AI 速览：提出 Multi-View MoE，用多个路由器聚合专家选择偏好，并复用路由分数调制专家输入，在固定激活专家预算下提升下游性能。
Sparse mixture-of-experts (MoE) models expand parameter capacity by activating a small subset of experts per token. Expert selection directly affects model capabilities under a fixed active-expert budget. Dense evaluation of all experts reveals weak agreement between single-router rankings and expert-utility evaluation rankings, especially in middle and deep layers. Richer signals for selection and computation incur additional cost: selection based on internal expert activations requires preliminary computation, while processing multiple full representations separately through the same expert repeats its computation. We propose Multi-View MoE to improve expert selection with multiple routers and reuse their preferences to modulate expert computation under a fixed expert budget. Its Multi-Router submodule aggregates sigmoid scores from independently initialized routers. These routers develop highly differentiated expert preferences during training, allowing experts strongly favored by one router or jointly supported by several routers to be selected. Multi-View further uses each selected expert's relative scores across routers to mix learned latent views into its input, reusing routing preferences for both selection and computation. Each selected expert executes one forward pass, preserving the active-expert count, expert FLOPs, and all-to-all communication volume. On a 24-layer 10B-A1B model trained on 708B tokens, full Multi-View MoE improves the nine-task downstream mean by 1.18 percentage points over the baseline. Multi-Router alone yields a 0.6-percentage-point gain and improves the rank correlation between router scores and evaluated expert utility, with relative increases of 8.1% globally and approximately 58% in the layer with the lowest single-router alignment. Controlled mixing interventions show the model uses input differences that depend on both the expert and the token.
Ziyi Guan, Yael Tauman Kalai, Ron Rothblum, Zoe Xi
AI 速览：提出可回卷交互证明（RIPs），利用验证者可回卷AI证明者状态的能力，在无需诚实证明者假设且不使用密码学的前提下实现更高效的可扩展监督。
Scalable oversight asks how a weak verifier can check the outputs of computations performed by more powerful AI systems. One proposed approach uses relativizing interactive proofs, in which a weak verifier checks the output of a complex oracle-aided computation by interacting with one or more powerful provers. A prominent example is debate, which is highly efficient but assumes that one of two powerful AI models, or provers, is truthful. For certain classes of oracle-aided computations, this assumption can be removed, but at substantially greater computational cost. In this work, we introduce \emph{rewindable interactive proofs} (RIPs), a new model of relativizing interactive proofs for scalable oversight. In an RIP, the verifier may rewind the prover to an earlier state of the interaction and continue from there. This is possible when the prover is an AI model, since the verifier can save a snapshot of the model's state and later restore it. We construct a relativizing RIP for computations whose outputs are robust to changing a small fraction of oracle answers. Our construction is more efficient than prior relativizing proofs that do not assume a truthful prover, and it uses no cryptography. In our construction the honest prover runs in time linear in that of the original computation, and the verifier, after a one-time preprocessing step, runs in time nearly linear in the input length (which can be much smaller than the computation itself). We implement our protocol, report a preliminary MNIST experiment, and show that an RIP can be faster than a state-of-the-art deployed proof system. RIPs may be of independent interest. Rewinding is possible whenever the verifier controls the prover's machine, for example when the prover runs on trusted hardware or in a virtual machine whose state can be checkpointed.
GUEST: Preliminary Guidelines for Using and Evaluating GenAI Tools to Support Systematic Literature Reviews
Barbara Kitchenham, Sebastián Pizard, Lech Madeyski, Ronnie de Souza Santos, Martin Shepperd, David Budgen
AI 速览：作者通过快速综述与经验反思提出GUEST框架，含51条建议，指导在系统文献综述（SLR）中规划、执行和透明报告GenAI辅助工作及其评估。
Context: Generative AI (GenAI) and Large Language Models (LLMs) are increasingly used for academic tasks in software engineering and beyond, including systematic literature reviews (SLRs). However, whilst their capabilities are rapidly developing, there is no guarantee they can meet the rigour, reliability, and transparency that SLRs require. Objectives: To support researchers intending to conduct SLRs using GenAI, or those conducting empirical studies to evaluate how well GenAI supports SLR tasks. Methods: First, we conducted a rapid review to identify studies that propose guidelines for evaluating and using GenAI and LLMs to support SLRs. Second, we drew on thought experiments, relevant guidance from the literature, and our own experience from conducting SLRs and evaluating tools, to develop recommendations for how to use and assess GenAI in the context of SLRs. Results: We classify methodological issues for the roles of evaluation and reviewing into four categories spanning SLR practice adjustments, general secondary-study standards, GenAI evaluation practices and core empirical rigour. Building on this, we introduce GUEST (GenAI Use and Evaluation in SLR Tasks) which is a comprehensive framework of 51 recommendations designed to guide researchers through planning, executing and transparently reporting GenAI-assisted literature reviews and validation studies. Conclusion: Current empirical evidence indicates that GenAI cannot be relied upon to perform unsupervised systematic reviews so requires human oversight. Nevertheless, it can offer cost-effective assistance for repetitive screening tasks and secondary validation. By standardizing how these tools are deployed and evaluated, the GUEST framework provides a necessary methodological baseline for trustworthy GenAI-assisted research in software engineering.
