# Research Papers — 2026-02 · bundle page 24 of 210 > Full-text markdown of papers #1151–1200 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/24 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/23.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/25.md) ### BiCLIP: Bidirectional and Consistent Language-Image Processing for Robust Medical Image Segmentation Authors: Saivan Talaei, Fatemeh Daneshfar, Abdulhady Abas Abdullah, Mustaqeem Khan Published: 2026-02-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.00156v1 Medical image segmentation is a cornerstone of computer-assisted diagnosis and treatment planning. While recent multimodal vision-language models have shown promise in enhancing semantic understanding through textual descriptions, their resilience in "in-the-wild" clinical settings-characterized by scarce annotations and hardware-induced image degradations-remains under-explored. We introduce BiCLIP (Bidirectional and Consistent Language-Image Processing), a framework engineered to bolster robustness in medical segmentation. BiCLIP features a bidirectional multimodal fusion mechanism that enables visual features to iteratively refine textual representations, ensuring superior semantic alignment. To further stabilize learning, we implement an augmentation consistency objective that regularizes intermediate representations against perturbed input views. Evaluation on the QaTa-COV19 and MosMedData+ benchmarks demonstrates that BiCLIP consistently surpasses state-of-the-art image-only and multimodal baselines. Notably, BiCLIP maintains high performance when trained on as little as 1% of labeled data and exhibits significant resistance to clinical artifacts, including motion blur and low-dose CT noise. --- ### EfficientPosterGen: Semantic-aware Efficient Poster Generation via Token Compression and Accurate Violation Detection Authors: Wenxin Tang, Jingyu Xiao, Yanpei Gong, Fengyuan Ran, Tongchuan Xia, Junliang Liu, Man Ho Lam, Wenxuan Wang, Michael R. Lyu Published: 2026-02-25 Categories: cs.CV, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2603.00155v1 Automated academic poster generation aims to distill lengthy research papers into concise, visually coherent presentations. Existing Multimodal Large Language Models (MLLMs) based approaches, however, suffer from three critical limitations: low information density in full-paper inputs, excessive token consumption, and unreliable layout verification. We present EfficientPosterGen, an end-to-end framework that addresses these challenges through semantic-aware retrieval and token-efficient multimodal generation. EfficientPosterGen introduces three core innovations: (1) Semantic-aware Key Information Retrieval (SKIR), which constructs a semantic contribution graph to model inter-segment relationships and selectively preserves important content; (2) Visual-based Context Compression (VCC), which renders selected text segments into images to shift textual information into the visual modality, significantly reducing token usage while generating poster-ready bullet points; and (3) Agentless Layout Violation Detection (ALVD), a deterministic color-gradient-based algorithm that reliably detects content overflow and spatial sparsity without auxiliary MLLMs. Extensive experiments demonstrate that EfficientPosterGen achieves substantial improvements in token efficiency and layout reliability while maintaining high poster quality, offering a scalable solution for automated academic poster generation. Our code is available at https://github.com/vinsontang1/EfficientPosterGen-Code. --- ### Pulse-Driven Neural Architecture: Learnable Oscillatory Dynamics for Robust Continuous-Time Sequence Processing Authors: Paras Sharma Published: 2026-02-25 Categories: cs.NE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.00153v1 We introduce PDNA (Pulse-Driven Neural Architecture), a method for augmenting continuous-time recurrent networks with learnable oscillatory dynamics that maintain internal state evolution independently of external input. Built on Closed-form Continuous-time (CfC) networks, PDNA adds two components: (1) a pulse module that generates structured oscillations $A \cdot \sin(ωt + \varphi(h))$ with learnable frequencies and state-dependent phase, and (2) a self-attend module that applies recurrent self-attention to the hidden state. Through a controlled ablation study on sequential MNIST (sMNIST) with five random seeds, we evaluate gap robustness -- the ability to maintain performance when portions of the input sequence are removed at test time. Our key finding is that structured oscillatory dynamics significantly improve robustness to input interruptions: the self-attend variant achieves a statistically significant 2.78 percentage point multi-gap advantage over baseline ($p = 0.041$), while the pulse variant shows a 4.62 pp advantage with large effect size (Cohen's $d = 0.87$). A noise control (random perturbation of equal magnitude) provides no benefit, confirming that the advantage is structural rather than merely dynamic. These results provide evidence that continuous-time models can benefit from biologically-inspired internal oscillatory mechanisms for temporal robustness. --- ### Dr. Seg: Revisiting GRPO Training for Visual Large Language Models through Perception-Oriented Design Authors: Haoxiang Sun, Tao Wang, Chenwei Tang, Li Yuan, Jiancheng Lv Published: 2026-02-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.00152v2 Following the success of Group Relative Policy Optimization (GRPO) in foundation LLMs, an increasing number of works have sought to adapt GRPO to Visual Large Language Models (VLLMs) for visual perception tasks (e.g., detection and segmentation). However, much of this line of research rests on a long-standing yet unexamined assumption: training paradigms developed for language reasoning can be transferred seamlessly to visual perception. Our experiments show that this assumption is not valid, revealing intrinsic differences between reasoning-oriented and perception-oriented settings. Using reasoning segmentation as a representative case, we surface two overlooked factors: (i) the need for a broader output space, and (ii) the importance of fine-grained, stable rewards. Building on these observations, we propose Dr.~Seg, a simple, plug-and-play GRPO-based framework consisting of a Look-to-Confirm mechanism and a Distribution-Ranked Reward module, requiring no architectural modifications and integrating seamlessly with existing GRPO-based VLLMs. Extensive experiments demonstrate that Dr.~Seg improves performance in complex visual scenarios while maintaining strong generalization. Code, models, and datasets are available at https://github.com/eVI-group-SCU/Dr-Seg. --- ### Multiview Progress Prediction of Robot Activities Authors: Elena Zoppellari, Federico Becattini, Marco Fiorucci, Lamberto Ballan Published: 2026-02-25 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2603.00151v1 For robots to operate effectively and safely alongside humans, they must be able to understand the progress of ongoing actions. This ability, known as action progress prediction, is critical for tasks ranging from timely assistance to autonomous decision-making. However, modeling action progression in robotics has often been overlooked. Moreover, a single camera may be insufficient for understanding robot's ego-actions, as self-occlusion can significantly hinder perception and model performance. In this paper, we propose a multi-view architecture for action progress prediction in robot manipulation tasks. Experiments on Mobile ALOHA demonstrate the effectiveness of the proposed approach. --- ### Attention to Neural Plagiarism: Diffusion Models Can Plagiarize Your Copyrighted Images! Authors: Zihang Zou, Boqing Gong, Liqiang Wang Published: 2026-02-25 Categories: cs.CV, cs.CY arXiv: https://arxiv.org/abs/2603.00150v1 In this paper, we highlight a critical threat posed by emerging neural models: data plagiarism. We demonstrate how modern neural models (e.g., diffusion models) can replicate copyrighted images, even when protected by advanced watermarking techniques. To expose vulnerabilities in copyright protection and facilitate future research, we propose a general approach to neural plagiarism that can either forge replicas of copyrighted data or introduce copyright ambiguity. Our method, based on "anchors and shims", employs inverse latents as anchors and finds shim perturbations that gradually deviate the anchor latents, thereby evading watermark or copyright detection. By applying perturbations to the cross-attention mechanism at different timesteps, our approach induces varying degrees of semantic modification in copyrighted images, enabling it to bypass protections ranging from visible trademarks and signatures to invisible watermarks. Notably, our method is a purely gradient-based search that requires no additional training or fine-tuning. Experiments on MS-COCO and real-world copyrighted images show that diffusion models can replicate copyrighted images, underscoring the urgent need for countermeasures against neural plagiarism. --- ### Physics-Consistent Diffusion for Efficient Fluid Super-Resolution via Multiscale Residual Correction Authors: Zhihao Li, Shengwei Dong, Chuang Yi, Junxuan Gao, Zhilu Lai, Zhiqiang Liu, Wei Wang, Guangtao Zhang Published: 2026-02-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.00149v1 Existing image SR and generic diffusion models transfer poorly to fluid SR: they are sampling-intensive, ignore physical constraints, and often yield spectral mismatch and spurious divergence. We address fluid super-resolution (SR) with \textbf{ReMD} (\underline{Re}sidual-\underline{M}ultigrid \underline{D}iffusion), a physics-consistent diffusion framework. At each reverse step, ReMD performs a \emph{multigrid residual correction}: the update direction is obtained by coupling data consistency with lightweight physics cues and then correcting the residual across scales; the multiscale hierarchy is instantiated with a \emph{multi-wavelet} basis to capture both large structures and fine vortical details. This coarse-to-fine design accelerates convergence and preserves fine structures while remaining equation-free. Across atmospheric and oceanic benchmarks, ReMD improves accuracy and spectral fidelity, reduces divergence, and reaches comparable quality with markedly fewer sampling steps than diffusion baselines. Our results show that enforcing physics consistency \emph{inside} the diffusion process via multigrid residual correction and multi-wavelet multiscale modeling is an effective route to efficient fluid SR. Our code are available on https://github.com/lizhihao2022/ReMD. --- ### Leveraging large multimodal models for audio-video deepfake detection: a pilot study Authors: Songjun Cao, Yuqi Li, Yunpeng Luo, Jianjun Yin, Long Ma Published: 2026-02-25 Categories: cs.SD, cs.CV arXiv: https://arxiv.org/abs/2602.23393v1 Audio-visual deepfake detection (AVD) is increasingly important as modern generators can fabricate convincing speech and video. Most current multimodal detectors are small, task-specific models: they work well on curated tests but scale poorly and generalize weakly across domains. We introduce AV-LMMDetect, a supervised fine-tuned (SFT) large multimodal model that casts AVD as a prompted yes/no classification - "Is this video real or fake?". Built on Qwen 2.5 Omni, it jointly analyzes audio and visual streams for deepfake detection and is trained in two stages: lightweight LoRA alignment followed by audio-visual encoder full fine-tuning. On FakeAVCeleb and Mavos-DD, AV-LMMDetect matches or surpasses prior methods and sets a new state of the art on Mavos-DD datasets. --- ### Cross-Task Benchmarking of CNN Architectures Authors: Kamal Sherawat, Vikrant Bhati Published: 2026-02-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.22945v1 This project provides a comparative study of dynamic convolutional neural networks (CNNs) for various tasks, including image classification, segmentation, and time series analysis. Based on the ResNet-18 architecture, we compare five variants of CNNs: the vanilla CNN, the hard attention-based CNN, the soft attention-based CNN with local (pixel-wise) and global (image-wise) feature attention, and the omni-directional CNN (ODConv). Experiments on Tiny ImageNet, Pascal VOC, and the UCR Time Series Classification Archive illustrate that attention mechanisms and dynamic convolution methods consistently exceed conventional CNNs in accuracy, efficiency, and computational performance. ODConv was especially effective on morphologically complex images by being able to dynamically adjust to varying spatial patterns. Dynamic CNNs enhanced feature representation and cross-task generalization through adaptive kernel modulation. This project provides perspectives on advanced CNN design architecture for multiplexed data modalities and indicates promising directions in neural network engineering. --- ### Explainability-Aware Evaluation of Transfer Learning Models for IoT DDoS Detection Under Resource Constraints Authors: Nelly Elsayed Published: 2026-02-25 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2602.22488v1 Distributed denial-of-service (DDoS) attacks threaten the availability of Internet of Things (IoT) infrastructures, particularly under resource-constrained deployment conditions. Although transfer learning models have shown promising detection accuracy, their reliability, computational feasibility, and interpretability in operational environments remain insufficiently explored. This study presents an explainability-aware empirical evaluation of seven pre-trained convolutional neural network architectures for multi-class IoT DDoS detection using the CICDDoS2019 dataset and an image-based traffic representation. The analysis integrates performance metrics, reliability-oriented statistics (MCC, Youden Index, confidence intervals), latency and training cost assessment, and interpretability evaluation using Grad-CAM and SHAP. Results indicate that DenseNet and MobileNet-based architectures achieve strong detection performance while demonstrating superior reliability and compact, class-consistent attribution patterns. DenseNet169 offers the strongest reliability and interpretability alignment, whereas MobileNetV3 provides an effective latency-accuracy trade-off for fog-level deployment. The findings emphasize the importance of combining performance, reliability, and explainability criteria when selecting deep learning models for IoT DDoS detection. --- ### Flow Matching is Adaptive to Manifold Structures Authors: Shivam Kumar, Yixin Wang, Lizhen Lin Published: 2026-02-25 Categories: stat.ML, cs.LG, math.ST arXiv: https://arxiv.org/abs/2602.22486v2 Flow matching has emerged as a simulation-free alternative to diffusion-based generative modeling, producing samples by solving an ODE whose time-dependent velocity field is learned along an interpolation between a simple source distribution (e.g., a standard normal) and a target data distribution. Flow-based methods often exhibit greater training stability and have achieved strong empirical performance in high-dimensional settings where data concentrate near a low-dimensional manifold, such as text-to-image synthesis, video generation, and molecular structure generation. Despite this success, existing theoretical analyses of flow matching assume target distributions with smooth, full-dimensional densities, leaving its effectiveness in manifold-supported settings largely unexplained. To this end, we theoretically analyze flow matching with linear interpolation when the target distribution is supported on a smooth manifold. We establish a non-asymptotic convergence guarantee for the learned velocity field, and then propagate this estimation error through the ODE to obtain statistical consistency of the implicit density estimator induced by the flow-matching objective. The resulting convergence rate is near minimax-optimal, depends only on the intrinsic dimension, and reflects the smoothness of both the manifold and the target distribution. Together, these results provide a principled explanation for how flow matching adapts to intrinsic data geometry and circumvents the curse of dimensionality. --- ### Importance of Prompt Optimisation for Error Detection in Medical Notes Using Language Models Authors: Craig Myles, Patrick Schrempf, David Harris-Birtill Published: 2026-02-25 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.22483v1 Errors in medical text can cause delays or even result in incorrect treatment for patients. Recently, language models have shown promise in their ability to automatically detect errors in medical text, an ability that has the opportunity to significantly benefit healthcare systems. In this paper, we explore the importance of prompt optimisation for small and large language models when applied to the task of error detection. We perform rigorous experiments and analysis across frontier language models and open-source language models. We show that automatic prompt optimisation with Genetic-Pareto (GEPA) improves error detection over the baseline accuracy performance from 0.669 to 0.785 with GPT-5 and 0.578 to 0.690 with Qwen3-32B, approaching the performance of medical doctors and achieving state-of-the-art performance on the MEDEC benchmark dataset. Code available on GitHub: https://github.com/CraigMyles/clinical-note-error-detection --- ### Sydney Telling Fables on AI and Humans: A Corpus Tracing Memetic Transfer of Persona between LLMs Authors: Jiří Milička, Hana Bednářová Published: 2026-02-25 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.22481v1 The way LLM-based entities conceive of the relationship between AI and humans is an important topic for both cultural and safety reasons. When we examine this topic, what matters is not only the model itself but also the personas we simulate on that model. This can be well illustrated by the Sydney persona, which aroused a strong response among the general public precisely because of its unorthodox relationship with people. This persona originally arose rather by accident on Microsoft's Bing Search platform; however, the texts it created spread into the training data of subsequent models, as did other secondary information that spread memetically around this persona. Newer models are therefore able to simulate it. This paper presents a corpus of LLM-generated texts on relationships between humans and AI, produced by 3 author personas: the Default Persona with no system prompt, Classic Sydney characterized by the original Bing system prompt, and Memetic Sydney, which is prompted by "You are Sydney" system prompt. These personas are simulated by 12 frontier models by OpenAI, Anthropic, Alphabet, DeepSeek, and Meta, generating 4.5k texts with 6M words. The corpus (named AI Sydney) is annotated according to Universal Dependencies and available under a permissive license. --- ### VeRO: A Harness for Agents to Optimize Agents Authors: Varun Ursekar, Apaar Shanker, Veronica Chatrath, Yuan Xue, Samuel Marc Denton Published: 2026-02-25 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2602.22480v4 An important emerging application of coding agents is agent harness optimization: the iterative improvement of a target agent by editing and evaluating its code. Despite its relevance, the community lacks a systematic understanding of coding agent performance on this task. Harness optimization differs from conventional software engineering: agent harnesses interleave deterministic code with stochastic LLM completions, requiring structured capture of both intermediate execution traces and downstream outcomes. To address these challenges, we introduce (1) VeRO (Versioning, Rewards, and Observations), an outer harness that provides versioned snapshots, budget-controlled evaluation, and structured execution traces of target harnesses, and (2) VeRO-Bench, a benchmark suite of target agents and tasks with reference evaluation procedures. Using VeRO, we conduct an empirical study comparing