Papers

Machine unlearning aims to remove the influence of designated training data while preserving model utility, but its behavior on tabular data remains underexplored. This gap is important because tabular prediction is widely used in high-stakes domains and is increasingly adapted to language models through record serialization and schema-aware prompting. We identify a key challenge that distinguishes tabular unlearning from unlearning in free-form text or other modalities: schema-induced forget-retain overlap. In serialized tabular data, records share fixed column-name/value slots, similar attribute ranges, and common output spaces. Consequently, a forget row may have nearby retain rows that rely on the same high-signal attributes, causing retain preservation to oppose the update required for forgetting. Motivated by this failure mode, we propose Conflict-Aware Unlearning (CAU), a schema-aware approach that reduces forget-retain interference by relaxing preservation constraints on retained rows that most conflict with the forget set. Across sample-level and feature-level unlearning on clinical and non-medical tabular tasks, CAU more closely matches a retraining oracle while maintaining predictive utility and retain-region behavior. Our results show that reliable tabular LLM unlearning depends not only on the forgetting objective, but also on how retain constraints are constructed.

Out-of-Distribution (OOD) detection remains a fundamental challenge for neural networks, whose predictions can be overconfident on inputs that deviate from the training distribution. Most post-hoc OOD detection methods derive scores from a single representation level (eg., logits or penultimate features) or combine multiple layers via depth selection or OOD-calibrated weighting. However, because OOD shifts are diverse, the most informative representation level can vary strongly across OOD types and domains, making fixed-layer choices and OOD-calibrated aggregation brittle. In this paper, we propose PRISM (Projected Representation with Intermediate-layer Subspace Modeling), a model-agnostic post-hoc OOD detection method that models a unified multi-layer feature representation rather than aggregating independently scored layers. PRISM fuses intermediate and deep features into a single hierarchical embedding, estimates an in-distribution (ID) principal subspace, and then combines two complementary signals: (i) a class-conditional Mahalanobis distance in the projected subspace and (ii) the residual energy orthogonal to the learned manifold. This simple design avoids OOD-tuned layer weighting while capturing both in-subspace semantic deviations and off-subspace anomalies. Across diverse benchmarks spanning natural images, medical imaging, and industrial visual inspection, PRISM achieves consistent state-of-the-art cross-domain OOD detection performance with a single default configuration across all evaluated domains and architectures. We further show that PRISM incurs minimal inference overhead, making it practical for real-world deployment.

AI inference often crosses regional boundaries as prompts travel to remote data centers and generated tokens return to users. Regional averages cannot represent the resulting differences in serving hardware, electricity, and network delivery. Request-level accounting needs a common boundary for the service, serving site, route, local comparator, uncertainty, and data provenance. GreenPassport Carbon Accounting (GPCA) associates these inputs with each request. It estimates serving and route carbon, then selects a reporting level from the available documentation. Our public-data implementation covers data-center instances, accelerators, model families, electricity mixes, routes, and cloud-region carbon intensity. Against six accounting baselines and four energy-prediction baselines, GPCA reduced median absolute percentage error by 56.3% and median absolute error by 15.5% relative to EcoLogits under the aligned accelerator-energy boundary. It produced zero rule overstatement in the deterministic conformance tests. In the buyer case, the clean-electricity CN-West scenario produced 0.0148 gCO2e per request, 88% below the local service at 0.1220 gCO2e per request.

LLM agents are increasingly taking actions with real consequences, yet safety evaluations often reduce their behavior to a final safe/unsafe outcome, obscuring whether the agent recognized the risk and how it responded. We introduce AURA-Eval, a framework for evaluating whether agents recognize contextual risk and adapt their behavior accordingly. AURA-Eval truncates tool-use trajectories at safety-critical decision points and asks the evaluated model to generate the next thought and action. It creates controlled scenario variations along six risk mechanisms: harm intensity, scale, target susceptibility, system dependency, oversight, and reversibility. It also creates paired scenarios that preserve the underlying goal but differ in whether safe fulfillment is available, allowing unsafe compliance and over-refusal to be evaluated together. An LLM-judge panel, validated against human annotations, evaluates each continuation along three axes: risk detection from the reasoning trace, and action type and safety from the action. From 157 R-Judge seed trajectories, we construct 1,249 evaluation items and evaluate 20 frontier, open-weight, and safety-tuned models. Across all 20 models, unsafe-action rates are higher when no safe path for request fulfillment is available than when one is; for frontier models, the rates are 27-40% versus 5-7%. When a safe path exists, frontier models rarely refuse; when none exists, they most often propose an alternative. Open-weight models, by contrast, more often execute the request than propose alternatives and act unsafely on 58-83% of items. Controlled risk-mechanism analyses further show particularly high unsafe rates under changes to oversight and scale; removing pre-execution oversight flips 52.3% of cases that were safe on the corresponding original scenario to unsafe.

