让下一篇重要论文，不再错过。

Deterministic benchmark scores show that an agent received credit, but not whether that credit was earned, reported honestly, or would hold on a second run. We introduce a Trust Layer for Agent Evaluation, an additive post-hoc framework that reports, beside each recorded score, whether it should be believed. It verifies four properties: whether the result is supported by the benchmark's own grading logic, whether a passing answer was earned through traceable computation, whether the agent's completion claim matches what occurred, and whether the result is stable under repeated execution. The first three use only saved artifacts; the fourth re-runs the agent. Model judgments only label evidence under majority voting; all verdicts follow deterministic rules and never modify the recorded score. Applied to five agent configurations on 108 tasks from Agents' Last Exam, every model shows passing runs with no traceable computation (at rates varying tenfold), confirmed false completion claims, and unstable results: 18-46% of tasks do not stay in one score band over five runs. Only 22.6% of recorded passes clear all four checks (95% CI 15.0-32.6, n=84). Measuring what an agent can do and verifying that it did it are different problems, and current benchmarks address only the first.

The Arthur-Nimue-Merlin degrees are a generalization of the Turing degrees introduced by Kihara as a tangible description of the partially ordered set of Lawvere-Tierney topologies on the effective topos (equivalently, subtoposes of the effective topos). They are defined in terms of a three-player game that introduces both angelic and demonic non-determinism into oracle queries. We construct an order embedding of the Turing degrees with their order reversed into the Arthur-Nimue-Merlin degrees, whose image we call the "co-Turing degrees"; we then study the order relationship of these co-Turing degrees with the (naturally embedded) Turing degrees within the Arthur-Nimue-Merlin degrees. This is a short version of arXiv:2603.19946, focused on the main results.

Models of collective motion usually reduce social interactions to pairwise forces, despite empirical evidence for many-body effects. We introduce the directional atomic cluster expansion (dACE), which adapts the atomic cluster expansion (ACE) of interatomic potentials to self-propelled agents. dACE provides a systematically improvable, exactly equivariant expansion of an agent's acceleration that splits uniquely into 1-, 2-, 3-body and higher contributions, along with a self term for the agent's own past motion that is fitted so that it does not absorb the interactions. On simulated collectives in two and three dimensions with known rules, dACE recovers the interaction law body order by body order from little data, while the neural model SocialNet, the current closest competitor, needs more data, has much larger errors on many-body or chiral rules and is restricted to 2D. On real data sets of tracked zebrafish and golden shiners, the laws learned by dACE agree better between disjoint halves of the data than SocialNet's. The learned laws are interpretable, and in the shiners the 3-body term opposes the pairwise response as neighbourhoods get dense. Finally, we show that next-step prediction accuracy mostly measures self-propulsion and noise rather than the interactions, and suggest more robust combinations of error measures for interaction learning.

Automatic sleep stage classification from electroencephalography (EEG) signals is a critical task in clinical sleep medicine. While deep learning models have shown promising results in this domain, their performance is fundamentally constrained by the quality of training labels, which human experts manually annotate and that are subject to inter-rater disagreement and systematic labeling errors. In this paper, we propose a novel LLM-assisted label-noise filtering pipeline that operates exclusively during training to identify and remove unreliable sleep-stage annotations before retraining the classifier. Specifically, TinySleepNet is first trained on the original dataset to extract per-epoch SoftMax confidence scores, then low-confidence epochs are submitted to LLaMA 3.1 along with their EEG spectral features and surrounding sequence context. The LLM evaluates each epoch against AASM sleep-scoring guidelines and assigns a verdict of RELIABLE or SUSPICIOUS. Suspicious epochs are removed from the training set, and TinySleepNet is retrained on the cleaned data. Evaluated on the Sleep-EDF Expanded dataset using 20-fold cross-validation, our method improves overall accuracy from 81.8% to 84.6% and Macro F1-score from 75.6% to 77.4%, with particularly notable gains in REM detection. Crucially, because the LLM operates only during training, the lightweight TinySleepNet architecture (1.3M parameters) is preserved at inference, making the proposed pipeline suitable for real-time, wearable sleep monitoring applications.

