analyze the economic implications of mitigating detected group bias for profit-maximizing personalized targeting, thereby characterizing when bias correction alters targeting decisions and profits, and the trade-offs involved. Applications to large-scale experimental data at major digital platforms validate our theoretical results and demonstrate empirical performance.

---

### Case-Aware LLM-as-a-Judge Evaluation for Enterprise-Scale RAG Systems

Authors: Mukul Chhabra, Luigi Medrano, Arush Verma
Published: 2026-02-23
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.20379v1

Enterprise Retrieval-Augmented Generation (RAG) assistants operate in multi-turn, case-based workflows such as technical support and IT operations, where evaluation must reflect operational constraints, structured identifiers (e.g., error codes, versions), and resolution workflows. Existing RAG evaluation frameworks are primarily designed for benchmark-style or single-turn settings and often fail to capture enterprise-specific failure modes such as case misidentification, workflow misalignment, and partial resolution across turns. We present a case-aware LLM-as-a-Judge evaluation framework for enterprise multi-turn RAG systems. The framework evaluates each turn using eight operationally grounded metrics that separate retrieval quality, grounding fidelity, answer utility, precision integrity, and case/workflow alignment. A severity-aware scoring protocol reduces score inflation and improves diagnostic clarity across heterogeneous enterprise cases. The system uses deterministic prompting with strict JSON outputs, enabling scalable batch evaluation, regression testing, and production monitoring. Through a comparative study of two instruction-tuned models across short and long workflows, we show that generic proxy metrics provide ambiguous signals, while the proposed framework exposes enterprise-critical tradeoffs that are actionable for system improvement.

---

### Exploiting Low-Rank Objective Structure in Discrete Quadratic Optimization

Authors: Ria Stevens, Fangshuo Liao, Barbara Su, Thanasis Hadjidimoulas, Jianqiang Li, Anastasios Kyrillidis
Published: 2026-02-23
Categories: cs.DS, cs.LG, math.OC, quant-ph
arXiv: https://arxiv.org/abs/2602.20376v3

We study the problem of maximizing a complex-valued quadratic form over the $K^{\text{th}}$ roots of unity. We show that when the objective matrix $\mathbf{Q}^\star \in \mathbb{C}^{n \times n}$ of the quadratic has rank $r$, the global maximizer belongs to a candidate set of size $O(rn^{2r-1})$. This set can be constructed deterministically in $O(rn^{2r+1})$ time by enumerating the vertices of a hyperplane arrangement in $\mathbb{R}^{2r}.$ The algorithm is embarrassingly parallel; with~$P$ processors, the time complexity drops to $O(r n^{2r+1}/P)$. For approximately low-rank settings, where the objective matrix is a noise-perturbed variant of a rank-$r$ matrix, we prove that applying our framework to a spectral truncation yields a multiplicative $(1 - O(\left\|\mathbf{H}\right\|_2 / δ^{\star}))$-approximation guarantee, where $δ^{\star}$ denotes the eigengap of the underlying rank-$r$ matrix and $\mathbf{H}$ represents the perturbation. To scale to high-dimensional problems, we establish a randomized sampling variant. We prove that uniformly sampling $S \geq O(1/\varepsilon^{r-1})$ candidates achieves a $(1-\varepsilon)\cos^2(π/ K)$-approximation of the optimal rank-$r$ solution with high probability. Crucially, this sample size is entirely independent of $n$, reducing the overall runtime to $O(S \cdot n^2)$. Computational experiments on synthetic benchmarks and large-scale graphs for \textsc{Max-3-Cut} confirm that our algorithms match or exceed semi-definite programming solution quality on structured instances while enabling massive parallelization across heterogeneous hardware and scaling seamlessly to problems where $n \geq 10^6$.