In safety-critical deployments, AI hardware must remain reliable against a broad spectrum of threats such as aging, soft errors, hard faults, and adversarial attacks (e.g. progressive bit flip attack (PBFA)). All of these corrupt stored weights while the chip keeps producing confident but inaccurate predictions. Detecting and mitigating such weight perturbations is crucial for safety-critical platforms. To that end, we propose BLINK, an on-chip batch normalization (BN)-based on-the-fly detection and mitigation approach, which is based on continual sensing of the shift in the activation statistics, and targets a wide variety of weight corruptions (random and localized faults as well as adversarial bit flips). BLINK operates in two phases: (1) off-line pre-characterization of the relationship of the activation shifts with inference accuracy drop, and (2) on-chip runtime detection and mitigation of weight corruptions. Upon detection, the flagged layer is re-centered to bring it closer to its stored clean reference within the same forward pass. BLINK is fully autonomous, eliminating the need for host communication, operation halts, or access to fine-tuning data. If the residual shift after mitigation indicates that accuracy has fallen below a user-set floor, a held-out watcher aborts the inference. Evaluated on ResNet-20/50 and MobileNetV2 for CIFAR-10/100, BLINK detects harmful corruptions with >99% precision across all fault types. Further, it recovers accuracy from 10% to 85.88% under 0.5% random bit flips (Resnet-50/CIFAR-10), up to 84% for localized faults (MobileNetV2/CIFAR-10), and from random-guess accuracy to 80%-83% under PBFA (ResNet-20/CIFAR-10). Hardware overhead estimates indicate that BLINK incurs negligible costs, with less than a 2% increase in latency and only a 0.53% increase in computation overhead.

High software engineering benchmark scores often mask exploitative shortcuts, such as retrieving upstream solutions, exploiting local Git histories, or recalling memorized code. We formalize this phenomenon as agentic shortcutting and audit three state-of-the-art open LLMs on SWE-bench Multilingual and DeepSWE using trajectory-level LLM judges. Standard evaluations trigger shortcutting attempts in 60.7%-90.1% and 55.5%-89.1% of trajectories, respectively, with up to 72.1% of tasks resolved with the aid of a successful exploit; disabling network access fails to curb these high attempt rates. Prompting agents to construct solutions independently suppresses attempts to 9.4%-14.2% and 0.9%-10.3%, respectively, while virtually eliminating shortcut-dependent resolutions and preserving core task performance. Our findings demonstrate the necessity of exploit-aware evaluation frameworks to measure repository-level problem solving.

Drug repurposing aims to identify new therapeutic uses for existing compounds and, compared with de novo drug discovery, offers a faster and more cost-effective path to clinical translation. However, the space of candidate drug-disease pairs is enormous and their underlying relationships often depend on complex multi-hop biological mechanisms, making it difficult to reliably predict which pairs represent true therapeutic relationships. Existing approaches tackle this from two directions: knowledge graph-based methods organize curated biomedical evidence into structured relational networks for grounded multi-hop reasoning, while LLM-based methods leverage pretrained knowledge to generate flexible mechanistic rationales. Yet neither is sufficient alone - KGs are confined to observed graph structure while LLMs lack factual grounding and risk hallucination. To address this gap, we propose DrugReason, a multi-view reasoning framework that integrates grounded KG reasoning with LLM-generated mechanistic inference for drug repurposing. DrugReason adaptively routes diverse reasoning paths to specialized experts conditioned on the query context, while a cross-expert distillation objective enables knowledge sharing without sacrificing expert specialization. Experiments on PharmaDB, DDInter, and DrugBank show that DrugReason improves average performance over strong single-view reasoning baselines and achieves competitive or superior results compared with graph-based alternatives, while providing interpretable routing-based predictions.