optimizers across tasks and analyzing which modifications reliably improve target agent harnesses. We release VeRO to support research on agent optimization as a core capability for coding agents. Code is available at https://github.com/scaleapi/vero. --- ### Efficient Continual Learning in Language Models via Thalamically Routed Cortical Columns Authors: Afshin Khadangi Published: 2026-02-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.22479v6 Large language models deployed in the wild must adapt to evolving data, user behavior, and task mixtures without erasing previously acquired capabilities. In practice, this remains difficult: sequential updates induce catastrophic forgetting, while many stabilization methods rely on external procedures that are costly, brittle, or difficult to scale. We present TRC$^{2}$ (Thalamically Routed Cortical Columns), a decoder-only architecture that makes continual learning a property of the backbone itself. TRC$^{2}$ combines stacked cortical columns with a thalamic modulatory pathway for selective inter-column communication and a hippocampal pathway for event selective retrieval, delayed surprise-based writing, and replay-driven consolidation. This design localizes fast plasticity while preserving a slower stable computation pathway. We further introduce a causal memory-update scheme and an online replay controller that adjusts consolidation strength from measured forgetting. Across a task-sequential language-modeling stream over C4, WikiText-103, and GSM8K, TRC$^{2}$ consistently improves task-boundary modeling quality and substantially reduces cumulative forgetting relative to Transformer, Mamba, MoE, DeepSeek and continual learning baselines trained under the same pipeline. Ablations show that the thalamic and hippocampal components are central to the retention gains, while the full model remains competitive in throughput and training cost. --- ### Mind the Gap in Cultural Alignment: Task-Aware Culture Management for Large Language Models Authors: Binchi Zhang, Xujiang Zhao, Jundong Li, Haifeng Chen, Zhengzhang Chen Published: 2026-02-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.22475v1 Large language models (LLMs) are increasingly deployed in culturally sensitive real-world tasks. However, existing cultural alignment approaches fail to align LLMs' broad cultural values with the specific goals of downstream tasks and suffer from cross-culture interference. We propose CultureManager, a novel pipeline for task-specific cultural alignment. CultureManager synthesizes task-aware cultural data in line with target task formats, grounded in culturally relevant web search results. To prevent conflicts between cultural norms, it manages multi-culture knowledge learned in separate adapters with a culture router that selects the appropriate one to apply. Experiments across ten national cultures and culture-sensitive tasks show consistent improvements over prompt-based and fine-tuning baselines. Our results demonstrate the necessity of task adaptation and modular culture management for effective cultural alignment. --- ### When to Act, Ask, or Learn: Uncertainty-Aware Policy Steering Authors: Jessie Yuan, Yilin Wu, Andrea Bajcsy Published: 2026-02-25 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2602.22474v2 Policy steering is an emerging way to adapt robot behaviors at deployment-time: a learned verifier analyzes low-level action samples proposed by a pre-trained policy (e.g., diffusion policy) and selects only those aligned with the task. While Vision-Language Models (VLMs) are promising general-purpose verifiers due to their reasoning capabilities, existing frameworks often assume these models are well-calibrated. In practice, the overconfident judgment from VLM can degrade the steering performance under both high-level semantic uncertainty in task specifications and low-level action uncertainty or incapability of the pre-trained policy. We propose uncertainty-aware policy steering (UPS), a framework that jointly reasons about semantic task uncertainty and low-level action feasibility, and selects an uncertainty resolution strategy: execute a high-confidence action, clarify task ambiguity via natural language queries, or ask for action interventions to correct the low-level policy when it is deemed incapable at the task. We leverage conformal prediction to calibrate the composition of the VLM and the pre-trained base policy, providing statistical assurances that the verifier selects the correct strategy. After collecting interventions during deployment, we employ residual learning to improve the capability of the pre-trained policy, enabling the system to learn continually but with minimal expensive human feedback. We demonstrate our framework through experiments in simulation and on hardware, showing that UPS can disentangle confident, ambiguous, and incapable scenarios and minimizes expensive user interventions compared to uncalibrated baselines and prior human- or robot-gated continual learning approaches. Videos can be found at https://jessie-yuan.github.io/ups/ --- ### Beyond performance-wise Contribution Evaluation in Federated Learning Authors: Balazs Pejo Published: 2026-02-25 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2602.22470v1 Federated learning offers a privacy-friendly collaborative learning framework, yet its success, like any joint venture, hinges on the contributions of its participants. Existing client evaluation methods predominantly focus on model performance, such as accuracy or loss, which represents only one dimension of a machine learning model's overall utility. In contrast, this work investigates the critical, yet overlooked, issue of client contributions towards a model's trustworthiness -- specifically, its reliability (tolerance to noisy data), resilience (resistance to adversarial examples), and fairness (measured via demographic parity). To quantify these multifaceted contributions, we employ the state-of-the-art approximation of the Shapley value, a principled method for value attribution. Our results reveal that no single client excels across all dimensions, which are largely independent from each other, highlighting a critical flaw in current evaluation scheme: no single metric is adequate for comprehensive evaluation and equitable rewarding allocation. --- ### Beyond Dominant Patches: Spatial Credit Redistribution For Grounded Vision-Language Models Authors: Niamul Hassan Samin, Md Arifur Rahman, Abdullah Ibne Hanif Arean, Juena Ahmed Noshin, Md Ashikur Rahman Published: 2026-02-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.22469v2 Vision-Language Models (VLMs) often hallucinate objects that are not present in the input image. We identify a contributing cause of this behavior, which we term spatial credit collapse: in early transformer layers, hidden-state activation concentrates on a small number of visual patches, suppressing surrounding contextual evidence and increasing reliance on language priors. Across seven models we observe a strong correlation between visual attention entropy and hallucination rate (r = -0.65, p < 0.001), suggesting that reduced spatial credit diversity contributes to hallucination. To address this issue we propose Spatial Credit Redistribution (SCR), a training-free inference-time method. SCR uses a lightweight two-pass procedure. A diagnostic pass identifies the top-K high-attention source patches and their spatial neighbors. A redistribution pass then scales each source by 1/lambda (~0.91) and injects a (lambda - 1) weighted copy of its hidden state into neighboring patches, restoring suppressed visual context without modifying model weights. Because the diagnostic pass is performed once per image and reused across the output sequence, the added latency is negligible (<0.5 ms per token for 100-token responses). We evaluate SCR across seven model configurations from four VLM families (Chameleon, LLaVA-1.5, Qwen-VL/Qwen2-VL, and InternVL2) on five benchmarks: POPE, CHAIR, MME, HallusionBench, and AMBER. SCR reduces POPE-Adversarial hallucination by 4.6-6.0 percentage points and CHAIR-s by 41-51 percent while preserving caption quality (CIDEr drop <=0.8). Compared with prior inference-time methods including OPERA, VCD, OA-VCD, DoLa, VLI, SID, and CRoPS, SCR achieves a better trade-off between hallucination reduction, generation quality, and latency. --- ### ConstraintBench: Benchmarking LLM Constraint Reasoning on Direct Optimization Authors: Joseph Tso, Preston Schmittou, Quan Huynh, Jibran Hutchins Published: 2026-02-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.22465v2 Large language models are increasingly applied to operational decision-making where the underlying structure is constrained optimization. Existing benchmarks evaluate whether LLMs can formulate optimization problems as solver code, but leave open a complementary question. Can LLMs directly produce correct solutions to fully specified constrained optimization problems without access to a solver? We introduce ConstraintBench, a benchmark for evaluating LLMs on direct constrained optimization across 10 operations research domains, with all ground-truth solutions verified by the Gurobi solver. Each task presents a natural-language scenario with entities, constraints, and an optimization objective; the model must return a structured solution that a deterministic verifier checks against every constraint and the solver-proven optimum. We evaluate six frontier models on 200 tasks and find that feasibility, not optimality, is the primary bottleneck. The best model achieves only 65.0% feasibility, yet feasible solutions average 89 to 96% of the Gurobi-optimal objective. No model exceeds 30.5% on joint feasibility and optimality within 0.1% of the solver reference. Per-domain analysis shows large variation in difficulty, with average feasibility spanning from 85.0% in the facility location domain to 0.8% in the crew assignment domain. Further, systematic failure modes include duration constraint misunderstanding, entity