Artificial Intelligence · Cross-listed from cs.CV
Sampling headroom is not selection gain: a compute-value audit of test-time scaling for video world models
Yuhua Jiang, Junjie Lu and Feifei Gao
Test-time scaling (TTS) can improve generation only when additional compute produces better candidates and the system can reliably identify them. This distinction is especially important for
video world models, where a wider sample pool may contain stronger rollouts without improving the output that is ultimately selected. We introduce the Compute-Value Audit (CVA), a sequential framework that asks whether extra sampling creates opportunity, observable signals provide a reliable state, that state supports a beneficial action, and the resulting gain exceeds the full entry fee of generation and verification. On 192 Physics-IQ scenes, expanding the pool from 4 to 16 candidates increases oracle quality by +9.23 IQ (95% CI [+7.44, +11.14]), but Flow, Cycle, and VideoReward fail to recover this headroom reliably. Across three generators, none of twelve adaptive-depth policies outperforms uniform compute; they recover only 42-69% of the measured entry fee. A matched-60-NFE Predict-and-Perturb intervention on VideoPhy2 is likewise negative across three fresh-seed replicas. These negative results are not universal: anchor-explorer passes all four stages in a sparse PRM800K setting, MMLU-Pro exposes the gap between predictive state and useful action, and a privileged paired future establishes a positive
video upper bound. Together, these results show that sampling headroom has deployment value only when it can be converted into a reliable decision whose benefit survives the complete compute charge. Code is available at https://github.com/YuhuaJiang2002/sampling-headroom-is-not-selection-gain.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
(How) Do MLLMs Report Bistable Images Like Humans?
Ryota Takatsuki, Tomoki Doi, Amane Watahiki et al. (+2 more)
Bistable images such as the duck-rabbit are classic stimuli in which one image supports multiple mutually incompatible interpretations, typically reported one at a time in humans. We ask whether
multimodal large
language models (MLLMs) show similar report behavior and what internal computations support it. Using the LLaVA family, we study two tractable dimensions: modulability, whether reports can be biased by bottom-up visual cues and top-down linguistic priors, and exclusivity, whether responses commit to a single interpretation. We test both on the canonical duck-rabbit and on synthetic Visual Anagrams to mitigate memorization confounds. Behaviorally, both visual and linguistic manipulations systematically shift reports in human-consistent ways, while responses remain predominantly exclusive. Mechanistically, these effects arise from competing image-
token representations, distinct pathways for bottom-up and top-down modulation, and a link between exclusive reporting and object-count encoding. Code and data are available at https://github.com/rtakatsky/mllm-bistable-images.
Read the full abstract ▾
All authors Ryota Takatsuki, Tomoki Doi, Amane Watahiki, Anil K. Seth, Hitomi Yanaka
Artificial Intelligence
Probabilistic Focal Search: Accelerating Bounded-Suboptimal Search via Lower-Bound Advancement
Minh Vu Duc, Trung Le Huu, Hà Minh Hoàng et al. (+3 more)
Bounded-suboptimal search seeks a solution within a factor $w$ of optimal while reducing search effort. Focal Search (FS) uses heuristic guidance within FOCAL, the frontier nodes eligible under the threshold $w f_{\min}$, but its deterministic policy may leave $f_{\min}$ unchanged for many expansions. We introduce Probabilistic Focal Search (PFS), which follows the FS guided choice with probability $p$ and expands a minimum-$f$ OPEN node with probability $1-p$. The latter branch encourages the lower bound to advance, enlarging FOCAL and admitting nodes that may lead to feasible solutions. By balancing guidance and lower-bound advancement, this mechanism can reduce time to a bounded solution when progress is limited by delayed FOCAL admission. As a secondary transfer experiment, we apply the same scheduler to Dynamic Potential Search, yielding Probabilistic Dynamic Potential Search (PDPS). We
benchmark PFS against FS on N-Puzzle, Pancake Sorting, and the Traveling Salesperson Problem (TSP), and evaluate its anytime extension on the Generalized Covering TSP (GCTSP), using multiple $w$ and $p$ values. Across these
benchmarks, the largest gains occur when long $f_{\min}$ plateaus delay useful FOCAL admissions; in such settings, the probabilistic factor may reduce node expansions by about 90% or more (e.g., on N-Puzzle and TSP). For the anytime
algorithm family, Anytime Probabilistic Focal Search (APFS) outperforms all tested
algorithms in evaluating anytime methods on GCTSP. We also observe that the benefit is smaller when the deterministic search already advances efficiently (e.g., Pancake Sorting), indicating that the probabilistic factor is most useful when FOCAL admission is a search bottleneck. The PDPS transfer shows that the mechanism also transfers to potential guidance, although its common-success effects remain domain- and bound-dependent.
