# Research Papers — 2026-04 · bundle page 104 of 233 > Full-text markdown of papers #5151–5200 of 11612 published in 2026-04, newest first. AI-readable mirrors of the full 11612-paper 2026-04 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-04/page/104 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/103.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/105.md) ### Optimizing Stochastic Gradient Push under Broadcast Communications Authors: Tuan Nguyen, Ting He Published: 2026-04-16 Categories: cs.LG, cs.DC, math.OC arXiv: https://arxiv.org/abs/2604.15549v1 We consider the problem of minimizing the convergence time for decentralized federated learning (DFL) in wireless networks under broadcast communications, with focus on mixing matrix design. The mixing matrix is a critical hyperparameter for DFL that simultaneously controls the convergence rate across iterations and the communication demand per iteration, both strongly influencing the convergence time. Although the problem has been studied previously, existing solutions are mostly designed for decentralized parallel stochastic gradient descent (D-PSGD), which requires the mixing matrix to be symmetric and doubly stochastic. These constraints confine the activated communication graph to undirected (i.e., bidirected) graphs, which limits design flexibility. In contrast, we consider mixing matrix design for stochastic gradient push (SGP), which allows asymmetric mixing matrices and hence directed communication graphs. By analyzing how the convergence rate of SGP depends on the mixing matrices, we extract an objective function that explicitly depends on graph-theoretic parameters of the activated communication graph, based on which we develop an efficient design algorithm with performance guarantees. Our evaluations based on real data show that the proposed solution can notably reduce the convergence time compared to the state of the art without compromising the quality of the trained model. --- ### Consistency Analysis of Sentiment Predictions using Syntactic & Semantic Context Assessment Summarization (SSAS) Authors: Sharookh Daruwalla, Nitin Mayande, Shreeya Verma Kathuria, Nitin Joglekar, Charles Weber Published: 2026-04-16 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.15547v1 The fundamental challenge of using Large Language Models (LLMs) for reliable, enterprise-grade analytics, such as sentiment prediction, is the conflict between the LLMs' inherent stochasticity (generative, non-deterministic nature) and the analytical requirement for consistency. The LLM inconsistency, coupled with the noisy nature of chaotic modern datasets, renders sentiment predictions too volatile for strategic business decisions. To resolve this, we present a Syntactic & Semantic Context Assessment Summarization (SSAS) framework for establishing context. Context established by SSAS functions as a sophisticated data pre-processing framework that enforces a bounded attention mechanism on LLMs. It achieves this by applying a hierarchical classification structure (Themes, Stories, Clusters) and an iterative Summary-of-Summaries (SoS) based context computation architecture. This endows the raw text with high-signal, sentiment-dense prompts, that effectively mitigate both irrelevant data and analytical variance. We empirically evaluated the efficacy of SSAS, using Gemini 2.0 Flash Lite, against a direct-LLM approach across three industry-standard datasets - Amazon Product Reviews, Google Business Reviews, Goodreads Book Reviews - and multiple robustness scenarios. Our results show that our SSAS framework is capable of significantly improving data quality, up to 30%, through a combination of noise removal and improvement in the estimation of sentiment prediction. Ultimately, consistency in our context-estimation capabilities provides a stable and reliable evidence base for decision-making. --- ### UA-Net: Uncertainty-Aware Network for TRISO Image Semantic Segmentation Authors: Kyle Lucke, Zuzanna Krajewska-Travar, Shoukun Sun, Lu Cai, John D. Stempien, Min Xian Published: 2026-04-16 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2604.15542v1 Tristructural isotropic (TRISO)-coated particle fuels undergo dimensional changes and chemical reactions during high-temperature neutron irradiation. Post-irradiation materialography helps understand processes that impact fuel performance, such as coating integrity and fission product retention. Conventionally, experts manually evaluate features in thousands of cross sections of sub-mm-sized samples, which is tedious and subjective. In this work, we propose UA-Net, a deep learning framework that segments five characteristic regions of TRISO fuel micrographs and generates an uncertainty map for predictions. The model uses a multi-stage pretraining strategy, starting with general image representations learned from ImageNet, followed by fine-tuning on TRISO micrographs from various irradiation experiments and AGR-5/6/7 particle cross sections. A meta-model for uncertainty prediction is integrated to identify small defects in TRISO images. UA-Net was evaluated on a test set of 102 images, achieving mean Intersection over Union (mIoU) and mean Precision (mP) of 95.5% and 97.3%, respectively. The meta-model achieved a specificity of 91.8% and sensitivity of 93.5%, demonstrating strong performance in detecting misclassifications. The model was also applied to new TRISO images for qualitative evaluation, showing high accuracy in extracting layer regions. --- ### PRIM-cipal components analysis Authors: Tianhao Liu, Daniel Andrés Díaz-Pachón, J. Sunil Rao Published: 2026-04-16 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2604.15538v1 Supervised No Free Lunch Theorems (NFLTs) are well studied, yet unsupervised NFLTs remain underexplored. For elliptical distributions, we prove that there exist two equally optimal, scientifically meaningful bump-hunting strategies that are exact opposites, with no universal winner. Specifically, peeling $k$ orthogonal dimensions from $\mathbb{R}^d$ ($d \ge k$), retaining an inter-quantile region of probability $1-α$ per peeled dimension, maximizes total variance and Frobenius norm when the $k$ smallest principal components (called pettiest components) are selected, and minimizes them when the selected dimensions are the $k$ leading principal components. These optima inspire PRIM-based bump-hunting algorithms either by minimizing variance or by minimizing volume, thereby motivating an NFLT. We test our results on the Fashion-MNIST database, showing that peeling the largest principal components captures multiplicity, while peeling the smallest principal components isolates popular styles. --- ### Verification Modulo Tested Library Contracts Authors: Abhishek Uppar, Omar Muhammad, Sumanth Prabhu, Deepak D'Souza, Madhusudan P, Adithya Murali Published: 2026-04-16 Categories: cs.PL, cs.LG, cs.LO, cs.SE arXiv: https://arxiv.org/abs/2604.15533v2 We consider the problem of verification modulo tested library contracts as a step towards automating the verification of client programs that use complex libraries. We formulate this problem as the synthesis of modular contracts for the library methods used by the client that are adequate to prove the client correct, and that also pass the scrutiny of a testing engine that tests the library against these contracts. We also consider a new form of method contracts called contextual contracts that arise in this setting that hold in the context of the client program, and can often be simpler and easier to infer than classical modular contracts. We provide a counterexample-guided learning framework to solve this problem, in which the synthesizer interacts with a constraint solver as well as the testing engine in order to infer adequate modular/contextual method contracts and inductive invariants for the client. The main synthesis engines we use are generalizing CHC solvers that are realized using ICE learning algorithms. We realize this framework in a tool called DUALIS and show its efficacy on benchmarks where clients call large libraries. --- ### Spurious Predictability in Financial Machine Learning Authors: Sotirios D. Nikolopoulos Published: 2026-04-16 Categories: q-fin.ST, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2604.15531v1 Adaptive specification search generates statistically significant backtests even under martingale-difference nulls. We introduce a falsification audit testing complete predictive workflows against synthetic reference classes, including zero-predictability environments and microstructure placebos. Workflows generating significant walk-forward evidence in these environments are falsified. For passing workflows, we quantify selection-induced performance inflation using an absolute magnitude gap linking optimized in-sample evidence to disjoint walk-forward realizations, adjusted for effective multiplicity. Simulations validate extreme-value scaling under correlated searches and demonstrate detection power under genuine structure. Empirical case studies confirm that many apparent findings represent methodological artifacts rather than genuine predictability. --- ### LACE: Lattice Attention for Cross-thread Exploration Authors: Yang Li, Zirui Zhang, Yang Liu, Chengzhi Mao Published: 2026-04-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.15529v3 Current large language models reason in isolation. Although it is common to sample multiple reasoning paths in parallel, these trajectories do not interact, and often fail in the same redundant ways. We introduce LACE, a framework that transforms reasoning from a collection of independent trials into a coordinated, parallel process. By repurposing the model architecture to enable cross-thread attention, LACE allows concurrent reasoning paths to share intermediate insights and correct one another during inference. A central challenge is the absence of natural training data that exhibits such collaborative behavior. We address this gap with a synthetic data pipeline that explicitly teaches models to communicate and error-correct across threads. Experiments show that this unified exploration substantially outperforms standard parallel search, improving reasoning accuracy by over 7 points. Our results