Papers

The transition from passive foundation models to autonomous, goal-directed agentic AI systems has introduced unprecedented capabilities by coupling recursive cognitive reasoning loops, persistent memory architectures, live tool execution planes, and multi-agent collaboration topologies. However, granting probabilistic neural cores execution authority across filesystems, networks, and cloud infrastructure dissolves classical security perimeters: natural language simultaneously serves as input data, internal control code, and communication protocols, exposing a Turing-complete blast radius where untrusted data represents executable instructions. This survey delivers a comprehensive systems-security reference framework for trustworthy agentic AI, synthesizing 206 foundational studies and regulatory standards. We formalize the general agent architecture as a stateful 5-tuple and establish a 6-dimensional trustworthiness taxonomy covering security, safety, privacy, explainability, fairness, and accountability. We systematically analyze threat surfaces across intra-execution loops and interaction planes, formulate a multi-layered zero-trust defense-in-depth architecture integrating Dual-LLM isolation, Capability-Based Access Control, kernel eBPF probes, and sandboxed runtimes, review standardized evaluation benchmarks, and map technical controls to international AI governance frameworks.

Reliable progress in offline policy learning depends on careful reporting, well-tuned baselines, and evaluation across diverse conditions. Prior work has shown that results can be sensitive to reporting choices, hyperparameter tuning, and dataset properties, but these sources of variability have not been systematically investigated together at the scale needed to understand how they shape conclusions. To address this gap, we present a large-scale empirical study of offline reinforcement and imitation learning, training over 160,000 policies across 114 datasets. At this scale, no algorithm dominates: aggregate performance among the strongest methods is often close, but the leaders differ substantially across environments. We find that proper hyperparameter tuning frequently reshuffles perceived algorithm rankings and that benchmark composition can produce conflicting conclusions. We also study hyperparameter sensitivity and transfer across environments, identifying a simple strategy for deriving strong default configurations. We use our findings to develop a dataset-conditioned recommender that provides task-specific algorithm recommendations for practitioners. Finally, we release JumpStart: a resource suite containing every trained policy, per-model scores and hyperparameters, strong baselines across all environments, training and evaluation code, and an extensible website for retrieving, analyzing, and contributing results. Together, these resources aim to make offline policy-learning research more reliable and enable future work beyond the scope of this study.

We present the Variational Incompressible Optimal Transport (VIOT) operator, a generative neural operator for amortized incompressible density transport. Given a new source-target density pair, VIOT predicts a divergence-free velocity field and generates the full transport trajectory by feed-forward inference, replacing the hour-scale per-pair optimization used by adjoint fluid solvers and differentiable simulation baselines. The system consists of three components: a stream-function or vector-potential representation that enforces incompressibility by construction, a regularized incompressible transport objective that balances endpoint accuracy and flow smoothness, and a Fourier Neural Operator backbone that amortizes the solve across new pairs and grid resolutions. Together, these components make incompressible transport a reusable neural operator that facilitates various transport processes. Further, the generative capability extends beyond the training distribution, with VIOT producing incompressible transports for user-drawn source-target pairs in a real-time interactive system. We demonstrate VIOT on 2D and 3D density-transport benchmarks. Both 2D and 3D rollouts complete in seconds per pair, while per-instance baselines in our 2D comparisons optimize each new pair from scratch and require on the order of an hour, a roughly $10^4\times$ online speedup.

Historical Linux kernel patches capture defect knowledge that applies beyond their original repair sites. Recent work has shown that large language models (LLMs) can generate static-analysis checkers from historical patches and use them to uncover new kernel bugs. However, complete-checker generation requires the model both to recover the defect semantics expressed by a patch and to implement sophisticated program-analysis machinery, including object tracking, alias analysis, path-state maintenance, and interprocedural propagation. Coupling these responsibilities in a single end-to-end code-generation task can turn a simple defect rule into an unstable and expensive analyzer-implementation problem. To address this problem, we present TyPatch, which decouples patch-specific defect semantics from analyzer implementation. An LLM translates each patch into a typestate rule specifying its tracked object, actions, guards, transitions, and violations. A shared backend then executes these rules, binding their actions to program events, tracking object identity across aliases, propagating typestate along program paths, and producing reports for all rules. On Linux v6.16, TyPatch finds 559 distinct bugs, 121 of which have been confirmed by kernel developers. In a matched 38-patch comparison with the state-of-the-art complete-checker construction workflow, TyPatch uses 88.3-90.1% fewer generation tokens, while its initial report pools achieve 3.42-14.95$\times$ the precision of those produced by that workflow.