We present \textsc{Ginger}, a state-of-the-art open-source C++ library for graph-based approximate nearest neighbor search (ANNS). We developed \textsc{Ginger} at Google to push the speed and memory efficiency of graph search on large and high-dimensional embedding datasets. \textsc{Ginger} surpasses existing ANNS libraries with regards to query throughput and indexing time while matching the memory footprint of the most space-efficient competitors. \textsc{Ginger} builds upon recent advances in proximity graph construction (PiPNN) and vector quantization (TurboQuant). We introduce Nested TurboQuant (NTQ), a two-level quantizer which supports low precision graph navigation and high precision reranking in a single code. This representation achieves near floating point precision with $2.6\times$ less memory. We also compress the size of our proximity graphs by up to $2.5\times$ without impacting query throughput. We combine graph reordering with a new lossless compression codec called AdaptiveGap, which builds upon StreamVByte. At $95\%$ recall, \textsc{Ginger} speeds up query throughput by an average of $1.8\times$ over each dataset's fastest competitor and by at least $2.3\times$ over any single library. This lead grows to $2.9\times$ over compact libraries on high-dimensional embeddings.

Large language models (LLMs) solve complex problems yet fail on simpler variants, suggesting they achieve correct outputs through mechanisms fundamentally different from human reasoning. To understand this gap, we synthesize cognitive science research into a taxonomy of 28 cognitive elements spanning reasoning invariants, meta-cognitive controls, representations for organizing reasoning and knowledge, and transformation operations. We introduce a fine-grained evaluation framework and apply it to 192K traces from 18 models across text, vision, and audio, alongside 1,346 human think-aloud traces on a new, domain-agnostic dataset for human-model comparison. We find that models are able to deploy cognitive elements seen in human reasoning but differ in how they use them. Leveraging these patterns, we develop test-time reasoning guidance that automatically scaffolds successful reasoning topologies, improving the accuracy of the strongest models by 9.7 percentage points on ill-structured problems. Meta-analysis of 1.6K LLM reasoning papers reveals the research community concentrates on easily quantifiable elements but rarely targets self-awareness, whose use differs between human and model reasoning. By establishing a shared vocabulary between cognitive science and LLM research, our framework enables diagnosis of reasoning failures and principled development of models that reason through robust cognitive mechanisms rather than spurious shortcuts, while providing tools to test theories of human cognition at scale.

LLM pruning must preserve quality while meeting hardware- and workload-specific constraints on latency, throughput, and memory. Existing pruning workflows often target parameter counts, requiring practitioners to manually select model sizes that meet latency, throughput, and GPU memory limits. However, parameter count alone does not predict these metrics, which depend on the model architecture, workload, hardware, and serving engine. We introduce AutoCompress, a hardware-guided compression framework that directly incorporates such constraints into differentiable architecture search. AutoCompress jointly optimizes global and per-layer structure to produce heterogeneous architectures, guided by serving-engine cost models validated against end-to-end latency, throughput, and memory measurements. We evaluate AutoCompress on long-context local coding, batched datacenter serving, and latency-sensitive in-game interaction. Compared to the state-of-the-art Minitron pruning framework, AutoCompress improves average accuracy across eight benchmarks by 6.57, 2.35, and 0.57 percentage points on RTX 5070, RTX 5080, and H100, respectively. AutoCompress also compresses Nemotron 3.5 Super from 120B to 74B parameters for single-B200 BF16 serving at 128K context, retaining 95% of its mean benchmark score.

Trajectory-based failure predictors for software engineering (SE) agents read the partial trajectory of a run to flag whether it is going right or wrong. If it is going wrong, the run can be stopped, retried, or switched to another model. We ask whether these predictors learn anything about the run itself. On public SWE-bench Verified trajectories, where each model attempts each issue once, two run-independent factors dominate predictor performance. The first is issue difficulty: a reference score that never looks at the run, only at how hard the issue is for other models, reaches 0.92 AUROC, whereas trajectory predictors reach about 0.62. The second is model ability: within an issue, knowing which model ran predicts failure better than our predictors do, and the predictors largely reproduce the overall ability ranking of the models. Beyond difficulty and ability, what predictors gain from the trajectory is statistically equivalent to zero. This confusion carries over to the actions taken after a prediction. Model switching is often motivated by the gap between the best single model's resolution rate and an any-model oracle. This gap is no larger than random variation alone produces. Per-issue switching gains nothing on held-out runs. In a repeated-run pilot, the same model often solves an issue in some runs and fails it in others. Retrying thus has real room to repair failures, but it rescues only failures caused by a bad run, not those on an issue beyond the model's ability. Current predictors cannot tell the causes apart, as they mostly predict the issue and the model, not the run. We call for failure prediction that explains why a run fails, evaluated on repeated-run benchmarks and in closed-loop, equal-budget settings.