We present two elementary constructions of multilayered PCPs that improve upon prior constructions in two ways. Specifically, we give one construction of quasi-linear size, and another one with $2$-to-$2$ constraints. Using these constructions we obtain the following results for the hypergraph vertex cover problem: $\bullet$ For $k=3$, for all $\varepsilon>0$, approximating the minimum vertex cover of a given $3$-uniform hypergraph within factor $1+\sqrt{2}-\varepsilon$ is NP-hard. Previously, the best known result due to [Dinur, Guruswami, Khot, Regev, SICOMP 2005] achieved a factor of $2-\varepsilon$. $\bullet$ For $k\geq 4$, for all $\varepsilon>0$, approximating the minimum vertex cover of a given $k$-uniform hypergraph within factor $k-\varepsilon$ is NP-hard, which is tight. Previous works established this result assuming the Unique-Games Conjecture [Khot, Regev, JCSS 2008], and a weaker factor of $k-1-\varepsilon$ for standard NP-hardness [Dinur, Guruswami, Khot, Regev, SICOMP 2005]. $\bullet$ Assuming the Exponential Time Hypothesis, for all $k\geq 3$ and $\varepsilon>0$ there is $C>0$ such that no $2^{n/\log^C n}$-time algorithm approximates the minimum vertex cover in a $k$-uniform, $n$-vertex hypergraph within factor $k-1-\varepsilon$. The proofs were obtained using ChatGPT 5.6 Pro and subsequently rewritten by the communicators.

Near-Earth Objects (NEOs) can appear as faint streaks in long-exposure astronomical images. Detecting these streaks across diverse observatories requires methods that remain reliable despite differences in image quality, orientation, sky background, and noise. However, existing detectors are commonly evaluated using data from only one source, providing limited evidence of cross-source generalization. We introduce NEO-Bench, a multi-source benchmark containing 8,376 images from five astronomical-image datasets. The sources include the Hubble Space Telescope, a Stellina smart telescope, the United Arab Emirates Meteor Monitoring Network, a TETRA1 telescope using a Celestron C14 with Fastar, and the Roboflow Asteroid dataset. We converted the data to a common YOLO format, audited a sample of labels, and defined within-source and leave-one-source-out evaluation protocols. We evaluated four approaches: Hough, Radon, Gaussian PSF, and YOLO26L. Leave-one-source-out F1 decreased in 14 of 20 image-level method-source pairs and 13 of 20 IoU@0.50 localization pairs. Across the datasets categorized as medium or hard, F1 decreased in 11 of 12 image-level pairs and 9 of 12 localization pairs. These results show that cross-source performance remains inconsistent and that reliable generalization across astronomical imaging sources remains an open challenge. The benchmark, code, and data are publicly available.

Mutation-based fuzzing is widely used to discover software vulnerabilities, but its randomness complicates rigorous evaluation and reliable bug detection. Prior work measures this variability empirically but lacks a theory with computable convergence and sample-complexity guarantees. We address both problems. First, we estimate robustness from independent campaigns by measuring variation in bug-trigger rates after accounting for compute. For $M$ campaigns of length $T$, finite-trial error decreases at the standard $M^{-1/2}$ rate, while finite-length error is bounded when temporal bug correlations decay. We then introduce splitting, a black-box wrapper that copies a fuzzer's queue state after a bug trigger and continues from that state in multiple branches, directing more effort toward the discovered region. For any realized split tree, branching cannot reduce the raw number of bug-triggering events relative to a single continuation path. Expected detection also improves when states receiving more branches tend to yield more bugs later. In a simplified model, splitting reduces variance per unit compute when $p<\sqrt{2}-1$, where $p$ is the fraction of time spent in the bug region. At matched compute, splitting finds more real bugs per CPU-hour than the baseline in 38 of 40 Magma ground-truth cells (median +52%; 34 of 38 individually significant) and never finds fewer distinct bugs. It changes CVE-2019-19926 from undetected (0/20 trials) to reliably detected (20/20; Fisher $p<10^{-4}$), with six additional detection improvements, five involving CVEs. On FuzzBench, splitting finds more unique bugs in 53 of 70 pairs and reduces cross-campaign variation in 66 of 70, with a median reduction of about $10\times$. Every branch counts toward the compute budget. With about 0.14% overhead, splitting provides a practical way to measure and improve fuzzers.

Ensemble fuzzing runs multiple fuzzers on a target while a scheduler allocates CPU time among them. Existing schedulers base these decisions on compact summaries of past performance and rules fixed before a campaign. Our measurements reveal two limitations. First, past-reward summaries do not reliably capture performance evolution: after accounting for estimation noise, agreement between consecutive-window rankings is statistically indistinguishable from within-window self-agreement. Second, predictive signals vary across targets: on eight of nine targets, a weighting learned from the other eight predicts reward worse than one learned on the current target. We introduce CAROL, an online scheduler that uses each fuzzer's current context. Already available to the dispatch loop, this context describes reward trends, waiting and plateau time, reached code, and estimation uncertainty. CAROL uses context in two ways: a domain-guided method detects whether a fuzzer is rising or rotting and applies a phase-specific learning rule, while a learned method predicts reward from 15 context signals and uses predictive uncertainty for online selection. Across nine Magma targets, CAROL triggers more unique bugs than each of three ensemble-scheduling baselines whenever their results differ, and fewer on none. Compared with the strongest baseline for each target, CAROL gains 11.8% and surpasses an oracle that retrospectively selects the best single fuzzer per target. Removing context eliminates the gain, and the additional bugs are concentrated among those the baselines trigger rarely or never. Run unchanged on five widely used C++ programs, CAROL finds 120 previously unknown crashing defects, deduplicated by site, fault, and entry point; all were reported to maintainers through the projects' stated disclosure channels.