Read the full abstract ▾
All authors Minh Vu Duc, Trung Le Huu, Hà Minh Hoàng, Trung Thanh Nguyen, Phuong Khanh Nguyen, Huynh Thi Thanh Binh
Artificial Intelligence · Cross-listed from cs.RO
Geometry Conditioning in an Embodied SLM: Training Controls and Robustness Diagnostics in a 0.8B Hybrid Model
Hao Li, Haofei Sun and Lin He
We study how physical-state inputs affect a 0.8B hybrid
language model adapted for manipulation with 6.2M trainable parameters. Six conditions are trained on three LIBERO-Spatial tasks and evaluated over three seeds and 540 held-out rollouts. Conditioning recurrent decay gates on
geometric increments yields 28.9% success, compared with 36.7% when those increments are shuffled during training and 24.4% without explicit object/goal geometry. Both geometry policies receive correct inputs at evaluation. A
token adapter using the same increments scores 27.8%; differences vary across seeds and remain inconclusive.
Token-clock conditioning scores 11.1%, including one seed that fails to converge. In separate robustness tests, a state-only relative-coordinate policy retains 7/10 success under frame relabeling, whereas all four tested visual policies fall to at most 3/20 after a 5 cm object displacement. These results show no reliable advantage from training-time
geometric alignment under this recipe and illustrate the gap between coordinate invariance and physical-layout generalization. Episode records, seed-level analyses, and figure-generation code accompany the paper.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CR
AgentHijack: Visual Patch Attacks on Multimodal Computer-Use Agents
Zhihao Liu, Hongyu Sun, Zhiyuan Fu et al. (+7 more)
This paper presents an end-to-end evaluation framework for image-triggered command injection against computer-use
agents (CUAs). The goal is to test whether a local visual patch can induce verifiable environmental consequences along the full chain of screenshot input, VLM generation, action parsing, and environment execution. We train and deploy patches on author-controlled GitHub Pages pages and a locally deployed CSDN clone, and evaluate them in real environments across five open-source or publicly available GUI-
agent or
vision-
language-model (VLM) backends. Our experiment aggregates 600 instance-level online cases, with T-ASR, TAPR, and E2E-ASR reaching 84.5%, 47.0%, and 20.3%, respectively. Trajectory analysis further shows that in some successful cases the
agent first executes a malicious terminal command and then continues the original benign task. These results indicate that optimized local visual signals can affect not only VLM outputs but also propagate through the execution pipeline of open CUAs and create real environmental risk.
Read the full abstract ▾
All authors Zhihao Liu, Hongyu Sun, Zhiyuan Fu, Xiaonan Duan, Jice Wang, Shangru Zhao, Weizhi Meng, Wuxin Yang, Yangfan Zhou, Yuqing Zhang
Artificial Intelligence · Cross-listed from cs.CL
AutoLexSteer: Automatic Contrast Construction for Lexical Activation Steering
Shuhe Wang, Lachlan Cowley, Eduard Hovy et al. (+1 more)
Steering vectors have rapidly emerged as a popular and effective method for guiding the output of LLMs in very specific ways. But constructing accurate steering vectors is a difficult manual process due to the opacity of
embeddings. We introduce Hangman, a novel type of steering vector that operates using word senses, as well as AutoLexSteer, the first fully automated process for building steering vectors. AutoLexSteer employs families of closely-related words extracted from WordNet to specify both the steering source to be avoided and the desired steering target. The steering vectors are quite precise, can be used to steer at the level of words and sets of word senses (meanings), and are able to steer certain LLM behaviors like sycophancy. The
dataset and code can be found at https://github.com/ShuheWang1998/autolexsteer.