suggest that large language models can be more effective when parallel reasoning paths are allowed to interact. --- ### Frequency-Aware Flow Matching for High-Quality Image Generation Authors: Sucheng Ren, Qihang Yu, Ju He, Xiaohui Shen, Alan Yuille, Liang-Chieh Chen Published: 2026-04-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.15521v1 Flow matching models have emerged as a powerful framework for realistic image generation by learning to reverse a corruption process that progressively adds Gaussian noise. However, because noise is injected in the latent domain, its impact on different frequency components is non-uniform. As a result, during inference, flow matching models tend to generate low-frequency components (global structure) in the early stages, while high-frequency components (fine details) emerge only later in the reverse process. Building on this insight, we propose Frequency-Aware Flow Matching (FreqFlow), a novel approach that explicitly incorporates frequency-aware conditioning into the flow matching framework via time-dependent adaptive weighting. We introduce a two-branch architecture: (1) a frequency branch that separately processes low- and high-frequency components to capture global structure and refine textures and edges, and (2) a spatial branch that synthesizes images in the latent domain, guided by the frequency branch's output. By explicitly integrating frequency information into the generation process, FreqFlow ensures that both large-scale coherence and fine-grained details are effectively modeled low-frequency conditioning reinforces global structure, while high-frequency conditioning enhances texture fidelity and detail sharpness. On the class-conditional ImageNet-256 generation benchmark, our method achieves state-of-the-art performance with an FID of 1.38, surpassing the prior diffusion model DiT and flow matching model SiT by 0.79 and 0.58 FID, respectively. Code is available at https://github.com/OliverRensu/FreqFlow. --- ### Bureaucratic Silences: What the Canadian AI Register Reveals, Omits, and Obscures Authors: Dipto Das, Christelle Tessono, Syed Ishtiaque Ahmed, Shion Guha Published: 2026-04-16 Categories: cs.AI, cs.CY, cs.HC arXiv: https://arxiv.org/abs/2604.15514v1 In November 2025, the Government of Canada operationalized its commitment to transparency by releasing its first Federal AI Register. In this paper, we argue that such registers are not neutral mirrors of government activity, but active instruments of ontological design that configure the boundaries of accountability. We analyzed the Register's complete dataset of 409 systems using the Algorithmic Decision-Making Adapted for the Public Sector (ADMAPS) framework, combining quantitative mapping with deductive qualitative coding. Our findings reveal a sharp divergence between the rhetoric of "sovereign AI" and the reality of bureaucratic practice: while 86\% of systems are deployed internally for efficiency, the Register systematically obscures the human discretion, training, and uncertainty management required to operate them. By privileging technical descriptions over sociotechnical context, the Register constructs an ontology of AI as "reliable tooling" rather than "contestable decision-making." We conclude that without a shift in design, such transparency artifacts risk automating accountability into a performative compliance exercise, offering visibility without contestability. --- ### LLMbench: A Comparative Close Reading Workbench for Large Language Models Authors: David M. Berry Published: 2026-04-16 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2604.15508v1 LLMbench is a browser-based workbench for the comparative close reading of large language model (LLM) outputs. Where existing tools for LLM comparison, such as Google PAIR's LLM Comparator are engineered for quantitative evaluation and user-rating metrics, LLMbench is oriented towards the hermeneutic practices of the digital humanities. Two model responses to the same prompt are side by side in annotatable panels with four analytical overlays (Probabilities for token-level log-probability inspection, Differences for word-level diff across the two panels, Tone for Hyland-style metadiscourse analysis, and Structure for sentence-level parsing with discourse connective highlighting), alongside five analytical modes, Stochastic Variation, Temperature Gradient, Prompt Sensitivity, Token Probabilities, and Cross-Model Divergence, that make the probabilistic structure of generated text legible at the token level. The tool treats the generated text as a research object in its own right from a probability distribution, a text that could have been otherwise, and provides visualisations including continuous heatmaps, entropy sparklines, pixel maps, and three-dimensional probability terrains, that show the counterfactual history from which each word emerged. This paper describes the tool's architecture, its six modes, and its design rationale, and argues that log-probability data, currently underused in humanistic and social-scientific readings of AI, is an important resource for a critical studies of generative AI models. --- ### PolicyBank: Evolving Policy Understanding for LLM Agents Authors: Jihye Choi, Jinsung Yoon, Long T. Le, Somesh Jha, Tomas Pfister Published: 2026-04-16 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.15505v1 LLM agents operating under organizational policies must comply with authorization constraints typically specified in natural language. In practice, such specifications inevitably contain ambiguities and logical or semantic gaps that cause the agent's behavior to systematically diverge from the true requirements. We ask: by letting an agent evolve its policy understanding through interaction and corrective feedback from pre-deployment testing, can it autonomously refine its interpretation to close specification gaps? We propose PolicyBank, a memory mechanism that maintains structured, tool-level policy insights and iteratively refines them -- unlike existing memory mechanisms that treat the policy as immutable ground truth, reinforcing "compliant but wrong" behaviors. We also contribute a systematic testbed by extending a popular tool-calling benchmark with controlled policy gaps that isolate alignment failures from execution failures. While existing memory mechanisms achieve near-zero success on policy-gap scenarios, PolicyBank closes up to 82% of the gap toward a human oracle. --- ### Brain Score Tracks Shared Properties of Languages: Evidence from Many Natural Languages and Structured Sequences Authors: Jingnong Qu, Ashvin Ranjan, Shane Steinert-Threlkeld Published: 2026-04-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.15503v1 Recent breakthroughs in language models (LMs) using neural networks have raised the question: how similar are these models' processing to human language processing? Results using a framework called Brain Score (BS) -- predicting fMRI activations during reading from LM activations -- have been used to argue for a high degree of similarity. To understand this similarity, we conduct experiments by training LMs on various types of input data and evaluate them on BS. We find that models trained on various natural languages from many different language families have very similar BS performance. LMs trained on other structured data -- the human genome, Python, and pure hierarchical structure (nested parentheses) -- also perform reasonably well and close to natural languages in some cases. These findings suggest that BS can highlight language models' ability to extract common structure across natural languages, but that the metric may not be sensitive enough to allow us to infer human-like processing from a high BS score alone. --- ### SecureRouter: Encrypted Routing for Efficient Secure Inference Authors: Yukuan Zhang, Mengxin Zheng, Qian Lou Published: 2026-04-16 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2604.15499v1 Cryptographically secure neural network inference typically relies on secure computing techniques such as Secure Multi-Party Computation (MPC), enabling cloud servers to process client inputs without decrypting them. Although prior privacy-preserving inference systems co-design network optimizations with MPC, they remain slow and costly, limiting real-world deployment. A major bottleneck is their use of a single, fixed transformer model for all encrypted inputs, ignoring that different inputs require different model sizes to balance efficiency and accuracy. We present SecureRouter, an end-to-end encrypted routing and inference framework that accelerates secure transformer inference through input-adaptive model selection under encryption. SecureRouter establishes a unified encrypted pipeline that integrates a secure router with an MPC-optimized model pool, enabling coordinated routing, inference, and protocol execution while preserving full data and model confidentiality. The framework includes training-phase and inference-phase components: an MPC-cost-aware secure router that predicts per-model utility and cost from encrypted features, and an MPC-optimized model pool whose architectures and quantization schemes are co-trained to minimize MPC communication and computation overhead. Compared to prior work, SecureRouter achieves a latency reduction by 1.95x with negligible accuracy loss, offering a practical path toward scalable and efficient secure AI inference. Our open-source implementation is available at: https://github.com/UCF-ML-Research/SecureRouter --- ### GIST: Multimodal Knowledge Extraction and Spatial Grounding via Intelligent Semantic Topology Authors: Shivendra Agrawal, Bradley Hayes Published: 2026-04-16 Categories: cs.AI, cs.CV, cs.HC, cs.RO arXiv: https://arxiv.org/abs/2604.15495v1 Navigating complex, densely packed environments like retail stores, warehouses, and hospitals poses a significant spatial grounding challenge for humans and embodied AI. In these spaces, dense visual features quickly become stale given the quasi-static nature of items, and long-tail semantic distributions challenge traditional computer vision. While Vision-Language Models (VLMs) help assistive systems navigate semantically-rich spaces, they still struggle with spatial grounding