---

### How communicatively optimal are exact numeral systems? Once more on lexicon size and morphosyntactic complexity

Authors: Chundra Cathcart, Arne Rubehn, Katja Bocklage, Luca Ciucci, Kellen Parker van Dam, Alžběta Kučerová, Jekaterina Mažara, Carlo Y. Meloni, David Snee, Johann-Mattis List
Published: 2026-02-23
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.20372v1

Recent research argues that exact recursive numeral systems optimize communicative efficiency by balancing a tradeoff between the size of the numeral lexicon and the average morphosyntactic complexity (roughly length in morphemes) of numeral terms. We argue that previous studies have not characterized the data in a fashion that accounts for the degree of complexity languages display. Using data from 52 genetically diverse languages and an annotation scheme distinguishing between predictable and unpredictable allomorphy (formal variation), we show that many of the world's languages are decisively less efficient than one would expect. We discuss the implications of our findings for the study of numeral systems and linguistic evolution more generally.

---

### Quantitative Approximation Rates for Group Equivariant Learning

Authors: Jonathan W. Siegel, Snir Hordan, Hannah Lawrence, Ali Syed, Nadav Dym
Published: 2026-02-23
Categories: cs.LG, math.NA
arXiv: https://arxiv.org/abs/2602.20370v2

The universal approximation theorem establishes that neural networks can approximate any continuous function on a compact set. Later works in approximation theory provide quantitative approximation rates for ReLU networks on the class of $α$-Hölder functions $f: (0,1)^N \to \mathbb{R}$. The goal of this paper is to provide similar quantitative approximation results in the context of group equivariant learning, where the learned $α$-Hölder function is known to obey certain group symmetries. While there has been much interest in the literature in understanding the universal approximation properties of equivariant models, very few quantitative approximation results are known for equivariant models. In this paper, we bridge this gap by deriving quantitative approximation rates for several prominent group-equivariant and invariant architectures. The architectures that we consider include: the permutation-invariant Deep Sets architecture; the permutation-equivariant Sumformer and Transformer architectures; joint invariance to permutations and rigid motions using invariant networks based on frame averaging; and general bi-Lipschitz invariant models. Overall, we show that equally-sized ReLU MLPs and equivariant architectures are equally expressive over equivariant functions. Thus, hard-coding equivariance does not result in a loss of expressivity or approximation power in these models.

---

### Aesthetic Camera Viewpoint Suggestion with 3D Aesthetic Field

Authors: Sheyang Tang, Armin Shafiee Sarvestani, Jialu Xu, Xiaoyu Xu, Zhou Wang
Published: 2026-02-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.20363v1

The aesthetic quality of a scene depends strongly on camera viewpoint. Existing approaches for aesthetic viewpoint suggestion are either single-view adjustments, predicting limited camera adjustments from a single image without understanding scene geometry, or 3D exploration approaches, which rely on dense captures or prebuilt 3D environments coupled with costly reinforcement learning (RL) searches. In this work, we introduce the notion of 3D aesthetic field that enables geometry-grounded aesthetic reasoning in 3D with sparse captures, allowing efficient viewpoint suggestions in contrast to costly RL searches. We opt to learn this 3D aesthetic field using a feedforward 3D Gaussian Splatting network that distills high-level aesthetic knowledge from a pretrained 2D aesthetic model into 3D space, enabling aesthetic prediction for novel viewpoints from only sparse input views. Building on this field, we propose a two-stage search pipeline that combines coarse viewpoint sampling with gradient-based refinement, efficiently identifying aesthetically appealing viewpoints without dense captures or RL exploration. Extensive experiments show that our method consistently suggests viewpoints with superior framing and composition compared to existing approaches, establishing a new direction toward 3D-aware aesthetic modeling.

---

### Learning During Detection: Continual Learning for Neural OFDM Receivers via DMRS

Authors: Mohanad Obeed, Ming Jian
Published: 2026-02-23
Categories: cs.IT, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.20361v1

