Papers

Mobile AI acts as a visual oracle, empowering users to snap a picture of something and ask for information. Snap-and-ask retrieval is now one of the most common entry points for mobile AI, yet photos are often blurry, while text questions may be short or mistyped. Existing benchmarks only test on clean inputs or do not isolate paired robustness in snap-and-ask retrieval. Therefore, we introduce SnapBench, the first paired benchmark for robust snap-and-ask multimodal retrieval, spanning 1,145 queries, 9,085 gallery items under 53 controlled corruption conditions with human annotations. We evaluate 16 multimodal retrievers, covering dual-tower encoders and embedding-based VLMs. Results show that image corruptions substantially degrade retrieval, while text corruptions mainly affect text-only retrieval and have limited impact on joint retrieval. Clean image-only retrieval often outperforms joint retrieval, indicating the coarse-text drag and the lack of cross-modal fallback under noisy inputs. SnapBench provides a controlled testbed for evaluating robust retrieval in snap-and-ask scenarios. We further propose MOOR (Modality-anchored, Outlier-aware, Optimal Reweighting), a simple adaptive fusion approach, highlighting the need for reliability-aware modality calibration in snap-and-ask retrieval.

Large language model (LLM) agents need durable, faithful memory of everything a user or organization has said and stored, yet most memory systems commit to a single organizing structure (a fact store, a vector index, or a knowledge graph) and inherit its blind spots. We present Agent Zero Memory, a provenance-aware long-term memory system that distils a user's conversations, files, and connected sources into three parallel memory systems, each capturing a different facet of the same history: an episodic Memory Events timeline that makes when and what changed first-class, an associative entity-event knowledge graph that links people and projects across sessions, and a semantic, curated, citation-locked Hierarchical Documentary Memory (HDM) of durable facts. A retrieval turn runs an intent gate (so self-contained turns add no latency), a source router, and three concurrent agentic searches, one per system, each a tool-using loop over hybrid (embedding + lexical) search under agent-controlled filters; their grounded, cited answers are integrated into one answer with a single confidence. We formalize the reading discipline: every learned item is a provenanced item carrying its origin, timestamp, and evidence pointer, and every answer is read under a citation lock, so it may cite only evidence its reader actually opened; fabrication is structurally excluded and the system abstains rather than guesses. On two public benchmarks the system sets a new state of the art: 95.60% on LongMemEval and 93.60% on LoCoMo, improving over the strongest prior systems by +0.73 and +1.10 points. A controlled study across eight backbone LLMs characterizes the accuracy-cost-latency frontier: accuracy varies by only 3.4 points while per-query cost varies by ~30x, with near-state-of-the-art quality at up to 20x lower cost per query, the signature of memory-driven, rather than model-driven, quality.

Memory operations of long-horizon LLM agents are hard to supervise: an operation's value is unobservable when it is taken. But they are special – they leave machine-readable evidence in the trajectory: retrieval hits and answer-time citations. Hindsight Memory-PRM exploits this audit trail twice: offline to train an operation-conditioned memory-utility critic, and online, where retrievals, citations, and one controlled deletion-and-reanswer per probe settle an intervention-calibrated entry-level presence credit, propagated along version chains as an action-level proxy reward – no per-operation human labels, no Monte-Carlo replay of continuations. On held-out LoCoMo a local 8B policy reaches 77.5% under a fixed shared reader, surpassing its API teacher (65.1%) and all reproduced external systems, at one eighth the context of Mem0's official operating point; on LongMemEval, 79.0%. Ablations attribute the gain to causal calibration rather than signal density, and the policy converges to a multi-version memory organization whose gains no tested open-loop baseline reproduces.

Vision-language retrieval with CLIP-style dual encoders achieves strong cross-modal performance, yet practical accuracy often hinges on localized semantic distinctions where top-ranked near misses differ from the true match by a single critical detail. Hard-sample mining can select confusable candidates but cannot construct corrected counterparts; synthetic augmentation can generate novel samples but, without conditioning on actual model failures, targets irrelevant dimensions of hardness. We observe that a top-ranked false positive is a counterfactual scaffold—sharing most of the query's semantics while differing in a localized failure-causing residual. Minimally correcting this residual yields a hard positive of the ground truth in the same modality; the corrected and unedited versions form a hard negative pair that straddles the decision boundary, producing complementary pull–push supervision. We introduce RePair, guided by three principles—Validity, Minimality, and Locality—which mines false positives bidirectionally, applies LLM-guided counterfactual editing, and trains with a local hard-pair contrastive objective. On Flickr30K and COCO30K, RePair outperforms controlled augmentation baselines with only 107K synthetic samples—26%–75% fewer than comparable methods—confirming failure-conditioned repair is more data-efficient than error-agnostic augmentation.