Recent advances in artificial intelligence (AI) have expanded the capabilities of non-player characters (NPCs), enabling them to perceive game states, perform in-game actions. In immersive virtual reality (VR) games, such assistance is not limited to providing hints or interface-level support: an AI companion can appear as a co-present character, share the player's spatial environment, and visibly act on game objects. This raises a design question for VR gameplay: how can AI companions best assist players while preserving their active participation in the virtual world? To explore this question, we developed a VR puzzle game for Apple Vision Pro featuring an AI companion across four gameplay modes: no assistance, command-based assistance, discussion-based assistance, and autonomous agent play. A within-subjects study with 24 participants showed that AI assistance significantly reduced players' workload. However, autonomous agent play, despite producing the lowest workload, substantially diminished player experience by reducing challenge, autonomy, immersion, and enjoyment. Qualitative analysis further showed that players evaluated the companion not only by its usefulness, but also by whether it felt like a tool, a teammate, or an integrated character in the game world. We categorised participants into four player types and summarised their expectations of AI companions. These findings provide design implications for AI companions as embodied participants in VR games.

An external record may contain a procedure to apply or text to read, depending on the user's request. IBBench-Light tests both uses against the same record. Twelve semantic bases yield 144 matched pairs per model; four quantized instruction models produced 1,152 archived greedy responses. Paired exact-contract accuracy (PECA) requires both members to satisfy their output contracts. Qwen succeeds on 132 execute and 109 process prompts, but only 97 complete pairs, showing what marginal averages omit. We audit literal-target exposure and case normalization, then add 1,722 logged CPU generations to test directive-absent controls, twelve additional semantic bases, within-base wording changes, and generation stopping. In the pinned Phi rerun, changing the end-of-sequence (EOS) set changes exact paired success from 0/144 to 62/144. A bounded IHEval comparison uses the same SmolLM2 checkpoint and output budget while preserving its published instruction roles and scorer. The benchmark measures conditional task and output-contract success. Its task margins and paired count need to be read together with the stopping policy.

Quantum Natural Language Processing (QNLP) uses pregroup grammars to translate grammatical structure into diagrammatic representations and quantum circuits. Recent Hindi QNLP work has shown that Hindi-specific pregroup grammars can support grammar-sensitive compositional models, but grammatical type assignment is still largely manual, limiting scalability. This paper formulates automatic Hindi pregroup supertagging as a token-level classification task. Using a manually annotated corpus of 380 Hindi sentences, we evaluate lexical, contextual, prompting-based, lexical-repair, and suffix/morphology-aware methods. Results show that simple lexical and contextual models are strong in this low-resource setting: contextual backoff achieves the best completed accuracy of 64.56%, while raw Qwen2.5 prompting reaches only 11.65%. Lexical repair raises LLM-assisted prediction to 64.08%, demonstrating the value of constraining generative outputs with symbolic grammar knowledge. Diagnostic analysis further shows that seen and unambiguous tokens are much easier than unseen tokens, and suffix/morphology features improve karaka-token accuracy but not overall performance. These results show that automatic Hindi pregroup assignment is feasible and can reduce reliance on manual annotation in future multilingual QNLP pipelines.

Open-source software ecosystems are web-scale dependency networks. A downstream package can become exposed to security risk not because its own source code changes, but because one of its transitive dependencies later receives a vulnerability advisory. Existing vulnerability-detection work often focuses on whether code is currently vulnerable or whether a known vulnerable dependency is already present. We study a different problem: future transitive vulnerability exposure. Given a package-version dependency graph observed at release time, the task is to predict whether any non-root dependency will receive a vulnerability advisory within a future horizon. This problem is important for Web intelligence and software supply-chain security because it supports proactive dependency triage before future exposure is visible. It is also easy to evaluate incorrectly: current vulnerable dependencies can leak the label, and different versions of the same root package can create package-level memorization across train and test splits. We therefore construct PatchRisk, a leakage-aware benchmark from Open Source Vulnerability advisories and deps.dev dependency graphs for npm and PyPI. The benchmark uses filtration-aware labels, package-disjoint evaluation, temporal testing, and nested 1K, 3K, 5K, and 10K sampling scales. The largest cleaned setting contains 9,007 root package-version graphs spanning 4,157 root packages. We evaluate three feature families: TimeOnly, GraphStruct, and HistoryGraph. On the 10K temporal-test benchmark, HistoryGraph improves AUPRC over the strongest TimeOnly baseline from 0.351 to 0.640 for 90-day forecasting and from 0.473 to 0.813 for 365-day forecasting. The improvement remains stable across smaller scales and package-group shuffle robustness tests.