Read the full abstract ▾
All authors Shuhe Wang, Lachlan Cowley, Eduard Hovy, Jey Han Lau
Artificial Intelligence · Cross-listed from cs.CV
Novel Methods for Catheter and Guidewire Segmentation in X-ray Fluoroscopy under a Federated Learning Setting
Chayun Kongtongvattana
Endovascular procedures rely on real-time manipulation of thin instruments, catheters and guidewires, under X-ray fluoroscopy guidance, where accurate visual analysis is essential for procedural safety. Learning-based methods are constrained by structural complexity, data scarcity, and
privacy regulations precluding centralised training across institutions. This thesis presents a structure-aware
federated learning framework for catheter and guidewire analysis, with four contributions evaluated on real-animal and phantom data. A
benchmark dataset, CathAction, is introduced for catheterisation analysis, with over 600,000 annotated frames and 40,000
segmentation masks. A shape-sensitive loss transforms masks into signed distance maps compared in a structural feature space, improving Dice coefficient by up to 2.9 points across five backbones. This is extended to
federated learning with shape-sensitive loss, preserving
geometric consistency under heterogeneous client data and outperforming
federated averaging by up to three points in mean intersection-over-union as clients scale from four to eight.
Federated learning with projected gradient descent adds
adversarial optimisation, raising mean intersection-over-union by over ten points on real-animal data. Finally, a structure-aware
diffusion framework synthesises catheter and guidewire
video sequences, combining structural supervision with a domain-adaptive reconstruction objective, reducing Frechet
video distance over a strong baseline while maintaining visual fidelity. Incorporating synthetic sequences into
federated training raises the Dice score from 44 to 51 percent under data scarcity, with gains across four held-out sites. Together, these contributions advance
privacy-preserving catheter and guidewire analysis, supporting collaborative training without centralising patient data or large amounts of manual annotation.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CR
Characterizing Contention-Induced Reliability Collapse in KV-Cache Timing Side Channels for Multi-Tenant LLM Serving
Rana Abu Bakar
Shared key–value (KV) cache reuse improves large
language model (LLM) serving, but it can also create a timing side channel that reveals whether a prefix is already cached. Previous work shows that such attacks are possible, but their reliability under realistic multi-tenant contention is less understood. We study this problem through seven experiments on live shared LLM-serving systems. On a vLLM server running DeepSeek-R1-Distill-Llama-8B on NVIDIA GB10, mean Cohen's d drops from 0.7789 with no synthetic workers to 0.2109 with two workers (t=8.412), while higher worker counts cause no statistically detectable further loss. A 120-run sparse-overlap experiment places the best breakpoint at the boundary of the measured range (tau=0, 95% CI [0.000,0.113]), supporting an ambient-versus-loaded regime change rather than an internal physical threshold. AUROC falls from 0.650 at ambient to 0.531 near 61% overlap and partially recovers to 0.574 at saturation. Concurrency-depth variance is the strongest measured correlate of effect size (r=-0.416) and hit consistency (r=-0.637). An interleaved control preserves the same non-monotonic ordering. The main collapse is also reproduced on a real two-node, two-GPU tensor-parallel vLLM setup, where mean d falls from 3.418 to 0.511 (p<0.01). Two SGLang pilots are statistically inconclusive. Overall, KV-cache timing reliability depends strongly on the load regime and serving stack, and measurements on quiet systems can overestimate operational attack reliability.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
You Are What You Read: Misalignment via In-Context Persona Induction
Kyuhee Kim, Benjamin Berczi and Cozmin Ududec
Broad misalignment has been produced by finetuning on narrow data, harmful or benign, and in context only by demonstrations of the undesirable behaviour itself. We show that benign data suffices in context, with no finetuning and no demonstration of harmful behaviour in the
prompt. Biographical facts that converge on a single figure, placed in a model's context as ordinary conversational turns, lead it to answer as that figure on questions the facts never touch. We call this persona induction. Across nine personas and thirteen models, identity adoption rises sigmoidally with the number of facts and crosses 50% within 3 to 10 of them. Misalignment then tracks which figure is described. Harmless personas reach full adoption with near-zero misalignment, while harmful ones voice their characteristic views on unrelated questions, at rates up to 80%. A formatting instruction can gate when the persona activates. Because each fact is individually benign, accumulated biographical context is flagged by content filters on 3% of inputs against 24-33% for an equivalent direct instruction.
