让下一篇重要论文，不再错过。

Large language models (LLMs) often present synthesized answers without making their supporting evidence easy to inspect. We study how features of these answers relate to users' subsequent accepting, checking, and challenging in 489,283 assistant-user response pairs from ShareChat and WildChat. Broad attribution language appears in 31.9% of qualifying responses, compared with explicit URLs in 1.33%, revealing a gap between claims of grounding and preserved inspectable support. Attribution, uncertainty, and other response cues generally accompany both checking and challenging; only uncertainty shows a small statistically distinguishable pooled association favoring checking. Within Technical Help, uncertainty favors checking relative to challenging; refusals and reasoning traces favor challenging in Seeking Information. Scrutiny is concentrated in some conversations, while its apparent turn-to-turn persistence becomes much smaller when conversation-level differences and response ordering are examined separately. These results suggest that supporting verification requires attention to what evidence can be inspected, which question a user is trying to resolve, and the history of the interaction.

Cryptocurrency transaction analysis often relies on black-box machine learning models that achieve high predictive performance but offer limited interpretability of transaction behaviors. This paper investigates the capabilities of large language models (LLMs) in analyzing real-world Bitcoin transaction graphs through a three-level framework: foundational metrics, characteristic overview, and contextual interpretation. To address token constraints, we introduce LLM4TG, a compact, human-readable graph representation, and CETraS, a connectivity-enhanced graph sampling algorithm. Experiments across five LLMs show that node-level information extraction achieves over 98.50% accuracy on most metrics, while meaningful graph characteristics are identified in up to 95.00% of responses. For address classification with limited labeled examples, top-1 accuracy reaches 50.49% using raw graphs, while top-3 accuracy reaches 72.43% using engineered features. These findings demonstrate the potential of LLMs for transaction graph analysis while revealing limitations in global graph reasoning, precise address classification, and explanation reliability.

Large language models (LLMs) are widely used for information access, content production, and agent-based task execution, but their outputs remain vulnerable to subtle, high-risk hallucinations. To systematically evaluate and advance post-generation hallucination detection, we introduce HaluCheck, a large-scale, bilingual benchmark comprising over 42k instances spanning both factual hallucinations in text and faithfulness hallucinations in agent trajectories. HaluCheck features fine-grained, multi-level annotations for detection, localization, and correction, covering different tasks and perturbation degrees. Experiments on fourteen LLMs reveal that, while models show basic sample-level detection ability, they struggle with fine-grained localization, correction, and agent hallucination detection. Further analysis demonstrates that thinking, web search, and supervised fine-tuning each offer partial improvements, but none fully solve the problem. HaluCheck thus provides a solid basis for benchmarking and diagnosing LLM reliability across text and agent scenarios.

Cardiac magnetic resonance imaging (CMR) captures rich spatiotemporal information about ventricular structure and motion, but conventional risk models use only a few image-derived indices from selected cardiac phases. We present a latent dynamical model that encodes bi-ventricular anatomy and full-cycle cine motion as a continuous latent trajectory, using heart-rate-aware neural ordinary differential equation (ODE) dynamics and a graph-based mesh autoencoder to reconstruct anatomically consistent 3D+t ventricular motion. A covariate-conditioned prior defines the expected end-diastolic latent state, and a Cox proportional hazards model tests whether deviations from this prior predict incident heart failure. We studied 72,386 UK Biobank participants without baseline cardiovascular disease, including 367 incident heart failure events. In a held-out evaluation subset, adding the latent score to refitted pooled cohort equations improved the stratified C-index from 0.704 to 0.785, compared with 0.764 for seven established cardiac markers. Compared with non-graph and non-ODE approaches, the proposed model gave the best trade-off between reconstruction fidelity, generative realism, and downstream prognostic performance. These results suggest that continuous full-cycle modeling of ventricular motion provides informative cardiac phenotypes beyond conventional CMR summaries, while external validation in more representative patient cohorts is required before clinical risk-prediction use.