Generalist Anomaly Detection (GAD) aims to detect anomalies in unseen domains using only a few reference samples. Recent normal-abnormal guided methods improve this setting by exploiting abnormal references, but their residuals often mix transferable anomaly cues with domain-specific appearance factors such as texture, geometry, and acquisition conditions. This residual domain entanglement limits cross-domain transfer and may produce spurious activations on novel domains. We propose DART, a plug-in framework for normal-abnormal guided GAD that learns to separate residuals into anomaly-relevant and domain-specific components. DART combines a Residual Disentanglement Module, which preserves anomaly-discriminative information while suppressing domain information, with Cross-Domain Meta-Training, which forms episodes across source domains to make the separation effective. The method is architecture-agnostic and can be inserted between residual computation and the detection head of existing GAD pipelines. Experiments on MVTec AD, VisA, and BraTS show consistent improvements over multiple base methods, with the largest gains under stronger domain shifts. https://github.com/aqeeelmirza/DART

After a runtime or API migration, an LLM-repaired procedure can run cleanly yet return wrong results, and a release check on typical test inputs ships it. We report a preregistered study of 73 tasks covering 60 documented changes in CPython, Node.js and SQLite. Every candidate is executed on the real runtimes against withheld contracts. Over the complete repair space, the all-assertions gate on typical inputs released 0.410 of wrong repairs. One edge input written from the release note cut this to 0.065, and to 0.061 on 15 unseen clusters. Three inputs from a blind GPT-5.6-luna writer that never saw the program reached 0.070. Two further frozen stages enlarged the menu to 1491 fragments and then added 233 hard distractors that match the legacy output on typical inputs. The edge input (0.058) and the frontier-model writer (0.058) passed their preregistered tests. Yet 0.168 and 0.153 of the hard wrong programs still passed. Two local-model writers failed their preregistered tests. Across four model families, the edge input cut wrong releases per attempt in all three open-weight families on all three menus, for example from 0.233 to 0.057, without lowering correct completion. Self-tests helped less. A blind AI audit flagged 34 contracts as stricter than their requirements. Dropping the disputed checks changed 0 verdicts, but class-label disputes remain open. No model-written code was executed. Artifacts are available from the authors on request.

We identify a key limitation of existing feed-forward 3DGS methods: Gaussian attributes are typically predicted in a radial-distance-normalized space that canonicalizes a global radial statistic of the reconstructed geometry, while the spacing between neighboring Gaussian centers can still vary substantially across scene scales and camera configurations. This mismatch induces systematic shifts in Gaussian-scale targets, leading to ambiguous supervision. To address this, we propose SplatAnything with Gaussian Spacing Normalization (GSNorm), which canonicalizes a robust scene-level statistic of Gaussian spacing to provide a more consistent spatial reference for Gaussian prediction. To rigorously assess our method, we further establish a systematic benchmark spanning diverse datasets, input sparsity levels, and challenging extrapolated viewpoints. Extensive experiments demonstrate that SplatAnything achieves state-of-the-art performance, with particularly strong gains under substantial variations in scene scale and viewpoint.