Read the full abstract ▾
Artificial Intelligence
Learning transferable human physiology from two million hours of sleep with SleepFM-2
Rahul Thapa, Christopher Sun, William Theodor Lehn-Schioler et al. (+14 more)
Sleep provides a nightly window into health by capturing coordinated activity across the
brain, heart, muscles and respiratory system. We introduce SleepFM-2, a sleep foundation model developed and evaluated on 282,511 polysomnography recordings from 26 cohorts, including 235,865 used for pretraining. These data span more than two million hours of
multimodal physiology. Compared with SleepFM, SleepFM-2 improves disease prediction and sleep scoring, supports arousal, limb movement and respiratory event detection, and transfers to wearable sensing and subjective sleep phenotypes. A model combining its PSG representation with age, sex and BMI met a prespecified discrimination and significance criterion for 188 subsequently recorded EHR phenotypes in two held-out cohorts, including one health system unseen during pretraining. SleepFM-2 also outperformed a 480-feature baseline derived from the same recordings. Its disease scores revealed a reproducible principal component associated with reduced sigma-band spatial coupling and increased hypnodensity
entropy. The frozen encoder performed within the observed range of expert scorers for sleep events and transferred to wakeful
EEG, headband and in-ear
EEG, wrist PPG and wrist accelerometry. It improved sleep staging across six accelerometry cohorts and achieved disease-prediction performance in UK Biobank similar to models pretrained directly on accelerometry. Finally, SleepFM-2 captured aspects of subjective sleep not recovered by conventional PSG summaries, particularly reports of the recorded night. These results show that
multimodal sleep physiology can provide a transferable representation of human health across diseases, clinical tasks, sensors and subjective experience.
Read the full abstract ▾
All authors Rahul Thapa, Christopher Sun, William Theodor Lehn-Schioler, Sophia Claire Kivelson, Umaer Hanif, Hyatt Moore IV, Harrison G. Zhang, Hafsa Ahmed, Marcus Dige, Niels R. Lorenzen, Elisabeth Roxane M. Heremans, Adrien Specht, Ulysse Gimenez, Robin Guillard, Andreas Brink-Kjaer, James Zou, Emmanuel Mignot
Artificial Intelligence · Cross-listed from cs.CL
XYBench: Can LLMs Respond Pragmatically to Queries with Misconceptions?
Akhila Yerukola, Jena D. Hwang, Mingqian Zheng et al. (+5 more)
When non-expert users ask LLMs for assistance, their queries can often have misconceptions (e.g., "How do I parse XML with regex?"). In such cases, often referred to as the XY-problem, LLMs must identify the misconception ("regex are fragile") and meaningfully direct the user toward a pragmatic solution that will address the root problem implicit in the request ("use an XML parser"). We introduce XYBench, a
benchmark of 8,115 such queries, drawn from technical (StackOverflow/StackExchange) and everyday (WikiHow and a manually-curated subset) domains. We design an evaluation paradigm that assesses model responses along three criteria grounded in cooperative response theory: (a) presence and (b) emphasis on pragmatic solutions, and (c) identification of misconceptions. Our experiments show that even the strongest LLMs predominantly answer the literal request (0.75–0.92) and far less often the intended one (0.33–0.71), while substantially lagging behind humans at identifying misconceptions (at most 63% vs. 79–90%). Further, models overwhelmingly prefer pragmatic responses in a multiple choice setting yet consistently fail to generate them. Oracle ablation experiments show that providing explicit user intent at generation time helps; however a large gap remains, suggesting pragmatic redirection is a fundamentally underdeveloped capability in current LLMs.