Deep neural networks (DNNs) have been increasingly explored for receiver design because they can handle complex environments without relying on explicit channel models. Nevertheless, because communication channels change rapidly, their distributions can shift over time, often making periodic retraining necessary. This paper proposes a zero-overhead online and continual learning framework for orthogonal frequency-division multiplexing (OFDM) neural receivers that directly detect the soft bits of received signals. Unlike conventional fine-tuning methods that rely on dedicated training intervals or full resource grids, our approach leverages existing demodulation reference signals (DMRS) to simultaneously enable signal demodulation and model adaptation. We introduce three pilot designs: fully randomized, hybrid, and additional pilots that flexibly support joint demodulation and learning. To accommodate these pilot designs, we develop two receiver architectures: (i) a parallel design that separates inference and fine-tuning for uninterrupted operation, and (ii) a forward-pass reusing design that reduces computational complexity. Simulation results show that the proposed method effectively tracks both slow and fast channel distribution variations without additional overhead, service interruption, or catastrophic performance degradation under distribution shift.

---

### Momentum Guidance: Plug-and-Play Guidance for Flow Models

Authors: Runlong Liao, Jian Yu, Baiyu Su, Chi Zhang, Lizhang Chen, Qiang Liu
Published: 2026-02-23
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2602.20360v2

Flow-based generative methods offer a simple and effective framework for high-fidelity generation, yet pretrained flow models are rarely used in their vanilla conditional form: in image generation, samples without guidance often appear diffuse and lack fine-grained detail. Existing guidance techniques such as classifier-free guidance (CFG) improve fidelity but reduce sample diversity. We introduce Momentum Guidance (MG), a guidance method that improves sample quality by extrapolating the current velocity away from an exponential moving average of past velocities along the ODE trajectory, while preserving the standard one-evaluation-per-step cost. MG provides gains beyond CFG, improving the precision-recall Pareto frontier. Experiments demonstrate the effectiveness of MG across benchmarks. On ImageNet-256, MG improves FID by 36.54% without CFG and 25.42% with CFG on average across sampling settings, attaining an FID of 1.553 at 16 sampling steps. Evaluations on large flow-based models, including Stable Diffusion 3 and FLUX.1-dev, further confirm improvements across standard metrics.

---

### 3DSPA: A 3D Semantic Point Autoencoder for Evaluating Video Realism

Authors: Bhavik Chandna, Kelsey R. Allen
Published: 2026-02-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.20354v1

AI video generation is evolving rapidly. For video generators to be useful for applications ranging from robotics to film-making, they must consistently produce realistic videos. However, evaluating the realism of generated videos remains a largely manual process -- requiring human annotation or bespoke evaluation datasets which have restricted scope. Here we develop an automated evaluation framework for video realism which captures both semantics and coherent 3D structure and which does not require access to a reference video. Our method, 3DSPA, is a 3D spatiotemporal point autoencoder which integrates 3D point trajectories, depth cues, and DINO semantic features into a unified representation for video evaluation. 3DSPA models how objects move and what is happening in the scene, enabling robust assessments of realism, temporal consistency, and physical plausibility. Experiments show that 3DSPA reliably identifies videos which violate physical laws, is more sensitive to motion artifacts, and aligns more closely with human judgments of video quality and realism across multiple datasets. Our results demonstrate that enriching trajectory-based representations with 3D semantics offers a stronger foundation for benchmarking generative video models, and implicitly captures physical rule violations. The code and pretrained model weights will be available at https://github.com/TheProParadox/3dspa_code.

---

### BiRQA: Bidirectional Robust Quality Assessment for Images

Authors: Aleksandr Gushchin, Dmitriy S. Vatolin, Anastasia Antsiferova
Published: 2026-02-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.20351v1

Full-Reference image quality assessment (FR IQA) is important for image compression, restoration and generative modeling, yet current neural metrics remain slow and vulnerable to adversarial perturbations. We present BiRQA, a compact FR IQA metric model that processes four fast complementary features within a bidirectional multiscale pyramid. A bottom-up attention module injects fine-scale cues into coarse levels through an uncertainty-aware gate, while a top-down cross-gating block routes semantic context back to high resolution. To enhance robustness, we introduce Anchored Adversarial Training, a theoretically grounded strategy that uses clean "anchor" samples and a ranking loss to bound pointwise prediction error under attacks. On five public FR IQA benchmarks BiRQA outperforms or matches the previous state of the art (SOTA) while running ~3x faster than previous SOTA models. Under unseen white-box attacks it lifts SROCC from 0.30-0.57 to 0.60-0.84 on KADID-10k, demonstrating substantial robustness gains. To our knowledge, BiRQA is the only FR IQA model combining competitive accuracy with real-time throughput and strong adversarial resilience.