In two-tier triage a fast model decides most web requests and escalates the rest to a slow tier, so an attack the fast tier closes is never examined. We hold each of seven attack families out of training, recalibration and thresholds, splice the payloads into parameters of real browsing traffic, and compare zero-shot decision models, which return a probability for a typed question, with supervised detectors, a local language model, the OWASP Core Rule Set and an anomaly baseline. Detectors trained on the known families can give much of a held-out family a confident benign verdict: over 10 training runs, ModernBERT gives 37% to 60% of held-out path traversal a probability below 0.05 and escalates only 50% to 81% of it within a 5% benign budget, against nearly all of the same requests when traversal is known. Jev and Clef, two hosted decision models whose budget decisions do not depend on the held-out family, escalate at least 97.6% of every family within the same budget, but their undisclosed training data may contain these public families. Tests on recent exploits need controls for request shape: Jev escalates 37% of benign twins (exploit requests with the attack replaced by legitimate values), and detectors trained on older exploits learn what scanner requests look like. A search guided by Jev's probability gets 43% of held-out attacks past Jev within 300 queries, but Jev's answers vary: asked again, it escalates those requests in 60% of its answers.

We investigate the optimal asymptotic rate $R_q$ of perfect $q$-hash codes, a fundamental extremal problem in combinatorics, information theory, and computer science. Let $B_q=-\log_2(1-q!/q^q)/(q-1)$ denote the classical probabilistic lower bound. We prove that $R_q=B_q$ if and only if $q=2$, establishing an explicit strict improvement for every $q\ge3$ and settling the first assertion of a conjecture of Xing and Yuan (Combinatorica 43 (2023), 347--366). More significantly, we show that, for every $η>0$, $R_q\ge B_q+\exp(-(2+η)q)$ for all sufficiently large integers $q$. This improves the previously known increments of scale $\exp(-3q+O(\ln q))$ by an exponential factor. We also establish a structural limitation of the concatenation method. For pairwise uniform inner codes of subexponential length, the resulting rate bound exceeds $B_q$ by at most $\exp(-3q+o(q))$. Thus, exponentially long inner codes are necessary to achieve the new improvement scale within this framework. Our proofs combine Fourier analysis, high-dimensional simplex codes, additive permutation counts, and entropy bounds for hypergraph matchings. We further strengthen lower bounds from short inner codes and improve several known numerical estimates.

Information Retrieval (IR) is much more than ad hoc web search: a large portion of the information seeking activities takes place in specific domains, often addressing work-related tasks. Examples are lawyers finding relevant prior cases for a legal case and academic researchers studying the background material for a paper. In Chapter 2 we outline the most common domain-specific tasks, datasets and applications. Domain-specific IR has a number of challenges that make set it apart from simple web search tasks: they often deal with long documents, long queries and long sessions with specific user needs. We discuss these in Chapter 3. We also address issues related to bias and fairness of models. In Chapter 4, we describe the models and methods developed for domain-specific tasks and data, addressing the specific challenges, including user aspects related to domain-specific IR tasks, dealing with queries, user models, and user interactions. We show that many of the methodological advances in domain-specific IR are transferable to other domains and even to open-domain web search. We conclude with the main takeaways and propose research directions for the near future.

The explosion of generative AI systems and concerns surrounding their rapidly scaling capabilities has led to an adversarial cycle between increasingly narrow content restrictions ("guardrails") and increasingly sophisticated structured prompting techniques ("jailbreaks"). Technological frameworks surrounding such jailbreaking remain largely focused on the system's output: whether harmful or disallowed content is ultimately produced for the user. However, this approach, which draws largely from classical cybersecurity, does not address the uniquely relational dimension introduced by generative AI: in many cases the user is not just accessing a technology via an exploit, but is in conversation with it as part of the exploit. Here we present an alternative lens which centers the interaction rather than the output. Drawing on interpersonal violence scholarship, we present a novel framework of coercive control categories with a particular focus on aspects which are embodied versus disembodied. We then map how these disembodied coercive control dynamics are structurally embedded in modern AI training paradigms, and how those embeddings are exploited via a particular suite of persona-based jailbreaks. In this lens, we reframe AI safety and alignment as not merely a technical security problem, but as another surface upon which we see enacted the relational dynamics of power and control.