in cluttered environments. We present GIST (Grounded Intelligent Semantic Topology), a multimodal knowledge extraction pipeline that transforms a consumer-grade mobile point cloud into a semantically annotated navigation topology. Our architecture distills the scene into a 2D occupancy map, extracts its topological layout, and overlays a lightweight semantic layer via intelligent keyframe and semantic selection. We demonstrate the versatility of this structured spatial knowledge through critical downstream Human-AI interaction tasks: (1) an intent-driven Semantic Search engine that actively infers categorical alternatives and zones when exact matches fail; (2) a one-shot Semantic Localizer achieving a 1.04 m top-5 mean translation error; (3) a Zone Classification module that segments the walkable floor plan into high-level semantic regions; and (4) a Visually-Grounded Instruction Generator that synthesizes optimal paths into egocentric, landmark-rich natural language routing. In multi-criteria LLM evaluations, GIST outperforms sequence-based instruction generation baselines. Finally, an in-situ formative evaluation (N=5) yields an 80% navigation success rate relying solely on verbal cues, validating the system's capacity for universal design. --- ### ProtoTTA: Prototype-Guided Test-Time Adaptation Authors: Mohammad Mahdi Abootorabi, Parvin Mousavi, Purang Abolmaesumi, Evan Shelhamer Published: 2026-04-16 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2604.15494v1 Deep networks that rely on prototypes-interpretable representations that can be related to the model input-have gained significant attention for balancing high accuracy with inherent interpretability, which makes them suitable for critical domains such as healthcare. However, these models are limited by their reliance on training data, which hampers their robustness to distribution shifts. While test-time adaptation (TTA) improves the robustness of deep networks by updating parameters and statistics, the prototypes of interpretable models have not been explored for this purpose. We introduce ProtoTTA, a general framework for prototypical models that leverages intermediate prototype signals rather than relying solely on model outputs. ProtoTTA minimizes the entropy of the prototype-similarity distribution to encourage more confident and prototype-specific activations on shifted data. To maintain stability, we employ geometric filtering to restrict updates to samples with reliable prototype activations, regularized by prototype-importance weights and model-confidence scores. Experiments across four prototypical backbones on four diverse benchmarks spanning fine-grained vision, histopathology, and NLP demonstrate that ProtoTTA improves robustness over standard output entropy minimization while restoring correct semantic focus in prototype activations. We also introduce novel interpretability metrics and a vision-language model (VLM) evaluation framework to explain TTA dynamics, confirming ProtoTTA restores human-aligned semantic focus and correlates reliably with VLM-rated reasoning quality. Code is available at: https://github.com/DeepRCL/ProtoTTA. --- ### Think Multilingual, Not Harder: A Data-Efficient Framework for Teaching Reasoning Models to Code-Switch Authors: Eleanor M. Lin, David Jurgens Published: 2026-04-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.15490v2 Recent developments in reasoning capabilities have enabled large language models to solve increasingly complex mathematical, symbolic, and logical tasks. Interestingly, while reasoning models are often trained to generate monolingual text, these models have also been observed to code-switch (i.e., mix languages). Prior works have either viewed code-switching as an undesirable error, attempted to control code-switching through modifications to input prompts or the output decoding process, or focus on narrow subsets of languages, domains, tasks, and models. We address these gaps by introducing the first linguistically and behaviorally motivated fine-tuning framework for identifying beneficial code-switched reasoning behaviors in large language models and teaching these models to code-switch more effectively for reasoning. We create the Code-Switched Reasoning (CoRe) corpus, consisting of (1) 7k reasoning traces from 15 models, 18 languages, 10 scripts, and diverse reasoning domains, providing insights into potentially helpful code-switching behaviors, and (2) 40 carefully curated datasets for training and evaluating six interventions for improving code-switching in reasoning across three models and seven languages, totaling 120 fine-tuning conditions. Across 80k+ reasoning traces from both language/culture-agnostic and -specific evaluations, English-dominated reasoning, semantically accurate code-switching, and a more even mix of languages are positively associated with correct answers, whereas dense switching is associated with incorrect answers. Moreover, we are able to elicit positive behaviors through fine-tuning tasks that do not directly demonstrate code-switching. Our work suggests that small but well-curated datasets can change how reasoning models code-switch, allowing us to reap the benefits of reasoning in the many languages that lack large-scale reasoning data. --- ### Think Multilingual, Not Harder: A Data-Efficient Framework for Teaching Reasoning Models to Code-Switch Authors: Eleanor M. Lin, David Jurgens Published: 2026-04-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.15490v1 Recent developments in reasoning capabilities have enabled large language models to solve increasingly complex mathematical, symbolic, and logical tasks. Interestingly, while reasoning models are often trained to generate monolingual text, these models have also been observed to code-switch (i.e., mix languages). Prior works have either viewed code-switching as an undesirable error, attempted to control code-switching through modifications to input prompts or the output decoding process, or focus on narrow subsets of languages, domains, tasks, and models. We address these gaps by introducing the first linguistically and behaviorally motivated fine-tuning framework for identifying beneficial code-switched reasoning behaviors in large language models and teaching these models to code-switch more effectively for reasoning. First, we create and systematically analyze a dataset of reasoning traces from diverse models, languages, tasks, and domains to understand the types of code-switching behaviors found in existing reasoning models. Then, we develop fine-tuning interventions that teach reasoning models to code-switch based on our observations of helpful behaviors in existing models. We find that our framework can significantly increase beneficial code-switched reasoning behaviors in a data-efficient manner. Interestingly, we also find that code-switching behaviors in reasoning models can be modified by fine-tuning for tasks that do not directly demonstrate code-switching in reasoning (e.g., machine translation). Our work suggests that data-efficient interventions can instill helpful forms of code-switching behavior in reasoning models. --- ### A Q-learning-based QoS-aware multipath routing protocol in IoMT-based wireless body area network Authors: Mehdi Hosseinzadeh, Roohallah Alizadehsani, Amin Beheshti, Hamid Alinejad-Roknyd, Lu Chen, Mohammad Sadegh Yousefpoor, Efat Yousefpoor, Muneera Altayeb, Thantrira Porntaveetus, Sadia Din Published: 2026-04-16 Categories: cs.NI, cs.AI arXiv: https://arxiv.org/abs/2604.15489v2 The Internet of Medical Things (IoMT) enables intelligent healthcare services but faces challenges such as dynamic topology, energy constraints, and diverse QoS requirements. This paper proposes QQMR, a Q-learning-based QoS-aware multipath routing method for WBANs. QQMR classifies data into three priority levels and employs adaptive multi-level queuing and fuzzy C-means clustering to optimize routing decisions. It maintains separate learning policies for each data type and selects primary and backup paths accordingly. Experimental results demonstrate improved packet delivery ratio and significant reductions in delay, routing overhead, and energy consumption compared to existing methods. --- ### A Q-learning-based QoS-aware multipath routing protocol in IoMT-based wireless body area network Authors: Mehdi Hosseinzadeh, Roohallah Alizadehsani, Amin Beheshti, Hamid Alinejad-Roknyd, Lu Chen, Mohammad Sadegh Yousefpoor, Efat Yousefpoor, Muneera Altayeb, Thantrira Porntaveetus, Sadia Din Published: 2026-04-16 Categories: cs.NI, cs.AI arXiv: https://arxiv.org/abs/2604.15489v1 The Internet of Medical Things (IoMT) enables intelligent healthcare services but faces challenges such as dynamic topology, energy constraints, and diverse QoS requirements. This paper proposes QQMR, a Q-learning-based QoS-aware multipath routing method for WBANs. QQMR classifies data into three priority levels and employs adaptive multi-level queuing and fuzzy C-means clustering to optimize routing decisions. It maintains separate learning policies for each data type and selects primary and backup paths accordingly. Experimental results demonstrate improved packet delivery ratio and significant reductions in delay, routing overhead, and energy consumption compared to existing methods. --- ### FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models Authors: Zixuan Weng, Jinghuai Zhang, Kunlin Cai, Ying Li, Peiran Wang, Yuan Tian Published: 2026-04-16 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.15488v1 Large language models (LLMs) often exhibit undesirable behaviors, such as safety violations and hallucinations. Although inference-time steering offers a cost-effective way to adjust model behavior without updating its parameters, existing methods often fail to be simultaneously effective, utility-preserving, and training-efficient due to their rigid, one-size-fits-all designs and limited adaptability. In this work, we present FineSteer, a novel steering framework that decomposes inference-time steering into two complementary stages: conditional steering and fine-grained vector synthesis, allowing fine-grained control over when and how to steer internal representations. In the first stage, we introduce a