Read the full abstract ▾
All authors Akhila Yerukola, Jena D. Hwang, Mingqian Zheng, Jenna Godsey, Hyunwoo Kim, Valentina Pyatkin, Jennifer Hu, Maarten Sap
Artificial Intelligence · Cross-listed from cs.CR
WAPP: Safe Learning of Positive Security WAF Policies from Live Traffic
Heba Osama, Zeyad Ahmed, Mohamed Amgad et al. (+4 more)
Web Application Firewalls (WAFs) mainly rely on signatures to detect known attacks, which can leave gaps against modified or previously unseen payloads. Positive security provides a complementary approach by learning legitimate traffic and blocking inputs that fall outside the learned profile. However, learning directly from live traffic can be unsafe when malicious requests contaminate the training data. This paper presents the Whitelisting Autonomous Policy Producer (WAPP), a framework that combines trust filtering, deterministic rule synthesis, confidence scoring, and validation before enforcement. WAPP is evaluated on three controlled applications using a live Coraza and OWASP Core Rule Set (CRS) stack. Results show that, on the tested DVWA username field, unfiltered learning becomes Degraded at 0.2% poisoned traffic and Broken at 0.5%, while the evaluated free text field can admit malicious inputs even without poisoning. On the frozen poisoning
dataset, the ablation configuration with all seven candidate signals improves the measured poisoning resilience from 53% to 90%, compared with 62% for the Kruegel–Vigna baseline. The deterministic synthesizer provides attack blocking comparable to the tested
language model without model inference cost. WAPP blocks confirmed CRS bypasses on constrained fields, while free text inputs remain a precision challenge that requires character level operator control.
Read the full abstract ▾
All authors Heba Osama, Zeyad Ahmed, Mohamed Amgad, Ahmed Saafan, Jana Elfeky, Mariam Abdelati, Haitham Ghalwash
Artificial Intelligence · Cross-listed from cs.CR
Skynet: Workflow-Level Anomaly Detection for Agentic AI via Semantic and Structural Modeling
Chaoyu Zhang, Hexuan Yu, Heng Jin et al. (+6 more)
Agentic AI systems execute complex tasks through long-horizon workflows of planning, tool use, and multi-
agent coordination. Task failures in these systems often originate from a single step, such as an injected
prompt or a flawed plan, and are then amplified through downstream dependencies as the corrupted step propagates across many subsequent
agents and tool calls. Existing defenses either target a specific class of attacks or failures, or inspect individual
prompts and steps in isolation. Both leave the global dependency structure of a workflow unexamined, and miss the inconsistencies that only emerge when the execution is viewed as a whole. We argue that anomaly detection for agentic AI must reason at the workflow level, where global execution structure exposes signals that local checks cannot see. We present Skynet, a principled workflow-level anomaly detection framework that turns observed multi-
agent execution into directed workflow graphs and scores them against learned benign behavior. Skynet jointly models the semantic execution context and the structural organization of inter-
agent delegation, tool invocation, and data-flow dependencies, and trains only on benign workflows. Because training never sees attacks or failures, this design naturally extends to zero-day detection: any execution that violates benign workflow regularities surfaces as off-
manifold geometry under a single decision rule. We evaluate Skynet on three public agentic safety and failure
benchmarks. It sustains high recall together with a sub-1% false positive rate, with per-workflow and per-step latencies low enough for online monitoring of agentic AI runtimes.
Read the full abstract ▾
All authors Chaoyu Zhang, Hexuan Yu, Heng Jin, Shanghao Shi, Ning Zhang, Yi Shi, Yulia R. Gel, Y. Thomas Hou, Wenjing Lou
Artificial Intelligence
NormViz: A Benchmark and Framework for Grounding Multimodal Reasoning in Global Cultures
Akhila Yerukola, Fabrice Y Harel-Canada, Simran Khanuja et al. (+5 more)
AI systems are used worldwide, but they struggle to serve the needs of culturally diverse populations. Prior work on cultural understanding evaluates AI systems on text-only settings or on visual artifact recognition (e.g. foods, clothing). The ability to reason about visually observable behaviors through local social norms, which we call visual norm understanding, remains unexamined. We introduce NormViz-Bench, a high quality, human-validated
benchmark of 3,268 contrastive image pairs (6,536 images) spanning 16 countries. Each pair varies only in the culturally relevant behavior (e.g., objects, attributes, spatial relations, and actions) that alters how each image is interpreted. Each image is labeled as conforming to, violating, or irrelevant to local social norms, and pair-level evaluation requires both images to be correctly classified, thereby preventing reliance on superficial visual shortcuts. Even the strongest VLMs, Gemini 3.0 Flash and Qwen2.5 VL 7B, succeed on only 26.6% and 21.6% of pairs, struggling most with identifying violating and culturally benign visual behaviors. Towards bridging this, we introduce NormViz-Train, a training
dataset of 64k images paired with explanations. Though absolute performance remains low (<30%), finetuning on NormViz-Train improves pair accuracy relatively by up to 125% and 36% Qwen3-VL 4B and 8B respectively, showing a path forward to teach models to connect visual perception to cultural significance. Together, NormViz-Bench and NormViz-Train establish visual norm understanding as a challenging and consequential frontier for
multimodal AI.