---

### Hierarchical Molecular Representation Learning via Fragment-Based Self-Supervised Embedding Prediction

Authors: Jiele Wu, Haozhe Ma, Zhihan Guo, Thanh Vinh Vo, Tze Yun Leong
Published: 2026-02-23
Categories: cs.LG, cs.AI, q-bio.QM
arXiv: https://arxiv.org/abs/2602.20344v1

Graph self-supervised learning (GSSL) has demonstrated strong potential for generating expressive graph embeddings without the need for human annotations, making it particularly valuable in domains with high labeling costs such as molecular graph analysis. However, existing GSSL methods mostly focus on node- or edge-level information, often ignoring chemically relevant substructures which strongly influence molecular properties. In this work, we propose Graph Semantic Predictive Network (GraSPNet), a hierarchical self-supervised framework that explicitly models both atomic-level and fragment-level semantics. GraSPNet decomposes molecular graphs into chemically meaningful fragments without predefined vocabularies and learns node- and fragment-level representations through multi-level message passing with masked semantic prediction at both levels. This hierarchical semantic supervision enables GraSPNet to learn multi-resolution structural information that is both expressive and transferable. Extensive experiments on multiple molecular property prediction benchmarks demonstrate that GraSPNet learns chemically meaningful representations and consistently outperforms state-of-the-art GSSL methods in transfer learning settings.

---

### Large-scale Photorealistic Outdoor 3D Scene Reconstruction from UAV Imagery Using Gaussian Splatting Techniques

Authors: Christos Maikos, Georgios Angelidis, Georgios Th. Papadopoulos
Published: 2026-02-23
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2602.20342v1

In this study, we present an end-to-end pipeline capable of converting drone-captured video streams into high-fidelity 3D reconstructions with minimal latency. Unmanned aerial vehicles (UAVs) are extensively used in aerial real-time perception applications. Moreover, recent advances in 3D Gaussian Splatting (3DGS) have demonstrated significant potential for real-time neural rendering. However, their integration into end-to-end UAV-based reconstruction and visualization systems remains underexplored. Our goal is to propose an efficient architecture that combines live video acquisition via RTMP streaming, synchronized sensor fusion, camera pose estimation, and 3DGS optimization, achieving continuous model updates and low-latency deployment within interactive visualization environments that supports immersive augmented and virtual reality (AR/VR) applications. Experimental results demonstrate that the proposed method achieves competitive visual fidelity, while delivering significantly higher rendering performance and substantially reduced end-to-end latency, compared to NeRF-based approaches. Reconstruction quality remains within 4-7\% of high-fidelity offline references, confirming the suitability of the proposed system for real-time, scalable augmented perception from aerial platforms.

---

### Emergent Manifold Separability during Reasoning in Large Language Models

Authors: Chanwoo Chun, Alexandre Polo, SueYeon Chung
Published: 2026-02-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.20338v2

Chain-of-Thought (CoT) prompting significantly improves reasoning in Large Language Models, yet the temporal dynamics of the underlying representation geometry remain poorly understood. We investigate these dynamics by applying Manifold Capacity Theory (MCT) to two compositional reasoning tasks: a controlled Boolean logic tree that supports deep mechanistic analysis, and a natural-language eligibility task in which the model has to extract attributes from prose, compare them to thresholds, and compose the local decisions through a fixed evaluation tree. MCT lets us quantify the linear separability of latent representations without the confounding factors of probe training. On both tasks, and across several open-weight models, reasoning manifests as a transient geometric pulse: concept manifolds are untangled into linearly separable subspaces immediately prior to computation and rapidly compressed thereafter. This behavior diverges from standard linear probe accuracy, which remains high long after computation, suggesting a fundamental distinction between information that is merely retrievable and information that is geometrically prepared for processing. We interpret this phenomenon as Dynamic Manifold Management, a mechanism where the model dynamically modulates representational capacity to optimize the bandwidth of the residual stream throughout the reasoning chain.