Recent neural decoding approaches achieve strong performance by training on large collections of paired neural-behavioral recordings, but such datasets are expensive, invasive, and difficult to scale. In contrast, behavioral data is abundant and easy to collect, raising the question of whether neural decoding can benefit from decoupling behavioral and neural representation learning. We introduce BEEMO, a flexible multi-session framework that enables training with arbitrary mixtures of paired neural-behavioral recordings and unpaired behavioral data. A behavior decoder learns movement dynamics directly from behavioral trajectories, while neural activity is incorporated through cross-attention layers when available, allowing behavioral and neural supervision to scale independently. Across multiple intracortical motor datasets and tasks in nonhuman primates, we show that incorporating unpaired behavioral data improves decoding performance, particularly when transferring to new tasks, and that adding even a small amount of behavioral data from the target task further improves transfer. By decoupling neural and behavioral data, we unlock a new dimension for scaling: unpaired behavioral data, which is substantially cheaper and easier to collect than paired neural recordings, can be used directly to improve decoding performance. We further show that behavior-only pretraining, without any neural pretraining, achieves performance comparable to models pretrained on substantially larger neural datasets. Together, our results suggest that scaling behavioral data offers a practical and cost-effective path toward neural decoding models that generalize across subjects and tasks. Code is available at https://github.com/nerdslab/beemo.

Partial single-motor loss of effectiveness (LoE) changes the remaining control-authority geometry of a quadrotor and can change which control allocator performs best during emergency landing[cite: 11]. We compare three allocators in Crazyflie software-in-the-loop simulation: bounded weighted least squares (reported as PINV), a finite-candidate residual allocator (QP-lite), and the same residual allocator with scoring parameters tuned offline by the Cross-Entropy Method (CEM)[cite: 11]. For this study, fault geometry is represented by the known failed-motor index[cite: 11]. At $η=0.496$ remaining effectiveness, matched development trials select CEM for M1, M3, and M4 and PINV for M2; the M3 selection is a one-trial margin (29/30 versus 28/30)[cite: 11]. After freezing this routing map, the policy achieves 117/120 safe first-contact touchdowns on fresh seeds and 115/120 in a separate randomized-order integrated-supervisor evaluation[cite: 11]. For the critical M2/PINV branch, Firth regression gives a nominal $η_{50}\approx0.4956$ with a within-model 95% bootstrap interval of approximately [0.4955, 0.4956][cite: 11]. One-factor-at-a-time $\pm10\%$ plant perturbations shift $η_{50}$ by up to 0.05495 for thrust coefficient and 0.04974 for mass; the most frequent violated first-contact criterion also changes from vertical speed in many conditions to angular rate for mass -10% and thrust-coefficient +10%[cite: 11]. At fixed $η=0.496$, PINV has a higher M2 safe count than frozen CEM in 9/11 tested plant states and ties in 2/11; the two ties are both 0/30[cite: 11]. The experiments therefore distinguish motor-conditioned allocator selection from sensitivity to plant-model mismatch[cite: 11].

Recent advances in speech generation have spurred the development of speech editing techniques. However, achieving high-quality speech editing remains challenging due to two key limitations. First, the major hurdle is the lack of large-scale, high-quality speech editing datasets. Constructing such datasets is costly, while open-source, scalable data pipelines remain limited. Second, the learning dynamics of speech editing models remain poorly understood. In particular, how models acquire editing capabilities and the relationship between generation and editing remain unclear. To address these challenges, we introduce VoxCanvas-41M, a large-scale bilingual dataset comprising approximately 41 million speech editing pairs. VoxCanvas-41M covers two major categories: content editing, including single-span, multi-span, and location-reference editing, and paralinguistic editing, covering the insertion and deletion of 39 classes of nonverbal events such as laughter, sighs, and coughs. Building on VoxCanvas-41M, we train VoxCanvas-Edit, an instruction-based speech editing model, demonstrating the effectiveness of our dataset in improving editing performance. Furthermore, we systematically investigate the learning dynamics of speech editing, examining how models learn different editing operations and how data scale, task interactions, and training strategies affect editing performance. The dataset, pipeline, and demos are publicly available.