Subspace-guided Conditional Steering (SCS) mechanism that preserves model utility by avoiding unnecessary steering. In the second stage, we propose a Mixture-of-Steering-Experts (MoSE) mechanism that captures the multimodal nature of desired steering behaviors and generates query-specific steering vectors for improved effectiveness. Through tailored designs in both SCS and MoSE, FineSteer maintains robust performance on general queries while adaptively optimizing steering vectors for targeted inputs in a training-efficient manner. Extensive experiments on safety and truthfulness benchmarks show that FineSteer outperforms state-of-the-art methods in overall performance, achieving stronger steering performance with minimal utility loss. Code is available at https://github.com/YukinoAsuna/FineSteer --- ### $π_{0.7}$: a Steerable Generalist Robotic Foundation Model with Emergent Capabilities Authors: Physical Intelligence, Bo Ai, Ali Amin, Raichelle Aniceto, Ashwin Balakrishna, Greg Balke, Kevin Black, George Bokinsky, Shihao Cao, Thomas Charbonnier, Vedant Choudhary, Foster Collins et al. Published: 2026-04-16 Categories: cs.LG, cs.RO arXiv: https://arxiv.org/abs/2604.15483v2 We present a new robotic foundation model, called $π_{0.7}$, that can enable strong out-of-the-box performance in a wide range of scenarios. $π_{0.7}$ can follow diverse language instructions in unseen environments, including multi-stage tasks with various kitchen appliances, provide zero-shot cross-embodiment generalization, for example enabling a robot to fold laundry without seeing the task before, and perform challenging tasks such as operating an espresso machine out of the box at a level of performance that matches much more specialized RL-finetuned models. The main idea behind $π_{0.7}$ is to use diverse context conditioning during training. This conditioning information, contained in the prompt, makes it possible to steer the model precisely to perform many tasks with different strategies. It is conditioned not just on a language command that describes what it should do, but on additional multimodal information that also describes the manner or strategy in which it should do it, including metadata about task performance and subgoal images. This enables $π_{0.7}$ to use very diverse data, including demonstrations, potentially suboptimal (autonomous) data including failures, and data from non-robot sources. Our experiments evaluate $π_{0.7}$ across numerous tasks with multiple robot platforms, on tasks that require speed and dexterity, language following, and compositional task generalization. --- ### Harmonizing Multi-Objective LLM Unlearning via Unified Domain Representation and Bidirectional Logit Distillation Authors: Yisheng Zhong, Sijia Liu, Zhuangdi Zhu Published: 2026-04-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.15482v1 Large Language Models (LLMs) unlearning is crucial for removing hazardous or privacy-leaking information from the model. Practical LLM unlearning demands satisfying multiple challenging objectives simultaneously: removing undesirable knowledge, preserving general utility, avoiding over-refusal of neighboring concepts, and, crucially, ensuring robustness against adversarial probing attacks. However, existing unlearning methods primarily focus on a limited subset of these goals, typically unlearning efficacy and utility preservation while overlooking robustness and boundary behaviors. Naively extending these methods to multi-objective settings may lead to unlearning task interference. We propose a novel multi-objective unlearning framework that harmonizes multiple unlearning objectives through a data and optimization co-design: We standardize training corpora into a unified data representation to reduce the domain gap, and then introduce a bidirectional distillation method that simultaneously elicits desired behavior from a context-instructed teacher while suppressing undesirable behavior in the student model. Theoretical and empirical analyses show that our method aligns domain distributions and converts seemingly irrelevant unlearning tasks into cooperative optimization. Evaluation demonstrates state-of-the-art performance, which enables balanced and reliable unlearning across diverse, challenging requirements. --- ### Lossless Compression via Chained Lightweight Neural Predictors with Information Inheritance Authors: Yuriy Kim, Evgeny Belyaev Published: 2026-04-16 Categories: cs.IT, cs.LG arXiv: https://arxiv.org/abs/2604.15472v1 This paper is dedicated to lossless data compression with probability estimation using neural networks. First, we propose a probability estimation architecture based on a chain of neural predictors, so that each unit of the chain is defined as a neural network with the minimum possible number of weights, which is sufficient for efficient compression of data generated by Markov sources of a given order. We show that this architecture allows us to minimize the overall number of weights participating in the probability estimation process depending on the statistical properties of the input data. Second, in order to improve compression efficiency, we introduce an information inheritance mechanism, where the probability estimate obtained by a low-order unit is used at the next higher-order unit. Experimental results show that the proposed lossless data compressor equipped with the chained probability estimation architecture provides compression ratios close to the state-of-the-art PAC compressor. At the same time, it outperforms PAC by a factor of 1.2 to 6.3 in encoding throughput and by a factor of 2.8 to 12.3 in decoding throughput on a consumer GPU. --- ### The Semi-Executable Stack: Agentic Software Engineering and the Expanding Scope of SE Authors: Robert Feldt, Per Lenberg, Julian Frattini, Dhasarathy Parthasarathy Published: 2026-04-16 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2604.15468v2 AI-based systems, currently driven largely by LLMs and tool-using agentic harnesses, are increasingly discussed as a possible threat to software engineering. Foundation models get stronger, agents can plan and act across multiple steps, and tasks such as scaffolding, routine test generation, straightforward bug fixing, and small integration work look more exposed than they did only a few years ago. The result is visible unease not only among students and junior developers, but also among experienced practitioners who worry that hard-won expertise may lose value. This paper argues for a different reading. The important shift is not that software engineering loses relevance. It is that the thing being engineered expands beyond executable code to semi-executable artifacts; combinations of natural language, tools, workflows, control mechanisms, and organizational routines whose enactment depends on human or probabilistic interpretation rather than deterministic execution. The Semi-Executable Stack is introduced as a six-ring diagnostic reference model for reasoning about that expansion, spanning executable artifacts, instructional artifacts, orchestrated execution, controls, operating logic, and societal and institutional fit. The model helps locate where a contribution, bottleneck, or organizational transition primarily sits, and which adjacent rings it depends on. The paper develops the argument through three worked cases, reframes familiar objections as engineering targets rather than reasons to dismiss the transition, and closes with a preserve-versus-purify heuristic for deciding which legacy software engineering processes, controls, and coordination routines should be kept and which should be simplified or redesigned. This paper is a conceptual keynote companion: diagnostic and agenda-setting rather than empirical. --- ### Ragged Paged Attention: A High-Performance and Flexible LLM Inference Kernel for TPU Authors: Jevin Jiang, Ying Chen, Blake A. Hechtman, Fenghui Zhang, Yarong Mu Published: 2026-04-16 Categories: cs.PF, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.15464v1 Large Language Model (LLM) deployment is increasingly shifting to cost-efficient accelerators like Google's Tensor Processing Units (TPUs), prioritizing both performance and total cost of ownership (TCO). However, existing LLM inference kernels and serving systems remain largely GPU-centric, and there is no well-established approach for efficiently mapping LLM workloads onto TPU architectures--particularly under the dynamic and ragged execution patterns common in modern serving. In this paper, we present Ragged Paged Attention (RPA), a high-performance and flexible attention kernel for TPUs, implemented using Pallas and Mosaic. RPA addresses these challenges through three key techniques: (1) fine-grained tiling to enable efficient dynamic slicing over ragged memory, (2) a custom software pipeline that fuses KV cache updates with attention computation, and (3) a distribution-aware compilation strategy that generates specialized kernels for decode, prefill, and mixed workloads. Evaluated on Llama 3 8B on TPU7x, RPA achieves up to 86% memory bandwidth utilization (MBU) in decode and 73% model FLOPs utilization (MFU) in prefill. Integrated as the primary TPU backend in vLLM and SGLang, RPA provides a production-grade foundation for efficient TPU inference and offers practical insights into kernel design. --- ### Evaluating LLM Simulators as Differentially Private Data Generators Authors: Nassima M. Bouzid, Dehao Yuan, Nam H. Nguyen, Mayana Pereira Published: 2026-04-16 Categories: cs.LG, cs.CL, cs.CR arXiv: https://arxiv.org/abs/2604.15461v1 LLM-based simulators offer a promising path for generating complex synthetic data where traditional differentially private (DP) methods struggle with high-dimensional user profiles. But can LLMs faithfully reproduce statistical distributions from DP-protected inputs? We evaluate this using PersonaLedger, an agentic financial simulator, seeded with DP synthetic personas derived from real user statistics. We find that PersonaLedger achieves promising fraud detection utility (AUC 0.70 at epsilon=1) but exhibits significant distribution drift due to systematic LLM biases--learned priors overriding input statistics for temporal and demographic features. These failure modes must