AI-powered gameplay support agents hold promise for game-based learning, yet grounding generative models in structured game data remains an open challenge. We present PEARL (Parallel Education Agent for Reflection and Learning), a dual-component Retrieval-Augmented Generation (RAG) system that combines semantic knowledge retrieval with structural board-state matching to deliver contextualized scaffolding in Parallel, a puzzle game for learning parallel programming. PEARL operates on two input streams (natural language queries and board topology), retrieving both conceptual explanations of gameplay moves and peer-generated board states as evidence: capabilities unavailable to a standard Large Language Model (LLM) with game state access alone. In a qualitative evaluation (N=10) comparing PEARL against an existing community-based Open Player Model (OPM) visualization system, participants preferred the visualization system on perceived usefulness and reported higher frustration with PEARL; five of ten minimized or abandoned the AI tool during play. Proactive delivery, generic responses, and trust deficits drove disengagement, while a subset of four participants found PEARL's grounded explanations complementary to visualization in specific contexts where they initiated the interaction. We position PEARL as a deployed design probe whose failure modes inform a concrete design agenda for AI gameplay support, captured as seven open problems for the community.

Masked reconstruction is widely used for EEG foundation models, but optimizing reconstruction on low-SNR waveforms does not necessarily produce the most useful latent representation. We introduce MANAS-2, a new EEG foundation model that combines a Raw-Band Hybrid (RBH) masked autoencoder with Constrained Reconstruction (ConRec), a physics-motivated regularizer. RBH jointly reconstructs temporal waveform patches and compact spectral-band targets, while ConRec acts only on the temporal decoder output, penalizing differences in RMS energy between adjacent short windows of the reconstructed waveform. ConRec is intended to shape the encoder by biasing it toward the organization of oscillatory-envelope information. Across seven held-out EEG datasets, adding ConRec to an otherwise identical RBH model increases frozen ridge recovery of six-band spectral power from mean R^2=0.860 to 0.906 and recovery of inter-patch band-energy dynamics from R^2=0.283 to 0.354, while temporal waveform information remains highly recoverable from the frozen latents. Applied to a temporal-only masked autoencoder, ConRec also improves frozen downstream transfer and frequency-dependent latent geometry despite receiving no spectral targets: i.e., the effects of ConRec are architecture-independent. MANAS-2 also outperforms leading EEG Foundation Models on most downstream knowledge-transfer tasks. From the effects of ConRec, we see that a physically motivated constraint imposed through the decoder can make for a more spectrally organized and transferable latent space. MANAS-2 therefore provides a new EEG foundation model built around constrained reconstruction as a mechanism for shaping representation–rather than reconstruction–quality.

As autonomous agents are increasingly deployed, they must be able to coordinate with previously unseen agents, such as humans. This challenge has been formalized as Ad Hoc Teamwork (AHT), and has attracted a substantial body of research. However, progress has been hindered by the prohibitive computational cost of the AHT research lifecycle, lack of standardized benchmark implementations, and the absence of a diverse, validated evaluation teammate suite. This work introduces JaxAHT, the first open-source, JAX-based library designed to accelerate and standardize the AHT research lifecycle. Leveraging JAX's hardware acceleration and massive parallelization capabilities, JaxAHT provides a unified framework for teammate generation, ego agent training, and evaluation against unseen teammates, achieving approximately 95x wall-clock speedup over existing PyTorch counterparts. Along with the library, we contribute a diverse suite of evaluation teammates across Level-Based Foraging, Overcooked, and Hanabi. Using JaxAHT, we conduct a large-scale, compute-controlled benchmark study of AHT algorithms, finding that no algorithm consistently performs best, that agent modeling primarily offers benefits in role-based scenarios, and that best response returns are underestimated by reinforcement learning from scratch.