Deep Learning Based Behavioral Drift Modeling for Continuous Biometric Authentication
Suprava Saha Dibya, Minar, Abdulla Al Noman, Md. Zafir Abid Shresto, Ahmed Sayef
AI 速览：提出两级击键动力学认证系统：固定文本登录用TCN+对比学习+PBT，登录后自由文本用四模型集成持续监测行为漂移并触发重认证。
This research proposes a two-level keystroke dynamics authentication system that provides defense-in-depth security through continuous behavioral drift monitoring. Level 1 employs fixed-text password authentication using Temporal Convolutional Networks (TCN) with contrastive learning and population-based training (PBT), achieving 3.77% EER for high-security login verification. Upon successful authentication, Level 2 continuously monitors user typing during natural free-text sessions using a 4-Model Deep Learning Ensemble. If suspicious behavioral drift is detected during monitoring, the system re-authenticates the user by returning to Level 1, providing a feedback loop against session hijacking and behavioral anomalies. The system explicitly models long-term behavioral drift through the fixed-text component's PBT mechanism, which adapts to temporal variations in password typing patterns. This research leverages free-text (Buffalo dataset) and fixed-text (GREYC dataset) keystroke dynamics datasets, extracting temporal and spatial features including hold times, up-down latencies, down-down intervals, and trigram patterns. The final system achieves 96%+ accuracy for fixed-text authentication (3.77% EER) and 83.53% True Acceptance Rate (TAR) at 5% False Acceptance Rate (FAR) for free-text continuous authentication (10.05% EER), demonstrating superior performance and strong resistance to impostor attacks through continuous behavioral monitoring.
In a compact storage system with side access, bins are arranged in adjacent vertical stacks. In each retrieval cycle, bins blocking access are lifted to create a temporary tunnel through which a robot extracts one requested bin from the side. The lifted bins are then lowered again, and the energy expenditure of the cycle equals the number of lifted bins. Given a pick list known in advance, we seek a retrieval order that minimizes total energy expenditure. For every number of stacks, we prove that the total energy separates into an instance constant and a pairwise penalty, and that every energy-optimal order is laminar within each stack. For two stacks, we prove that the retrieval sequencing problem is solvable in polynomial time. For three stacks, we give an exact polynomial-time reduction to a merge problem and characterize which merge-problem instances arise from the storage model. We define a recursive class of retrieval orders and construct a polynomial-time dynamic program that minimizes energy expenditure over this class. Finally, we quantify the additional energy savings from batching, which allows several requested bins to be retrieved in one cycle.
Jing Zhang, Lianghong Guo, Yanlin Wang, Terry Yue Zhuo, Yong Wang, Mingwei Liu, Jiachi Chen, Ensheng Shi 等 11 位作者
The Development Knowledge Question Answering (Dev Knowledge QA) task aims to provide accurate natural language answers to knowledge-seeking questions during software development. To investigate the importance of Dev Knowledge QA in AI-assisted software development and the extent to which it has been explored, we conduct a preliminary analysis of real user-LLM dialogues from WildChat. Our findings indicate that Dev Knowledge QA plays a significant role in real-world software development scenarios, and these raw dialogues cannot be directly used to construct a Dev Knowledge QA benchmark. Existing Dev Knowledge QA benchmarks are limited in development knowledge scope and often not built from real user queries. To bridge this gap, we design a three-phase pipeline that transforms real-world dialogue into simple development knowledge-seeking QA pairs. Through this pipeline, we introduce SimpleDevQA, a multilingual Dev Knowledge QA benchmark inspired by real user dialogues. This dataset covers three languages (English, Chinese, and Russian), and focuses on questions with unique, short, and verifiable answers, making evaluation more accurate and simple. Extensive experiments with 21 mainstream LLMs show that closed-source models generally perform best on SimpleDevQA. We also find that RAG-based knowledge injection improves accuracy, and that Dev Knowledge QA performance correlates with both model confidence and code-generation capability. To facilitate the replication study, we have released our data and code at: https://github.com/DeepSoftwareAnalytics/SimpleDevQA.