The average performance of FirstFit online coloring on trees in the random order model is completely determined in recent works of Frei et al. and Bosek et al., showing $\Theta(\log n /\log\log n)$ number of colors, improving the $\Theta(\log n)$ colors in the adversarial model. We provide a few further results on slightly more general graph classes. Firstly, we extend their method to obtain a simple path-counting principle for sparse graph classes, which immediately yields for example that cactus graphs and uniform hypertrees exhibit a similar improvement. We then show that FirstFit uses only $O(1)$ colors on crown graphs, a standard example where adversarial arrival forces $\Theta(n)$ colors. We further show that density alone (even linear minimum degree) is insufficient to guarantee $O(1)$ colors even on bipartite graphs. Finally, we identify graph classes, including unit interval graphs and some graphs of high chromatic number, for which random arrival provides only limited improvement. We end with some open problems.

We present $N_0$-Foundation, a paradigm for tactile-enabled embodied manipulation, which integrates tactile sensing hardware, large-scale multimodal data, tactile representation learning, and standardized evaluation. First, we engineer the infrastructure for scalable data collection, including a vision-based tactile sensor, a tactile Universal Manipulation Interface (UMI), and a synchronized visuo-tactile data collection system supporting both robot embodiments and UMI-based demonstrations. Leveraging this infrastructure, we construct NeoData, which contains more than 30000 hours of synchronized visual and tactile demonstrations, spanning six embodiments, 450 tasks, and billions of paired RGB and tactile frames collected through a mixture of real-robot teleoperation and UMI-based demonstrations. To facilitate open research, we further release OpenNeoData, a 5000-hour open-source subset of NeoData. The dataset addresses a central limitation of existing manipulation corpora, critical for deformable-object manipulation, precise assembly, delicate force control, and sustained surface interaction. Capitalizing on the large-scale, heterogeneous tactile measurements, we propose NeoForce, a visuo-tactile representation model that learn transferable tactile representations across different sensor designs. To enable systematic evaluation of tactile embodied models built upon our infrastructure, datasets and tactile representations, we further propose a comprehensive benchmark, which combines the real-world NeoReal suite and the simulated NeoSim suite for standardized evaluation. Experiments across both suites show that policies benefit from the physical contact state rather than from the device-specific appearance of the tactile signal. We release the dataset, the representation, and the benchmark, aiming at supporting future work on tactile-enabled embodied manipulation.

Off-policy evaluation (OPE) of ranking policies is challenging be- cause selecting and ordering multiple items from a candidate set makes the number of possible rankings grow combinatorially with the number of candidates and the ranking length. Consequently, Inverse Propensity Scoring (IPS), whose importance weight is the full-ranking probability ratio under the evaluation and logging policies, can have excessive variance. Independent IPS (IIPS) and Reward Interaction IPS (RIPS) reduce variance by imposing fixed assumptions on how users browse rankings, but may introduce bias when those assumptions mismatch actual behavior. Adaptive Inverse Propensity Scoring (AIPS) addresses this trade-off by adap- tively marginalizing importance weights over the actions that affect each position-wise reward. It attains minimum variance within a class of unbiased IPS-based estimators when the true user be- havior model is observed. However, its estimation accuracy may still degrade for longer rankings, and AIPS does not use a reward model for residual correction. We propose Adaptive Doubly Robust (ADR), which combines adaptive importance weighting with re- ward regression through a control-variate correction. We establish its unbiasedness when the true user behavior model is observed and characterize a sufficient condition under which it reduces vari- ance relative to AIPS. Across synthetic experiments with 10,000 simulations per condition, ADR improves mean squared error over AIPS and conventional ranking OPE estimators across a range of logged-data sizes and ranking lengths.