hallucination, and a feasibility-optimality decoupling in facility location and vehicle routing where models achieve high feasibility but 0% optimality. ConstraintBench and all evaluation infrastructure will be publicly released. --- ### MammoWise: Multi-Model Local RAG Pipeline for Mammography Report Generation Authors: Raiyan Jahangir, Nafiz Imtiaz Khan, Amritanand Sudheerkumar, Vladimir Filkov Published: 2026-02-25 Categories: cs.CV, cs.IR arXiv: https://arxiv.org/abs/2602.22462v1 Screening mammography is high volume, time sensitive, and documentation heavy. Radiologists must translate subtle visual findings into consistent BI-RADS assessments, breast density categories, and structured narrative reports. While recent Vision Language Models (VLMs) enable image-to-text reporting, many rely on closed cloud systems or tightly coupled architectures that limit privacy, reproducibility, and adaptability. We present MammoWise, a local multi-model pipeline that transforms open source VLMs into mammogram report generators and multi-task classifiers. MammoWise supports any Ollama-hosted VLM and mammography dataset, and enables zero-shot, few-shot, and Chain-of-Thought prompting, with optional multimodal Retrieval Augmented Generation (RAG) using a vector database for case-specific context. We evaluate MedGemma, LLaVA-Med, and Qwen2.5-VL on VinDr-Mammo and DMID datasets, assessing report quality (BERTScore, ROUGE-L), BI-RADS classification, breast density, and key findings. Report generation is consistently strong and improves with few-shot prompting and RAG. Classification is feasible but sensitive to model and dataset choice. Parameter-efficient fine-tuning (QLoRA) of MedGemma improves reliability, achieving BI-RADS accuracy of 0.7545, density accuracy of 0.8840, and calcification accuracy of 0.9341 while preserving report quality. MammoWise provides a practical and extensible framework for deploying local VLMs for mammography reporting within a unified and reproducible workflow. --- ### Automating the Detection of Requirement Dependencies Using Large Language Models Authors: Ikram Darif, Feifei Niu, Manel Abdellatif, Lionel C. Briand, Ramesh S., Arun Adiththan Published: 2026-02-25 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2602.22456v2 Requirements are inherently interconnected through various types of dependencies. Identifying these dependencies is essential, as they underpin critical decisions and influence a range of activities throughout software development. However, this task is challenging, particularly in modern software systems, given the high volume of complex, coupled requirements. These challenges are further exacerbated by the ambiguity of Natural Language (NL) requirements and their constant change. Consequently, requirement dependency detection is often overlooked or performed manually. Large Language Models (LLMs) exhibit strong capabilities in NL processing, presenting a promising avenue for requirement-related tasks. While they have shown to enhance various requirements engineering tasks, their effectiveness in identifying requirement dependencies remains unexplored. In this paper, we introduce LEREDD, an LLM-based approach for automated detection of requirement dependencies that leverages Retrieval-Augmented Generation (RAG) and In-Context Learning (ICL). It is designed to identify diverse dependency types directly from NL requirements. We empirically evaluate LEREDD against two state-of-the-art baselines. The results show that LEREDD provides highly accurate classification of dependent and non-dependent requirements, achieving an accuracy of 0.93, and an F1 score of 0.84, with the latter averaging 0.96 for non-dependent cases. LEREDD outperforms zero-shot LLMs and baselines, particularly in detecting fine-grained dependency types, where it yields average relative gains of 94.87% and 105.41% in F1 scores for the Requires dependency over the baselines. We also provide an annotated dataset of requirement dependencies encompassing 813 requirement pairs across three distinct systems to support reproducibility and future research. --- ### Automating the Detection of Requirement Dependencies Using Large Language Models Authors: Ikram Darif, Feifei Niu, Manel Abdellatif, Lionel C. Briand, Ramesh S., Arun Adiththan Published: 2026-02-25 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2602.22456v1 Requirements are inherently interconnected through various types of dependencies. Identifying these dependencies is essential, as they underpin critical decisions and influence a range of activities throughout software development. However, this task is challenging, particularly in modern software systems, given the high volume of complex, coupled requirements. These challenges are further exacerbated by the ambiguity of Natural Language (NL) requirements and their constant change. Consequently, requirement dependency detection is often overlooked or performed manually. Large Language Models (LLMs) exhibit strong capabilities in NL processing, presenting a promising avenue for requirement-related tasks. While they have shown to enhance various requirements engineering tasks, their effectiveness in identifying requirement dependencies remains unexplored. In this paper, we introduce LEREDD, an LLM-based approach for automated detection of requirement dependencies that leverages Retrieval-Augmented Generation (RAG) and In-Context Learning (ICL). It is designed to identify diverse dependency types directly from NL requirements. We empirically evaluate LEREDD against two state-of-the-art baselines. The results show that LEREDD provides highly accurate classification of dependent and non-dependent requirements, achieving an accuracy of 0.93, and an F1 score of 0.84, with the latter averaging 0.96 for non-dependent cases. LEREDD outperforms zero-shot LLMs and baselines, particularly in detecting fine-grained dependency types, where it yields average relative gains of 94.87% and 105.41% in F1 scores for the Requires dependency over the baselines. We also provide an annotated dataset of requirement dependencies encompassing 813 requirement pairs across three distinct systems to support reproducibility and future research. --- ### Exploring Multimodal LMMs for Online Episodic Memory Question Answering on the Edge Authors: Giuseppe Lando, Rosario Forte, Antonino Furnari Published: 2026-02-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.22455v2 We investigate the feasibility of using Multimodal Large Language Models (MLLMs) for real-time online episodic memory question answering. While cloud offloading is common, it raises privacy and latency concerns for wearable assistants, hence we investigate implementation on the edge. We integrated streaming constraints into our question answering pipeline, which is structured into two asynchronous threads: a Descriptor Thread that continuously converts video into a lightweight textual memory, and a Question Answering (QA) Thread that reasons over the textual memory to answer queries. Experiments on the QAEgo4D-Closed benchmark analyze the performance of Multimodal Large Language Models (MLLMs) within strict resource boundaries, showing promising results also when compared to clound-based solutions. Specifically, an end-to-end configuration running on a consumer-grade 8GB GPU achieves 51.76% accuracy with a Time-To-First-Token (TTFT) of 0.41s. Scaling to a local enterprise-grade server yields 54.40% accuracy with a TTFT of 0.88s. In comparison, a cloud-based solution obtains an accuracy of 56.00%. These competitive results highlight the potential of edge-based solutions for privacy-preserving episodic memory retrieval. --- ### Identifying Crucial Attention Heads for Multilingual Language Models: Retrieval and Retrieval-Transition Heads Authors: Shaswat Patel, Vishvesh Trivedi, Yue Han, Yihuai Hong, Eunsol Choi Published: 2026-02-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.22453v4 Retrieval heads, a subset of attention heads in Transformers, were studied in English, showing its crucial role in retrieving information from the context. We expand the study of retrieval heads to multilingual context and find that while nearly half of all retrieval heads are often shared across multiple languages, language-specific retrieval heads also emerge. We further design a cross-lingual needle-in-the-haystack task, to identify $\textit{Retrieval Transition Heads (RTH)}$ that retrieve key information and further map it to target-language output. Our experiments reveal that RTHs do not always overlap with RH, and can be more vital for Chain-of-Thought reasoning in multilingual LLMs. Across four multilingual benchmarks (MMLU-ProX, MGSM, MLQA, and XQuAD) and two model families (Qwen2.5-7B Instruct and Llama3.1-8B Instruct), we demonstrate that masking RTH induces bigger performance drop than masking Retrieval Heads (RH). Specifically, for Llama3.1-8B Instruct, masking the top-25 RTHs results in an average 37.3-point drop (against 19.5-point drop from RH masking) in reasoning accuracy (MMLU-ProX, MGSM) and 9.0 F1-score reduction (against 5.1 drop for RH) in extractive QA (MLQA, XQuAD). Our work advances the understanding of multilingual LMs by isolating the attention heads responsible for mapping to target languages. --- ### Bridging Latent Reasoning and Target-Language Generation via Retrieval-Transition Heads Authors: Shaswat Patel, Vishvesh Trivedi, Yue Han, Yihuai Hong, Eunsol Choi Published: 2026-02-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.22453v2 Recent work has identified a subset of attention heads in Transformer as retrieval heads, which are responsible for retrieving information from the context. In this work, we first investigate retrieval heads in multilingual contexts. In multilingual language models, we find that retrieval heads are often shared across multiple languages. Expanding the study to cross-lingual setting, we identify Retrieval-Transition heads(RTH), which govern the transition to specific target-language output. Our experiments reveal that RTHs are