An updated model can improve an aggregate metric while degrading a slice that matters to a downstream user. We study checkpoint selection subject to non-regression tolerances relative to a retained incumbent. The central distinction is between failing to detect harm and certifying non-inferiority: the former can release harmful updates with high probability when evaluation is noisy. We give a reproducible release procedure that separates candidate search from independent, paired evaluation and returns the exact incumbent when certification fails. Applying established intersection-union and Learn-then-Test principles, we state finite-sample guarantees for one frozen candidate, a finite candidate library, and a prespecified testing order. A joint release decision does not require a slice-count Bonferroni penalty, although certification power can still decrease with the number of slices. In bounded-score simulations, a no-detected-harm gate releases a harmful candidate in 99.7% of trials in one 32-slice setting, compared with 2.6% for an exact non-inferiority gate at a 5% target. A constructed two-block family yields larger certified utility than a scalar path under matched candidate counts. Public digits experiments, including a subsequent continuation that improves average aggregate accuracy, return the incumbent in every run because certification is underpowered. These results establish an auditable protocol and its limitations; they do not establish benefits on foundation-model or multilingual translation upgrades.

Many real-world scenarios can be represented using graph-structured data. However, traditional GNNs that transmit messages based on first-order neighbors have long faced several fundamental contradictions: increasing depth leads to over-smoothing, long-range dependencies cause over-compression, fixed neighborhoods restrict the receptive field, and on heterophilous graphs, topological neighbors become a source of noise. Although many works have addressed these issues individually, few mechanisms can simultaneously alleviate all of these challenges. To address the aforementioned problems, we propose a Position Encoding-Based Deformable Spatial Aggregation Module (PEBDSAM) that solves them all in one step. Specifically, we utilize a deformable mechanism in the position space to identify relevant nodes to supplement the original first-order neighbor information of GNNs, allowing traditional GNNs to adapt to heterophilous scenarios. Through diagnostic experiments, we obtained several major findings: current offsets fail to have any effect; subsequently, we analyzed the causes of offset failure and why model performance still improves even after offset failure, pointing out future research directions. Based on these diagnostic experiments, we streamlined the original PEBDSAM, resulting in a simplified version, which we call the Position Encoding-Based Spatial Aggregation Module (PEBSAM). In addition, we propose a PEBSAM-Speed to adapt to large datasets. Finally, we designed the module to be plug-and-play and applied it to GCN, GAT, GIN, and GraphSAGE, achieving desirable results on three homophilous datasets and six heterophilous graph datasets.

Selecting a decentralized Multi-Robot Task Allocation (MRTA) method for embedded deployment on autonomous platforms requires considering more than route performance alone. We benchmark six decentralized MRTA allocators (CBAA, ACBBA, PI, HIPC, DMCHBA, and DGA) in the Collaborative Visit (CV) scenario to characterize tradeoffs among MinMax and MinSum travel, communication robustness and demand, allocation reliability, computational burden, and scale sensitivity. The core study uses 500 paired ten-target instances across 25 ideal and degraded communication conditions spanning Bernoulli loss, Gilbert–Elliott loss, and Rayleigh fading, with additional campaigns examining pre-allocation, execution-integrated computation, and sensitivity to grid size, robot density, and target load. Across the 24 impaired core conditions, DGA and DMCHBA achieved the lowest mean MinMax travel at 24.49 and 24.78 steps, respectively. HIPC narrowly led mean MinSum travel at 66.95 steps, followed by DGA at 67.22, with both methods occupying the top two in every impaired condition. DMCHBA had the lowest publication intensity at 2.08 publications per team step. In ten-target pre-allocation, HIPC and DMCHBA remained viable and stable in every tested condition, while ACBBA, PI, and DGA lost stability or viability as communication degraded. Under ideal delivery, median full-protocol computation $\Cterm$ in the primary ten-target comparison ranged from 4.88 ms for DMCHBA to 1.346 s for DGA. Static route quality preserved DGA and DMCHBA as the leading MinMax methods, while DGA led MinSum at three of four target loads and HIPC led at 50 targets. Static and execution-integrated computation rankings diverged as task load increased. The results identify distinct allocator operating regions across route objective, communication behavior, reliability, and computational constraints.

Human corrections identify editable spans, but the examples receiving corrections may come from a selective feedback channel. We analyze this interaction at a fixed model checkpoint by decomposing a localized gradient into edited and retained untouched components. Squared relative selection bias is a ratio of quadratics whose derivative has the sign of an explicit quadratic polynomial. Localization can increase, decrease, or nonmonotonically change this diagnostic; its direction depends on component biases and geometry. Oracle importance weighting recovers the population mean for each fixed localization objective, but these objectives have different targets. Against one common full-gradient target, we derive the finite-sample mean-squared error, an analytic optimal retention coefficient, and a fixed-clipping extension. Exact finite-population calculations and 10,000 Monte Carlo repetitions per sample size verify the identities and counterexamples. Public human-post-edit experiments use two translation directions and pretrained models, with declared synthetic selection. An English-German extension differentiates 73.89 million native parameters. In all three declared settings, hard localization has higher relative bias but lower absolute bias than full retention. Untouched-component biases are nonzero and selected component means have negative inner products, so the general criterion applies where the simple unbiased/aligned explanation fails. Output-bias diagnostics show the same endpoint ordering of relative bias across both directions, with one interior maximum. Mechanisms reuse each language's records and include a mixture; they are not independent replications. The evidence separates relative amplification from absolute gradient error and establishes estimation properties, without inferring translation-quality gains or identifying actual complaint propensities.