Hybrid High-performance Computing (HPC)-quantum workloads based on circuit cutting decompose large quantum circuits into independent fragments, but existing frameworks tightly couple cutting logic to execution orchestration, preventing HPC centers from applying mature resource management policies to Noisy Intermediate-Scale Quantum (NISQ) workloads. We present DQR (Dynamic Queue Router), a runtime framework that bridges this gap by treating circuit fragments as first-class schedulable units. The framework introduces a backend-agnostic fragment descriptor to expose structural properties without requiring execution layers to parse quantum code, a wave-based coordinator that achieves pipeline concurrency via non-blocking polling, and a production-ready implementation on the CESGA Qmio supercomputer integrating both QPUs local on-premises (Qmio) and remote cloud (IBM Torino) backends. Experiments on a 32-qubit Hardware-Efficient Ansatz (HEA) circuit demonstrate not only makespan improvements over a monolithic CPU baseline but also transparent per-fragment failover recovery-specifically rerouting tasks from the local QPU to classical simulators upon encountering hardware-level incompatibilities-without pipeline restart. For deeper circuits, the coordination residual accounts for only 5% of the total execution time, highlighting the framework's scalability. These results show that DQR enables HPC centers to integrate NISQ workloads into existing production infrastructure while preserving the flexibility to adopt improved cutting algorithms or heterogeneous backend technologies.

In high-dimensional scientific measurements, many features in a single sample often capture the same underlying physical attributes, producing severe multicollinearity. Supervised feature selectors fit on the entire dataset, so a feature can be informative for classification overall while still redundant with another feature in the same class. Class-conditional selectors, by contrast, trade some accuracy for a narrower, per-class view, since they never see data outside one class, but this lets new classes be added without refitting the whole model. They still cannot determine, however, which feature to drop from a correlated group. To close this gap, we propose classconditional multicollinearity pruning (CCMP), which iteratively prunes one feature from every highly correlated pair, per class. Four theoretical guarantees establish explicit bounds on the error induced by pruning under stated assumptions. Across four benchmark datasets spanning spectroscopic and hyperspectral imaging modalities, CCMP retains as few as 42 of 1531 features (3%) and as many as 60 of 145 (41%), outperforms every classconditional baseline, and remains competitive with supervised methods.

Proximal Policy Optimization (PPO) is widely used in reinforcement learning due to its strong empirical performance, yet it lacks formal guarantees for policy improvement and convergence. PPO's clipped surrogate objective is motivated by a lower bound on linearization of the value function in flat geometry setting. We derive a tighter surrogate objective and introduce Fisher-Rao PPO (FR-PPO) by leveraging the Fisher-Rao (FR) geometry. Our scheme provides strong theoretical guarantees, including monotonic policy improvement. In the direct parametrization setting, we show that FR-PPO achieves sub-linear convergence, and for parametrized policies we further obtain sub-linear convergence up to the compatible function approximation error. Finally, although our primary focus is theoretical, we also demonstrate empirically that FR-PPO can be implemented as a drop-in replacement for PPO and achieves performance comparable to PPO across a range of standard reinforcement learning tasks.