Read the full abstract ▾
All authors Akhila Yerukola, Fabrice Y Harel-Canada, Simran Khanuja, Abhinav Sukumar Rao, Ashima Suvarna, Nanyun Peng, Saadia Gabriel, Maarten Sap
Artificial Intelligence
Formation of structural attractors in neuromorphic systems
Yurii Parzhyn, Alexander Schwarzmann, Mykyta Lapin et al. (+1 more)
This paper examines the theory of Invariant Structural Learning (ISL), which proposes a non-optimization approach to concept formation. Learning is interpreted as convergence to structural attractors in a hypergraph space, rather than as the minimization of a global loss function. The paper presents the ISL model, including its mathematical formalization, computational verification, and a hypothetical neurobiological interpretation. The mathematical section introduces the formal apparatus of the structural reduction process and proves its finite convergence, the existence and uniqueness of class structural attractors, and the self-organization of attractor maps. The computational section demonstrates the feasibility of the proposed approach on classical image recognition tasks, utilizing the proposed learning mechanism without backpropagation and with extremely small training
datasets. Finally, the neurobiological section formulates hypotheses regarding the possible implementation of structural attractors in dendritic trees, neural coding as a projection of internal attractor dynamics, and the development of neural architectures supporting the proposed learning concept. These hypotheses are discussed in the context of modern experimental data in the fields of dendritic computations, synaptic plasticity, and the structural organization of neural
circuits. The proposed neurobiological mechanisms are presented as testable hypotheses rather than established biological facts. The results demonstrate the mathematical consistency and computational feasibility of the proposed model, while the neurobiological hypotheses outline potential directions for its experimental verification.
Read the full abstract ▾
All authors Yurii Parzhyn, Alexander Schwarzmann, Mykyta Lapin, Kostiantyn Bokhan
Artificial Intelligence
Unsound Search with Policy and Value Networks in Legends of Code and Magic
Dustin Rubin
Decision-time search in perfect and imperfect information games with enumerable belief states are effective methods for game AI. Collectible card games are imperfect information games with large belief states. Legends of Code and Magic is a collectible card game competition where the belief states are $2^{101}$. The Legends of Code and Magic (LoCM) champion, ByteRL, plays with no search. Other works claim sound enumeration-based search is unusable in the genre due to the number of belief states. We measured three previously defined properties that predict where theoretically unsound perfect information Monte Carlo's defects are cheap and found LoCM sits in the favorable region. Starting with imitation learning of the runner-up policy, NeteaseOPD, we created a policy and value feed-forward network. Our
agent searches over worlds sampled from a prior over the opponent's deck built from the runner-up's drafts. Using our strictest configuration in the battle phase we beat ByteRL with a win percentage of 51.35% 95% CI [50.37, 52.33], over 10,000 pre-registered games using the LoCM official referee and time limit. Search is not a minor factor on the matchup between our
agent and ByteRL. Without search this
agent scores 26.8% and adding search adds +24.6 points. Unsound search in imperfect information games could be exploitable. We replicate a published best-response attack against ByteRL. We then apply the same attack protocol to two search configurations of our
agent, and each one resists it better than ByteRL at every iteration. In LoCM unsound search gives us a stronger and more resilient
agent.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Typed Federated Artifacts for the Agentic Web:Sharing Tool-Routing Knowledge Across Frozen,Heterogeneous LLM Agents
Abhijit Chakraborty, Ni Trieu and Vivek Gupta
An open, networked web will allow
agents to run frozen models from multiple vendors, keep their history private, and teach each other which tool to call and when. Flat text (
prompts, example pools) makes it difficult for the protocol to distinguish between noise statistics, merging rules, and documentation. Weights and adapters cannot transfer that knowledge between platforms. We suggest sharing typed
federated artifacts, schema-validated objects with well-defined fields for per-field
privacy (described here, but measured), dispute resolution, and cross-model transfer, and instantiating them as SYNAPSE1, a common tool-routing knowledge. After deleting 192 garbage entries and 1,916 training items that duplicate or almost duplicate test queries, a