Differentiable decision trees (DDTs) support end-to-end optimisation and explicit decision paths, but dense oblique splits can obscure the role of individual input features. We propose the Euclidean-Concentrated Differentiable Decision Tree (EU-DDT), which regularises the relative absolute feature weights at each internal node using their normalised squared Euclidean distance from the uniform distribution. This encourages dominance by a small number of features while retaining probabilistic soft routing. Across five matched random seeds, EU-DDT reduces the mean effective number of features from 8.94 to 1.54 on Wine and from 45.28 to 9.06 on Digits. Mean test accuracy changes from 100.0% to 93.9% on Wine and from 92.3% to 94.6% on Digits, illustrating the dataset-dependent trade-off between concentration and predictive performance. We also use EU-DDT to parameterise a PPO actor with an MLP critic. Two random-seed runs per environment show a consistent qualitative increase in concentration while preserving effective task performance. In representative CartPole-v1 and MiniPacman runs, EU-DDT reaches 100% final evaluation success, while mean node concentration increases from 0.1272 to 0.7179 and from 0.0437 to 0.7237, respectively. These results support EU regularisation as a mechanism for reducing node-level feature complexity; the reinforcement-learning evidence remains preliminary because only two seeds are evaluated.
LLM agentic workflows increasingly employ different models for specialized roles. Users may prefer different trade-offs between task quality and deployment cost, sometimes also considering latency. Finding good assignments incurs a separate search cost from evaluating multiple candidates. We introduce Cost-Coupled Gittins (CC-Gittins), a multi-objective extension of single-objective cost-aware Gittins search for Pareto recommendation. It exploits the coupling between evaluation and deployment costs: assignments that cost more to deploy also cost more to evaluate. The search alternates between seeking higher quality and lower deployment cost, reusing each evaluation to inform both searches. After each batch, CC-Gittins recommends assignments that are nondominated under uncertainty-adjusted estimates of quality and deployment cost. We evaluate CC-Gittins on eight quality--cost matrices from workflows with two to five roles and up to 1,681 candidate assignments. We also evaluate the method with latency as a third objective. Across the eight benchmarks, CC-Gittins recovers a substantial fraction of the true Pareto frontier at roughly 10% of the exhaustive-evaluation cost, and recovers most of the frontier with few false positives by 30%.
Social annotation platforms such as Perusall and Hypothesis are widely used to support student engagement with course readings, often through required commenting. Yet visible participation does not necessarily produce sustained or substantive peer exchange. Analyzing six weeks of Perusall activity from a graduate course (2,873 comments), we found that participation was often fragmented: 53.5% of comments received no reply, 38.3% were posted within the final 12 hours before the deadline, and over one-third of a double-coded sample went no further than repeating or agreeing with the reading or a peer. Interviews pointed to two linked difficulties: locating a discussion worth entering and contributing something that meaningfully advances it. We present Lookover, an AI-assisted annotation system that scaffolds both stages without writing for students. Discussion Overview helps students identify active themes and relevant threads, while Spark Thinking poses questions that encourage them to move beyond reaction and restatement toward questioning, extending, and substantively responding to peers. A preliminary study with five participants found Discussion Overview valuable for those who noticed it, while the usefulness of Spark Thinking depended on how much a participant already knew about the topic.
LLM-based agents are increasingly used to complete complex, long-horizon tasks without human intervention. To make progress toward the task goal, agents need to perform different duties, such as planning and verification, when needed. To understand how single agents manage these duties during long-horizon execution, we conduct a preliminary study. Our analysis shows that verification has the strongest association with task success, but often occurs late, leaving limited opportunities for correction. We also find that the proportion of duty-relevant information decreases as records from different duties accumulate in a shared context. These findings lead us to examine whether multi-agent systems (MAS) can address these problems by assigning duties to agents with separate contexts. Our analysis shows that this separation alone is insufficient. Agents can lose track of the overall goal and repeat prior investigations. They may also lack necessary background while receiving irrelevant information from others. To maintain goal awareness and coordinate collaboration as task needs change, we propose Goal-Aware Dynamic Multi-Agent Collaboration (GAD). It uses a growing execution graph to organize subtasks and their dependencies. To keep agents focused on their goals, each context retains the original instruction and the assigned task's goal and acceptance conditions. To adapt collaboration and information sharing during execution, agents can divide tasks into subtasks and specify dependencies based on execution evidence. These dependencies guide when agents work and which results they receive. Verification and recovery check subtask results and full task completion against their goals, providing feedback for repair when checks fail.