The mechanical memory of fabrics often leads to persistent wrinkles, which reflect key physical properties and habitual wear patterns. Simulating these wrinkles accurately is essential for visual plausibility in digital garments, yet no dedicated approach exists for inferring the parameters that govern their formation due to the lack of precise datasets and estimation methods. We introduce Fabric-101, an inclusive, accurate, and extendable fabric dataset comprising over 101 common fabrics following textile standards. Unlike existing datasets, it captures three physically distinct deformation components (i.e., self-recoverable (elastic), recoverable (friction-driven), and unrecoverable (plastic)), from cyclic loading-unloading measurements. Building on this data, we propose a differentiable cloth simulator combining an elasto-plastic model with friction, designed to capture recoverable and unrecoverable wrinkle formation. Our simulator is differentiable and uses adjoint method to learn fabric physical parameters from the measured hysteresis curves, learning fabric-specific wrinkle behaviors. Through extensive experiments, we demonstrate that our model reproduces persistent wrinkles that are visually and physically similar to real fabrics across diverse materials and motions. Dataset and code are available in https://github.com/GongDeshan/Fabric_101_for_Wrinkles.

Co-salient object detection (Co-SOD) requires a model to find foreground regions that are salient in individual images and supported by the image group. We present Rank-Consistent Set Reasoning (RCSR), a supervised dense-prediction framework that models a group as an unordered set rather than as a sequence of images or a semantic label. The core idea is to rank how strongly each spatial region agrees with a small collection of learned group slots at every image scale, and to aggregate these ranks with a robust trimmed statistic. This suppresses accidental pairwise matches and prevents one atypical group member from dominating the shared representation. A set encoder builds group slots directly from multi-scale visual features, while a rank-consistency gate measures whether the ordering of candidate regions is stable across group members. The gated slots are decoded jointly with per-image features to produce co-saliency maps. The model contains no natural-language branch, no open-vocabulary detector, and no external segmentation model. We further introduce a group permutation objective and hard-distractor augmentation so that the model learns the properties of a set-level target rather than memorizing image order or isolated visual saliency. We formulate an evaluation protocol for CoCA, CoSal2015, and CoSOD3k, together with tests of group-size robustness, distractor rejection, order invariance, and cross-dataset transfer.

In the best-arm identification problem, we are given $n$ stochastic arms with unknown means and wish to identify the arm with the largest mean with probability at least $1-\delta$, using as few samples as possible. We consider independent Gaussian rewards with unit variance and means in $[0,1]$. Chen and Li [2016] conjectured that the instance-wise sample complexity of this problem is characterized by the gap entropy, up to an additive term arising from the two-arm problem. In this paper, we resolve their gap-entropy and almost instance-wise optimality conjectures. For an instance $I$, let $\Delta_{[i]}$ be the gap between the largest and the $i$-th largest mean, let $H(I)=\sum_{i=2}^{n}\Delta_{[i]}^{-2}$, and let Ent$(I)$ denote the entropy of the normalized complexities of its dyadic gap groups. For every $0<\delta<0.1$, we show that the order-oblivious instance-wise lower bound is $ {\Theta} (H(I)[\log(1/\delta)+Ent(I)]). $ We also give a single $\delta$-correct algorithm with expected sample complexity $ O ( H(I)[\log(1/\delta)+Ent(I)] +D\log(e+\log(e+D))),D=\Delta_{[2]}^{-2}, $ without prior knowledge of the gaps. Our lower bound removes the dyadic-gap and monotonicity restrictions of previous work, and our upper bound removes the additional polylogarithmic factor multiplying the two-arm term. Thus, a single algorithm attains the instance-wise lower bound up to an additive two-arm term. The main theorems have been formalized and proved in Lean 4.