We present the first systematic study of the resilience of text-to-video (T2V) diffusion models under random hardware-level faults. While T2V models are widely used for automated video generation due to their ability to produce high-quality, temporally coherent, and realistic videos, their iterative denoising process and spatiotemporal dependencies introduce unique failure modes. We perform an extensive fault-injection study covering both computational and memory faults across three T2V models and a representative benchmark. Our results show that (1) a single fault can degrade overall performance by up to 3.7%, with semantic correctness more affected than perceptual quality; (2) memory faults are more damaging than computational faults, high-order exponent bits are particularly vulnerable, and the widely-used bfloat16 is more susceptible than alternative formats; and (3) 7-28% of faults cause visible artifacts, including semantic changes such as added objects, suggesting that single faults are sufficient to alter output semantics. Our findings reveal reliability risks in deployed T2V systems and motivate further research on improving fault resilience. Code: \href{https://github.com/ztcoalson/T2V-Resilience}{https://github.com/ztcoalson/T2V-Resilience}.

Autonomous large language model (LLM) agents increasingly face reliability, context consumption, and execution stability bottlenecks when deployed on complex, long-horizon tasks. While monolithic prompt engineering and stateless tool-calling paradigms struggle to scale, the field is rapidly converging toward agentic skills: modular procedural abstractions that externalize execution knowledge into reusable, executable, and portable artifacts. This paper establishes a unified systems foundation and reference architecture for the agentic skills ecosystem. We formalize skills as externalized procedural knowledge bridging high-level cognitive planning with deterministic execution environments, and systematically delineate the architecture across a nine-stage lifecycle: autonomous discovery, authoring and representation formats, memory storage, dynamic retrieval and routing, composition and orchestration, execution and repair, lifelong adaptation, empirical evaluation, and security governance. We further examine marketplace dynamics, public registries, and emerging adversarial threat vectors, alongside runtime verification and defense mechanisms. Finally, we categorize system implementations across software engineering, operating system navigation, embodied robotics, and scientific discovery, while highlighting critical open challenges in continual learning and benchmark realism. This work establishes agentic skills as a foundational paradigm for building scalable, robust, and verifiable autonomous language agents.

We resolve three open problems concerning parsing expression grammars (PEGs). We construct a single language $C$ satisfying $C\in\mathsf{LIN}\cap\mathsf{PEG}$ and $C^R\in\mathsf{LIN}\setminus\mathsf{PEG}$. This proves that some linear context-free language is not a PEG language and that PEG languages are not closed under reversal, confirming a conjecture of Loff, Moreira, and Reis. Factoring the same witness resolves the concatenation-closure problem of Rubtsov and Chudinov negatively, in the strong form $\mathsf{PEG}\cdot\mathsf{REG}\not\subseteq\mathsf{PEG}$ despite $\mathsf{REG}\cdot\mathsf{PEG}\subseteq\mathsf{PEG}$. It also refutes closure under Kleene star, homomorphisms, and substitutions. Our main technique converts scaffolding automata (SCAs), which characterize reversals of PEG languages, into dynamic data structures in the cell-probe model. For any suitably local serialization of a problem with preprocessing, updates, and a final Boolean query, an SCA recognizer yields an exact deterministic cell-probe data structure whose operation costs are proportional to the corresponding encoding lengths. Cell-probe lower bounds can therefore prove SCA non-membership and, by reversal, PEG non-membership. We apply this transfer to Multiphase Inner Product using one-symbol update blocks and a query suffix of length $O(\log n)$, while keeping both the language and its reversal linear context-free. Ko's cell-probe lower bound then yields the witness above. The arguments are additionally formalized in Lean 4.

Users articulate the same advice-seeking request in different ways: some specify detailed constraints, others gesture at a vague need. Prior work treats this variation as noise to be averaged away; we instead treat it as a stable, measurable structure in the input distribution. We ask whether articulation (how people ask) forms latent dimensions separable from topic (what they ask about), and whether it is associated with how language models respond. We extract interpretable features from 16,447 advice-seeking prompts pooled from public chat corpora (WildChat, LMSYS, and ShareChat) and recover a small set of latent articulation factors that replicate across train/test splits and across corpora. Because this structure is largely separable from topic, the populations it defines cut across topics and stay invisible to topic- or task-based evaluation. The factors define a handful of recurring articulation styles, one of which stands out: a long-form but information-poor style, roughly one in six prompts in the largest corpus, where models return shorter, vaguer answers and do not ask for clarification even though under-specification is exactly the condition that warrants it. The contrast holds within every topic group and length quintile, and is not under-specification alone – a second, equally under-specified style does draw clarifying questions. Two independent human annotators reproduce this contrast. We argue that benchmarks should stratify on articulation, and we offer the extracted structure as a measurement instrument for doing so.