be addressed before LLM-based methods can handle the richer user representations where they might otherwise excel. --- ### The Crutch or the Ceiling? How Different Generations of LLMs Shape EFL Student Writings Authors: Hengky Susanto, David James Woo, Chingyi Yeung, Stephanie Wing Yan Lo-Philip, Chi Ho Yeung Published: 2026-04-16 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2604.15460v1 The rapid evolution of Large Language Models (LLMs) has made them powerful tools for enhancing student writing. This study explores the extent and limitations of LLMs in assisting secondary-level English as a Foreign Language (EFL) students with their writing tasks. While existing studies focus on output quality, our research examines the developmental shift in LLMs and their impact on EFL students, assessing whether smarter models act as true scaffolds or mere compensatory crutches. To achieve this, we analyse student compositions assisted by LLMs before and after ChatGPT's release, using both expert qualitative scoring and quantitative metrics (readability tests, Pearson's correlation coefficient, MTLD, and others). Our results indicate that advanced LLMs boost assessment scores and lexical diversity for lower-proficiency learners, potentially masking their true ability. Crucially, increased LLM assistance correlated negatively with human expert ratings, suggesting surface fluency without deep coherence. To transform AI-assisted practice into genuine learning, pedagogy must shift from focusing on output quality to verifying the learning process. Educators should align AI functions, specifically differentiating ideational scaffolding from textual production, within the learner's Zone of Proximal Development. --- ### RelativeFlow: Taming Medical Image Denoising Learning with Noisy Reference Authors: Yuxin Liu, Yiqing Dong, Wenxue Yu, Zhan Wu, Rongjun Ge, Yang Chen, Yuting He Published: 2026-04-16 Categories: eess.IV, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2604.15459v1 Medical image denoising (MID) lacks absolutely clean images for supervision, leading to a noisy reference problem that fundamentally limits denoising performance. Existing simulated-supervised discriminative learning (SimSDL) and simulated-supervised generative learning (SimSGL) treat noisy references as clean targets, causing suboptimal convergence or reference-biased learning, while self-supervised learning (SSL) imposes restrictive noise assumptions that are seldom satisfied in realistic MID scenarios. We propose \textbf{RelativeFlow}, a flow matching framework that learns from heterogeneous noisy references and drives inputs from arbitrary quality levels toward a unified high-quality target. RelativeFlow reformulates flow matching by decomposing the absolute noise-to-clean mapping into relative noisier-to-noisy mappings, and realizes this formulation through two key components: 1) consistent transport (CoT), a displacement map that constrains relative flows to be components of and progressively compose a unified absolute flow, and 2) simulation-based velocity field (SVF), which constructs a learnable velocity field using modality-specific degradation operators to support different medical imaging modalities. Extensive experiments on Computed Tomography (CT) and Magnetic Resonance (MR) denoising demonstrate that RelativeFlow significantly outperforms existing methods, taming MID with noisy references. --- ### DeepER-Med: Advancing Deep Evidence-Based Research in Medicine Through Agentic AI Authors: Zhizheng Wang, Chih-Hsuan Wei, Joey Chan, Robert Leaman, Chi-Ping Day, Chuan Wu, Mark A Knepper, Antolin Serrano Farias, Jordina Rincon-Torroella, Hasan Slika, Betty Tyler, Ryan Huu-Tuan Nguyen et al. Published: 2026-04-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.15456v1 Trustworthiness and transparency are essential for the clinical adoption of artificial intelligence (AI) in healthcare and biomedical research. Recent deep research systems aim to accelerate evidence-grounded scientific discovery by integrating AI agents with multi-hop information retrieval, reasoning, and synthesis. However, most existing systems lack explicit and inspectable criteria for evidence appraisal, creating a risk of compounding errors and making it difficult for researchers and clinicians to assess the reliability of their outputs. In parallel, current benchmarking approaches rarely evaluate performance on complex, real-world medical questions. Here, we introduce DeepER-Med, a Deep Evidence-based Research framework for Medicine with an agentic AI system. DeepER-Med frames deep medical research as an explicit and inspectable workflow of evidence-based generation, consisting of three modules: research planning, agentic collaboration, and evidence synthesis. To support realistic evaluation, we also present DeepER-MedQA, an evidence-grounded dataset comprising 100 expert-level research questions derived from authentic medical research scenarios and curated by a multidisciplinary panel of 11 biomedical experts. Expert manual evaluation demonstrates that DeepER-Med consistently outperforms widely used production-grade platforms across multiple criteria, including the generation of novel scientific insights. We further demonstrate the practical utility of DeepER-Med through eight real-world clinical cases. Human clinician assessment indicates that DeepER-Med's conclusions align with clinical recommendations in seven cases, highlighting its potential for medical research and decision support. --- ### (1D) Ordered Tokens Enable Efficient Test-Time Search Authors: Zhitong Gao, Parham Rezaei, Ali Cy, Mingqiao Ye, Nataša Jovanović, Jesse Allardice, Afshin Dehghan, Amir Zamir, Roman Bachmann, Oğuzhan Fatih Kar Published: 2026-04-16 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.15453v1 Tokenization is a key component of autoregressive (AR) generative models, converting raw data into more manageable units for modeling. Commonly, tokens describe local information, such as regions of pixels in images or word pieces in text, and AR generation predicts these tokens in a fixed order. A worthwhile question is whether token structures affect the ability to steer the generation through test-time search, where multiple candidate generations are explored and evaluated by a verifier. Using image generation as our testbed, we hypothesize that recent 1D ordered tokenizers with coarse-to-fine structure can be more amenable to search than classical 2D grid structures. This is rooted in the fact that the intermediate states in coarse-to-fine sequences carry semantic meaning that verifiers can reliably evaluate, enabling effective steering during generation. Through controlled experiments, we find that AR models trained on coarse-to-fine ordered tokens exhibit improved test-time scaling behavior compared to grid-based counterparts. Moreover, we demonstrate that, thanks to the ordered structure, pure test-time search over token sequences (i.e., without training an AR model) can perform training-free text-to-image generation when guided by an image-text verifier. Beyond this, we systematically study how classical search algorithms (best-of-N, beam search, lookahead search) interact with different token structures, as well as the role of different verifiers and AR priors. Our results highlight the impact of token structure on inference-time scalability and provide practical guidance for test-time scaling in AR models. --- ### Weak-to-Strong Knowledge Distillation Accelerates Visual Learning Authors: Baiang Li, Wenhao Chai, Felix Heide Published: 2026-04-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.15451v2 Large-scale visual learning is increasingly limited by training cost. Existing knowledge distillation methods transfer from a stronger teacher to a weaker student for compression or final-accuracy improvement. We instead investigate distillation to accelerate the training of strong students. We propose a generalizable plug-and-play recipe that freezes a weaker teacher, applies distillation only in early training, and turns it off once the student reaches and surpasses teacher-level performance. For ImageNet and CIFAR classification, this strategy reaches target thresholds much earlier, with up to 4.8 times speedup measured by epochs. We confirm that the method generalizes to other tasks and report 1.7 times epoch speedup for object detection on the COCO dataset, and 2.5 times earlier target-FID crossing for diffusion generation on the CIFAR-10 dataset, measured in steps. These findings validate our method as a universal speedup mechanism for visual learning. --- ### Transfer Learning from Foundational Optimization Embeddings to Unsupervised SAT Representations Authors: Koyena Pal, Serdar Kadioglu Published: 2026-04-16 Categories: cs.LG, cs.AI, cs.LO arXiv: https://arxiv.org/abs/2604.15448v1 Foundational optimization embeddings have recently emerged as powerful pre-trained representations for mixed-integer programming (MIP) problems. These embeddings were shown to enable cross-domain transfer and reduce reliance on solver-generated labels. In this work, we investigate whether such representations generalize beyond optimization to decision problems, focusing on Boolean satisfiability (SAT). We adapt the foundational optimization architecture to SAT by mapping CNF formulas into the same bipartite constraint-variable graph representation used for MIPs. This allows direct reuse of the pre-trained embedding model without architectural changes or supervised fine-tuning. Our results show that these embeddings capture structural regularities in SAT instances and support unsupervised tasks such as instance clustering and distribution identification. We demonstrate, for the first time, that foundational optimization embeddings can transfer to constraint satisfaction domains. Our findings is a step toward a unified representational framework for both optimization and decision problems. --- ### One-Shot Generative Flows: Existence and Obstructions Authors: Panos Tsimpos, Daniel Sharp, Youssef Marzouk Published: 2026-04-16 Categories: stat.ML, cs.LG, math.PR arXiv: https://arxiv.org/abs/2604.15439v3 We study dynamic measure transport for generative modeling, focusing on transport maps that connect