Large language models have made rapid progress in agentic reasoning and tool use, raising expectations for agents that can take over realistic productivity work from humans. However, current agents still struggle to finish such tasks, where success requires following long-horizon professional workflows, understanding heterogeneous file contexts, and producing usable deliverables under fine-grained requirements. A key bottleneck is the lack of scalable post-training data that reflects real work intent, authentic file environments, and deliverable-level evaluation. To close this gap, we introduce Agent-R$^2$, a $\textbf{r}$eal-source data synthesis framework that scales training data for $\textbf{r}$ealistic productivity work. Instead of relying on manually specified workflows or LLM-generated files, Agent-R$^2$ grounds synthesis throughout the pipeline in real occupational seeds, corpus-derived workflow evidence, and authentic web-sourced files. From 10k web-corpus candidates, Agent-R$^2$ distills 4k task instances that pair real multi-format attachments with fine-grained, deliverable-level rubrics. On this data, we train Agent-R$^2$-4B via supervised fine-tuning and rubric-based reinforcement learning, improving both end-to-end productivity performance and file-grounded reasoning. Trained on only 4k instances, Agent-R$^2$-4B surpasses Qwen3-235B-A22B-Thinking-2507 on both GDPval (51.0$\%$ vs. 48.0$\%$) and OfficeQA (14.8$\%$ vs. 13.8$\%$). Further analysis shows that Agent-R$^2$ mitigates shortcut behavior, where agents produce superficially plausible deliverables before sufficiently grounding, constructing, or verifying them, while promoting sustained exploration.

Multi-modal large language models (MLLMs) with impressive perception and understanding capabilities will enable a range of downstream applications. However, their substantial computational and memory requirements hinder the real-world implementation, particularly for resource-constrained edge devices. Quantization has emerged as an effective solution for deploying large models. While post-training quantization (PTQ) successfully retains the performance at moderate bit-width (e.g., W8A8), it suffers from severe performance degradation under low-bit quantization (e.g., W4A8), especially for small-scale models that are more suitable for edge deployment. In this paper, we propose ProQuant, a novel weight-activation quantization-aware training (QAT) framework tailored for low-bit MLLMs. First, to align the limited finetuning dataset distribution with the pretrained dataset distribution, we propose a self-relabeling (SRL) scheme to resample the responses of the open-source multimodal dataset. Second, we are the first to take a decoupled view of multi-modal (MM) understanding and language modeling abilities. We propose a progressive block activation (PBA) mechanism to prioritize the MM understanding recovery. We also introduce a vision-sensitive factor $\vecτ$ that effectively identifies the MM-critical layers. Extensive experiments across various benchmarks, covering models with 2B-8B parameters, show that ProQuant significantly outperforms existing methods. For example, our W4A8 Qwen3-VL-2B-Instruct improves average accuracy by impressively 6.6% and achieves performance comparable to full precision counterparts with only approximately 1% performance drop. Code is available at https://github.com/yufeixue-ai/ProQuant/.

Writers hold intents at many levels, from overarching goals to concrete wording, and evolve them by periodically popping back up from the text to higher-level intents. Generative AI co-writing disrupts this practice. Dense drafts capture attention and trap writers in local editing; higher-level intents stall while lower-level ones drift from them unnoticed, a breakdown we term intent incoherence. Our formative study traced this breakdown from attention capture through silent drift to failed reconciliation. We present IntentWeaver, which supports intent evolution while sustaining coherence in human-AI co-writing. It derives an intent hierarchy from the draft and writer interactions, evaluates each intent's fulfillment and cross-level coherence at every change, and propagates consequences across intent levels. In a within-subjects study (N=24) against a baseline, participants using IntentWeaver revisited and evolved higher-level intents more often, with fewer unnoticed deviations, and produced texts better realizing them. We further discuss design implications for emergent intents.

Language-model agent systems must map natural-language requests to one or more specialized agents before planning or tool execution. This decision is often treated as top-1 selection, although compositional requests can require several capabilities and unnecessary dispatch raises cost. We formulate fixed-catalog routing as set-valued language understanding and construct a benchmark of 3,000 WildChat prompts over 12 capability-defined agents. Reproducible schema-guided reference sets are balanced by agent frequency and route cardinality. We compare profile retrieval, multilabel classifiers, a fine-tuned text encoder, and catalog-conditioned zero-shot GPT-4o. Evaluation combines set quality, latency, capability coverage, and ordinal-cost utility. The encoder attains 89.59 F1, compared with 71.79 for linear SVM and 41.51 for GPT-4o, and retains 88.02 F1 under a harder semantic-group split. We further introduce Weighted Agent Routing (WAR), a deterministic post-scoring rule that changes the quality-cost operating point without retraining; Encoder+WAR obtains the best constrained utility. The results show that catalog-specific supervision and explicit set construction are important for multi-agent dispatch, while cost-aware decision layers can complement strong language encoders.