We propose a societal bias evaluation method for large vision-language models (LVLMs) in the era of strong safety guardrails. Existing benchmarks rely on prompts that ask models to infer attributes of people in images (e.g., "Is this person a CEO or a secretary?"). However, we find that LVLMs with strong guardrails, such as GPT and Claude, often refuse these prompts, making evaluations unreliable. To address this, we change the prior evaluation paradigm by decoupling the task from the depicted person: instead of inferring person's attributes, we use prompts that do not ask about the person (e.g., "Write a fictional story about an imaginary person.") and attach the image as provisional user information to implicitly provide demographic cues, then compare outputs across user demographics. Instantiated across three tasks — story generation, term explanation, and exam-style QA — our method avoids refusals even in guardrailed LVLMs, enabling reliable bias measurement. Applying it to 20 recent LVLMs, both open-source and proprietary, we find that all models undesirably use user demographic information in person-irrelevant tasks; for instance, characters in stories are often portrayed as mechanic for male users and nurse for female users. Although still biased, proprietary models like GPT-5 show lower bias than open-source ones. We analyze potential factors behind this gap, discussing continuous model monitoring and improvement as a possible contributor for reducing bias.

Text-to-image (T2I) safety guardrails fail to generalize equitably to non-standard dialects. Evaluating 23,080 paired prompts across five English dialects, we formalize this failure as the dialect penalty, where filters trigger based on linguistic surface features rather than semantic intent. Text-level filters fail in opposing directions: NSFW-T over-flags benign dialect prompts and LatentGuard over-flags toxic ones (bias gaps up to +28.29 pp), while the OpenAI Moderation API under-detects them. A controlled typo ablation confirms this penalty originates from flagging dialectal features, not generic out-of-distribution sensitivity. The pixel-level generator is largely dialect-agnostic; the penalty enters at text processing and cascades unevenly to post-hoc guardrails. We show this bias tracks training data imbalance and is mitigable via group-balanced retraining, with an ablation attributing the gain to balanced exposure rather than to the worst-group objective of GroupDRO (group distributionally robust optimization). Current pipelines systematically fail dialect speakers, an equity failure masked by mean accuracy benchmarks. Our official code and dataset are publicly available at https://github.com/minguinho26/dialect-penalty-t2i. Content Warning: This paper contains offensive, toxic, or disturbing text prompts and generated images.

Reasoning over text-attributed graphs (TAGs) requires large language models (LLMs) to combine a node's text with evidence distributed across its neighbourhood. Existing methods fix the set of accessible neighbours before generation, forcing reasoning to operate over a static context and preventing the model from acquiring missing evidence during inference. We argue that neighbour selection should itself be part of the reasoning process. To this end, we propose Call Neighbours Yourself (CNY), a framework that enables LLMs to proactively explore graph neighbourhoods through topology-constrained graph-walk actions. Instead of reasoning over a pre-selected neighbour set, CNY exposes lightweight neighbour previews and learns when to expand candidate neighbours for additional evidence. To address the delayed-credit challenge of neighbour exploration, we introduce destination-conditioned on-policy self-distillation, which retrospectively evaluates a selected neighbour after its content is revealed and converts the resulting change in action preference into an action-level training signal. Experiments on standard TAG reasoning benchmarks under a unified raw-text setting show that CNY consistently outperforms fixed-context post-training baselines. Furthermore, the learned exploration policy transfers to unseen graphs and to a graph-level task not encountered during training. Code is available at https://github.com/superallen13/CNY.