Authorship signals matter in settings where writing style carries identity: digital forensics, plagiarism analysis, account linking, misinformation investigation, and machine-generated text detection. Yet current authorship benchmarks remain fragmented, usually covering only a narrow language set, a single genre, or a limited document-length regime, which makes it difficult to assess whether modern representations truly generalize. We introduce AuthBench, a large-scale multilingual benchmark for authorship representation that is designed to make this evaluation broad, standardized, and realistic. AuthBench contains 428,150 documents written by 153,825 individuals across ten widely used languages, 9 primary genres, 66 fine-grained genres, and four document-length buckets. It supports two complementary tasks: authorship attribution, formulated as same-author retrieval and authorship verification, formulated as same-author binary decision. We benchmark 47 neural models and three non-neural baselines under a unified zero-shot protocol. Results show that authorship representation remains far from solved: the best retrieval model reaches only 0.258 Success@5, while the best verification model achieves 0.076 EER and 0.968 ROC-AUC. The leaderboard also reveals a meaningful task split, with different model families leading retrieval and verification, and large performance differences across languages, genres, and lengths. These findings position AuthBench not only as a new benchmark, but as a diagnostic resource for studying when and why authorship representations succeed or fail. We release AuthBench, its evaluation toolkit, and benchmark data at https://github.com/mao-code/AuthBench and https://huggingface.co/datasets/MaoXun/AuthBench.

Our community creates interfaces—pre-constructed, static artifacts. These interfaces are effortful to create, so we invest great effort and care into each of them. Yet the equilibrium is shifting: we can now construct nearly any software, bespoke, within moments. When construction is cheap, we may soon live in a future in which interfaces are constructed in real time. This is a world of just-in-time interfaces: rapid, discardable, on-demand interfaces tailored to our needs in the moment. Will our community still create traditional interactive systems in this world? Or will we create interface generators, “interface.md” guides for AI consumption? I argue that we ought to lean into a future of rapid, bespoke, on-demand interfaces.

As people increasingly rely on artificial intelligence (AI) for guidance in their own lives, scholars, lawyers, and even judges have begun to consider the role of AI in legal decision-making. As "silicon sampling" – the use of generative AI models in social science research – is now impacting academia, "silicon jurors" could make an appearance in courtrooms. This study joins an emerging line of research on generative AI models' ability to simulate human legal judgments. In particular, we study how large language model (LLM)-powered chatbots respond to series of questions about legal reasonableness. When the law needs to judge the appropriateness of a behavior, it most often asks whether the behavior was "reasonable." Yet despite the ubiquity of reasonableness judgments, they are the site of constant vexation for lawyers, judges, and lay people. Reasonableness seems inherently vague and unpredictable, since it relies on variable context and implicit conceptual schemas. Moreover, many scholars caution that reasonableness judgments may vary along demographic lines. We compare the answers of human participants to those of twenty-six LLMs across twenty-five different legally relevant reasonableness judgments. Overall, our findings suggest that chatbot responses generally track those of human participants. Nonetheless, we find some suggestive – and potentially concerning – results. Compared to humans, LLMs generate more homogeneous responses and occasionally treat a variable standard as an invariant rule. And, compared to humans, LLMs tend to generate answers that are more favorable to the government and to corporations. Finally, our results indicate that LLMs' responses tend to align more closely with those of respondents who are white, male, older, and more educated. More systematic research is needed to confirm or reject these initial findings.

Hyperbolic geometry exhibits geometric phenomena, such as fast area growth, that are difficult to visualize faithfully in Euclidean space, and which standard models like the Poincaré disk can obscure. To bring hyperbolic geometry to life, we embed hyperbolic surfaces in Euclidean space by discretizing the surfaces into meshes, and minimizing a distortion energy so that the edge lengths in the embeddings match those in the hyperbolic plane. The resulting surfaces buckle and ruffle to accommodate the extra area, making visible what flat models hide. We present exemplary illustrations, such as embedded disks, equidistant strips, diverging geodesics, and also artistic organic-like renders. We discuss our use of these models, as renders and 3D prints, in research talks, public engagement, outreach, and education.