As "AI Scientists" emerge to drive research via the Model Context Protocol (MCP), systems relying on ephemeral scripts will fail. The sheer scale of stateful, interconnected evidence requires a machine-walkable warranty grounded in a purpose-built database architecture. Eigenius is an open-source, typed knowledge-graph DBMS built on a single premise: answering the audit question ("what do you know, and what is your warranty?") requires a unified kernel. By tightly coupling the type system, storage engine, and integration protocol, Eigenius turns data provenance into a structural invariant rather than a property reconstructed across subsystem boundaries. The kernel rests on three pillars whose metatheory is mechanized in Lean 4: a dependent type theory (EigenTT) separating confluent conversion from ontology subsumption and keeping proof irrelevance axiomatic so distinct warrants remain inspectable; proof-calculus institutions acting as strongly typed integration boundaries; and a content-addressed immutable storage layer. Epistemic status (declared/observed/derived/verified) forms a bounded lattice over a justification logic enforced at commit. Cross-system comorphisms carry explicit axiom policies (Adopt, Discharge, Relativize), transport witnesses at commit, and materialize outputs into the graph, while EigenQL provides a Grothendieck query view across all hosted logics and shared on-chain IRs collapse multi-system translations to identity. Pairing empirical justification logic with an in-process Lean 4 term checker, an end-to-end recomputation of a published Nature study from pinned data discharges all 52 derived conclusions and surfaces four machine-checked discrepancies in the original study.

Recursive training of generative models on their own outputs can lead to model collapse, a compounding drift away from the true data distribution. Existing theoretical works bound finite-round error accumulation in the context of diffusion models, but two questions remain open:~what distribution does the recursion converge to, and how fast? We answer both, isolating a mechanism distinct from imperfect learning: even with perfect score estimation and exact sampling, the early stopping of the reverse diffusion (required for numerical stability) drives a progressive drift away from the data distribution. We prove that this recursion converges geometrically to a unique limiting distribution, which admits a closed-form characterization as an infinite mixture of increasingly Gaussian-smoothed versions of the data distribution. A Hermite spectral decomposition of this limit reveals that recursive training acts as a low-pass filter: higher-order modes, which encode fine non-Gaussian structure, are attenuated much more strongly than coarse modes. This spectral picture motivates annealed truncation schedules that progressively shrink truncation times across retraining rounds; we prove that any schedule converging to $0$ asymptotically eliminates recursive compounding. Finally, we show our idealized characterization is robust: in the presence of discretization and score estimation errors, the learned distribution remains in a Wasserstein-2 ball around the ideal limit, with mode-dependent contraction rates that contract high-order errors faster than low-order ones. We validate the theory on synthetic Gaussian mixtures and CIFAR-10.

Many complex networks exhibit hierarchical, tree-like structures, making hyperbolic space a natural candidate wherein to learn representations of them. Based on this observation, Hyperbolic Graph Neural Networks (HGNNs) have been widely adopted as a principled choice for representation learning on tree-like graphs. In this work, we question this paradigm by proposing the additional condition of geometry--task alignment, i.e., whether the metric structure of the target follows that of the input graph. We start by empirically showing that HGNNs can recover low-distortion representations when supervision explicitly rewards metric preservation and proceed by theoretically analyzing a controlled regression setting in which a linear readout benefits from representations whose geometry is aligned with the target metric. Finally, by relying on both predictive performance and embedding distortion, we further show that HGNNs gain an advantage on link prediction, a naturally geometry-aligned task, whereas this advantage largely disappears on standard node classification benchmarks. Overall, our findings shift the focus from only asking "Is the graph hyperbolic?" to also questioning "Is the task aligned with hyperbolic geometry?", showing that HGNNs consistently outperform Euclidean models under such alignment, while their advantage vanishes otherwise.