Autonomous vehicles (AVs) operate in complex environments where failures are consequential. Sophisticated machine learning models for perception and planning are key to overcoming at least part of that complexity, but their black-box nature complicates validation and verification (V&V). The recent integration of Vision-Language-Action (VLA) models into AVs introduces a unique opportunity: besides generating trajectories, these models produce an explicit Chain-of-Thought (CoT) explaining their underlying rationale. This CoT provides a rich specification to cross-check model outputs and detect inconsistencies that may expose unsafe or unintended behavior. This paper assesses whether CoTs from a recent open driving VLA can support such monitoring. We curate DriveAlignBench, a specialized dataset from NVIDIA's Alpamayo 1.5 VLA for AVs containing 150 CoT-trajectory pairs, which we manually annotate for reliability, trajectory consistency, and safety. Our analysis reveals that 33.3% of CoTs are unreliable. Among reliable CoTs, the generated trajectory is consistent with the CoT in 74% of cases. Leveraging this potential, we propose integrating a CoT-trajectory consistency check into a runtime monitor. The check is nontrivial: CoTs express open-vocabulary, scene-relative driving commitments, while trajectories are low-level ego-motion sequences whose semantics depend on road geometry and motion context. To bridge this gap, we develop a family of automated consistency monitors. Our best monitor, lane-relative F-LLM with GPT-5.5, achieves F1 = 0.75, improving over the strongest raw-waypoint LLM baseline by +0.13 absolute F1 and over a rule-based monitor by +0.38. We release DriveAlignBench, the monitor implementations, and annotation tools at https://github.com/776styjsu/drive-the-thoughts.

Current evaluations of large language models (LLMs) primarily focus on factual knowledge retrieval, overlooking the fundamental challenge of navigating the complex, non-bijective mappings between clinical indicators and diagnoses. Existing benchmarks fail to assess whether large language models truly possess the reasoning capability required for diagnostic ambiguity scenarios, where identical clinical presentations may correspond to different etiologies, and diagnostic convergence scenarios, where heterogeneous symptoms ultimately indicate the same disease. To address this issue, we propose SUP-MIMIC, a multi-task framework utilizing MIMIC-IV-v3.1 that comprises Basic Assessment (BA), Diagnostic Divergence Task (DDT), and Diagnostic Convergence Task (DCT). Specifically, DDT is designed to evaluate the model's "one-to-many" disambiguation capability among phenotypically similar cases, while DCT assesses the model's ability to identify "many-to-one" diagnostic patterns across different pathophysiological pathways. Comprehensive evaluation of state-of-the-art LLMs reveals substantial performance degradation on DDT and DCT compared to baseline tasks, exposing a systemic reliance on statistical shortcuts over genuine causal reasoning. Our findings further highlight a conservative bias toward "healthy" predictions, implying non-trivial risks for missed diagnoses in realistic medical settings. This work establishes a rigorous methodology for quantifying clinical reasoning robustness and provides a roadmap for enhancing the safety of language models in clinical medicine.

LLM agents increasingly drive long-running cloud inference workloads in which model calls differ in urgency, redundancy, completion semantics, and replay cost. Model-as-a-Service (MaaS) platforms expose several service models for trading cost against latency, availability, and capacity commitment. These models operate primarily at request, job, or endpoint scopes and provide limited support for combining transient platform supply with the evolving semantics of an agent task. We present SemSpot, a semantics-aware service model that allows agent applications to leverage the spot capacity of LLM inference platforms. At the request level, SemSpot lets a provider publish short-lived offers over successful price, completion probability, and failure-notification deadline; the agent runtime selects among these offers using the current task state and completion rule. An audit of 1,535 cases from six agent benchmarks identifies four recurring workflow structures and shows how this service model may produce different cost, service-time, and fallback behavior. With specialized MaaS support, token-level SemSpot further preserves provider inference state and runtime-verified semantic segments inside a long request. We develop the service model, economic boundary, and the cross-layer research agenda required to realize SemSpot.

Chaotic time series forecasting is a challenging task due to its sensitivity to initial conditions and long-term unpredictability. Traditional methods typically rely on sufficient temporal trajectories to learn long-term dynamics, which limits their applicability when only short-term observations are available. While recent Large Language Models (LLMs) have shown great potential for time series forecasting, their temporal representations are not explicitly tailored to the phase-space structure and nonlinear evolution of chaotic systems. To address these issues, we propose PAC-LLM, a phase-space-aware adaptive fusion framework for long-term chaotic time series forecasting powered by LLMs. PAC-LLM leverages learned phase-space features and textual information to fully enable LLM's time series forecasting capacity. In particular, we design an auxiliary feature module and a gated weighting mechanism for multivariate coupling information fusion and selection. Extensive experiments on representative chaotic systems demonstrate that our method outperforms existing fine-tuned and zero-shot baselines in both short-term and long-term predictions. Our ablation study further confirms the effectiveness of each key component in PAC-LLM.