Mathematical modeling turns an open-ended real-world problem into assumptions, a model, a solution, and a defended recommendation, and its answers matter only if they are both close to a credible reference and physically feasible; existing benchmarks either score solver fragments or grade reports with an LLM judge, leaving those numbers unchecked. We introduce TB-MathModel (the Terminal-style Mathematical Modeling Bench), the first benchmark to make complete contest-style modeling problems agentic, verifiable, and terminal at once, over 18 real CUMCM and MCM problems (2023--2025). Each task ships the verbatim statement, official attachments, and figures in a containerized terminal; the agent returns one JSON artifact, scored on the numeric core of the final question against a reproduction of the Outstanding-award paper. Two design choices distinguish it: direction-aware, one-sided scoring, which never penalises beating the anchor, and two-layer feasibility verification---a programmatic gate over six decidable invariant forms plus 624 Lean~4 obligations---with a hard gate that zeroes infeasible answers. Each task is scored against a panel of human outstanding papers rather than one, so a model must be close to many accepted answers; across seven multimodal entries (three seeds each) the strongest reach a multi-reference O-Eval of 64.58\%, while the \$2.54 open model holds 59.81\% at $1/100$ the cost. TB-MathModel turns the numeric core of modeling into a reproducible, machine-checkable signal for measuring long-horizon modeling competence and for collecting agent trajectories. The source code is available at https://github.com/wxj630/terminal-bench-math-modeling.

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.

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.

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.

This paper addresses safe coordination of scalar agents with constrained input dynamics over fixed rooted digraphs. We propose a networked Admissibility-Preserving Control (APC) architecture for a common moving output corridor under heterogeneous asymmetric input bounds, wherein the Admissibility-Preserving Input Realization (APIR) generates the physical inputs. In logarithmic barrier coordinates, the closed-loop dynamics form an exact cascade of exponentially decaying realization errors and directed consensus dynamics. We derive direction-specific compatibility conditions that guarantee uniform corridor and input margins, bounded commands, unique complete solutions, and exponential consensus for compact initial sets. The closed-form expression for the agreement value quantifies the effect of the initial APIR mismatch. Under the corresponding compatibility conditions, partial pinning guarantees safe reference tracking whenever the root component contains at least one informed agent. Simulations illustrate the coordination guarantees.

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/.

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.

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.

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.

The Rectified Power Unit (RePU) activation function, a differentiable generalization of the Rectified Linear Unit (ReLU), has shown promise in constructing neural networks due to its smoothness properties. However, deep RePU networks often suffer from critical issues such as vanishing or exploding values during training, rendering them unstable regardless of hyperparameter initialization. Leveraging the perspective of effective field theory, we identify the root causes of these failures and propose the Modified Rectified Power Unit (MRePU) activation function. MRePU addresses RePU's limitations while preserving its advantages, such as differentiability and universal approximation properties. Theoretical analysis demonstrates that MRePU satisfies the criticality conditions in the limit of a small kernel, and a finite-kernel analysis yields an initialization rule for deep MRePU networks. Experiments on polynomial regression, physics-informed neural networks (PINNs) and real-world vision tasks show that MRePU networks initialized by this rule remain trainable at depths at which RePU networks fail, while their accuracy relative to standard activations depends on the task.

Quadratic ball discrepancy measures how uniformly a code meets Hamming balls over all centers and radii. Perfect codes minimize this quantity among codes of the same cardinality. We prove a quantitative refinement: at the parameters of every perfect code other than a one-word code or the full space, the discrepancy excess over the minimum is at least an explicit positive multiple of the discrepancy at the packing radius. The latter equals the tiling defect divided by the square of the code cardinality. This defect is the total squared deviation of the covering multiplicity from one. The comparison applies to all codes of that cardinality. For one-error perfect codes, the coefficient is at least one, and no larger constant holds for all such codes; explicit coefficients depending on the parameters can be much larger. The tiling defect also measures the failure of uniform ball noise to smooth a code distribution. Consequently, the same discrepancy excess gives explicit bounds on holes, overlaps, and divergence from the uniform distribution.

On-Policy Self-Distillation (OPSD) improves reasoning by training a student on its own reasoning, using the same model conditioned on reference solutions as a teacher. Applying OPSD to multilingual reasoning requires the teacher to provide useful feedback across languages, even when the student makes mistakes in intermediate steps. We observe a phenomenon we call Teacher Drift: as these mistakes accumulate, the teacher may follow the student's incorrect steps instead of correcting them. Our analysis shows that this shift tends to occur earlier in lower-resource languages. To account for these differences across languages, we propose Teachable On-Policy Self-Distillation (TOPSD), which determines where and whether teacher supervision should be applied to each reasoning trajectory. TOPSD uses teacher-student likelihood to estimate where drift begins and select a prefix for supervision. It then verifies whether the teacher can recover the correct answer from that prefix, applying distillation only to prefixes that pass verification. Experiments on multilingual mathematical reasoning across ten languages and three model scales show that TOPSD consistently outperforms conventional OPSD, particularly in low- and medium-resource languages.