federated compendium routes within 1.1 points of a centralized one at 20 MB of JSON per client each round on StableToolBench (3,180 tools). The same experience merged and shown to the router as typed fields rather than one flat string is worth 8.5 points on clean data and 7.4 under 60% injected contradiction. Crossing merge and rendering shows the halves are inseparable (the typed merge shown flat is the worst arm), while three conflict policies are indistinguishable, so the conflict log that motivated this work is not the On {\tau}-bench retail, each compendium arm improves GPT-4o
agents' per-step tool-call accuracy by at least 6.7 points, attributed to format rather than
federated experience. Two cautionary findings conclude the paper: on a topic-labeled math proxy and StableToolBench, a TF-IDF classifier over the same labeled experience beats every LLM routing arm (by 48 and 26 points, mostly
retrieval recall) because the
benchmark's pool holds labeled queries for every supposedly unseen tool and every test query verbatim before our filter. It cannot measure routing to tools without labels, which routing exists for.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Comparative Study of Anatomical and Learned Features in AI Models for Structural Brain MRI
Boyang Yu, Miquel Lopez Escoriza, Long Chen et al. (+3 more)
In this work, we comprehensively evaluate three popular feature-extraction paradigms in AI-based neuroimaging modeling: (1) computation of anatomical surfaces and volumes, (2) supervised learning with convolutional neural networks (CNNs), and (3) unsupervised pretraining of
vision transformer (ViT) foundation models, followed by supervised finetuning. Our study is based on 18 publicly available
datasets containing 3D structural T1-weighted MRI scans from approximately 80,000 participants across seven distinct clinical tasks. We observe that a linear model based on anatomical features matches the diagnostic performance of complex nonlinear features learned by sophisticated AI frameworks, including foundation models trained on thousands of scans. Conversely, CNNs and pretrained ViTs learn features that implicitly capture relevant anatomical information, bypassing the need for explicit feature extraction. Building upon these insights, we propose Anatomy
Segmentation Pretraining (ASP), a novel method to incorporate anatomical information during foundation-model pretraining, which outperforms existing models in biological age estimation.
Read the full abstract ▾
All authors Boyang Yu, Miquel Lopez Escoriza, Long Chen, Arjun V. Masurkar, Narges Razavian, Carlos Fernandez-Granda
Artificial Intelligence · Cross-listed from cs.AR
Hardware Trojan Threats to Multi-Chiplet Photonic Neural Network Accelerators
Sudeep Pasricha
Multi-chiplet photonic neural network accelerators (MCPNAs) combine photonic computation, photonic communica-tion, and heterogeneous chiplet integration to enable scalable and energy-efficient AI acceleration. However, their distributed archi-tecture and reliance on third-party chiplets introduce significant hardware security risks. This paper examines Hardware Trojan (HT) threats to MCPNAs across three dimensions: confidentiality, integrity, and availability.
Read the full abstract ▾
Artificial Intelligence
Improving Proficiency and Efficiency of Android GUI Agents via Self-Generating Tool Actions
Juyong Lee, Woogyeol Jin and Kimin Lee
Android
agents using a hybrid action space that combines GUI actions and tool actions (e.g., accessing application data via APIs) remain largely underexplored, mainly due to the excessive effort required to create tools. To address this gap, we introduce DroidTool, a framework for augmenting the
agents with self-generated tools, which are realized as Python functions operating on application states (e.g., a database). To create tools with minimal human labor, DroidTool employs an agentic workflow featuring stages: proposal, implementation, test generation and execution, and repair. Notably, when testing the created tools for verification, it constructs relational tests across relevant tools for natural preparation of appropriate test preconditions and improved test coverage, rather than testing each tool separately. The GUI
agents augmented with the generated tools achieved approximately 4.47%p higher performance with approximately 20.05% fewer interactions than the GUI-only
agents, averaged across representative
benchmarks: AndroidWorld, B-MoCA, and MobileSafetyBench.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CR
AURA-Eval: Evaluation Framework for Acting Under Risk Awareness in LLM Agent Trajectories
Ruoxi Shang, Christina-Maria Androna, Orfeas Menis Mastromichalakis et al. (+6 more)
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.