The Just-In-Time (JIT) defect prediction model serves as a critical tool for ensuring the quality of software development and enhancing software performance. It assists development teams in promptly identifying and addressing potential issues by predicting whether code submissions may introduce defects. However, due to the existence of data noise and insufficient semantic connections in real-world scenarios, existing approaches face challenges in accurately identifying the code commits that introduce defects and capturing the potential semantic relationships. To address these challenges, we propose the BIC- Hunter(Bug-Inducing Commits Hunter) model, which mitigates data noise and improves semantic understanding, thereby enhancing the accuracy of bug-inducing commit identification. BIC - Hunter model consists of two components: a data denoising component and a semantic relationship capturing component. Specifically, the data denoising component addresses the challenges posed by inaccurate annotations and inconsistencies in real-world data, enhancing the reliability of training data and improving overall model robustness. The semantic relation- ship capturing component constructs homogeneous graphs and applies graph convolutional networks to facilitate a more comprehensive analysis of code context, enabling the identification of defects caused by code commits and enhancing the confidence in pinpointing their root causes. Experimental studies on a large-scale dataset integrated from three open-source datasets show that BIC- Hunter exhibits outstanding performance. BIC- Hunter outperforms the state-of-the-art by 6.16%, 7.13%, and 5.53% on Recall@1, Recall@2, and Recall@3, respectively, while the MFR index increases by 8.43% to 32.82%. These results demonstrate the superior capability of our method in identifying bug-inducing commits.
We study distributed storage over public communication channels where privacy is realized using shared secret keys. Specifically, a user wishes to store a file across $L$ servers such that any subset of at least $t$ servers can reconstruct the file, while any subset of at most $z$ colluding servers learns no more than a fraction $α$ of the file. Unlike classical secret-sharing models that assume secure communication channels between the user and each server, we consider a setting where all transmissions occur over a public channel and the user shares an individual secret key of length $n$ bits with each server. For a fixed key length $n$, we characterize the trade-off between the privacy leakage parameter $α$ and the maximum file size that can be securely stored. Additionally, we determine the minimum local randomness, public communication, and storage required to achieve this optimal trade-off.
Whether generative AI (GenAI) use helps or hinders critical thinking remains contested, and existing accounts emphasize exposure to the tool rather than how a person structures their engagement with it. Extending Transactive Memory Systems (TMS) theory to human-AI partnerships, we test a structural account of critical thinking in GenAI-assisted academic work among 891 college students in the United States and Türkiye. Self-appraised thinking ability and confidence in the partnership shaped how much practical experience a person built up with GenAI, but neither predicted critical thinking directly. That experience mattered only through two downstream behaviors, dividing and coordinating cognitive labor with the tool, and actively reworking its output rather than accepting it as given. A multigroup comparison found this structure largely invariant, with two theoretically interpretable exceptions. This study offers a structural, TMS-based account of critical thinking in GenAI-assisted work.
AI coding agents increasingly rely on retrieved code and development history to guide software changes. However, highly relevant artifacts may describe implementations that are inactive or incompatible with the target deployment. Neither semantic similarity nor recency establishes whether retrieved information remains applicable under feature flags, architectural migrations, and deployment-specific configurations. We challenge relevance-oriented retrieval by introducing operational context validity, a task-, deployment-, and time-dependent criterion for determining whether software evidence can legitimately guide implementation decisions. We instantiate this new retrieval principle in CASE, an agent-agnostic framework that connects repository artifacts with runtime configurations and architectural evolution, classifies evidence as valid, invalid, or unknown, and generates context packages distinguishing actionable guidance from historical rationale and unresolved constraints. We investigate its feasibility through a reproducible preliminary evaluation involving six development tasks, 15 artifacts, and three deployments. Conventional retrieval exposes 16 incompatible artifact occurrences as actionable, whereas CASE excludes them while retaining all applicable artifacts under the prototype's reference rules. Recency filtering reduces valid recall to 0.43, while removing feature-flag evidence from CASE reduces it to 0.13. Although these results demonstrate feasibility rather than improvements in coding-agent correctness, they reveal limitations of relevance-based retrieval and motivate a new research direction: enabling coding agents to reason not only about which information is relevant, but also whether it remains operationally valid.
Smart contracts are immutable programs deployed on blockchain platforms, where vulnerabilities can translate directly into financial loss. Among the techniques proposed for their detection, recent work has relied increasingly on Large Language Models (LLMs) guided by carefully crafted prompts. However, the evidence accumulated so far rests almost entirely on the dense Transformer architecture behind the GPT line and on model snapshots already scheduled for deprecation, leaving open the question of whether the reported behaviors reflect a general property of LLMs or an artifact of that specific design. This paper presents an extended replication of the empirical study by Chen et al. on LLM-based smart contract vulnerability detection. We replicate the original protocol on GPT-4 as a baseline, followed by a differentiated replication, executing the protocol on representative models based on Mixture-of-Experts and RNN-like designs, together with an attempted preliminary evaluation of State Space Models. The exact replication confirms the findings of Chen et al., including the high-recall, low-precision detection pattern they report on GPT-4. Nevertheless, the differentiated replication shows that this pattern does not transfer uniformly across the evaluated models. Those from the same architectural family may also exhibit different behaviors, indicating that architectural family alone is insufficient to predict the resulting detection profile. We observe the same qualitative dense-Transformer profile in both GPT-4 and Gemma-3, despite a gap of roughly two orders of magnitude in parameter counts, whereas two Mixture-of-Experts models from different lineages exhibit qualitatively divergent behaviors, indicating that architectural family alone is insufficient to predict the detection profile.