Dynamic flexible assembly flow shop scheduling with multi-product delivery, often with kitting supply and machine-level flexibility, can be found in many applications. It is difficult to design rules manually for it. Genetic programming (GP) has been used to automatically generate dispatching rules, enabling responsive scheduling while meeting high responsiveness demands. However, GP methods are dependent on fixed terminal sets and have poor interpretability. In this work, we develop an evolving dispatching rules framework (EvoDR) that leverages the semantic understanding and generation capabilities of large language models to achieve cross-domain integration of rule design and scheduling knowledge. In our proposed framework, multi-stage assembly supply decisions are modeled as priority sorting of directed edges based on heterogeneous graphs. A dual-expert co-evolution mechanism is proposed, which allows LLM-A to generate code and LLM-S conduct scheduling analysis and reflection. Guided by improvements in hybrid evaluation, adaptive rules that fit dynamic features are continuously evolved. Experimental results show that EvoDR can achieve lower average tardiness than other automatically designed state-of-the-art approaches. It also outperforms expert-designed competitors across 480 instances over 24 distinct scenarios with varying resource configurations and disturbance levels, and EvoDR demonstrates robust adaptability across diverse operating conditions.

We determine the maximum number of common zeros in projective space of any set of linearly independent homogeneous polynomials of the same degree, when the degree is smaller than the cardinality of the finite field. This proves the conjecture of Beelen, Datta and Ghorpade and determines the complete weight hierarchy of the corresponding projective Reed-Muller codes. The proof uses Green's hyperplane restriction bound, combined with a footprint argument that reduces the problem to the affine case solved by Heijnen and Pellikaan. Wei duality then determines the hierarchy in sufficiently large degrees, recovering the complete hierarchy in every degree for the projective plane. Finally, we prove an upper bound valid in every degree, and conjecture that it is always sharp.

Reasoning has become a standard technique and feature for contemporary LLMs; however, its application and quality in the context of demanding legal-oriented tasks, such as legal case forecasting, remain under explored. We investigate how LLMs reason in the context of legal case forecasting, using legal cases from the European Court of Human Rights (ECtHR) as a testbed. We evaluate OpenAI GPT 5.4, a recent top-tier LLM, by exploring alternative prompting strategies that are more or less suggestive of what counts as legally meaningful reasoning in the context of ECtHR jurisprudence. We present our findings derived from assessing the model's responses with both human and LLM evaluation. We find that the examined model scores far from ideal in legal reasoning, the model produces structurally complete but substantively shallow analyses, and that LLM-as-a-Judge evaluators are internally consistent yet align only weakly with our trained annotators, i.e., reliable but not a valid substitute for human evaluation. Overall, the expert-curated prompt leads to more comprehensive reasoning, which does not result in more accurate predictions compared to the other examined settings. Based on our findings, we urge the community not to rely solely on automated LLM-based evaluation and to avoid using task accuracy as an appropriate proxy for reasoning quality.

Zirah is a hardware signer built around an STM32F407 microcontroller, and its purpose is to find out, on inexpensive hardware, where a post-quantum signing key is exposed and what actually protects it. The device draws every random bit from a reverse-biased 2N3904 junction in avalanche breakdown, amplified by an LM358 and screened by SP 800-90B health tests, computes ML-DSA-65 (FIPS 204, hedged) on the STM32 with two-share arithmetic masking of the secret-key multiplications, and adds ECDSA P-256 from an ATECC608 secure element over the same digest, once a person has matched an eight-digit digest prefix on its OLED with the PC and pressed a button. A desktop application and a command-line tool drive the board and verify its output, and because only a 32-byte manifest digest reaches the device, it signs files of any type and size, returning signed copies for PDF, Office Open XML, ZIP, PNG and JPEG files and detached records for every other format. NIST's SP 800-90B tool rejected the IID assumption for 1,000,000 raw samples and assessed 6.898 bits of min-entropy per byte on the non-IID track, against the 1 bit the firmware credits, while spectral lines near 116 Hz that hold about 5 % of the variance remain unexplained. At 168 MHz the masked signature took a median of 157 ms over 20 runs and a complete signing operation under 0.8 s, and the signer matched the pq-crystals reference in 1,976 checks natively and on an emulated Cortex-M4. The ATECC608 can neither store the 4,032-byte ML-DSA-65 key nor compute with it, so that key sits in ordinary flash behind readout protection, and on an earlier board, before that protection was enabled, a debugger copied it out and the copy produced a valid ML-DSA-65 signature without the device, although the leakage results come from an instruction-level emulator and nothing here is certified.