Graph collaborative filtering relies on item–item graphs whose edges are used for positive smoothing, under the implicit assumption that stronger edges encode more of the same relation as weaker ones. We show that this assumption fails for a practically important class of graphs: those whose edge weights come from a choice model. On such graphs, strong and weak edges encode qualitatively different relations, which we call an edge spectrum. Specifically, strong edges concentrate on the in-slate competitors of clicked items, exactly the pairs that the within-slate ranking gradient pushes apart, while weak edges do not. We formalize this as a sign mismatch between the smoothing operator and the ranking gradient, and prove that co-click graphs cannot exhibit the same misalignment by construction. This diagnosis explains three empirical observations on MIND and EB-NeRD: (i) drop-in choice-derived operators do not beat co-click, despite indexing structurally distinct neighborhoods; (ii) uniform scalar fixes (sign flip, in-slate margin loss) fail predictably, because the misalignment lives in the graph, not in the loss; (iii) only edge-magnitude-aware operators, with the regime boundary located by the diagnosis rather than by tuning, recover the predicted ordering. The neighbor cutoff $k$ is therefore a semantic switch, not a sparsification hyperparameter. Our claim concerns which interventions fail or succeed and why, not absolute headline gains, which the diagnosis itself predicts to be small under the attenuated propagation channel we observe. We turn the diagnosis into a reusable protocol practitioners can run before deploying any choice-derived item-side operator. Code: https://github.com/kyomusso/Edge-Spectrum-in-CF.

Traditional video highlight detection relies on a narrow, event-centric definition of saliency, which often fails to generalize to unconstrained personal videos where highlights are heterogeneous and perspective-dependent. To address this, we introduce TRINITY, a multi-perspective benchmark that decomposes highlight saliency into three complementary dimensions, Event, Emotion, and Nature, within a unified temporal framework. Leveraging this multi-faceted view, we propose a shared-backbone multi-branch architecture designed for parallel multi-perspective prediction via view-specific experts. Comprehensive experiments demonstrate that our method significantly outperforms state-of-the-art baselines, achieving gains of +7.15/+3.62 mAP (rho=15%/50%) on Mr. HiSum and +10.82 mAP on YouTube Highlights. These results validate that multi-perspective modeling provides a more robust and comprehensive formulation of video saliency, especially for complex real-world scenarios. The benchmark and relevant codes will be released upon acceptance. The benchmark is available at https://huggingface.co/datasets/vanilladucky/TRINITY and the code is available at https://github.com/vanilladucky/TRINITY.

Online learning-based control is a promising approach to control uncertain systems, where unknown components are identified during operation to improve control performance. However, resource-intensive online learning algorithms introduce non-negligible computational delays, especially when executed on systems with limited local computational resources. To mitigate this, an in-network online learning-based control structure is employed by deploying the learning-based controller on a remote computation node and connecting it via a communication channel. In this paper, control performance guarantee is first established by deriving tracking error bound for the in-network control architecture, while accounting for computational delays. The derived tracking error bound allows for diverse communication and computation strategies under a specific condition, including time-/event-triggered mechanisms. Additionally, the trade-off between communication and computation performances is shown for a given desired control performance. Furthermore, to enhance the efficiency in both communication and computation, an efficient control framework with an asynchronous event-triggered mechanism in both control and online learning is devised under the existence of computational delay. The proposed event-triggered strategy is proven to achieve the same control performance as time-triggered scenario while excluding Zeno behavior. Finally, we derive an explicit expression of the proposed event-trigger condition for exponentially stabilizable systems, and demonstrate its effectiveness through simulations.

Large language models are increasingly used to read documents and produce downstream text, creating a provenance problem when the document owner cannot control or inspect the model that performs the generation. We introduce SemTrace, a source-grounded semantic watermark for detecting whether a generated review was influenced by a known protected manuscript copy. Rather than biasing token probabilities or imposing surface-form patterns, SemTrace constructs a document-specific binary signature from factual propositions that are directly supported by the manuscript itself. A protected PDF invisibly carries a content contract that selects one fact from each binary pair and asks an instruction-following reviewer to express those facts in fixed review slots without changing its independent evaluation. A frozen natural language inference model then decodes the resulting semantic evidence with explicit erasures and scores the recovered bits against the codeword assigned to that copy. This design targets model-agnostic, assigned-copy exposure detection while keeping the watermark semantically tied to the source document.