Tong Zhao, Di Liang, Yiming Zeng, Bo Xu, Yingzhi Tang, Chen Bai
In the era of large models, stereo matching is developing towards generalizable foundation models trained on million-scale synthetic images. However, how model performance scales up with synthetic data is still underexplored. In this work, we preliminarily investigate the in-domain and cross-domain data scaling laws in stereo matching. A realistic synthetic dataset, named XStereo, containing 200 thousand samples is first built to serve as a high-quality benchmark for data scaling research. In-domain training on five large-scale datasets demonstrate a two-regime scaling behavior with data, transitioning from the standard power law to saturation, where the critical transition point is approximately invariant under a fixed model. Cross-domain performance exhibits a substantially weaker and less predictable dependence on the source-domain data scale. The distribution and coverage diversity are more effective for diminishing domain gaps. More instructive suggestions are provided for high-efficiency data construction and training. The insightful findings are significant verification and extension of the existing scaling laws in both language and vision, paving the way to efficient and stronger stereo matching. The XStereo dataset is public at https://huggingface.co/datasets/Tong-Zhao/XStereo.
Retrieval-Augmented Generation (RAG) has become the standard paradigm for grounding Large Language Model outputs in external knowledge. Lumer et al. presented the first systematic evaluation comparing vector-based agentic RAG against hierarchical node-based reasoning systems for financial document QA across 1,200 SEC filings, finding vector-based systems achieved a 68% win rate. Concurrently, the PageIndex framework reported 98.7% accuracy on FinanceBench through purely reasoning-based retrieval. This paper extends their work by: (i) implementing and evaluating three retrieval configurations: Vector RAG, Tree Reasoning, and the proposed Adaptive Hybrid Retrieval (AHR), on a small controlled corpus of financial, legal, and medical documents; (ii) introducing a four-tier query complexity benchmark; and (iii) employing LLM-as-judge evaluation with GPT-4o-mini. Experiments reveal that Tree Reasoning achieves the highest overall score (0.900), but no single paradigm dominates across all tiers: AHR scores highest on cross-reference queries (0.850), all three methods tie on multi-section queries (0.929), and Vector RAG scores highest on the single multi-document query (0.900). Vector RAG has the lowest mean latency (1.61 s against 3.40 s for Tree Reasoning). On the first 50 publicly released FinanceBench questions, using the evidence snippets supplied with the benchmark as the retrieval corpus, Tree Reasoning scores 0.938, Hybrid AHR 0.901, and Vector RAG 0.821. Because the configurations also differ in document access, generation prompts and output length limits, these differences cannot be attributed to retrieval architecture alone. In these preliminary results the adaptive router does not outperform fixed tree reasoning overall (0.845 vs. 0.900); they motivate a larger evaluation of when query-based routing helps, rather than establishing its benefit.
Frozen vision-language-action (VLA) policies generate temporally extended action chunks, but long-horizon manipulation remains vulnerable to accumulated execution error and visual aliasing across task stages. Successful rollouts provide useful corrective evidence, yet current frame retrieval can return progress-misaligned actions,while direct replay or time-domain fusion can overwrite the reactive structure of the policy proposal. We introduce Retrieve in Time, Correct in Frequency (RTCF), a training-free test-time correction framework that improves frozen VLA performance with low model-side overhead.RTCF separates which experience to retrieve from which part of its action to transfer. Progressive Memory Alignment (PMA) causally aligns the growing visual execution history with complete successful trajectories through incrementally updated monotonic frontiers, jointly identifying a relevant memory and the current aligned memory position without stage labels. From the aligned action chunk,RTCF transfers a coefficient-wise-clipped low-frequency residual on motion channels. Higher-frequency components and gripper decisions remain inherited from the frozen policy. Across four LIBERO suites and 2,000 episodes per condition, RTCF raises aggregate success from 86.4% to 88.4% and improves LIBERO-Long from 61.6% to 68.6%.These gains require no parameter updates, repeated VLA inference, or additional GPU resources: correction can be performed on the client CPU after a single policy invocation, and the median latencies sum to only 10.99 ms per action chunk
Shuhao Ye, Yufei Wei, Demao Wang, Shichao Zhai, Rong Xiong, Yue Wang
Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires instruction-consistent planning and reliable execution under collision constraints. Yet many hierarchical approaches optimize the planner while keeping execution fixed. We introduce MATCH, a framework that jointly learns a language-conditioned planner and a goal-conditioned primitive-action executor. An execution-aware topological graph represents start-dependent execution options and integrates executor value estimates with realized outcome memory, enabling the planner to select execution requests and refine their targets through bounded continuous offsets. A transition-aware dense macro reward balances ordered progress along the reference route against execution residual, encouraging executable requests without substituting local success for instruction following. A staged curriculum culminates in synchronized on-policy updates, with the executor learning on planner-generated requests and the planner adapting its requests to the executor's current behavior. With 0.5B parameters, MATCH achieves state-of-the-art performance on the R2R-CE and RxR-CE benchmarks. Preliminary real-robot deployments further demonstrate its practical potential.