Accurate job runtime prediction can improve scheduling-aware resource management in grid and distributed computing environments, but prediction models must be evaluated under realistic deployment constraints. This paper revisits CPU burst time prediction on the GWA-T-4 AuverGrid workload trace and reformulates it as leakage-safe pre-execution job runtime prediction. We define the target as job-level runtime, use only submission-time attributes, exclude post-execution variables, and evaluate models under temporal and cold-start settings rather than relying only on random cross-validation. We compare standard regressors, chronological historical baselines, categorical encoding strategies, and CatBoost with native categorical handling. We further add temporal hyperparameter tuning, runtime predictability analysis, feature ablation, error analysis by job length, and a minimal scheduling simulation. After temporal-validation tuning, CatBoost achieves the strongest deployment-oriented result with R^2=0.239, MAE=27,019, RMSE=46,587, and LogMAE=2.646 on the held-out temporal test set. A single-server simulation over all 69,523 held-out temporal test jobs shows that prediction-informed SJF reduces average waiting time by 50.92% relative to FCFS. The results show that random-split evaluation overestimates performance, categorical-native boosting improves temporal generalization, and long-job underestimation remains a scheduler-relevant challenge.

Adaptive technology for older adults with cognitive impairment is typically designed around individual preference, yet most of this population lives and cooks with a spouse or family member. This paper examines a co-design workshop in which four dyads and two individuals (N=10) built kitchen cabinet designs from twenty-one options across five features. Thematic analysis of thirty selections identifies recurring patterns: visual access retained through enclosure rather than open shelving, physical effort treated as a household concern, and automation accepted when predictable. Structured analysis of ten interaction episodes shows how some patterns were negotiated in practice, including care partners contributing embodied constraints distinct from the primary participant, and disagreements resolving through documented deliberation. Together, the two analyses show that adaptive technology preferences are not always individual properties but can be shaped through household interaction. We offer candidate design implications for facilitation protocols and collaborative systems supporting shared decision-making in aging-in-place contexts.

Chunked vision language action (VLA) policies execute several commands per query, but jerk within chunks and across replanning boundaries can induce oscillatory motion and sharp actuator transients. We present GROOVE, an online regulator that searches directional correction regions around the raw three dimensional end effector (EEF) path, without retraining or additional VLA inference. It optimizes the new chunk using delivered commands as boundary conditions, reducing boundary and within chunk jerk while bounding cumulative translation and local axis angle deviation from the raw plan after every command. Using quadratic programs (QPs), GROOVE generates a cube reference and thirteen directional candidates, then selects the one with the lowest command space jerk under a reference relative deviation cap. On a held out LIBERO benchmark, GROOVE achieves the largest reductions among the evaluated methods, reducing translational and rotational EEF jerk by 33.02% and 43.42%, respectively, with task success of 95.75% versus 93.75% for raw execution. Across 50 matched UR5e pairs with measured execution timing, it reduces translational and rotational tool center point (TCP) jerk by 16.39% and 19.49% and joint current slew by 29.09%.

Pronunciation assessment requires acoustic evidence that is temporally precise, diagnostically meaningful, and faithful to the learner's actual production. However, existing acoustic models often struggle to provide recognition and segmentation evidence simultaneously. CTC-based phone recognizers can predict phone sequences flexibly, but their sparse and peaky posteriors often miss phone boundaries and fine-grained pronunciation cues. In contrast, text-dependent forced aligners provide reliable temporal information when transcripts are available, but are not directly applicable to reference-free pronunciation analysis. In this work, we propose a topology-aware frame-wise acoustic model that learns dense ordered state posteriors within each phone. The key idea is to recover phone-internal state structure in a neural acoustic model by combining ordered subphonetic states with optimal temporal transport classification (OTTC). This combination encourages dense monotonic frame-level state discrimination while preserving phone recognition ability. Experiments on read, spontaneous, and L2 speech show improved segmentation over neural baselines with competitive recognition performance. Downstream evaluations further show gains in mispronunciation detection and automatic pronunciation assessment. Probing analysis suggests that the learned states capture phoneme-dependent acoustic structure rather than arbitrary frame-level distributions.