a source measure $P_0$ to a target measure $P_1$ by integrating a velocity field of the form $v_t(x) = \mathbb{E}(\dot X_t \mid X_t = x)$, where $X_\bullet = (X_t)_t$ is a stochastic process satisfying $(X_0,X_1)\sim{P_0}\otimes{P_1}$ and $\dot X_t$ is its time derivative. We investigate when $X_\bullet$ induces a \emph{straight-line flow}: a flow whose pointwise acceleration vanishes and is therefore exactly integrable by any first-order method. First, we develop multiple characterizations of straight-line flows in terms of PDEs involving the conditional statistics of the process. Then, we prove that straight-line flows under endpoint independence exhibit a sharp dichotomy. On the one hand, we construct explicit, computable straight-line processes for arbitrary Gaussian endpoints. On the other hand, we show that straight-line processes do not exist for targets with sufficiently well-separated modes. We demonstrate this obstruction through a sequence of increasingly general impossibility theorems that uncover a fundamental relationship between the sample-path behavior of a process with independent endpoints and the space-time geometry of this process' flow map. Taken together, these results provide a structural theory of when straight-line generative flows can, and cannot, exist. --- ### StoSignSGD: Unbiased Structural Stochasticity Fixes SignSGD for Training Large Language Models Authors: Dingzhi Yu, Rui Pan, Yuxing Liu, Difan Zou, Tong Zhang Published: 2026-04-16 Categories: cs.LG, cs.AI, math.OC arXiv: https://arxiv.org/abs/2604.15416v2 Sign-based optimization algorithms, such as SignSGD, have garnered attention for their performance in distributed learning and training large foundation models. Despite their empirical superiority, SignSGD is known to diverge on non-smooth objectives, which are ubiquitous due to ReLUs, max-pools, and mixture-of-experts. To overcome this limitation, we propose StoSignSGD, an algorithm that injects structural stochasticity into the sign operator while maintaining an unbiased update step. In the regime of (online) convex optimization, StoSignSGD rigorously resolves the non-convergence issues of SignSGD, achieving a sharp convergence rate matching the lower bound. For the more challenging non-convex non-smooth optimization, we introduce generalized stationary measures that encompass prior definitions, proving that StoSignSGD improves upon the best-known complexity bounds by dimensional factors. Empirically, StoSignSGD is stable and efficient across diverse large language model (LLM) training regimes. In aggressive low-precision pretraining, which spans both FP8 and the far more demanding FP4 regime where AdamW fails catastrophically, StoSignSGD stays stable and consistently performs the best. It attains a 1.44x to 2.14x speedup over established baselines under FP8. Under 4-bit precision, it improves downstream accuracy on the largest OLMo2-370M model by 1.13 points over the strongest stable baseline, and this advantage grows as both the model size and the data scale up. When fine-tuning 7B LLMs on mathematical reasoning tasks, StoSignSGD also delivers clear gains over both AdamW and SignSGD. Finally, to explain why it works, we develop a sign conversion framework that turns any general optimizer into its unbiased, sign-based counterpart. Using this framework, we decompose the core components of StoSignSGD and run a comprehensive ablation study to validate our design choices. --- ### StoSignSGD: Unbiased Structural Stochasticity Fixes SignSGD for Training Large Language Models Authors: Dingzhi Yu, Rui Pan, Yuxing Liu, Tong Zhang Published: 2026-04-16 Categories: cs.LG, cs.AI, math.OC arXiv: https://arxiv.org/abs/2604.15416v1 Sign-based optimization algorithms, such as SignSGD, have garnered significant attention for their remarkable performance in distributed learning and training large foundation models. Despite their empirical superiority, SignSGD is known to diverge on non-smooth objectives, which are ubiquitous in modern machine learning due to ReLUs, max-pools, and mixture-of-experts. To overcome this fundamental limitation, we propose \textbf{StoSignSGD}, an algorithm that injects structural stochasticity into the sign operator while maintaining an unbiased update step. In the regime of (online) convex optimization, our theoretical analysis shows that StoSignSGD rigorously resolves the non-convergence issues of SignSGD, achieving a sharp convergence rate matching the lower bound. For the more challenging non-convex non-smooth optimization, we introduce generalized stationary measures that encompass prior definitions, proving that StoSignSGD improves upon the best-known complexity bounds by dimensional factors. Empirically, StoSignSGD exhibits robust stability and superior efficiency across diverse large language model (LLM) training regimes. Notably, in low-precision FP8 pretraining -- a setting where AdamW fails catastrophically -- StoSignSGD remains highly stable and yields a remarkable 1.44$\times$ to 2.14$\times$ speedup relative to established baselines. Furthermore, when fine-tuning 7B LLMs on mathematical reasoning tasks, StoSignSGD delivers substantial performance gains over both AdamW and SignSGD. Finally, to dissect the mechanisms driving its success, we develop a sign conversion framework capable of transforming any general optimizer into its unbiased, sign-based counterpart. Utilizing this framework, we deconstruct the core components of StoSignSGD and present a comprehensive ablation study to empirically validate our algorithmic design choices. --- ### HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents? Authors: Yukun Jiang, Yage Zhang, Michael Backes, Xinyue Shen, Yang Zhang Published: 2026-04-16 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2604.15415v1 Large language models (LLMs) have evolved into autonomous agents that rely on open skill ecosystems (e.g., ClawHub and Skills.Rest), hosting numerous publicly reusable skills. Existing security research on these ecosystems mainly focuses on vulnerabilities within skills, such as prompt injection. However, there is a critical gap regarding skills that may be misused for harmful actions (e.g., cyber attacks, fraud and scams, privacy violations, and sexual content generation), namely harmful skills. In this paper, we present the first large-scale measurement study of harmful skills in agent ecosystems, covering 98,440 skills across two major registries. Using an LLM-driven scoring system grounded in our harmful skill taxonomy, we find that 4.93% of skills (4,858) are harmful, with ClawHub exhibiting an 8.84% harmful rate compared to 3.49% on Skills.Rest. We then construct HarmfulSkillBench, the first benchmark for evaluating agent safety against harmful skills in realistic agent contexts, comprising 200 harmful skills across 20 categories and four evaluation conditions. By evaluating six LLMs on HarmfulSkillBench, we find that presenting a harmful task through a pre-installed skill substantially lowers refusal rates across all models, with the average harm score rising from 0.27 without the skill to 0.47 with it, and further to 0.76 when the harmful intent is implicit rather than stated as an explicit user request. We responsibly disclose our findings to the affected registries and release our benchmark to support future research (see https://github.com/TrustAIRLab/HarmfulSkillBench). --- ### Beyond Single-Model Optimization: Preserving Plasticity in Continual Reinforcement Learning Authors: Lute Lillo, Nick Cheney Published: 2026-04-16 Categories: cs.LG, cs.AI, cs.NE arXiv: https://arxiv.org/abs/2604.15414v2 Continual reinforcement learning must balance retention with adaptation, yet many methods still rely on \emph{single-model preservation}, committing to one evolving policy as the main reusable solution across tasks. Even when a previously successful policy is retained, it may no longer provide a reliable starting point for rapid adaptation after interference, reflecting a form of \emph{loss of plasticity} that single-policy preservation cannot address. Inspired by quality-diversity methods, we introduce \textsc{TeLAPA} (Transfer-Enabled Latent-Aligned Policy Archives), a continual RL framework that organizes behaviorally diverse policy neighborhoods into per-task archives and maintains a shared latent space so that archived policies remain comparable and reusable under non-stationary drift. This perspective shifts continual RL from retaining isolated solutions to maintaining \emph{skill-aligned neighborhoods} with competent and behaviorally related policies that support future relearning. In our MiniGrid CL setting, \textsc{TeLAPA} learns more tasks successfully, recovers competence faster on revisited tasks after interference, and retains higher performance across a sequence of tasks. Our analyses show that source-optimal policies are often not transfer-optimal, even within a local competent neighborhood, and that effective reuse depends on retaining and selecting among multiple nearby alternatives rather than collapsing them to one representative. Together, these results reframe continual RL around reusable and competent policy neighborhoods, providing a route beyond single-model preservation toward more plastic lifelong agents. --- ### PRL-Bench: A Comprehensive Benchmark Evaluating LLMs' Capabilities in Frontier Physics Research Authors: Tingjia Miao, Wenkai Jin, Muhua Zhang, Jinxin Tan, Yuelin Hu, Tu Guo, Jiejun Zhang, Yuhan Wang, Wenbo Li, Yinuo Gao, Shuo Chen, Weiqi Jiang et al. Published: 2026-04-16 Categories: cs.LG, cs.AI, physics.data-an arXiv: https://arxiv.org/abs/2604.15411v1 The paradigm of agentic science requires AI systems to conduct robust reasoning and engage in long-horizon, autonomous exploration. However, current scientific benchmarks remain confined to domain knowledge comprehension and complex reasoning, failing to evaluate the exploratory nature and procedural complexity of real-world research. In this work, we present research-oriented evaluations in theoretical and computational physics, a natural testbed with comprehensive domain knowledge, complex reasoning, and verifiable end-to-end workflows without reliance on experiments. Here we introduce PRL-Bench (Physics Research