This paper presents the design and evaluation of an accessible virtual reality (VR) nature experience developed to promote mindfulness, reduce stress, and support emotional well-being. The system immerses users in a calming natural environment through realistic landscapes, ambient soundscapes, guided breathing exercises, and interactive checkpoints that encourage reflection. Accessibility was a central design consideration, particularly for users with diverse physical and sensory abilities or limited access to natural environments and traditional mindfulness resources. A pilot study with 10 participants indicated that the experience could support relaxation and emotional well-being. Participants also reported greater immersion with continuous movement than with teleportation, highlighting the importance of intuitive locomotion in designing inclusive, nature-based VR experiences for mindfulness and stress reduction.

Image classification models often encounter objects in diverse and unpredictable contexts at test time, which may differ substantially from those seen during training. This phenomenon, termed context shift, exposes a key fragility in neural networks: when models rely on non-causal contextual cues for prediction, shifts in context can lead to significant performance degradation. In this paper, we propose a novel training framework to improve the robustness of convolutional neural networks under context shift. Our approach leverages spatial feature attribution to guide models toward making predictions that rely less on contextual regions and more on object-relevant features. As a first step, recognizing a theoretical limitation of existing feature attribution methods we introduce a new variant, ContrastiveCAMs, which produces more faithful attribution maps of model predictions. Building on ContrastiveCAMs, we further propose Context-Regularized Cross-Entropy (CR-CE), a modification of the standard cross-entropy loss that regularizes the model's attention by suppressing the influence of contextual regions, thereby improving robustness to context shift. We evaluate the effectiveness of our approach on several medium-to-large scale datasets (Waterbirds, Spawrious, ImageNet/ImageNet-BG, Hard-ImageNet), and report consistent improvements in context-shift robustness.

Tree-based speculative decoding accelerates large language model inference by verifying multiple candidate branches in parallel. However, in practical serving scenarios, similar requests repeatedly induce overlapping candidate branches. While retrieval-based methods mitigate this by reusing historical drafts, the resulting candidate trees often contain many low-quality branches as the candidate tree grows, which reduces verification efficiency and wastes target-side computation. To address this, we propose ValuSpec, a plug-and-play candidate valuation mechanism that filters low-quality branches from a supplied candidate tree before expensive target-side verification. ValuSpec introduces transfer-based supervision to align filtering with the target model's behavior. A filtering threshold is estimated from the target model's greedy trajectories on a calibration split, without any parameter training. The target model then verifies the filtered tree under the output-identical greedy rule, so accepted tokens are guaranteed to match standard autoregressive decoding exactly. Experimental results on HumanEval, GSM8K, Dolly, and SpecBench show that, in our main evaluation, ValuSpec achieves up to 2.38x end-to-end speedup in retrieval-based tree settings. Furthermore, integrating ValuSpec into the EAGLE-3 dynamic tree framework yields up to 2.78x end-to-end speedup without modifying its tree construction strategy, demonstrating that ValuSpec serves as a generally applicable and plug-and-play candidate valuation module.

This paper presents a novel task of describing human facial expressions of a facial image in natural language, which captures the nuances of facial actions and emotional states beyond traditional emotion categories or facial action units (AUs). To achieve the facial expression captioning model, we propose a three-stage training framework that trains a vision-to-language model using synthesized image-text pairs and the BLIP-2 pre-training techniques. To overcome the challenge of missing training image-text pairs for facial expression captioning, we propose a strategy that involves synthesizing and combining captions using GPT-3.5 and existing annotations on either emotion categories or AUs. Experiments demonstrate the effectiveness of our method in generating captions that describe details of facial actions and emotions, as well as the inferential relationship between them, even when those emotions are not present in the training data. It is also demonstrated that the vision-to-language task enhances the performance of the intermediate visual features on both AU detection and emotion classification tasks.