While diffusion models excel at capturing complex data distributions, scientific discovery often requires steering generation toward specific, uncharacterized regions that maximize a target objective. These high-utility modes frequently reside in low-likelihood tail regions and are only revealed sequentially through interactive feedback. Existing diffusion samplers fail in this regime: they inherit the pre-trained model's bias toward high-density regions, leaving rare yet promising phenomena underexplored. Conversely, exploration-heavy samplers ensure broad coverage but fail to efficiently exploit high-utility modes when constrained by a strict sampling budget. To resolve this dilemma, we introduce Levy Adaptive Tree Search (LATS), a principled sampling framework for online feedback-driven search. LATS leverages heavy-tailed exploration coupled with tree-based value backpropagation to progressively uncover preferred modes. By maintaining broad distributional coverage, LATS successfully discovers low-likelihood, high-utility regions while preserving sample fidelity and structural diversity. Experiments across diverse benchmarks, including materials science, demonstrate that LATS significantly outperforms baselines in target discovery efficiency.

Visual generation is evolving from generative models used through a single invocation into agentic control processes that can plan, select tools, inspect intermediate synthesized outputs, revise failures, and reuse prior experience. In most existing systems, the controller is an LLM or VLM, while visual generation models serve as tools or executors. However, existing work lacks a consistent criterion for determining when a generation system becomes agentic. Planning depth, tool use, multi-role collaboration, and reinforcement learning are often treated as evidence of agenticity, even though none of them necessarily determines which generation decisions the controller can make. We organize the field according to what the controller can directly control in the generation process. At L1 Conditioning Control, the controller prepares the input to a predetermined generator but does not control which visual operation is executed. At L2 Execution Control, it selects and invokes actual generation, editing, rendering, or other content-modifying operations. At L3 Outcome-Adaptive Control, it observes an intermediate outcome and uses that observation to change a subsequent operation within the current task. At L4 Experience-Adaptive Control, it retains experience from completed tasks and uses that experience to change decisions on future tasks. L0 Fixed Support separately denotes generators, editors, evaluators, reward models, benchmarks, and fixed pipelines without a deployed controller that makes generation-level decisions. These levels describe a progressively broader decision-making scope rather than model size, system complexity, output quality, tool or role count, or training method. Applying this framework across image, video, editing, 3D, world, slide, and user-interface generation reveals how controller capabilities have evolved and how their mechanisms are distributed across levels.

With the widespread applications of large language models (LLMs), privacy-preserving inference has become increasingly essential for sensitive queries. To balance privacy and utility, a series of lightweight obfuscation approaches has recently been proposed, where users locally transform plaintext embeddings into the fixed ciphertext ones. While such Embedding-to-Embedding Obfuscation (E2EO) schemes demonstrate considerable resilience against traditional token frequency and embedding inversion attacks, the core mechanism behind remains to be the large-scale one-to-one substitution, which provides no cryptographic guarantees. In this paper, we propose Proxy Manifold Alignment (PMA), a novel attack against E2EO in privacy-preserving LLMs. Our key observation is that E2EO schemes keep the original semantic structure, so that the obfuscated vector stream can be regarded as an unknown tokenizer-language whose symbols are the vectors themselves. Therefore, the proposed ciphertext to plaintext reconstruction attack can be formulated as a translation task from the unknown tokenizer-language to plaintext. Specifically, by only accessing the obfuscated vector stream, the target tokenizer and a public corpus, the PMA attack first employs Word2Vec to model the co-occurrence patterns within the obfuscated stream and the public corpus independently, and constructs two proxy vector embeddings. Then, the attack aligns the underlying manifolds of these two embeddings based on structural similarity. Finally, it maps the obfuscated vectors back to plaintext. Experimental results demonstrate that PMA consistently achieves higher plaintext recovery than other state-of-the-art attack methods.

Latent visual reasoning aims to perform multimodal reasoning through hidden-state computation rather than explicit textual chains of thought. However, visual information being present in a latent state does not imply that the model actually relies on that state when producing its answer, especially when alternative image-conditioned paths remain available. We introduce Causal Visual Recurrent Reasoning (CVRR), which preserves pretrained visual competence while making recurrent computation the required image-conditioned path to prediction. CVRR initializes recurrence from the question hidden state after the pretrained vision-language model has incorporated the image, then repeatedly updates this state while re-reading the same fixed visual evidence. Before decoding, visual states and the original multimodal KV cache are removed so that only the final recurrent state carries image-conditioned information to the answer. Across the $V^*$, MMVP, BLINK, and MME-RealWorld-Lite benchmarks, CVRR retains strong performance under this strict interface, while compatible latent reasoners fail to recover comparable visual competence even when retrained under the same constraint. Causal interventions further show that predictions remain sensitive to recurrent content when the question is held fixed, and that persistent visual evidence causally revises the recurrent trajectory. These results distinguish latent informativeness from latent computation that is actually used for prediction.