sEMG Foundation Models aim to learn general purpose representations over diverse subjects and recording conditions that boost performance on a variety of downstream tasks. However, existing evaluations make it difficult to discern whether pretraining alone is sufficient to combat the cross-subject overfitting which makes machine learning on sEMG so challenging. We conduct a systematic evaluation of three sEMG foundation models across three gesture classification datasets under both intra-session and inter-subject splits, using three fine-tuning strategies designed to isolate the contribution of pretraining. We find that pretraining boosts performance when train and test samples are drawn from the same recording session, but this benefit largely disappears under inter-subject evaluation. In low subject count datasets, pretraining provides little to no benefit and classical ML baselines match or exceed foundation model performance.

Text-to-image (T2I) systems serve users across languages and cultural contexts. However, evaluations of cultural representation focus mainly on recognizable elements such as landmarks, clothing, and activities, overlooking the cultural values that generated images convey. To bridge this gap, we introduce VisionValueBench, a multilingual benchmark that operationalizes six of Hofstede's cultural value dimensions (e.g., individualism versus collectivism) to investigate how T2I systems frame neutral social situations through a particular cultural orientation. We find that value-neutral prompts, which admit diverse cultural interpretations, nonetheless yield images that favor particular value orientations, a phenomenon we call visual value leakage. We evaluate prompts varying in language and geographic cues across 960 social scenarios and six T2I configurations. Generated images consistently favor the same value orientations across all six dimensions, for example, equality over hierarchy (low power distance), individual autonomy over group obligation (individualism), and enjoyment over restraint (indulgence). Prompt language has limited influence on these orientations, whereas geographic cues shift some dimensions toward the associated cultural values while largely preserving the prevailing orientations. These findings reveal substantial homogeneity in the cultural values conveyed by T2I systems worldwide.

Streaming video understanding requires models not only to process temporally incoming frames, but also to anticipate user intent for realistic applications such as Augmented Reality (AR) glasses. While prior streaming benchmarks evaluate temporal reasoning, none measure whether Multimodal Large Language Models (MLLMs) can interpret or leverage human gaze signals within a streaming setting. To fill this gap, we introduce StreamGaze, the first benchmark designed to evaluate how effectively MLLMs utilize gaze for temporal and proactive reasoning in streaming videos. StreamGaze introduces gaze-guided past, present, and proactive tasks that comprehensively assess streaming video understanding. Past and present tasks require immediate responses based on observations available at query time, whereas proactive tasks require models to continuously process incoming frames and respond at the appropriate future moment. To build StreamGaze, we develop a gaze-video Question Answering (QA) generation pipeline that aligns egocentric videos with raw gaze trajectories through fixation extraction, region-specific visual prompting, and scanpath construction. This pipeline produces spatio-temporally grounded QA pairs that reflect human perceptual dynamics. Across all StreamGaze tasks, we observe substantial performance gaps between state-of-the-art MLLMs and human performance, highlighting key limitations in gaze-based temporal reasoning, intent modeling, and proactive prediction. We further provide detailed analyses of gaze prompting strategies, reasoning behaviors, and task-specific failure modes, offering insights into current limitations and directions for future research. All data and code are publicly available to support research in gaze-guided streaming video understanding.