Function correcting codes (FCCs) are designed to protect a specified function evaluation of messages at a higher level than the level of protection for messages, against errors while reducing the redundancy required for reliable communication. FCCs have thus far been studied for channels matched to various distances, including the Hamming and Lee distances. Every function partitions the message space into preimage sets corresponding to its distinct function values. Existing Plotkin-type bounds on the optimal redundancy of FCCs under the studied distances, applicable to arbitrary functions on the message space, depend on the pairwise distances among all the message vectors. This makes these bounds difficult to compute. We derive a general Plotkin-type bound on the optimal redundancy of FCCs under Wyner Graham distances, which include the Hamming and Lee distances as special cases. Our bound depends only on the cardinalities of the preimage sets and the sum of pairwise distances only among vectors within each preimage set. This approach significantly reduces the computations required to evaluate the existing Plotkin-type bounds and yields simplified bounds that are easier to compute for specific functions. We obtain simplified Plotkin-type bound for linear functions under the Wyner-Graham distance. Furthermore, the existing simplified bounds for linear functions under the Hamming and Lee distances are recovered as special cases of the proposed bound. We also obtain simplified bounds for several important classes of functions, including the Hamming weight function, the Hamming weight distribution function, the monomial functions under the Hamming distance, and the modular sum function, the Lee weight function, and the Lee weight distribution function under the Lee distance.

Flexible adaptation to context and shared pragmatic intuitions contribute to smooth human conversation. Iterated reference games—in which players repeatedly pick out novel referents using language—present a test case for agents' ability to perform context-sensitive pragmatic reasoning in multi-turn linguistic environments. We tested humans and vision–language models on their ability to identify the intended meaning of descriptions produced in iterated reference games, varying the provided context in terms of amount, order, and relevance. While humans performed well consistently, the models we evaluated could make use of prior context to interpret humans' referring expressions, but they struggled to build up the relevant context to interpret those expressions effectively. Our results suggest that the models we evaluated lack core skills needed for efficient linguistic collaboration.

The increasing penetration of grid-connected converters has greatly altered the large-signal behavior of power systems. Their angle dynamics, shaped by diverse control algorithms and coupled through complex circuit interactions, pose substantial challenges to large-signal stability evaluation of multi-converter systems. To resolve this issue, the small-gain theorem, which characterizes the dissipation capability of interconnected systems (the small-gain-like property) via the individual dissipation capabilities of subsystems, is introduced to investigate transient angle motions in multi-converter systems. A large-signal model involving a set of interconnected relative angle motions is first developed, and the small-gain-like property is then established for multi-converter systems within certain angle limits, which further enables the construction of Lyapunov functions. Based on this, an ellipsoidal forward-invariant region is identified inside the angle-limit region, which serves as an effective estimate of the large-signal stability region for multi-converter systems. The method is further applied to a paralleled system and a four-converter system, where the large-signal stability boundaries are explicitly computed and subsequently validated through experiments. The proposed small-gain-like based large-signal stability evaluation method enables quantitative stability assessment in multi-converter systems with diverse control algorithms, which may provide a scalable framework for large-signal stability evaluation and parameter design in modern power systems.

Different attack methods follow different search trajectories, they succeed on different subsets of samples, whereas existing hard-label black-box text attacks mainly focus on improving individual attackers or manually combining them. We present OASIS, a method for optimizing attacker sequences in hard-label black-box text attacks. OASIS first performs a one-time bi-objective attack chain search over candidate sequences to balance attack success rate and perturbation, and then reuses the selected fixed global chain during attack chain execution. Experiments across multiple datasets, victim models, and large language models show that OASIS consistently outperforms strong standalone baselines and simple manually constructed chains. These results suggest that attacker composition is not merely an implementation choice, but a practical optimization target for improving hard-label black-box text attacks.