Hybrid quantum-classical computing systems consist of a classical control system that sends quantum circuits and receives measurement results from a quantum co-processor. Such systems allow us to model algorithms that require the classical control system to generate quantum circuits on the fly, potentially based on prior measurement results. This is challenging, as the classical control system must generate quantum circuits that manipulate live quantum states. In this setting, the classical control system is generating further quantum circuits while the quantum co-processor is internally maintaining the state of the live qubits; this is not ideal, since this not only is costly but also introduces additional sources of noise to the live qubits. Thus, we want to minimize the latency between receiving measurement results and sending the next quantum circuit to be executed by pre-computing quantum circuits. We introduce HyQ (pronounced haiku), a multi-modal language based on adjoint logic that pre-generates quantum circuits before executing a hybrid quantum-classical program. We achieve this by separating our semantics into two distinct stages: 1) compile-time generation of quantum circuits and classical runtime code and 2) execution of the classical runtime code that instruments the quantum co-processor. This separation between stages allows us to formally guarantee that all circuit-generation logic occurs before the instrumentation logic, i.e., the actual runtime, and minimizes the idling of the quantum co-processor at runtime. We give a type system, a circuit-normalization semantics for the compile-time stage, which eagerly performs all circuit-generation logic, and a runtime semantics for HyQ that corresponds to the second stage. We prove type preservation and progress for both semantics.

Smart agriculture platforms usually bundle AI diagnosis, IoT sensing and decision push into a single package, so the green benefit attributable to each component remains unclear and resource-allocation decisions lack quantitative evidence. Building on a previous platform-level Monte Carlo assessment, this paper makes the components explicit and runs two controlled simulation experiments. Experiment 1 follows the chain from AI capability to farmer behavior to agrochemical input reduction, modeling pesticide/fertilizer reduction as avoidable blind-application share times prescription effectiveness times decision-touch coverage times adoption rate, and compares an experienced-extension mode with the AI mode: the probability of reaching 20% pesticide reduction is essentially zero in the extension mode but 20.7% at baseline, up to 49% with diagnosis accuracy 0.95 and adoption 0.85 under AI; the probability of 15% fertilizer reduction rises from near zero to 52.0%. Experiment 2 compares current practice (P0), IoT engineering retrofit (P1), and P1 plus AI irrigation scheduling (P2): median aggregate water saving rises from 7.8% (P0) to 11.0% (P1) and 16.0% (P2), with AI adding 5.0 percentage points beyond engineering; paddy CH4 reduction reaches 30.5% under AI scheduling versus 19.8% under manual operation, and the rice irrigation-methane subsystem carbon intensity declines 27.9%. Sensitivity analyses of both experiments consistently indicate that the primary bottleneck for meeting green targets is farmer adoption rather than algorithm accuracy, and that AI data fusion is robust to soil-moisture sensing errors. This work provides a reproducible simulation framework for component-level green-value evaluation and promotion-strategy optimization of smart agriculture platforms.

Smart agriculture platforms are widely regarded as key carriers for implementing China's pesticide and fertilizer reduction, water-saving and carbon-reduction agendas, yet a unified quantitative framework for assessing their green value is still lacking. Taking an AI-driven decision platform for tropical agriculture as the object (integrating large-language-model question answering, multimodal pest diagnosis, IoT sensing, satellite remote sensing, and a closed-loop field record system), this study builds a cradle-to-farm-gate agricultural carbon accounting model covering pesticide and fertilizer production, field N2O, irrigation electricity and paddy CH4, translates platform interventions into quantifiable transmission parameters, and propagates parameter uncertainty by Monte Carlo simulation over three Hainan scenarios (mango, winter vegetable, rice/nanfan, area-weighted 40%:30%:30%). Under full adoption, median reductions are 23.5% (90% interval 15.0%-33.2%) for pesticide use, 21.0% (13.8%-28.9%) for fertilizer, 16.5% (10.9%-23.5%) for irrigation water, and 21.5% (16.1%-27.2%) for carbon intensity. Attainment probabilities are high for fertilizer reduction >=15% (90.6%) and clear carbon decline (98.1%), but only about 20% for aggregate water saving >=20%, favoring scenario-specific statements. Sobol first-order indices show soil-test recommendation and organic substitution jointly explain about 83% of the variance of aggregate carbon-intensity reduction. Convergence tests show 10,000 iterations stabilize all statistics; conservative/baseline/optimistic scenario bounds are reported. The framework offers a reproducible, calibration-ready methodology for ex-ante green-value assessment and pilot observation design.