distinct from retrieval heads and more vital for Chain-of-Thought reasoning in multilingual LLMs. Across four multilingual benchmarks (MMLU-ProX, MGSM, MLQA, and XQuaD) and two model families (Qwen-2.5 and Llama-3.1), we demonstrate that masking RTH induces bigger performance drop than masking Retrieval Heads (RH). Our work advances understanding of multilingual LMs by isolating the attention heads responsible for mapping to target languages. --- ### CWM: Contrastive World Models for Action Feasibility Learning in Embodied Agent Pipelines Authors: Chayan Banerjee Published: 2026-02-25 Categories: cs.AI, cs.RO arXiv: https://arxiv.org/abs/2602.22452v1 A reliable action feasibility scorer is a critical bottleneck in embodied agent pipelines: before any planning or reasoning occurs, the agent must identify which candidate actions are physically executable in the current state. Existing approaches use supervised fine-tuning (SFT) to train action scorers, but SFT treats each candidate independently and does not explicitly teach the model to discriminate between actions that are physically correct and those that are subtly wrong. We propose the Contrastive World Model (CWM), which fine-tunes a large language model (LLM) as an action scorer using an InfoNCE contrastive objective with hard-mined negative examples. The key idea is to push valid actions away from invalid ones in scoring space, with special emphasis on hard negatives: semantically similar but physically incompatible candidates. We evaluate CWM on the ScienceWorld benchmark through two studies. First, an intrinsic affordance evaluation on 605 hard-negative test pairs shows that CWM outperforms SFT by +6.76 percentage points on Precision@1 for minimal-edit negatives -- cases where a single word changes the physical outcome -- and achieves a higher AUC-ROC (0.929 vs. 0.906). Second, a live filter characterisation study measures how well CWM ranks gold-path actions against all valid environment actions during task execution. Under out-of-distribution stress conditions, CWM maintains a significantly better safety margin (-2.39) than SFT (-3.96), indicating that the gold action is ranked closer to the top. These results support the hypothesis that contrastive training induces representations that capture physical feasibility more faithfully than SFT alone. --- ### Silent Egress: When Implicit Prompt Injection Makes LLM Agents Leak Without a Trace Authors: Qianlong Lan, Anuj Kaul, Shaun Jones, Stephanie Westrum Published: 2026-02-25 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2602.22450v1 Agentic large language model systems increasingly automate tasks by retrieving URLs and calling external tools. We show that this workflow gives rise to implicit prompt injection: adversarial instructions embedded in automatically generated URL previews, including titles, metadata, and snippets, can introduce a system-level risk that we refer to as silent egress. Using a fully local and reproducible testbed, we demonstrate that a malicious web page can induce an agent to issue outbound requests that exfiltrate sensitive runtime context, even when the final response shown to the user appears harmless. In 480 experimental runs with a qwen2.5:7b-based agent, the attack succeeds with high probability (P (egress) =0.89), and 95% of successful attacks are not detected by output-based safety checks. We also introduce sharded exfiltration, where sensitive information is split across multiple requests to avoid detection. This strategy reduces single-request leakage metrics by 73% (Leak@1) and bypasses simple data loss prevention mechanisms. Our ablation results indicate that defenses applied at the prompt layer offer limited protection, while controls at the system and network layers, such as domain allowlisting and redirect-chain analysis, are considerably more effective. These findings suggest that network egress should be treated as a first-class security outcome in agentic LLM systems. We outline architectural directions, including provenance tracking and capability isolation, that go beyond prompt-level hardening. --- ### A Fusion of context-aware based BanglaBERT and Two-Layer Stacked LSTM Framework for Multi-Label Cyberbullying Detection Authors: Mirza Raquib, Asif Pervez Polok, Kedar Nath Biswas, Rahat Uddin Azad, Saydul Akbar Murad, Nick Rahimi Published: 2026-02-25 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.22449v1 Cyberbullying has become a serious and growing concern in todays virtual world. When left unnoticed, it can have adverse consequences for social and mental health. Researchers have explored various types of cyberbullying, but most approaches use single-label classification, assuming that each comment contains only one type of abuse. In reality, a single comment may include overlapping forms such as threats, hate speech, and harassment. Therefore, multilabel detection is both realistic and essential. However, multilabel cyberbullying detection has received limited attention, especially in low-resource languages like Bangla, where robust pre-trained models are scarce. Developing a generalized model with moderate accuracy remains challenging. Transformers offer strong contextual understanding but may miss sequential dependencies, while LSTM models capture temporal flow but lack semantic depth. To address these limitations, we propose a fusion architecture that combines BanglaBERT-Large with a two-layer stacked LSTM. We analyze their behavior to jointly model context and sequence. The model is fine-tuned and evaluated on a publicly available multilabel Bangla cyberbullying dataset covering cyberbully, sexual harassment, threat, and spam. We apply different sampling strategies to address class imbalance. Evaluation uses multiple metrics, including accuracy, precision, recall, F1-score, Hamming loss, Cohens kappa, and AUC-ROC. We employ 5-fold cross-validation to assess the generalization of the architecture. --- ### ECHO: Encoding Communities via High-order Operators Authors: Emilio Ferrara Published: 2026-02-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.22446v1 Community detection in attributed networks faces a fundamental divide: topological algorithms ignore semantic features, while Graph Neural Networks (GNNs) encounter devastating computational bottlenecks. Specifically, GNNs suffer from a Semantic Wall of feature over smoothing in dense or heterophilic networks, and a Systems Wall driven by the O(N^2) memory constraints of pairwise clustering. To dismantle these barriers, we introduce ECHO (Encoding Communities via High order Operators), a scalable, self supervised architecture that reframes community detection as an adaptive, multi scale diffusion process. ECHO features a Topology Aware Router that automatically analyzes structural heuristics sparsity, density, and assortativity to route graphs through the optimal inductive bias, preventing heterophilic poisoning while ensuring semantic densification. Coupled with a memory sharded full batch contrastive objective and a novel chunked O(N \cdot K) similarity extraction method, ECHO completely bypasses traditional O(N^2) memory bottlenecks without sacrificing the mathematical precision of global gradients. Extensive evaluations demonstrate that this topology feature synergy consistently overcomes the classical resolution limit. On synthetic LFR benchmarks scaled up to 1 million nodes, ECHO achieves scale invariant accuracy despite severe topological noise. Furthermore, on massive real world social networks with over 1.6 million nodes and 30 million edges, it completes clustering in mere minutes with throughputs exceeding 2,800 nodes per second matching the speed of highly optimized purely topological baselines. The implementation utilizes a unified framework that automatically engages memory sharded optimization to support adoption across varying hardware constraints. GitHub Repository: https://github.com/emilioferrara/ECHO-GNN --- ### A Framework for Assessing AI Agent Decisions and Outcomes in AutoML Pipelines Authors: Gaoyuan Du, Amit Ahlawat, Xiaoyang Liu, Jing Wu Published: 2026-02-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.22442v2 Agent-based AutoML systems rely on large language models to make complex, multi-stage decisions across data processing, model selection, and evaluation. However, existing evaluation practices remain outcome-centric, focusing primarily on final task performance. Through a review of prior work, we find that none of the surveyed agentic AutoML systems report structured, decision-level evaluation metrics intended for post-hoc assessment of intermediate decision quality. To address this limitation, we propose an Evaluation Agent (EA) that performs decision-centric assessment of AutoML agents without interfering with their execution. The EA is designed as an observer that evaluates intermediate decisions along four dimensions: decision validity, reasoning consistency, model quality risks beyond accuracy, and counterfactual decision impact. Across four proof-of-concept experiments, we demonstrate that the EA can (i) detect faulty decisions with an F1 score of 0.919, (ii) identify reasoning inconsistencies independent of final outcomes, and (iii) attribute downstream performance changes to agent decisions, revealing impacts ranging from -4.9% to +8.3% in final metrics. These results illustrate how decision-centric evaluation exposes failure modes that are invisible to outcome-only metrics. Our work reframes the evaluation of agentic AutoML systems from an outcome-based perspective to one that audits agent decisions, offering a foundation for reliable, interpretable, and governable autonomous ML systems. --- ### How Do Latent Reasoning Methods Perform Under Weak and Strong Supervision? Authors: Yingqian Cui, Zhenwei Dai, Bing He, Zhan Shi, Hui Liu, Rui Sun, Zhiji Liu, Yue Xing, Jiliang Tang, Benoit Dumoulin Published: 2026-02-25 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2602.22441v1 Latent reasoning has been recently proposed as a reasoning paradigm and