---

### Natural Language Processing Models for Robust Document Categorization

Authors: Radoslaw Roszczyk, Pawel Tecza, Maciej Stodolski, Krzysztof Siwek
Published: 2026-02-23
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.20336v1

This article presents an evaluation of several machine learning methods applied to automated text classification, alongside the design of a demonstrative system for unbalanced document categorization and distribution. The study focuses on balancing classification accuracy with computational efficiency, a key consideration when integrating AI into real world automation pipelines. Three models of varying complexity were examined: a Naive Bayes classifier, a bidirectional LSTM network, and a fine tuned transformer based BERT model. The experiments reveal substantial differences in performance. BERT achieved the highest accuracy, consistently exceeding 99\%, but required significantly longer training times and greater computational resources. The BiLSTM model provided a strong compromise, reaching approximately 98.56\% accuracy while maintaining moderate training costs and offering robust contextual understanding. Naive Bayes proved to be the fastest to train, on the order of milliseconds, yet delivered the lowest accuracy, averaging around 94.5\%. Class imbalance influenced all methods, particularly in the recognition of minority categories. A fully functional demonstrative system was implemented to validate practical applicability, enabling automated routing of technical requests with throughput unattainable through manual processing. The study concludes that BiLSTM offers the most balanced solution for the examined scenario, while also outlining opportunities for future improvements and further exploration of transformer architectures.

---

### DMCD: Semantic-Statistical Framework for Causal Discovery

Authors: Samarth KaPatel, Sofia Nikiforova, Giacinto Paolo Saggese, Paul Smith
Published: 2026-02-23
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.20333v1

We present DMCD (DataMap Causal Discovery), a two-phase causal discovery framework that integrates LLM-based semantic drafting from variable metadata with statistical validation on observational data. In Phase I, a large language model proposes a sparse draft DAG, serving as a semantically informed prior over the space of possible causal structures. In Phase II, this draft is audited and refined via conditional independence testing, with detected discrepancies guiding targeted edge revisions. We evaluate our approach on three metadata-rich real-world benchmarks spanning industrial engineering, environmental monitoring, and IT systems analysis. Across these datasets, DMCD achieves competitive or leading performance against diverse causal discovery baselines, with particularly large gains in recall and F1 score. Probing and ablation experiments suggest that these improvements arise from semantic reasoning over metadata rather than memorization of benchmark graphs. Overall, our results demonstrate that combining semantic priors with principled statistical verification yields a high-performing and practically effective approach to causal structure learning.

---

### No One Size Fits All: QueryBandits for Hallucination Mitigation

Authors: Nicole Cho, William Watson, Alec Koppel, Sumitra Ganesh, Manuela Veloso
Published: 2026-02-23
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.20332v1

Advanced reasoning capabilities in Large Language Models (LLMs) have led to more frequent hallucinations; yet most mitigation work focuses on open-source models for post-hoc detection and parameter editing. The dearth of studies focusing on hallucinations in closed-source models is especially concerning, as they constitute the vast majority of models in institutional deployments. We introduce QueryBandits, a model-agnostic contextual bandit framework that adaptively learns online to select the optimal query-rewrite strategy by leveraging an empirically validated and calibrated reward function. Across 16 QA scenarios, our top QueryBandit (Thompson Sampling) achieves an 87.5% win rate over a No-Rewrite baseline and outperforms zero-shot static policies (e.g., Paraphrase or Expand) by 42.6% and 60.3%, respectively. Moreover, all contextual bandits outperform vanilla bandits across all datasets, with higher feature variance coinciding with greater variance in arm selection. This substantiates our finding that there is no single rewrite policy optimal for all queries. We also discover that certain static policies incur higher cumulative regret than No-Rewrite, indicating that an inflexible query-rewriting policy can worsen hallucinations. Thus, learning an online policy over semantic features with QueryBandits can shift model behavior purely through forward-pass mechanisms, enabling its use with closed-source models and bypassing the need for retraining or gradient-based adaptation.