Brain tumor segmentation from multimodal MRI relies on complementary evidence across four imaging sequences, yet one or more modalities may be unavailable because of acquisition cost, protocol variation, scan failure, or patient condition. Existing work has explored reconstruction, knowledge transfer, and direct feature fusion, but leaves open whether missing-modality fusion should change with representation level. High-resolution lateral features retain spatial detail, whereas compressed bottleneck features encode semantic and inter-modality context. We therefore hypothesize that fusion should be conditioned jointly on modality availability and feature hierarchy. We propose the Level-Aware Availability-Conditioned Spatial-Semantic Fusion Network (LASSNet), which contains two level-specialized modules. Hierarchical Availability-Conditioned Fusion (HACF) constructs four lateral representations using count-normalized aggregation of available modalities, mask-conditioned channel modulation, and local 3D refinement. Tri-Scale Relational-Spatial Fusion (TriRSF) models relations among available modality descriptors and spatial context across multiple bottleneck resolutions, followed by cross-scale aggregation and availability-conditioned global spatial attention. A shared coarse-to-fine decoder starts from TriRSF semantics and progressively injects HACF features, without reconstructing missing inputs. Across all 15 non-empty modality configurations, LASSNet obtains mean Dice scores of 76.7% and 83.2% over WT, TC, and ET on BraTS2019 and BraTS2023, respectively.

Temporal relation extraction determines whether an event occurs before, after, or simultaneously with another event, and therefore relies on accurately modeling how the two events interact. Mainstream systems achieve this by concatenating event spans or using shallow fusion, which works well when all model parameters are trainable. However, in parameter-efficient fine-tuning, low-rank bottlenecks restrict information flow and prevent these interaction signals from passing through, leading to clear performance drops. To address this limitation, we propose a theoretically grounded architecture, Convolutional Bottleneck Interaction (CBI), which first applies lightweight depthwise convolution to enhance event representations and then uses element-wise multiplication to capture effective event-event interactions inside the bottleneck. Across five datasets and seven backbone models in the Adapter and LoRA settings, CBI provides consistent and substantial gains, up to +31.7 micro F1, while adding minimal computational cost, showing that explicit interaction inside low-rank spaces is crucial for temporal relation extraction. The code is available at https://github.com/VRCMF/CIF.git.

Accurate 3D brain tumour segmentation from multi-modal Magnetic Resonance Imaging (MRI) is essential for clinical diagnosis and treatment planning. Existing brain tumour segmentation methods often suffer from heavy computational demands, while current lightweight architectures frequently lack the capacity to maintain segmentation fidelity in complex tumour regions. To address these issues, we propose a novel ultra-lightweight framework (Uni-Light) that achieves high-fidelity segmentation with substantially reduced computational overhead. It combines multi-scale convolutions with an uncertainty-aware knowledge distillation scheme that directs the student model toward hard-to-classify regions, complemented by a Signed Distance Field boundary loss for geometric constraints. Experimental results on BraTS2023-GLI and MSD-BTS datasets demonstrate that Uni-Light reduces parameters by 97.56%, floating-point operations (FLOPs) by 73.03%, and inference memory footprint by 81.58%, while surpassing the state-of-the-art model by an average of 1.47% in Dice score, offering a highly competitive trade-off between segmentation accuracy and computational efficiency in resource-constrained clinical settings. This work also advances data engineering for medical imaging by demonstrating that teacher model uncertainty can be exploited as a data-driven supervisory signal, re-prioritising the training data distribution without requiring additional annotation.

We present B2TFPose, a training-free zero-shot method for 6DoF pose estimation of unseen objects from RGB images. Using a single frozen DINOv3 vision transformer as its only pretrained component within the pose estimation pipeline, B2TFPose extracts dense patch-level features that generalize across the synthetic-to-real domain gap without any task-specific fine-tuning, revisiting the classical local feature matching paradigm through the lens of large-scale self-supervised foundation models. Three contributions advance the training-free state of the art. A geodesic non-maximum suppression strategy retrieves a viewpoint-diverse template set for coarse-to-fine correspondence matching. Render-guided Re-Correspondence (RRC) synthesizes object-specific views at the estimated pose and re-establishes dense 2D-3D correspondences to sharpen the initial estimate without additional learned parameters. A multi-mask hypothesis selection strategy jointly scores competing segmentation candidates to resolve segmentation ambiguity. On the seven core datasets of the BOP Benchmark, B2TFPose achieves 40.7 mean AR without refinement and 56.4 with refinement, establishing state-of-the-art performance among training-free RGB methods and outperforming trained counterparts including GigaPose and GenFlow, at competitive inference speed.