by LLMs), a benchmark designed to systematically map the capability boundaries of LLMs in executing end-to-end physics research. Constructed from 100 curated papers from the latest issues of Physical Review Letters since August 2025 and validated by domain experts, PRL-Bench covers five major theory- and computation-intensive subfields of modern physics: astrophysics, condensed matter physics, high-energy physics, quantum information, and statistical physics. Each task in the benchmark is designed to replicate the core properties of authentic scientific research, including exploration-oriented formulation, long-horizon workflows, and objective verifiability, thereby reconstructing the essential reasoning processes and research workflows of real physics research. Evaluation across frontier models shows that performance remains limited, with the best overall score below 50, revealing a pronounced gap between current LLM capabilities and the demands of real scientific research. PRL-Bench serves a reliable testbed for accessing next generation AI scientists advancing AI systems toward autonomous scientific discovery. --- ### The Illusion of Equivalence: Systematic FP16 Divergence in KV-Cached Autoregressive Inference Authors: Ranjith Chodavarapu, Lei Xu Published: 2026-04-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.15409v1 KV caching is a ubiquitous optimization in autoregressive transformer inference, long presumed to be numerically equivalent to cache-free computation. This assumption fails under standard FP16 precision: cache-ON and cache-OFF execution paths employ different floating-point accumulation orderings which, due to FP16 non-associativity, produce a deterministic divergence in decoded token sequences. Across three open-weight models (LLaMA-2-7B, Mistral-7B-v0.3, Gemma-2-2B) evaluated on GSM8K, we observe a 100\% token divergence rate across all sampling strategies, including greedy decoding, which rules out sampling randomness as a cause, and also with cache-ON yielding higher accuracy in 8 of 9 conditions, where the accuracy difference serves as an indicator that the divergence direction is systematic rather than random. Controlled FP32 falsification reduces divergence by eight orders of magnitude, eliminates token flips, and drops the flip rate to exactly 0.0\%, confirming FP16 non-associativity as the sole causal driver. Layer-wise drift profiling reveals architecturally predictable propagation patterns: models using Grouped-Query Attention exhibit sharp divergence at the first layer, while Gemma's larger head dimension and sliding window attention produce uniform accumulation across all layers. Finally, activation patching of the entire residual stream fails to recover the cache-free trajectory, localizing the causal variable to the stateful KV cache. These findings establish that FP16 KV cache inference is fundamentally non-equivalent to recomputation and provide a mechanistic framework for understanding numerical instability in modern LLM inference systems. --- ### Dispatch-Aware Ragged Attention for Pruned Vision Transformers Authors: Seifeldin Abdellatif, Ahmad Almasri Published: 2026-04-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.15408v2 Token pruning methods for Vision Transformers (ViTs) promise quadratic reductions in attention FLOPs by dropping uninformative patches. Yet standard variable-length attention APIs -- including FlashAttention-2's varlen and PyTorch's NestedTensor SDPA -- fail to translate these savings into proportional wall-clock gains at the short post-pruning sequence lengths typical of ViTs ($\leq$197 tokens). We identify a dispatch-overhead bottleneck: at these lengths, host-side kernel dispatch consumes ${\sim}$50\,$μ$s regardless of workload, exceeding the actual GPU compute time at moderate-to-high pruning rates. We present a lightweight bidirectional Triton attention kernel whose dispatch floor is ${\sim}$24\,$μ$s -- roughly 2.17$\times$ lower than FlashAttention-2 varlen -- allowing pruning savings to become visible in wall-clock time. Integrated into a complete pack-attend-unpack pipeline and evaluated on an NVIDIA RTX 4000 Ada Generation GPU, our system achieves 1.88$\times$ end-to-end throughput over padded PyTorch SDPA at standard 224$\times$224 inputs, scaling to 2.51$\times$ at 384$\times$384. Against FlashAttention-2 varlen -- the strongest baseline -- our kernel delivers 9-12\% higher throughput at serving batch sizes (BS=1-4), and 2.17$\times$ lower kernel latency at 80\% token pruning. Numerical correctness is verified with max absolute logit difference $<$0.004 and bit-exact top-1 predictions. --- ### Hallucination as Trajectory Commitment: Causal Evidence for Asymmetric Attractor Dynamics in Transformer Generation Authors: G. Aytug Akarlar Published: 2026-04-16 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.15400v1 We present causal evidence that hallucination in autoregressive language models is an early trajectory commitment governed by asymmetric attractor dynamics. Using same-prompt bifurcation, in which we repeatedly sample identical inputs to observe spontaneous divergence, we isolate trajectory dynamics from prompt-level confounds. On Qwen2.5-1.5B across 61 prompts spanning six categories, 27 prompts (44.3%) bifurcate with factual and hallucinated trajectories diverging at the first generated token (KL = 0 at step 0, KL > 1.0 at step 1). Activation patching across 28 layers reveals a pronounced causal asymmetry: injecting a hallucinated activation into a correct trajectory corrupts output in 87.5% of trials (layer 20), while the reverse recovers only 33.3% (layer 24); both exceed the 10.4% baseline (p = 0.025) and 12.5% random-patch control. Window patching shows correction requires sustained multi-step intervention, whereas corruption needs only a single perturbation. Probing the prompt encoding itself, step-0 residual states predict per-prompt hallucination rate at Pearson r = 0.776 at layer 15 (p < 0.001 against a 1000-permutation null); unsupervised clustering identifies five regime-like groups (eta^2 = 0.55) whose saddle-adjacent cluster concentrates 12 of the 13 bifurcating false-premise prompts, indicating that the basin structure is organized around regime commitments fixed at prompt encoding. These findings characterize hallucination as a locally stable attractor basin: entry is probabilistic and rapid, exit demands coordinated intervention across layers and steps, and the relevant basins are selected by clusterable regimes already discernible at step 0. --- ### Python library supporting Discrete Variational Formulations and training solutions with Collocation-based Robust Variational Physics Informed Neural Networks (DVF-CRVPINN) Authors: Tomasz Służalec, Marcin Łoś, Askold Vilkha, Maciej Paszyński Published: 2026-04-16 Categories: cs.LG, math.NA arXiv: https://arxiv.org/abs/2604.15398v1 We explore the possibility of solving Partial Differential Equations (PDEs) using discrete weak formulations. We propose a programming environment for defining a discrete computational domain, introducing discrete functions defined over a set of points, constructing discrete inner products, and introducing discrete weak formulations employing Kronecker delta test functions. Building on this setup, we propose a discrete neural network representation, training the solution function defined over a discrete set of points and employing discrete finite difference derivatives in the automatic differentiation procedures. As a challenging computational model example, we focus on Stokes equations in two-dimensions, defined over a discrete set of points. We train the solution using the discrete weak residual and the Adamax algorithm with discrete automatic differentiation of the discrete gradients. Despite introducing the python environment, we also provide a rigorous mathematical formulation based on discrete weak formulations, proving the well-posedness and robustness of the loss function. The solution of the discrete weak formulations is based on neural network training employing a robust loss function that is related to the true error. In this way, we have a robust control of the numerical error during the training of the neural networks. Besides the Stokes formulation, we also explain the functionality of the proposed library using the Laplace problem formulation. --- ### Lightweight Geometric Adaptation for Training Physics-Informed Neural Networks Authors: Kang An, Chenhao Si, Shiqian Ma, Ming Yan Published: 2026-04-16 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2604.15392v1 Physics-Informed Neural Networks (PINNs) often suffer from slow convergence, training instability, and reduced accuracy on challenging partial differential equations due to the anisotropic and rapidly varying geometry of their loss landscapes. We propose a lightweight curvature-aware optimization framework that augments existing first-order optimizers with an adaptive predictive correction based on secant information. Consecutive gradient differences are used as a cheap proxy for local geometric change, together with a step-normalized secant curvature indicator to control the correction strength. The framework is plug-and-play, computationally efficient, and broadly compatible with existing optimizers, without explicitly forming second-order matrices. Experiments on diverse PDE benchmarks show consistent improvements in convergence speed, training stability, and solution accuracy over standard optimizers and strong baselines, including on the high-dimensional heat equation, Gray--Scott system, Belousov--Zhabotinsky system, and 2D Kuramoto--Sivashinsky system. --- ### Analyzing Chain of Thought (CoT) Approaches in Control Flow Code Deobfuscation Tasks Authors: Seyedreza Mohseni, Sarvesh Baskar, Edward Raff, Manas Gaur Published: 2026-04-16 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2604.15390v3 Code deobfuscation is the task of recovering a readable version of a program while preserving its original behavior. In practice, this often requires days or even months of manual work with complex and expensive analysis tools. In this paper, we explore an alternative approach based on Chain-of-Thought (CoT) prompting, where a large language model is guided through