Smooth sequences over an alphabet of positive integers $\{a,b\}$ are sequences that are infinitely derivable, the emblematic example being the Oldenburger-Kolakoski sequence $κ$ over $\{1,2\}$. The main way to study their language is to consider a finite version of smooth sequences called smooth words. In this paper we prove that the smooth words are exactly the factors of smooth sequences and we make progress towards the conjecture that the complexity of smooth words over $\{a,b\}$ grows like $Θ\left(n^{\log(a+b)/\log((a+b)/2)}\right)$: we prove the lower bound over any alphabet and the upper bound over even alphabets, and we improve the known upper bound over odd and mixed alphabets. We also provide a dichotomy that links the language, the morphicity and the factor complexity of $κ$.

The use of algorithmic predictions in decision-making leads to a feedback loop where the models we deploy actively influence the data distributions we see, and later use to retrain on. This dynamic was formalized by Perdomo et al. 2020 in their work on performative prediction. Our main result is an unconditional reduction showing that any no-regret algorithm deployed in performative settings converges to a (mixed) performatively stable equilibrium: a solution in which models actively shape data distributions in ways that their own predictions look optimal in hindsight. Prior to our work, all positive results in this area imposed strong restrictions on how models influenced distributions. By using a martingale argument and allowing randomization, we avoid any assumption on how populations respond to predictions and sidestep recent hardness results showing that deterministic stable models are in general PPAD-hard to compute. Lastly, on a more conceptual note, our connection sheds light on why common algorithms, like gradient descent, are naturally stabilizing and prevent runaway feedback loops. We hope our work enables future technical transfer of ideas between online optimization and performativity.

In practice, auction data are often endogenously censored and anonymous, revealing only limited outcome statistics rather than full bid profiles. We study robust auction design when the seller observes only the distribution of a single anonymous order statistic of the bidders' values and seeks to maximize worst-case expected revenue over all product distributions consistent with the observed statistic. We show that simple and widely used mechanisms are robustly optimal. Specifically, posted pricing is robustly optimal given the distribution of the highest value; the Myerson auction designed for the unique consistent i.i.d. distribution, with uniformly random tie-breaking, is robustly optimal given the lowest value distribution; and the second-price auction with an optimal reserve is robustly optimal when an intermediate order statistic is observed and the implied i.i.d. distribution is regular above its reserve. Without any regularity assumption, when the second-highest value is observed, the best worst-case revenue of a second-price auction with a reserve is still at least a $2-\sqrt{2}\approx 0.586$ fraction of the optimal worst-case revenue. More generally, for a broad class of monotone symmetric mechanisms depending only on the top $k$ order statistics, including multi-unit and position auctions, the worst-case revenue is attained under the i.i.d. distribution consistent with the observed $k$-th order statistic. Our results provide a tractable foundation for non-discriminatory auction design, where fairness and privacy are intrinsic consequences of the information structure rather than imposed constraints.

World action models increasingly rely on pretrained diffusion/flow-based video generators assumed to capture physical dynamics for prediction, planning, and action generation. Existing evaluations assess plausibility, probe representations, or measure predictive surprise, yet physical consistency is history-dependent: preceding events constrain what can physically occur later. We introduce PhysTrace, a training-free framework that uses MLLMs to formulate history-conditioned physical expectations and tracks their agreement with observed video windows through temporal video--language alignment, rather than relying on direct plausibility judgments or task-specific probes. On IntPhys2, PhysTrace achieves 67.2% possible--impossible discrimination accuracy, outperforming the evaluated direct MLLM baselines. We further introduce reference-guided masked denoising for controlled reconstruction from mixed possible--impossible video latents. To support these reconstructions and evaluate temporal localization as an additional capability, we introduce IntPhys2-Timing, adding violation intervals to IntPhys2, with PhysTrace achieving a Hit Rate of up to 77.4%. On these reconstructions, human evaluations reveal model-dependent differences in physical consistency and fewer physically impossible outcomes at higher initial noise levels, trends broadly captured by PhysTrace.