---

### Circuit Tracing in Vision-Language Models: Understanding the Internal Mechanisms of Multimodal Thinking

Authors: Jingcheng Yang, Tianhu Xiong, Shengyi Qian, Klara Nahrstedt, Mingyuan Wu
Published: 2026-02-23
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.20330v1

Vision-language models (VLMs) are powerful but remain opaque black boxes. We introduce the first framework for transparent circuit tracing in VLMs to systematically analyze multimodal reasoning. By utilizing transcoders, attribution graphs, and attention-based methods, we uncover how VLMs hierarchically integrate visual and semantic concepts. We reveal that distinct visual feature circuits can handle mathematical reasoning and support cross-modal associations. Validated through feature steering and circuit patching, our framework proves these circuits are causal and controllable, laying the groundwork for more explainable and reliable VLMs.

---

### CaDrift: A Time-dependent Causal Generator of Drifting Data Streams

Authors: Eduardo V. L. Barboza, Jean Paul Barddal, Robert Sabourin, Rafael M. O. Cruz
Published: 2026-02-23
Categories: cs.LG, cs.DB
arXiv: https://arxiv.org/abs/2602.20329v1

This work presents Causal Drift Generator (CaDrift), a time-dependent synthetic data generator framework based on Structural Causal Models (SCMs). The framework produces a virtually infinite combination of data streams with controlled shift events and time-dependent data, making it a tool to evaluate methods under evolving data. CaDrift synthesizes various distributional and covariate shifts by drifting mapping functions of the SCM, which change underlying cause-and-effect relationships between features and the target. In addition, CaDrift models occasional perturbations by leveraging interventions in causal modeling. Experimental results show that, after distributional shift events, the accuracy of classifiers tends to drop, followed by a gradual retrieval, confirming the generator's effectiveness in simulating shifts. The framework has been made available on GitHub.

---

### GSNR: Graph Smooth Null-Space Representation for Inverse Problems

Authors: Romario Gualdrón-Hurtado, Roman Jacome, Rafael S. Suarez, Henry Arguello
Published: 2026-02-23
Categories: cs.CV, eess.IV, math.OC
arXiv: https://arxiv.org/abs/2602.20328v2

Inverse problems in imaging are ill-posed, leading to infinitely many solutions consistent with the measurements due to the non-trivial null-space of the sensing matrix. Common image priors promote solutions on the general image manifold, such as sparsity, smoothness, or score function. However, as these priors do not constrain the null-space component, they can bias the reconstruction. Thus, we aim to incorporate meaningful null-space information in the reconstruction framework. Inspired by smooth image representation on graphs, we propose Graph-Smooth Null-Space Representation (GSNR), a mechanism that imposes structure only into the invisible component. Particularly, given a graph Laplacian, we construct a null-restricted Laplacian that encodes similarity between neighboring pixels in the null-space signal, and we design a low-dimensional projection matrix from the $p$-smoothest spectral graph modes (lowest graph frequencies). This approach has strong theoretical and practical implications: i) improved convergence via a null-only graph regularizer, ii) better coverage, how much null-space variance is captured by $p$ modes, and iii) high predictability, how well these modes can be inferred from the measurements. GSNR is incorporated into well-known inverse problem solvers, e.g., PnP, DIP, and diffusion solvers, in four scenarios: image deblurring, compressed sensing, demosaicing, and image super-resolution, providing consistent improvement of up to 4.3 dB over baseline formulations and up to 1 dB compared with end-to-end learned models in terms of PSNR.