An identifiability criterion is a condition on a tensor decomposition that certifies uniqueness when the condition holds. Kruskal's classical condition is one of the best-known deterministic criteria for identifiability. However, no polynomial-time decomposition algorithm is known under the Kruskal condition; verifying the condition itself is NP-hard. Lovitz and Petrov introduced a strictly more general identifiability condition which, in contrast, is polynomial-time verifiable, but no polynomial-time decomposition algorithm was known under this condition either. In this paper we give a randomized polynomial-time algorithm, in the algebraic model over $\mathbb R$, for tensor decomposition under the Lovitz–Petrov condition, and therefore also under the stricter Kruskal condition. Moreover, combining our algorithm with polynomial-time verification of the Lovitz–Petrov condition yields an efficient end-to-end certification procedure: after computing a decomposition, one can deterministically certify in polynomial time that it is unique and therefore of minimum rank.

LLM serving reuses KV cache by exact prefix match, so when a prompt is assembled from a set of reusable pieces – retrieved passages, tool definitions, few-shot exemplars – the order chosen for those pieces determines how much computation can be shared. Every deployed system fixes that order by a single global convention. We prove this is optimal only when requests contain at most two pieces, and asymptotically wrong in general. Our main result is a structure theorem: the minimum prefix-trie cost equals min_H sum_x w(x) t_x(H) over binary hierarchies H on the requests, where t_x(H) is the canonical decomposition size of the set of requests needing chunk x. Choosing chunk orders is therefore equivalent to choosing one hierarchy over requests. The identity yields an O(3^m) exact algorithm, identifies the two-chunk case as minimum vertex cover, and shows that on the leave-one-out family the optimum is the minimum external path length of a binary tree – the merge-sort recursion – so a global order pays Theta(n^2) against a true cost of Theta(n log n). Agglomerative clustering by common intersection is a tight 1/2-approximation for the achievable saving. On BM25 retrieval traces over three BEIR corpora the resulting layout reduces prefill by 17-36% against production RAG ordering, and the margin widens with retrieval depth as the theory predicts. Serving requests in the hierarchy's DFS order finally lets a cache holding one request's context attain the unbounded-cache optimum exactly, so cache capacity and reorder window act as substitutes.

Most existing visual odometry (VO) systems treat feature correspondences as deterministic measurements or assign uniform uncertainty, ignoring the inherent localization ambiguity of different observations. However, correspondence uncertainty is often anisotropic due to image structures such as edges, repetitive patterns, and motion blur, which can significantly affect geometric optimization. In this work, we propose MomentBA, a geometry-aware bundle adjustment framework that derives anisotropic correspondence uncertainty from second-order spatial moments of local similarity responses. Instead of introducing additional covariance prediction networks, the proposed method directly converts matching response distributions into interpretable covariance estimates and incorporates them into bundle adjustment as correspondence-specific information matrices for uncertainty-aware residual weighting. Furthermore, the proposed formulation is integrated into a differentiable optimization framework, establishing a direct connection between correspondence uncertainty and geometric estimation. Experiments on the EuRoC MAV and TartanAir v1 Hard datasets demonstrate that MomentBA improves monocular visual odometry accuracy compared with existing feature-based and learning-based approaches. The proposed anisotropic covariance model achieves lower rotational errors and more robust trajectory estimation than fixed and isotropic uncertainty models, validating the effectiveness of geometry-induced uncertainty modeling for challenging visual environments.

Sparse-view computed tomography (CT) reduces radiation dose and acquisition time but remains severely ill-posed because incomplete projections poorly constrain null-space information. Existing learning-based methods often estimate this information in high-dimensional image space, conflate physical measurement errors with prediction errors, and depend on fixed discretizations. We propose SONAR, a Structure-Consistent Neural Operator for Null-Space-Aware Reconstruction. Instead of recovering the full null-space component, SONAR predicts a low-dimensional null-space-aware representation from the acquired projections as pseudo-measurements. It separates measurement and pseudo-measurement residuals, lifts them into the image domain through physics operators, and applies independent neural operators to constrain their structural effects, thereby accommodating admissible errors while suppressing unsupported structures. To support cross-discretization reconstruction, an anisotropic U-shaped neural operator models the periodic angular and nonperiodic detector dimensions using direction-dependent continuous supports, while image-domain neural operators re-discretize continuous kernels on target grids. These components form an optimization-inspired unrolled network. Experiments on simulated AAPM and clinical MARS photon-counting CT data demonstrate consistent improvements across seen and unseen view settings and unseen image resolutions. On AAPM dataset, SONAR improves PSNR by 1.87~dB at 62 views and by 7.63~dB under zero-shot transfer to a $512\times512$ grid over the strongest competing methods. SONAR also achieves the best overall performance in all clinical settings evaluated, demonstrating accurate, structurally reliable, and discretization-robust sparse-view CT reconstruction.