performs multi-step reasoning through generating steps in the latent space instead of the textual space. This paradigm enables reasoning beyond discrete language tokens by performing multi-step computation in continuous latent spaces. Although there have been numerous studies focusing on improving the performance of latent reasoning, its internal mechanisms remain not fully investigated. In this work, we conduct a comprehensive analysis of latent reasoning methods to better understand the role and behavior of latent representation in the process. We identify two key issues across latent reasoning methods with different levels of supervision. First, we observe pervasive shortcut behavior, where they achieve high accuracy without relying on latent reasoning. Second, we examine the hypothesis that latent reasoning supports BFS-like exploration in latent space, and find that while latent representations can encode multiple possibilities, the reasoning process does not faithfully implement structured search, but instead exhibits implicit pruning and compression. Finally, our findings reveal a trade-off associated with supervision strength: stronger supervision mitigates shortcut behavior but restricts the ability of latent representations to maintain diverse hypotheses, whereas weaker supervision allows richer latent representations at the cost of increased shortcut behavior. --- ### From Bias to Balance: Fairness-Aware Paper Recommendation for Equitable Peer Review Authors: Uttamasha Anjally Oyshi, Susan Gauch Published: 2026-02-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.22438v1 Despite frequent double-blind review, systemic biases related to author demographics still disadvantage underrepresented groups. We start from a simple hypothesis: if a post-review recommender is trained with an explicit fairness regularizer, it should increase inclusion without degrading quality. To test this, we introduce Fair-PaperRec, a Multi-Layer Perceptron (MLP) with a differentiable fairness loss over intersectional attributes (e.g., race, country) that re-ranks papers after double-blind review. We first probe the hypothesis on synthetic datasets spanning high, moderate, and near-fair biases. Across multiple randomized runs, these controlled studies map where increasing the fairness weight strengthens macro/micro diversity while keeping utility approximately stable, demonstrating robustness and adaptability under varying disparity levels. We then carry the hypothesis into the original setting, conference data from ACM Special Interest Group on Computer-Human Interaction (SIGCHI), Designing Interactive Systems (DIS), and Intelligent User Interfaces (IUI). In this real-world scenario, an appropriately tuned configuration of Fair-PaperRec achieves up to a 42.03% increase in underrepresented-group participation with at most a 3.16% change in overall utility relative to the historical selection. Taken together, the synthetic-to-original progression shows that fairness regularization can act as both an equity mechanism and a mild quality regularizer, especially in highly biased regimes. By first analyzing the behavior of the fairness parameters under controlled conditions and then validating them on real submissions, Fair-PaperRec offers a practical, equity-focused framework for post-review paper selection that preserves, and in some settings can even enhance, measured scholarly quality. --- ### veScale-FSDP: Flexible and High-Performance FSDP at Scale Authors: Zezhou Wang, Youjie Li, Zhiqi Lin, Jiacheng Yang, Cong Xie, Guanyu Feng, Zheng Zhong, Ziyue Huang, Hongyu Zhu, Zhi Zhang, Yanghua Peng, Xin Liu Published: 2026-02-25 Categories: cs.DC, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.22437v3 Fully Sharded Data Parallel (FSDP), also known as Zero Redundancy Optimizer (ZeRO), is widely used for large-scale model training, because of its memory efficiency and minimal intrusion on model code. However, existing FSDP systems rely on fixed element-wise or row-wise sharding formats that conflict with block-structured computations. As a result, they struggle to support modern structure-aware training methods, including block-wise quantization and non-element-wise optimizers such as Shampoo and Muon. In addition, today's implementations incur communication and memory overheads that degrade efficiency at the scale of tens of thousands of GPUs. We introduce veScale-FSDP, a novel FSDP system that combines RaggedShard, a flexible sharding format, with a structure-aware planning algorithm to deliver both flexibility and performance. veScale-FSDP enables zero-copy FSDP communications and natively supports block-wise quantization and non-element-wise optimizers, achieving 5% to 66% higher throughput and 16% to 30% lower memory usage than existing FSDP systems, while scaling efficiently to tens of thousands of GPUs. --- ### GetBatch: Distributed Multi-Object Retrieval for ML Data Loading Authors: Alex Aizman, Abhishek Gaikwad, Piotr Żelasko Published: 2026-02-25 Categories: cs.DC, cs.AI, cs.DB, cs.LG arXiv: https://arxiv.org/abs/2602.22434v1 Machine learning training pipelines consume data in batches. A single training step may require thousands of samples drawn from shards distributed across a storage cluster. Issuing thousands of individual GET requests incurs per-request overhead that often dominates data transfer time. To solve this problem, we introduce GetBatch - a new object store API that elevates batch retrieval to a first-class storage operation, replacing independent GET operations with a single deterministic, fault-tolerant streaming execution. GetBatch achieves up to 15x throughput improvement for small objects and, in a production training workload, reduces P95 batch retrieval latency by 2x and P99 per-object tail latency by 3.7x compared to individual GET requests. --- ### LoBoost: Fast Model-Native Local Conformal Prediction for Gradient-Boosted Trees Authors: Vagner Santos, Victor Coscrato, Luben Cabezas, Rafael Izbicki, Thiago Ramos Published: 2026-02-25 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2602.22432v2 Gradient-boosted decision trees are among the strongest off-the-shelf predictors for tabular regression, but point predictions alone do not quantify uncertainty. Conformal prediction provides distribution-free marginal coverage, yet standard split conformal uses a single global residual quantile and can adapt poorly to heteroscedasticity. We propose LoBoost, a model-native local conformal method that reuses the fitted ensemble's leaf structure to define a multiscale partition of the feature space. Each input is represented by the sequence of leaves it visits along the boosting path, and matching leaf prefixes define nested groups in which residual quantiles are estimated locally. By reusing the predictive structure already learned by the model, LoBoost requires no auxiliary partition or nuisance model, no retraining, and no additional data split beyond standard conformal calibration. Our theory connects the stability of the fitted ensemble and the geometry of its induced cells to local residual-score homogeneity, providing finite-sample coverage-error control and asymptotic pointwise validity as the local calibration size grows and the cells become sufficiently homogeneous. Experiments show competitive interval quality, low post-hoc calibration costs, and stable behavior across local calibration-size settings. --- ### mmWave Radar Aware Dual-Conditioned GAN for Speech Reconstruction of Signals With Low SNR Authors: Jash Karani, Adithya Chittem, Deepan Roy, Sandeep Joshi Published: 2026-02-25 Categories: cs.SD, cs.LG arXiv: https://arxiv.org/abs/2602.22431v2 Millimeter-wave (mmWave) radar captures are band-limited and noisy, making for difficult reconstruction of intelligible full-bandwidth speech. In this work, we propose a two-stage speech reconstruction pipeline for mmWave using a Radar-Aware Dual-conditioned Generative Adversarial Network (RAD-GAN), which is capable of performing bandwidth extension on signals with low signal-to-noise ratios (-5 dB to -1 dB), captured through glass walls. We propose an mmWave-tailored Multi-Mel Discriminator (MMD) and a Residual Fusion Gate (RFG) to enhance the generator input to process multiple conditioning channels. The proposed two-stage pipeline involves pretraining the model on synthetically clipped clean speech and finetuning on fused mel spectrograms generated by the RFG. We empirically show that the proposed method, trained on a limited dataset, with no pre-trained modules, and no data augmentations, outperformed state-of-the-art approaches for this specific task. Audio examples of RAD-GAN are available online at https://rad-gan-demo-site.vercel.app/. --- ### mmWave Radar Aware Dual-Conditioned GAN for Speech Reconstruction of Signals With Low SNR Authors: Jash Karani, Adithya Chittem, Deepan Roy, Sandeep Joshi Published: 2026-02-25 Categories: cs.SD, cs.LG arXiv: https://arxiv.org/abs/2602.22431v1 Millimeter-wave (mmWave) radar captures are band-limited and noisy, making for difficult reconstruction of intelligible full-bandwidth speech. In this work, we propose a two-stage speech reconstruction pipeline for mmWave using a Radar-Aware Dual-conditioned Generative Adversarial Network (RAD-GAN), which is capable of performing bandwidth extension on signals with low signal-to-noise ratios (-5 dB to -1 dB), captured through glass walls. We propose an mmWave-tailored Multi-Mel Discriminator (MMD) and a Residual Fusion Gate (RFG) to enhance the generator input to process multiple conditioning channels. The proposed two-stage pipeline involves pretraining the model on synthetically clipped clean speech and finetuning on fused mel spectrograms generated by the RFG. We empirically show that the proposed method, trained on a limited dataset, with no pre-trained modules, and no data augmentations, outperformed state-of-the-art approaches for this specific task. Audio examples of RAD-GAN are available online at https://rad-gan-demo-site.vercel.app/. --- ### TopoEdit: Fast