---

### An artificial intelligence framework for end-to-end rare disease phenotyping from clinical notes using large language models

Authors: Cathy Shyr, Yan Hu, Rory J. Tinker, Thomas A. Cassini, Kevin W. Byram, Rizwan Hamid, Daniel V. Fabbri, Adam Wright, Josh F. Peterson, Lisa Bastarache, Hua Xu
Published: 2026-02-23
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2602.20324v1

Phenotyping is fundamental to rare disease diagnosis, but manual curation of structured phenotypes from clinical notes is labor-intensive and difficult to scale. Existing artificial intelligence approaches typically optimize individual components of phenotyping but do not operationalize the full clinical workflow of extracting features from clinical text, standardizing them to Human Phenotype Ontology (HPO) terms, and prioritizing diagnostically informative HPO terms. We developed RARE-PHENIX, an end-to-end AI framework for rare disease phenotyping that integrates large language model-based phenotype extraction, ontology-grounded standardization to HPO terms, and supervised ranking of diagnostically informative phenotypes. We trained RARE-PHENIX using data from 2,671 patients across 11 Undiagnosed Diseases Network clinical sites, and externally validated it on 16,357 real-world clinical notes from Vanderbilt University Medical Center. Using clinician-curated HPO terms as the gold standard, RARE-PHENIX consistently outperformed a state-of-the-art deep learning baseline (PhenoBERT) across ontology-based similarity and precision-recall-F1 metrics in end-to-end evaluation (i.e., ontology-based similarity of 0.70 vs. 0.58). Ablation analyses demonstrated performance improvements with the addition of each module in RARE-PHENIX (extraction, standardization, and prioritization), supporting the value of modeling the full clinical phenotyping workflow. By modeling phenotyping as a clinically aligned workflow rather than a single extraction task, RARE-PHENIX provides structured, ranked phenotypes that are more concordant with clinician curation and has the potential to support human-in-the-loop rare disease diagnosis in real-world settings.

---

### PhysMem: Scaling Test-Time Memory for Embodied Physical Reasoning

Authors: Haoyang Li, Yang You, Hao Su, Leonidas Guibas
Published: 2026-02-23
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2602.20323v6

Reliable object manipulation requires understanding physical properties that vary across objects and environments. Vision-language model (VLM) planners can reason about friction and stability in general terms; however, they often cannot predict how a specific ball will roll on a particular surface or which stone will provide a stable foundation without direct experience. We present PhysMem, a memory framework that enables VLM robot planners to learn physical principles from interaction at test time, without updating model parameters. The system records experiences, generates candidate hypotheses, and verifies them through targeted interaction before promoting validated knowledge to guide future decisions. A central design choice is verification before application: the system tests hypotheses against new observations rather than applying retrieved experience directly, reducing rigid reliance on prior experience when physical conditions change. We evaluate PhysMem on three real-world manipulation tasks and simulation benchmarks across four VLM backbones. On a controlled brick insertion task, principled abstraction achieves 76% success compared to 23% for direct experience retrieval, and real-world experiments show consistent improvement over 30-minute deployment sessions.

---

### TokEye: Fast Signal Extraction for Fluctuating Time Series via Offline Self-Supervised Learning From Fusion Diagnostics to Bioacoustics

Authors: Nathaniel Chen, Kouroche Bouchiat, Peter Steiner, Andrew Rothstein, David Smith, Max Austin, Mike van Zeeland, Azarakhsh Jalalvand, Egemen Kolemen
Published: 2026-02-23
Categories: eess.SP, cs.AI, physics.plasm-ph
arXiv: https://arxiv.org/abs/2602.20317v2

Next-generation fusion facilities like ITER face a "data deluge," generating petabytes of multi-diagnostic signals daily that challenge manual analysis. We present a "signals-first" self-supervised framework for the automated extraction of coherent and transient modes from high-noise time-frequency data across a variety of sensors. We also develop a general-purpose method and tool for extracting coherent, quasi-coherent, and transient modes for fluctuation measurements in tokamaks by employing non-linear optimal techniques in multichannel signal processing with a fast neural network surrogate on fast magnetics, electron cyclotron emission, CO2 interferometers, and beam emission spectroscopy measurements from DIII-D. Results are tested on data from DIII-D, TJ-II, and non-fusion spectrograms. With an inference latency of 0.5 seconds, this framework enables real-time mode identification and large-scale automated database generation for advanced plasma control. Repository is in https://github.com/PlasmaControl/TokEye.

---