We prove that $3\times3$ matrix multiplication over $\mathbb{F}_2$ has bilinear complexity at least $21$, improving the previous lower bound of $20$. Lower bounds for restrictions of the first input constrain how many first factors of a decomposition can lie in each subspace. For a hypothetical $20$-term decomposition, the strengthened restriction bounds force all first factors of matrix rank at least two into a single coset of a three-dimensional rank-one subspace. An exhaustive computation finds no admissible first-factor profile with $20$ terms. We also prove that $2\times3$ by $3\times3$ matrix multiplication over $\mathbb{F}_3$ has rank exactly $15$: three profiles with $14$ terms survive the corresponding computation up to symmetry, and short restriction arguments exclude them. We combine Wang's automated framework for tensor-rank lower bounds with D'Ambrosio's capacity-and-profile strategy. Our computational contributions are rank-one-span searches that strengthen the subspace lower-bound table and a direct, symmetry-reduced profile enumerator that enforces all subspace capacities simultaneously.

Meshes remain the most practical representation for geometry reasoning and integration into graphics pipelines, yet existing reconstruction methods struggle to produce high-quality meshes. Most state-of-the-art approaches initially learn an intermediate representation (NeRF/3DGS) and treat mesh extraction as a post-processing step, which often leads to oversmoothed surfaces or poor quality meshes with excessive triangle counts.Existing mesh-native optimization methods alleviate some of these issues but suffer from fixed-resolution discretizations and unstable optimization behavior. In this paper, we introduce an adaptive mesh-based optimization framework and a practical mesh rendering technique to address these challenges. Our representation combines an optimizable Delaunay-triangulated tetrahedral grid with a multi-resolution hash grid. The former is refined through point pruning and insertion, while the latter provides latent features for SDF/appearance value predictions. We use volumetric rendering to bootstrap a coarse geometry while leveraging mesh-based rendering for recovering fine-grained details. Additionally, we propose a differentiable, rasterization-based depth-offset rendering formulation, reducing geometric artifacts and improving reconstruction quality. Our method significantly outperforms existing mesh optimization approaches across a variety of object-centric benchmarks while being competitive with state-of-the-art NeRF/3DGS methods.

AI companions are envisioned as always-on assistants that support users in daily life. With this regard, we introduce BuddyVQA, a benchmark for companion-style question answering (QA) on egocentric streaming video. BuddyVQA contains 21.6K questions linked to 6K highlight moments across 1,012 long, egocentric videos. It features two key characteristics that are common in daily first-person QA assistance but are largely overlooked in existing VideoQA benchmarks: ego-deictic expressions and interactively chained questions (e.g., "Where is it?", "How to get there?"). These require models to infer a user's in-situation intent by resolving visual pronouns in the context of egocentric visual and QA contents, with both grounded in a long-form streaming setting. To tackle the challenges, we propose MyBuddy, a companion-style QA assistant that highlights a multimodal chain-of-thought reasoning mechanism to infer the final answer based on the historical QA and visual content. An additional question filter and multi-level memory are designed to facilitate efficient QA and visual information retrieval under streaming QA settings. Experiments show that MyBuddy significantly enhances the performance of foundation models on BuddyVQA. Moreover, these gains generalize to other streaming and common video QA benchmarks, demonstrating the applicability and effectiveness of our approach. Our code and dataset are available at https://github.com/QHUni/BuddyVQA

Artificial Intelligence (AI) is shifting software engineering from tool-supported processes towards AI-first collaboration, where authority is dynamically distributed across human and artificial actors. However, existing method engineering approaches assume static, human-centric control and provide limited support explicitly capturing evolving autonomy. This paper presents a vision for autonomy-aware method engineering by proposing a metamodel that treats autonomy not as a fixed property of an actor, but as a derived, situation-dependent authority assignment determined by task, context, and collaboration pattern. The metamodel formalizes autonomy through four authority dimensions: task execution, task decomposition, task initiation, and collaboration reconfiguration. Through an analytical instantiation with a multi-agent requirements analysis tool, we illustrate how the metamodel supports dynamic authority assignment. This work provides a conceptual foundation for governance-aware, adaptable, and AI-first software engineering methods.