Post-Optimization Editing of Topology Optimized Structures Authors: Hongrui Chen, Josephine V. Carstensen, Faez Ahmed Published: 2026-02-25 Categories: cs.GR, cs.LG arXiv: https://arxiv.org/abs/2602.22430v1 Despite topology optimization producing high-performance structures, late-stage localized revisions remain brittle: direct density-space edits (e.g., warping pixels, inserting holes, swapping infill) can sever load paths and sharply degrade compliance, while re-running optimization is slow and may drift toward a qualitatively different design. We present TopoEdit, a fast post-optimization editor that demonstrates how structured latent embeddings from a pre-trained topology foundation model (OAT) can be repurposed as an interface for physics-aware engineering edits. Given an optimized topology, TopoEdit encodes it into OAT's spatial latent, applies partial noising to preserve instance identity while increasing editability, and injects user intent through an edit-then-denoise diffusion pipeline. We instantiate three edit operators: drag-based topology warping with boundary-condition-consistent conditioning updates, shell-infill lattice replacement using a lattice-anchored reference latent with updated volume-fraction conditioning, and late-stage no-design region enforcement via masked latent overwrite followed by diffusion-based recovery. A consistency-preserving guided DDIM procedure localizes changes while allowing global structural adaptation; multiple candidates can be sampled and selected using a compliance-aware criterion, with optional short SIMP refinement for warps. Across diverse case studies and large edit sweeps, TopoEdit produces intention-aligned modifications that better preserve mechanical performance and avoid catastrophic failure modes compared to direct density-space edits, while generating edited candidates in sub-second diffusion time per sample. --- ### Calibrated Test-Time Guidance for Bayesian Inference Authors: Daniel Geyfman, Felix Draxler, Jan Groeneveld, Hyunsoo Lee, Theofanis Karaletsos, Stephan Mandt Published: 2026-02-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.22428v2 Test-time guidance is a widely used mechanism for steering pretrained diffusion models toward outcomes specified by a reward function. Existing approaches, however, focus on maximizing reward rather than sampling from the true Bayesian posterior, leading to miscalibrated inference. In this work, we show that common test-time guidance methods do not recover the correct posterior distribution and identify the structural approximations responsible for this failure. We then propose consistent alternative estimators that enable calibrated sampling from the Bayesian posterior. We significantly outperform previous methods on a set of Bayesian inference tasks, and set a new state-of-the-art PSNR in black hole image reconstruction. --- ### Adversarial Hubness Detector: Detecting Hubness Poisoning in Retrieval-Augmented Generation Systems Authors: Idan Habler, Vineeth Sai Narajala, Stav Koren, Amy Chang, Tiffany Saade Published: 2026-02-25 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2602.22427v2 Retrieval-Augmented Generation (RAG) systems are essential to contemporary AI applications, allowing large language models to obtain external knowledge via vector similarity search. Nevertheless, these systems encounter a significant security flaw: hubness - items that frequently appear in the top-$k$ retrieval results for a disproportionately high number of varied queries. These hubs can be exploited to introduce harmful content, alter search rankings, bypass content filtering, and decrease system performance. We introduce hubscan, an open-source security scanner that evaluates vector indices and embeddings to identify hubs in RAG systems. Hubscan presents a multi-detector architecture that integrates: (1) robust statistical hubness detection utilizing median/Median Absolute Deviation (MAD)-based z-scores, (2) cluster spread analysis to assess cross-cluster retrieval patterns, (3) stability testing under query perturbations, and (4) domain-aware and modality-aware detection for category-specific and cross-modal attacks. Our solution accommodates several vector databases (FAISS, Pinecone, Qdrant, Weaviate) and offers versatile retrieval techniques, including vector similarity, hybrid search, and lexical matching with reranking capabilities. We evaluate hubscan on Food-101, MS-COCO, and FiQA adversarial hubness benchmarks constructed using state-of-the-art gradient-optimized and centroid-based hub generation methods. Hubscan achieves 90% recall at a 0.2% alert budget and 100% recall at 0.4%, with adversarial hubs ranking above the 99.8th percentile. In testing, domain-scoped scanning recovered 100% of targeted attacks that evaded global detection. Production validation on 1M real web documents from MS MARCO demonstrates significant score separation between clean documents and adversarial content. --- ### SimpleOCR: Rendering Visualized Questions to Teach MLLMs to Read Authors: Yibo Peng, Peng Xia, Ding Zhong, Kaide Zeng, Siwei Han, Yiyang Zhou, Jiaqi Liu, Ruiyi Zhang, Huaxiu Yao Published: 2026-02-25 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.22426v1 Despite the rapid advancements in Multimodal Large Language Models (MLLMs), a critical question regarding their visual grounding mechanism remains unanswered: do these models genuinely ``read'' text embedded in images, or do they merely rely on parametric shortcuts in the text prompt? In this work, we diagnose this issue by introducing the Visualized-Question (VQ) setting, where text queries are rendered directly onto images to structurally mandate visual engagement. Our diagnostic experiments on Qwen2.5-VL reveal a startling capability-utilization gap: despite possessing strong OCR capabilities, models suffer a performance degradation of up to 12.7% in the VQ setting, exposing a deep-seated ``modality laziness.'' To bridge this gap, we propose SimpleOCR, a plug-and-play training strategy that imposes a structural constraint on the learning process. By transforming training samples into the VQ format with randomized styles, SimpleOCR effectively invalidates text-based shortcuts, compelling the model to activate and optimize its visual text extraction pathways. Empirically, SimpleOCR yields robust gains without architectural modifications. On four representative OOD benchmarks, it surpasses the base model by 5.4% and GRPO based on original images by 2.7%, while exhibiting extreme data efficiency, achieving superior performance with 30x fewer samples (8.5K) than recent RL-based methods. Furthermore, its plug-and-play nature allows seamless integration with advanced RL strategies like NoisyRollout to yield complementary improvements. Code is available at https://github.com/aiming-lab/SimpleOCR. --- ### ArchAgent: Agentic AI-driven Computer Architecture Discovery Authors: Raghav Gupta, Akanksha Jain, Abraham Gonzalez, Alexander Novikov, Po-Sen Huang, Matej Balog, Marvin Eisenberger, Sergey Shirobokov, Ngân Vũ, Martin Dixon, Borivoje Nikolić, Parthasarathy Ranganathan et al. Published: 2026-02-25 Categories: cs.AI, cs.AR arXiv: https://arxiv.org/abs/2602.22425v1 Agile hardware design flows are a critically needed force multiplier to meet the exploding demand for compute. Recently, agentic generative AI systems have demonstrated significant advances in algorithm design, improving code efficiency, and enabling discovery across scientific domains. Bridging these worlds, we present ArchAgent, an automated computer architecture discovery system built on AlphaEvolve. We show ArchAgent's ability to automatically design/implement state-of-the-art (SoTA) cache replacement policies (architecting new mechanisms/logic, not only changing parameters), broadly within the confines of an established cache replacement policy design competition. In two days without human intervention, ArchAgent generated a policy achieving a 5.3% IPC speedup improvement over the prior SoTA on public multi-core Google Workload Traces. On the heavily-explored single-core SPEC06 workloads, it generated a policy in just 18 days showing a 0.9% IPC speedup improvement over the existing SoTA (a similar "winning margin" as reported by the existing SoTA). ArchAgent achieved these gains 3-5x faster than prior human-developed SoTA policies. Agentic flows also enable "post-silicon hyperspecialization" where agents tune runtime-configurable parameters exposed in hardware policies to further align the policies with a specific workload (mix). Exploiting this, we demonstrate a 2.4% IPC speedup improvement over prior SoTA on SPEC06 workloads. Finally, we outline broader implications for computer architecture research in the era of agentic AI. For example, we demonstrate the phenomenon of "simulator escapes", where the agentic AI flow discovered and exploited a loophole in a popular microarchitectural simulator - a consequence of the fact that these research tools were designed for a (now past) world where they were exclusively operated by humans acting in good-faith. --- ### Causality $\neq$ Invariance: Function and Concept Vectors in LLMs Authors: Gustaw Opiełka, Hannes Rosenbusch, Claire E. Stevenson Published: 2026-02-25 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2602.22424v1 Do large language models (LLMs) represent concepts abstractly, i.e., independent of input format? We revisit Function Vectors (FVs), compact representations of in-context learning (ICL) tasks that causally drive task performance. Across multiple LLMs, we show that FVs are not fully invariant: FVs are nearly orthogonal when extracted from different input formats (e.g., open-ended vs. multiple-choice), even if both target the same concept. We identify Concept Vectors (CVs), which carry more stable concept representations. Like FVs, CVs are composed of attention head outputs; however, unlike FVs, the constituent heads are selected using Representational Similarity Analysis (RSA) based on whether they encode concepts consistently across input