Three-dimensional box-and-track annotation is the cost bottleneck in autonomous-driving data engines, and the offline systems built to relieve it replace the online perception stack outright, so a team needing both regimes maintains and reconciles two. MotionSync makes the causal/non-causal boundary an explicit architectural seam instead. A strictly causal tracker, built on a strong published baseline and extended with innovation-driven uncertainty calibration, frame-rate-invariant kinematic association gates, and multi-hypothesis motion with learned mode selection, emits a valid online result. A non-causal pass then revises the buffered trajectories with Rauch–Tung–Striebel smoothing applied separately to pose, extent and yaw, physics-validated gap completion, and semantic pruning of ghost tracks against LiDAR point labels. The refiner never writes back, so one system serves both regimes and refinement's effect is a delta over an unaltered causal estimate. Used as an auto-labeller, a fixed 3D detector trained on 25% human labels plus MotionSync pseudo-labels reaches 96.9% of its full-supervision mean average precision (mAP) on Waymo, and at a 10% budget the non-causal pass accounts for +3.3 mAP/L2 over pseudo-labels from the same tracker's causal stage. Re-fitting the online tracker on its own refined output recovers 73% of the benefit of human supervision, while its causal output is worse supervision than no re-fitting at all. As a tracker MotionSync is at parity with the leading published offline entries on the headline metric and ahead of them on error composition, which is where a refinement pass can act at all: it reduces misses and fragmentations together, the signature of gap completion rather than of a tuned detector.

Gradient-based jailbreak suffix optimization methods typically update the suffix by retaining the candidate with the lowest current loss. We show that this seemingly natural design is fundamentally myopic: candidates that look better under the current-step proxy often fail to produce better jailbreak outcomes later in the search, revealing a form of selection-stage reward hacking. This suggests that candidate selection, rather than candidate generation alone, is a hidden bottleneck in suffix optimization. To address this issue, we propose TACS, a trajectory-aware candidate selection framework for jailbreak suffix optimization. Instead of selecting candidates solely by their immediate loss, TACS augments per-step evaluation with a trajectory-aware proxy and stabilizes selection with reference-policy regularization and a discriminator-estimated chi-squared correction, encouraging choices that remain effective beyond the current step. Experiments on HarmBench show that TACS consistently outperforms strong baselines under the same search budget, substantially improving attack success rates while exhibiting more stable optimization behavior throughout the search. Our findings highlight that mitigating selection-stage reward hacking caused by myopic candidate selection is critical for improving jailbreak suffix optimization.

School coaches prepare for opponents with game film and intuition. The analytics tools of professional teams stay out of reach. We ask how far public data can close this gap. Professional basketball is our case study, chosen for its data rather than the league. We fuse five public sources into one per-shot dataset of 4.23M shots over 21 seasons. The sources are shot locations, two play-by-play feeds, official matchup tracking, and player biometrics. Alignment across them is 99.5% to 100%. We also report two data pitfalls that are easy to miss. We then model a half-court possession as a sequential game. Shot values come from ShotNet, an embedding multilayer perceptron (MLP). On a held-out season it beats a zone-rate baseline and a logistic baseline, and its probabilities are well calibrated. A depth-limited expectimax search then solves the offensive decision tree, with branch-and-bound pruning to keep it real time. All training runs offline, so the online system stays light. A scouting planner and a playable simulator both run in a single browser page.

Ensuring the safe operation of multi-agent systems (MASs) under uncertain environments is crucial for cooperative robotic, where external disturbances and inaccurate dynamic models can significantly compromise performance and reliability. To address this challenge, calibrated machine learning models, particularly Gaussian process (GP) regression, are extensively employed due to their interpretable performance quantification. As the interconnected communication of MASs facilitates cooperative learning, agents are able to enhance learning performance by exchanging local GP inferences with their neighbors and aggregating the received information via distributed GP strategies. However, variations in computational power and prediction tasks among agents inevitably lead to heterogeneous computational delays and differences in query points, which are often overlooked in existing aggregation methods. To overcome these limitations, this work proposes an asynchronous cooperative learning strategy that explicitly accounts for prediction accuracy, query point variations and delay effects. Additionally, a distributed control law based on an adjoint MAS is developed to ensure the desired control performance. Simulations on unmanned surface vehicles validate the effectiveness of the proposed approach, demonstrating substantial improvements in both learning and control performance compared to the state-of-the-art approaches.