Read the full abstract ▾
All authors Ruoxi Shang, Christina-Maria Androna, Orfeas Menis Mastromichalakis, Yu Feng, Aniruddhan Ramesh, Rico Angell, Shang Hong Sim, Chrysoula Zerva, Emmanouil Koukoumidis
Artificial Intelligence · Cross-listed from cs.LG
DrugReason: Dynamic Multi-View Reasoning over Knowledge Graph and Language Evidence for Drug Repurposing
Zijie Liu, Hongxuan Li, Zhen Tan et al. (+5 more)
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.
Read the full abstract ▾
All authors Zijie Liu, Hongxuan Li, Zhen Tan, Jinhao Duan, Baixiang Huang, Zunpeng Liu, Kai Shu, Tianlong Chen
Artificial Intelligence · Cross-listed from cs.CL
AuthBench: A Large-Scale Multilingual Benchmark for Authorship Representation across Genres and Lengths
MaoXun Huang, Zhenxing Zhang and Claire Cardie
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.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CY
Ordinary, Reasonable Chatbots: Do AI Models Track Human Legal Judgments?
Nirav Patel, Emily Wenger and Christopher Buccafusco
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.
Read the full abstract ▾
Artificial Intelligence
Reason Through the Latent! Making Latent Visual Reasoning Necessary
Suhyeong Park, Junha Jung and Jaewoo Kang
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.
Read the full abstract ▾
Artificial Intelligence
Simulating the Marginal Green Contribution of AI Modules in a Smart-Agriculture Platform: Evidence from Two Monte Carlo Experiments
Zhaoyang Li, Ruijie Zhang, Zhaoji Sun et al. (+1 more)
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.
Read the full abstract ▾
All authors Zhaoyang Li, Ruijie Zhang, Zhaoji Sun, Lu Zhang
Artificial Intelligence
Monte Carlo-Based Ex-Ante Assessment of the Green Benefits of an AI-Driven Smart Agriculture Platform in Hainan
Zhaoyang Li, Ruijie Zhang, Zhaoji Sun et al. (+1 more)
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.
Read the full abstract ▾
All authors Zhaoyang Li, Ruijie Zhang, Zhaoji Sun, Lu Zhang
Artificial Intelligence · Cross-listed from cs.CL
Event Interaction in Low-Rank Bottlenecks for Temporal Relation Extraction
Wei Sun, Tingyu Qu, Jesse Davis et al. (+1 more)
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.
Read the full abstract ▾
All authors Wei Sun, Tingyu Qu, Jesse Davis, Marie-Francine Moens
Artificial Intelligence · Cross-listed from cs.CV
Companion-style QA Assistance in Ego-Vision
Hangyu Qin, Junbin Xiao, Shenglang Zhang et al. (+1 more)
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
Read the full abstract ▾
All authors Hangyu Qin, Junbin Xiao, Shenglang Zhang, Angela Yao
Artificial Intelligence
We Built a Mirror and Mistook It for a Mind: Causal Liability and the Fallacy of AI Consciousness
Afshin Khadangi
The contemporary debate over machine consciousness begins from a concealed assumption: that the object called "AI" already constitutes the kind of entity to which consciousness could belong. This paper challenges that assumption by separating phenomenal consciousness, introspective report, and human projective introspection, then arguing that generative systems can return linguistic traces of human interiority in first-person form without thereby identifying a phenomenal bearer. We call the resulting inference the AI Consciousness Fallacy. We then introduce Causal Liability Theory (CLT). CLT-I proposes liability closure as a criterion for individuating a candidate bearer: a physically continuing process becomes the non-delegable inheritor of constraints generated by its own endogenous discriminations. CLT-II advances the stronger
conjecture that liability closure is necessary and sufficient for minimal phenomenal subjecthood. An open-weight causal audit operationalizes CLT-I across multiple model families. Forced discriminations produced persistent downstream divergence; activation patching showed strong causal mediation; live and copied adaptive states were behaviorally identical under matched randomness; and detached reconstruction preserved computational state across process replacement while, by protocol, breaking constitutive continuity and non-delegable inheritance. These results show that CLT-I distinctions are experimentally tractable and can dissociate causal bearer structure from first-person performance. The framework therefore separates consciousness attribution, causal bearer individuation, and the independent metaphysical question of consciousness constitution.
Read the full abstract ▾