Ke Jiang, Wen Jiang, Yoshinobu Kawahara, Xiaoyang Tan
We aim to address the problem of Out-of-Distribution (OOD) Mode Averaging, a critical problem that emerges when distilling Flow Matching (FM) based behavior policies in offline Reinforcement Learning (RL): When learning over multi-modal datasets, standard distillation inadvertently forces the policy to interpolate across different behavioral modes, causing the generated actions to collapse into invalid, OOD regions. To resolve this, we propose Value-Rectified Distillation (VRD), a novel framework that reformulates offline policy distillation as a value-guided generative trajectory alignment problem. By employing a dynamic coupling mechanism, VRD actively rectifies flow dynamics to explicitly decouple distinct behavioral modes, cleanly isolating high-value actions. Specifically, we instantiate VRD through two complementary algorithms: VRD-Q, which utilizes value-quantile behavior distillation to statistically filter out low-value behaviors, and VRD-R, which reorganizes the latent space to geometrically isolate high-value generative trajectories from the FM-based behavior policy. Extensive empirical evaluations demonstrate that VRD improves existing generative baselines across diverse continuous control and planning tasks on the D4RL, OGBench, and Minari benchmarks, especially over those multi-modal, non-expert datasets.
Asher Tempest Arya, Rajan Maghera, Nicholas Wu Jiang, Federico Mora, Aren A. Babikian, Marsha Chechik
Self-adaptive systems are designed to accommodate variants of their environment, which form a family of instances whose uncertainty is captured by probabilistic models, and must meet probabilistic requirements on each instance. Within such a family, changes in size and structure complicate the fundamental adaptation decision: whether to retain, reuse, or construct a new controller, since controllers are often synthesized for and specific to an instance. Large language models (LLMs) have recently been used to write reusable controllers, but existing approaches largely target deterministic domains, and probabilistic model checking of their output remains limited to preliminary single-instance studies. In this paper, we propose a verifier-guided framework for controller reuse with explicit support for families of environments. The framework introduces a novel combination of LLM-written controllers with probabilistic model checking to provide per-instance guarantees for probabilistic requirements. We evaluate our approach using three LLMs on three benchmarks, assessing its effectiveness and cost with respect to baseline implementations, the distribution of adaptation decisions, and the impact of individual framework components. On grid worlds, LLM-written rule lists are verified on about 90% of held-out instances, against at most 77% for the baselines, and verifying a stored rule list is 15 to 103 times faster than per-instance synthesis. Reuse serves most episodes at a small fraction of the cost of generation or per-instance synthesis, and model-checking feedback increases verified coverage over independent restarts.
Artificial intelligence (AI) technology has gradually been integrated into automated vehicles. However, how this technology could systematically support takeover transitions in SAE Level 3 automated vehicles remains unknown, even though this level may remain a major form of driving automation in the near future. To address this, we implemented the three AI roles proposed by the triadic Human-AI collaboration framework (Advisor, Co-pilot, and Guardian) as potential authority-ability configurations for AI agents within an automated system. We then examined their interactions with explanation type (why and action) and directional semantics (ipsilateral and contralateral) in an automated driving simulator study with 24 participants. Results showed that, across the three AI roles, Advisor had the shortest decision-making time, followed by Guardian and Co-pilot. Advisor and Guardian were associated with higher decision-making accuracy and higher satisfaction ratings than Co-pilot. Guardian was associated with the lowest workload, followed by Advisor and Co-pilot. The effect of explanation type on decision-making time depended on AI role. Action explanations were faster under Advisor, whereas why explanations were faster under Co-pilot. For directional semantics, ipsilateral semantics were associated with shorter decision-making time than contralateral semantics. Overall, these findings provide preliminary guidance for designing AI-role authority-ability configurations and their associated speech-based takeover messages.