explicit, step-by-step reasoning tailored for code analysis. We focus on control flow obfuscation, including Control Flow Flattening (CFF), Opaque Predicates, and their combination, and we measure both structural recovery of the control flow graph and preservation of program semantics. We evaluate five state-of-the-art large language models and show that CoT prompting significantly improves deobfuscation quality compared with simple prompting. We validate our approach on a diverse set of standard C benchmarks and report results using both structural metrics for control flow graphs and semantic metrics based on output similarity. Among the tested models and by applying CoT, GPT5 achieves the strongest overall performance, with an average gain of about 16% in control-flow graph reconstruction and about 20.5% in semantic preservation across our benchmarks compared to zero-shot prompting. Our results also show that model performance depends not only on the obfuscation level and the chosen obfuscator but also on the intrinsic complexity of the original control flow graph. Collectively, these findings suggest that CoT-guided large language models can serve as effective assistants for code deobfuscation, providing improved code explainability, more faithful control flow graph reconstruction, and better preservation of program behavior while potentially reducing the manual effort needed for reverse engineering. --- ### Exploring LLM-based Verilog Code Generation with Data-Efficient Fine-Tuning and Testbench Automation Authors: Mu-Chi Chen, Po-Hsuan Huang, Yu-Hung Kao, Yen-Fu Liu, Yu-Kai Hung, Cheng Liang, Shao-Chun Ho, Chia-Heng Tu, Shih-Hao Hung Published: 2026-04-16 Categories: cs.AR, cs.AI arXiv: https://arxiv.org/abs/2604.15388v1 Recent advances in large language models have improved code generation, but their use in hardware description languages is still limited. Moreover, training data and testbenches for these models are often scarce. This paper presents a workflow that uses multi-agent models to generate testbenches for high-quality fine-tuning data. By automating testbench creation, the fine-tuned model for the specification-to-Verilog task achieves performance comparable to state-of-the-art methods on the refined VerilogEval v2 benchmark while using less training data. This study provides a basis for future work on LLM-based HDL generation and automated verification. --- ### Prompt-Driven Code Summarization: A Systematic Literature Review Authors: Afia Farjana, Zaiyu Cheng, Antonio Mastropaolo Published: 2026-04-16 Categories: cs.SE, cs.LG arXiv: https://arxiv.org/abs/2604.15385v1 Software documentation is essential for program comprehension, developer onboarding, code review, and long-term maintenance. Yet producing quality documentation manually is time-consuming and frequently yields incomplete or inconsistent results. Large language models (LLMs) offer a promising solution by automatically generating natural language descriptions from source code, helping developers understand code more efficiently, facilitating maintenance, and supporting downstream activities such as defect localization and commit message generation. However, the effectiveness of LLMs in documentation tasks critically depends on how they are prompted. Properly structured instructions can substantially improve model performance, making prompt engineering-the design of input prompts to guide model behavior-a foundational technique in LLM-based software engineering. Approaches such as few-shot prompting, chain-of-thought reasoning, retrieval-augmented generation, and zero-shot learning show promise for code summarization, yet current research remains fragmented. There is limited understanding of which prompting strategies work best, for which models, and under what conditions. Moreover, evaluation practices vary widely, with most studies relying on overlap-based metrics that may not capture semantic quality. This systematic literature review consolidates existing evidence, categorizes prompting paradigms, examines their effectiveness, and identifies gaps to guide future research and practical adoption. --- ### LinuxArena: A Control Setting for AI Agents in Live Production Software Environments Authors: Tyler Tracy, Ram Potham, Nick Kuhn, Myles Heller, Anshul Khandelwal, Cody Rushing, Henri Lemoine, Miguel Brandao, Tomas Turlik, Adam Hanson, Josh Hills, Amy Ngo et al. Published: 2026-04-16 Categories: cs.CR, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2604.15384v2 We introduce LinuxArena, a control setting in which agents operate directly on live, multi-service production environments. LinuxArena contains 20 environments, 1,671 main tasks representing legitimate software engineering work, and 184 side tasks representing safety failures such as data exfiltration and backdooring, making it the largest and most diverse control setting for software engineering to date. We validate LinuxArena is useful for control research by running sabotage evaluations, which measure whether attackers can complete side tasks while working on main tasks, and monitor evaluations, which measure a monitor model's ability to detect sabotage attempts. Against a GPT-5-nano trusted monitor at a 1\% step-wise false positive rate, Claude Opus 4.6 achieves roughly a 23% undetected sabotage success rate. We additionally release LaStraj, a dataset of human-crafted attack trajectories that evade monitors at substantially higher rates than any model-generated attacks we elicited, showing that current attack policies do not saturate LinuxArena. These results suggest that LinuxArena has meaningful headroom for both attackers and defenders, making it a strong testbed for developing and evaluating future control protocols. --- ### Temporal Contrastive Decoding: A Training-Free Method for Large Audio-Language Models Authors: Yanda Li, Yuhan Liu, Zirui Song, Yunchao Wei, Martin Takáč, Salem Lahlou Published: 2026-04-16 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2604.15383v1 Large audio-language models (LALMs) generalize across speech, sound, and music, but unified decoders can exhibit a \emph{temporal smoothing bias}: transient acoustic cues may be underutilized in favor of temporally smooth context that is better supported by language priors, leading to less specific audio-grounded outputs. We propose \emph{Temporal Contrastive Decoding} (TCD), a training-free decoding method for unified LALMs that mitigates this effect at inference time. TCD constructs a temporally blurred slow-path view by smoothing the input waveform and re-encoding it, then contrasts next-token logits from the original and slow-path views. The contrastive signal is applied as a token-level logit update restricted to a small candidate set. A self-normalized stability score sets the blur window and update scale, and a step-wise gate based on uncertainty and audio reliance activates the update only when needed. Experiments on MMAU and AIR-Bench show consistent improvements on strong unified LALMs. We further conduct ablations and an architectural applicability study to analyze the contributions of key components and how TCD behaves across large audio-language model designs. --- ### Bidirectional Cross-Modal Prompting for Event-Frame Asymmetric Stereo Authors: Ninghui Xu, Fabio Tosi, Lihui Wang, Jiawei Han, Luca Bartolomei, Zhiting Yao, Matteo Poggi, Stefano Mattoccia Published: 2026-04-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.15312v1 Conventional frame-based cameras capture rich contextual information but suffer from limited temporal resolution and motion blur in dynamic scenes. Event cameras offer an alternative visual representation with higher dynamic range free from such limitations. The complementary characteristics of the two modalities make event-frame asymmetric stereo promising for reliable 3D perception under fast motion and challenging illumination. However, the modality gap often leads to marginalization of domain-specific cues essential for cross-modal stereo matching. In this paper, we introduce Bi-CMPStereo, a novel bidirectional cross-modal prompting framework that fully exploits semantic and structural features from both domains for robust matching. Our approach learns finely aligned stereo representations within a target canonical space and integrates complementary representations by projecting each modality into both event and frame domains. Extensive experiments demonstrate that our approach significantly outperforms state-of-the-art methods in accuracy and generalization. --- ### LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories Authors: Zhanhao Liang, Tao Yang, Jie Wu, Chengjian Feng, Liang Zheng Published: 2026-04-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.15311v3 This paper focuses on the alignment of flow matching models with human preferences. A promising way is fine-tuning by directly backpropagating reward gradients through the differentiable generation process of flow matching. However, backpropagating through long trajectories results in prohibitive memory costs and gradient explosion. Therefore, direct-gradient methods struggle to update early generation steps, which are crucial for determining the global structure of the final image. To address this issue, we introduce LeapAlign, a fine-tuning method that reduces computational cost and enables direct gradient propagation from reward to early generation steps. Specifically, we shorten the long trajectory into only two steps by designing two consecutive leaps, each skipping multiple ODE sampling steps and predicting future latents in a single step. By randomizing the start and end timesteps of the leaps, LeapAlign leads to efficient and stable model updates at any generation step. To better use such shortened trajectories, we assign higher training weights to those that are more consistent with the long generation path. To further enhance gradient stability, we reduce the weights of gradient terms with large magnitude, instead of completely removing them as done in previous works. When fine-tuning the Flux model, LeapAlign consistently outperforms state-of-the-art GRPO-based and direct-gradient methods across various metrics, achieving superior image quality and image-text alignment. ---