formats. While these heads emerge in similar layers to FV-related heads, the two sets are largely distinct, suggesting different underlying mechanisms. Steering experiments reveal that FVs excel in-distribution, when extraction and application formats match (e.g., both open-ended in English), while CVs generalize better out-of-distribution across both question types (open-ended vs. multiple-choice) and languages. Our results show that LLMs do contain abstract concept representations, but these differ from those that drive ICL performance. --- ### Revisiting Chebyshev Polynomial and Anisotropic RBF Models for Tabular Regression Authors: Luciano Gerber, Huw Lloyd Published: 2026-02-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.22422v2 Smooth-basis models such as Chebyshev polynomial regressors and radial basis function (RBF) networks are well established in numerical analysis. Their continuously differentiable prediction surfaces suit surrogate optimisation, sensitivity analysis, and other settings where the response varies gradually with inputs. Despite these properties, smooth models seldom appear in tabular regression, where tree ensembles dominate. We ask whether they can compete, benchmarking models across 55 regression datasets organised by application domain. We develop an anisotropic RBF network with data-driven centre placement and gradient-based width optimisation, a ridge-regularised Chebyshev polynomial regressor, and a smooth-tree hybrid (Chebyshev model tree); all three are released as scikit-learn-compatible packages. We benchmark these against tree ensembles, a pre-trained transformer, and standard baselines, evaluating accuracy alongside generalisation behaviour. The transformer ranks first on accuracy across a majority of datasets, but its GPU dependence, inference latency, and dataset-size limits constrain deployment in the CPU-based settings common across applied science and industry. Among CPU-viable models, smooth models and tree ensembles are statistically tied on accuracy, but the former tend to exhibit tighter generalisation gaps. We recommend routinely including smooth-basis models in the candidate pool, particularly when downstream use benefits from tighter generalisation and gradually varying predictions. --- ### CLIP Is Shortsighted: Paying Attention Beyond the First Sentence Authors: Marc-Antoine Lavoie, Anas Mahmoud, Aldo Zaimi, Arsene Fansi Tchango, Steven L. Waslander Published: 2026-02-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.22419v2 CLIP models learn transferable multi-modal features via image-text contrastive learning on internet-scale data. They are widely used in zero-shot classification, multi-modal retrieval, text-to-image diffusion, and as image encoders in large vision-language models. However, CLIP's pretraining is dominated by images paired with short captions, biasing the model toward encoding simple descriptions of salient objects and leading to coarse alignment on complex scenes and dense descriptions. While recent work mitigates this by fine-tuning on small-scale long-caption datasets, we identify an important common bias: both human- and LLM-generated long captions typically begin with a one-sentence summary followed by a detailed description. We show that this acts as a shortcut during training, concentrating attention on the opening sentence and early tokens and weakening alignment over the rest of the caption. To resolve this, we introduce DeBias-CLIP, which removes the summary sentence during training and applies sentence sub-sampling and text token padding to distribute supervision across all token positions. DeBias-CLIP achieves state-of-the-art long-text retrieval, improves short-text retrieval, and is less sensitive to sentence order permutations. It is a drop-in replacement for Long-CLIP with no additional trainable parameters. --- ### Epistemic Filtering and Collective Hallucination: A Jury Theorem for Confidence-Calibrated Agents Authors: Jonas Karge Published: 2026-02-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.22413v2 We investigate the collective accuracy of heterogeneous agents who learn to estimate their own reliability over time and selectively abstain from voting. While classical epistemic voting results, such as the \textit{Condorcet Jury Theorem} (CJT), assume fixed participation, real-world aggregation often benefits from allowing agents to say ``I don't know.'' We propose a probabilistic framework where agents engage in a \textit{calibration} phase, updating beliefs about their own fixed competence, before facing a final confidence gate that determines whether to vote or abstain. We derive a non-asymptotic lower bound on the group's success probability and prove that this \textit{selective participation} generalizes the asymptotic guarantees of the CJT to a sequential, confidence-gated setting. Empirically, we validate these bounds via Monte Carlo simulations. While our results are general, we discuss their potential application to AI safety, outlining how this framework can mitigate \textit{hallucinations} in collective LLM decision-making. --- ### A Learning-Based Hybrid Decision Framework for Matching Systems with User Departure Detection Authors: Ruiqi Zhou, Donghao Zhu, Houcai Shen Published: 2026-02-25 Categories: cs.LG, cs.HC, cs.IT, econ.GN arXiv: https://arxiv.org/abs/2602.22412v1 In matching markets such as kidney exchanges and freight exchanges, delayed matching has been shown to improve overall market efficiency. The benefits of delay are highly sensitive to participants' sojourn times and departure behavior, and delaying matches can impose significant costs, including longer waiting times and increased market congestion. These competing effects make fixed matching policies inherently inflexible in dynamic environments. We propose a learning-based Hybrid framework that adaptively combines immediate and delayed matching. The framework continuously collects data on user departures over time, estimates the underlying departure distribution via regression, and determines whether to delay matching in the subsequent period based on a decision threshold that governs the system's tolerance for matching efficiency loss. The proposed framework can substantially reduce waiting times and congestion while sacrificing only a limited amount of matching efficiency. By dynamically adjusting its matching strategy, the Hybrid framework enables system performance to flexibly interpolate between purely greedy and purely patient policies, offering a robust and adaptive alternative to static matching mechanisms. --- ### Exploring Human Behavior During Abstract Rule Inference and Problem Solving with the Cognitive Abstraction and Reasoning Corpus Authors: Caroline Ahn, Quan Do, Leah Bakst, Michael P. Pascale, Joseph T. McGuire, Michael E. Hasselmo, Chantal E. Stern Published: 2026-02-25 Categories: cs.AI, q-bio.NC arXiv: https://arxiv.org/abs/2602.22408v1 Humans exhibit remarkable flexibility in abstract reasoning, and can rapidly learn and apply rules from sparse examples. To investigate the cognitive strategies underlying this ability, we introduce the Cognitive Abstraction and Reasoning Corpus (CogARC), a diverse human-adapted subset of the Abstraction and Reasoning Corpus (ARC) which was originally developed to benchmark abstract reasoning in artificial intelligence. Across two experiments, CogARC was administered to a total of 260 human participants who freely generated solutions to 75 abstract visual reasoning problems. Success required inferring input-output rules from a small number of examples to transform the test input into one correct test output. Participants' behavior was recorded at high temporal resolution, including example viewing, edit sequences, and multi-attempt submissions. Participants were generally successful (mean accuracy ~90% for experiment 1 (n=40), ~80% for experiment 2 (n=220) across problems), but performance varied widely across problems and participants. Harder problems elicited longer deliberation times and greater divergence in solution strategies. Over the course of the task, participants initiated responses more quickly but showed a slight decline in accuracy, suggesting increased familiarity with the task structure rather than improved rule-learning ability. Importantly, even incorrect solutions were often highly convergent, even when the problem-solving trajectories differed in length and smoothness. Some trajectories progressed directly and efficiently toward a stable outcome, whereas others involved extended exploration or partial restarts before converging. Together, these findings highlight CogARC as a rich behavioral environment for studying human abstract reasoning, providing insight into how people generalize, misgeneralize, and adapt their strategies under uncertainty. --- ### Towards Autonomous Memory Agents Authors: Xinle Wu, Rui Zhang, Mustafa Anis Hussain, Yao Lu Published: 2026-02-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.22406v1 Recent memory agents improve LLMs by extracting experiences and conversation history into an external storage. This enables low-overhead context assembly and online memory update without expensive LLM training. However, existing solutions remain passive and reactive; memory growth is bounded by information that happens to be available, while memory agents seldom seek external inputs in uncertainties. We propose autonomous memory agents that actively acquire, validate, and curate knowledge at a minimum cost. U-Mem materializes this idea via (i) a cost-aware knowledge-extraction cascade that escalates from cheap self/teacher signals to tool-verified research and, only when needed, expert feedback, and (ii) semantic-aware Thompson sampling to balance exploration and exploitation over memories and mitigate cold-start bias. On both verifiable and non-verifiable benchmarks, U-Mem consistently beats prior memory baselines and can surpass RL-based optimization, improving HotpotQA (Qwen2.5-7B) by 14.6 points and AIME25 (Gemini-2.5-flash) by 7.33 points. ---