Scaling visual reinforcement learning (RL) with GPU-accelerated simulation is computationally expensive due to rendering and visual-policy inference costs. Consequently, two-stage teacher--student distillation is commonly used to train visual policies, but introduces an imitation gap. In this preliminary study, we introduce \echomethod{}, \textbf{a single-stage off-policy RL framework that scales experience collection without proportionally increasing visual computation}. Through \textbf{inverse distillation}, a state-based auxiliary policy imitates the evolving visual policy and collects inexpensive, unrendered experience. Echo leverages this experience for off-policy value learning, directly improving the visual policy through a shared privileged critic. We instantiate \echomethod{} with FastTD3 and evaluate it on three visual control tasks and two dexterous manipulation tasks in Genesis. Relative to \sdpgmethod{} under the evaluated configurations, Echo reduces time to reference returns by an average of \textbf{60\% across the three locomotion tasks} and \textbf{56\% across both hand tasks}, while improving peak mean returns by \textbf{62\% and 12\%}, respectively. Both hand tasks also achieve higher mean returns at matched simulator-transition budgets. These initial results suggest that scaling off-policy experience is a promising approach to efficient direct visual RL.
Han Wang, Jingyuan Bao, Juntao Wu, Saiao Zhou, Yuman Nie
Event cameras, spiking cochleas and similar sensors emit asynchronous events, yet most learning systems first bin them into frames or packets, so the output depends on how the stream was sliced. Networks whose state is updated exactly at every event and evolves in closed form between events are invariant to this slicing. We ask what more makes the output (i) independent of the processing order of simultaneous events and (ii) continuous in the time stamps, even when two events cross in time, while (iii) staying sensitive to temporal order. For arbitrary nonlinear event models we prove that (i) and (ii) are each equivalent to pairwise commutation of the event updates, and that once updates commute, all order dependence comes from their non-commutation with the inter-event dynamics and vanishes linearly in the time lag. This identifies a class of time-mediated non-commutative (TM) models and yields a resolution-robustness bound for any model. We construct the minimal TM layer, a learnable, provably Lipschitz generalization of the Hassenstein-Reichardt correlator; prove that no single additive layer can uniformly represent ordered pair interactions, whereas a three-dimensional TM state can; show that each TM layer adds two levels of temporal nesting versus one for additive layers; and give a single-layer higher-order construction (TM-k) and a stacking rule preserving all three properties. We instantiate these results as the Clock-Free Event (CFE) layer, linear in the number of events, give a topology-free variant for temporal point processes with closed-form likelihoods, and specify a preregistered clock-robustness protocol with a physical-time threat model for spike-retiming attacks. In preliminary development-set experiments, the TM state beats an otherwise identical additive state by 3.5-9.1 points on DVS128 Gesture and by 24.5 and 30.6 points on SHD and Speech Commands.
Document image binarization must preserve thin, broken, and low-contrast strokes against degraded backgrounds; Mamba-based state space models have so far been explored only preliminarily for it. We measure what state-space propagation does to document features and find that it does not attenuate foreground responses: every region gains amplitude, but the background gain is 1.8 times the stroke gain, compressing the foreground-background amplitude contrast from 1.86 to 1.03. This compression scales monotonically with the effective receptive field, suggesting it is not specific to state space models. Guided by this, we propose DeepMine-Mamba, whose Anti-Dilution Gate computes its modulation from the propagation-induced feature difference and confines it to stroke regions by a learned stroke prior. Under a strict leave-one-year-out protocol on DIBCO/H-DIBCO with no external training data it is competitive with recent transformer- and gated-convolution baselines; because published protocols differ and are often unstated, we report protocol-controlled evidence separately from cross-paper comparison. Ablations under a fixed objective show that the gate recovers stroke-background discriminability and improves all four metrics, including the two absent from the objective.
Approximate Dynamic Programming (ADP) enables online control-law adaptation through adaptive critic methods. A safety challenge in applying ADP to angle-of-attack (AoA) tracking control is that an overly sensitive neural network (NN) controller may generate oscillatory or saturated control actions under nonlinear dynamics, potentially compromising flight stability and increasing actuator stress. To address this challenge, this paper proposes two innovations: (1) the actuator rate constraints are enforced within a an Action-Increment-Constrained Policy Optimization (AI-CPO) framework inspired by safe reinforcement learning (RL), in which a primal-dual approach adaptively adjusts the penalty weight to address actuator rate constraints. This optimization is solved online using adaptive Temporally Smoothed Incremental Model-Based Heuristic Dynamic Programming (TS-IHDP) for smooth and computationally efficient online adaptive control; and (2) a low-pass filter integrated into the cascaded NN architecture to attenuate high-frequency pitch-rate commands while preserving the Markov property during online learning by exploiting the hierarchical actor structure. Compared with the IHDP baseline, simulations using a longitudinal air vehicle dynamics model demonstrate that TS-IHDP improves control smoothness and tracking performance, reduces system oscillations, and enhances the trained policy's robustness to model uncertainties.