Negation remains a longstanding challenge for both language models (LMs) and large language models (LLMs). Prior work mainly focuses on a small set of high-frequency single-word negation cues, such as not and never, with limited exploration of broader negation types and modern LLMs. To address this gap, we construct NegCue, a large-scale dataset containing over 1.8M samples spanning single-word, multi-word, and affixal negation with more than 200 unique cues. We further pre-train both encoder-only LMs and LLMs on NegCue to investigate how different negation types affect negation understanding. Experiments on five downstream benchmarks show that negation types contribute unevenly to performance gains under the same training scale. In particular, affixal negation yields the largest improvements, while the gains from the commonly studied single-word negation remain modest. Moreover, our results demonstrate that further pre-training improves negation understanding for both LMs and LLMs.

We introduce LayerRoute, a parameter-efficient method for adaptive transformer layer-skipping that combines per-layer hard-gated routing (trained via a straight-through estimator) with joint LoRA fine-tuning. LayerRoute augments each of the 24 transformer blocks in Qwen2.5-0.5B-Instruct with a lightweight per-layer router (~21.5K parameters) and LoRA adapters (rank 8, ~1.08M parameters), training both jointly under a gate-regularized language-modeling objective. Across 10 independently-seeded training runs, LayerRoute converges to an identical skip-pattern structure in every run - a consistent set of 9 middle layers (8-16) becomes skip-eligible in all 10 seeds - and delivers genuine, verified wallclock speedup in every run (1.02x-1.06x, mean 1.04x). Quality is preserved or improved in every configuration tested: joint LoRA adaptation yields a perplexity improvement over the unmodified backbone in all 10 seeds (mean delta = -1.16 and -1.11 across the two evaluation splits used). We further verify the router performs genuine, non-trivial per-input computation: gate decisions in skip-eligible layers change the actual skip/run outcome for 87-100% of held-out samples, confirming real input-dependent routing rather than a fixed pruning pattern. LayerRoute trains in under 7 minutes on a single A100 and adds negligible overhead beyond the routing decision itself. We report our full reproducibility methodology, including a systematic diagnostic investigation into what determines the router's per-input decisions, as part of this work.

Fine-tuning instruct models often improves target performance while inducing behavioral drift from the reference model, which can degrade existing capabilities. Rather than treating this drift as an uncontrolled consequence of optimization, we specify a behavioral drift budget before optimization and ask how to boost the target-task performance within it. Locally, behavioral drift induces a shared geometry anchored at the reference model, with the drift budget defining a boundary within this space. In this space, drift determines distance from the reference, leaving update direction as the remaining degree of freedom. Fine-tuning updates can therefore be compared through their directional efficiency, naturally reformulating fine-tuning as a direction-selection problem. This reformulation makes a concrete prediction: changing the accessible directions can qualitatively alter the outcome of fine-tuning. We test this prediction in a stringent QA-only setting, where strong instruct models are fine-tuned only on final answers but must still generate multi-step reasoning at inference. Despite this mismatch, a coarse layer-selective probe reverses the failure of QA-only fine-tuning and reveals the existence of effective directions, with multiple neighboring configurations improving target performance while preserving reasoning and general capabilities. Across Qwen3-8B and Qwen3-14B, these directions substantially improve scientific reasoning and multilingual translation. Over more than 100 languages, the resulting models match or outperform dedicated translation systems and provide a stronger initialization for subsequent reinforcement learning. Our results suggest that fine-tuning is not just about how much a model changes, but how that change is spent. https://github.com/CONE-MT/DCO and https://huggingface.co/collections/LLaMAX/dco

How can robot policies learn more effectively from a fixed demonstration budget? The first Real-world Embodied AI Learning (REAL-I) Challenge at ICRA 2026 examined this question through simulation, real-robot evaluation, and an on-site final on a shared dual-arm humanoid platform. We describe the challenge tasks, data and deployment interfaces, and competition results, then compare the approaches contributed by NUS-CLEAR, RCL-Lab, and DeepTouch AI. Their systems combined pretrained vision-language-action models and task-specific imitation policies with different strategies for data curation, staged adaptation, checkpoint selection, and action-space design. The team reports highlight the importance of adapting to the deployment environment while retaining prior capabilities, treating demonstration quality at an appropriate temporal scale, and suppressing errors in inactive robot components. They also expose the limitations of offline action-prediction metrics for forecasting closed-loop success. These observations motivate a view of fixed-data robot learning that integrates data, adaptation, evaluation, and deployment.