The spatial chromatic model (SCM) is a novel entity-oriented spatial data model proposed in recent years. Spatial tessellations formed by SCM have been applied in preliminary analyses of spatial point pattern recognition,spatial topology, and Voronoi diagram generation. Unlike previous spatial tessellation models, a key feature of SCM is that each subspace (cell) possesses a chromatic code, which serves as the foundation for various theoretical analyses and applications of SCM. The uniqueness of cell cluster codes in SCM constitutes an important property of the model. Previous studies have demonstrated the uniqueness of the chromatic codes of 2-cell and 3-cell connected disjoint clusters. Building on this analysis of connected cluster code characteristics, this paper proves the uniqueness of the chromatic codes of 4-cell connected disjoint clusters. The proof results and the new concepts introduced in this study help further refine the spatial chromatic model and provide a theoretical foundation for its subsequent applications.
Griffin Farrow, Lily Sijia Li, Jack Johnson, Tingyan Wang, Philip Torr, William Bolton, Fabio J. Fehr
Hallucinations can undermine clinician trust in LLMs, making it important that evaluation methods capture clinically relevant errors. Rubric-based evaluation has become the leading approach for assessing LLMs in medicine, but it is unclear whether rubric scores reflect such errors. We first study this in a controlled setting using MedHallu, finding that more specific rubrics better distinguish correct from hallucinated responses. To test this systematically, we develop a taxonomy of medical hallucination types and a clinician-validated error-injection pipeline that creates matched correct and error-injected responses. Across HealthBench, HealthBench Professional, and LiveMedBench, our clinically relevant hallucinations are missed by rubrics, often leaving scores unchanged. We find that rubrics are most effective when explicitly checking facts, and are less effective for additional or unexpected errors they do not anticipate. A preliminary retrieval-based factuality check recovers some of the rubric-blind errors, suggesting a complementary approach. These findings reveal systematic blind spots in current medical evaluation of LLMs and suggest that rubric scores alone are insufficient to establish clinical reliability, potentially undermining clinician trust and confidence in clinical deployment.
Modern Network Intrusion Detection Systems (NIDS) generate vast volumes of low-level alerts that remain semantically fragmented, requiring labor-intensive manual correlation with high-level adversarial behaviors. Existing automation, namely rule-based systems and machine learning classifiers, has critical limitations: rule-based approaches fail to adapt to novel attack variations, while machine learning methods lack contextual awareness and treat tactic-technique (TT) mapping as syntactic matching rather than reasoning. Although Large Language Models (LLMs) show promise in cybersecurity, preliminary experiments reveal that existing LLM-based methods frequently hallucinate technique-tactic pairs or produce decontextualized mappings due to single-step classification. We introduce RHINO, a framework that decomposes LLM-based attack analysis into three structured phases: (1) behavioral abstraction, translating raw logs into contextualized narratives; (2) partitioned inference over the ATT&CK tactic space, generating candidate techniques by evaluating behavioral evidence against MITRE ATT&CK knowledge; and (3) knowledge-grounded refinement, cross-referencing predictions with official MITRE definitions to reduce hallucinations. We evaluate RHINO on three benchmarks (DAPT2020, CICIDS2017, IoT23) across four backbone models (ChatGPT-4o, Gemini 2.5 Flash, Claude Sonnet 4, and DeepSeek V3). Under a scenario-documented single-label formulation covering 11 distinct techniques, RHINO achieves an average top-1 accuracy of 87.34% under micro-averaging and 63.77% under macro-averaging, surpassing the strongest baseline by 16.78 and 13.60 points respectively. These results show that structured LLM reasoning can effectively translate low-level network observations into high-level adversarial behaviors.
Yesung Cho, Dongmyung Shin, Sujeong Hong, Jooyeon Lee, Seongmin Park, Geongyu Lee, Won Young Park, Bongjin Park 等 10 位作者
Prostate cancer is among the most frequently diagnosed malignancies in men worldwide. However, precise prediction of biochemical recurrence (BCR) after radical prostatectomy remains challenging. Here, we propose a computationally efficient multi section whole slide image analysis framework designed to capture the whole gland tumor landscape. We curated a large scale dataset comprising 23,451 slides from 789 patients and systematically optimized patch and slide sub sampling to substantially reduce the computational cost of training and inference. Under this efficient configuration, the framework achieved strong predictive performance for 1- and 2-year BCR, with discrimination and clinical net benefit comparable to or exceeding those of established clinical benchmarks. In multivariable Cox proportional hazards analysis, the AI derived risk score remained an independent prognostic factor among the covariates examined, and its integration with clinical variables further improved prognostic performance. External validation in an independent cohort provided preliminary evidence of transferability. Finally, attention-dispersion analysis showed that the model drew prognostic information from multiple sections, consistent with the multifocal nature of prostate cancer. Collectively, these findings support the potential of multi section slide analysis as a scalable approach for postoperative BCR risk assessment in prostate cancer.