Papers

Reward-free latent world models can learn from offline videos and solve new image–goal tasks by optimizing actions through predicted latent futures. This setting places two demands on the planning state: its coordinates must be comparable with a goal image. Moreover, its dynamics must retain velocity, motion trend, contact, and other history–dependent information beyond those goal coordinates. Offline training creates a second mismatch: each recorded trajectory reveals one factual future, whereas a sampling–based planner compares many actions that were not taken from the same state. We introduce FIRM-WM (Factual–Interventional Recurrent World Model), a compact pixel world model designed around these two gaps. Its recurrent state separates a typed, goal–comparable configuration from a 128-dimensional dynamic fiber used for prediction but excluded from the terminal goal cost. Broad factual trajectories provide state coverage, while common–reset intervention branches provide observed outcomes for alternative action sequences. Before executing each branch, we reset the environment and restore the same recorded values exposed by the environment's state–setting interface. Under matched CEM planning and three independent full-pipeline seeds, FIRM-WM reaches 99.0$\pm$1.0% on TwoRoom, 92.7$\pm$2.1% on Reacher, and 88.0$\pm$3.0% on OGBench-Cube, compared with 89.0%, 88.0%, and 70.0% for LeWM. The deployed model uses 2.98–3.42M parameters and records 2.13–11.60$\times$ lower planning time on these tasks.

We propose an Urgent Interactive HPC workflow that dynamically integrates high-fidelity 3D nonlinear analysis with surrogate neural networks (NNs) to enable rapid decision-making during large-scale earthquakes. This approach achieves both "Resource Harvesting", which utilizes idle computing capacity during non-emergency periods, and immediate response during crises. By developing two specialized HPC kernels, the proposed method reduces energy-to-solution by 76% and improves throughput by 3.7-fold during normal operations to efficiently construct training datasets, while during emergencies, it couples NN-based inverse analysis with physics-based simulations and dynamic refinement to reduce conventional computational costs by over 97.9%, enabling the generation of highly reliable spatial time-history ground motion distributions within 30 minutes post-earthquake.

We present commonsense ranked search (CoRS), a novel path planner that turns an abstract instruction into a route that follows commonsense. While existing methods respect the considerations written down in advance, a robot working among people must follow those left unstated too, as with a wet floor that a worker avoids without being told. CoRS leverages large language models (LLMs) and vision-language models (VLMs) as commonsense knowledge to reason about these latent considerations in its planning. Given an abstract instruction (e.g., “move carefully”) and visual observations of each region in the environment, CoRS derives a consideration for each region, as in “this wet floor is slippery and worth a detour.” It then compares the considerations between regions to see which of the two the robot should avoid more, as in “the crowd is worse than the wet floor.” These judgments sort the regions into a commonsense ranking, whose costs drive a conventional search that always returns a valid route. We build a benchmark for planning under latent considerations, with three environments, 1350 problems, and five instructions at three levels of abstraction. Experiments show that CoRS discovers the unstated considerations and goes around the ones worth a detour while crossing the rest, a behavior that recent LLM-based planners do not achieve.

We construct the Yukawa couplings of the quark sector as overlap integrals of Gaussian wave functions in extra spatial dimensions. Assuming that the wave function of each chiral fermion is localised at a point in the extra dimensions, while that of the Higgs doublet is flat, the Yukawa matrix elements are determined by the relative positions of the three left-handed quark doublets, $q_1$, $q_2$, $q_3$, and the six right-handed quark singlets, $u_1$, $u_2$, $u_3$, $d_1$, $d_2$, $d_3$. We employ numerical optimisation techniques from machine learning to identify field configurations that satisfy all current experimental constraints on the quark Yukawa sector. In this framework, the large hierarchy of quark masses arises naturally, since the overlap integrals of Gaussian wave functions are exponentially sensitive to ${\mathcal O}(1)$ separations in the extra dimensions.

A wrist-mounted camera for UMI-style data collection must do two jobs: record the manipulation and localize in the scene. Most handheld devices localize online from workspace-facing views crowded by hands and objects, or add dedicated tracking hardware. Room-scale bimanual capture therefore still tends to instrument the operator or the scene for accurate localization. We present KIWI (Kinematic Interface for the Wild), a capture kit whose only electronics are off-the-shelf cameras. Our core system splits the two jobs across the two lenses of a 360-degree camera. The rear lens faces the room and builds a shared metric map that registers both hands, and an optional head camera, in one frame without workspace co-visibility; the front lens records the manipulation, and offline IMU fusion bridges front-lens tracking loss. Through our quick-release plate, the camera module attaches to chopstick grippers, parallel-jaw grippers, hand-wrist mounts, or robot flanges. Across six bimanual recordings, combining the rear and front lenses failed to localize only 0.1% of query frames, whereas front-only bimanual feature alignment failed on 24.8% of frames and lost one recording entirely; against evaluation fiducials, localization error stayed within 4.5 mm. KIWI's recovered poses were sufficiently consistent for the four wrist streams alone to reconstruct the scene as a 3D Gaussian splat.

Implicit Neural Representation (INR) leverages neural networks to represent discrete signals such as images as continuous ones, where the network weights serve as a compact form of the signal itself. Most existing INR methods adopt Multi-Layer Perceptrons (MLPs) as their backbone. Since these models render each pixel independently, they inherently fail to exploit the spatial correlations that exist between neighboring pixels. In contrast,convolutional INRs can process pixels in parallel while inherently accounting for inter-pixel dependencies, making them a more natural fit for representing images. Nevertheless, convolutional INRs remain relatively underexplored, and the majority of them rely on fixed architectural settings, leaving little room for image-specific adaptation. In this paper, we investigate network customization for convolutional INRs. We replace conventional filters with irregular directional kernels, whose allocation is guided by the directional energy in the image spectrum, i.e., directions exhibiting stronger energy are assigned a larger number of kernels, enabling content-tailored convolution settings. These kernels are further reformulated via an orthogonal basis to achieve a superior sparse representation. Moreover, we introduce an annealed Gumbel-Softmax-based mechanism for kernel-level activation function selection, which gives the most suitable activation function for each convolution kernel. Extensive experiments demonstrate that our method, namely C$^{2}$-INR, achieves superior performance against state-of-the-art approaches under comparable parameter budgets across a wide range of image processing tasks, including representation, inpainting, and super-resolution.

Natural language generation (NLG) ranges from highly constrained tasks, such as machine translation, to open-ended tasks like dialogue generation. Between them lie peer-review generation and image captioning, where one input admits several valid, overlapping outputs. We measure this intermediary region with Von Neumann entropy ($\hat{H}\approx0.6$ vs. 0.15 translation, 0.92 dialogue). Single-reference training discards valid perspectives, while multi-reference training introduces high-variance, unaligned targets. To tackle this, we propose target-side consolidation, that is, merging all references for an input into a single target which preserves every distinct information unit. To this end, we introduce MERC-67K, pairing 36,537 papers and 31,014 images with their original and consolidated references. In human evaluation, models trained using consolidated reviews obtain an average rank of 1.70 (out of 4) for coverage against 2.51-2.98 for baselines, and win 63.5-74.0% of pairwise comparisons. Models trained using consolidated captions obtain an average rank of 1.87 for overall caption quality (accuracy and naturalness) against 2.64-2.82 for baselines and obtain the highest reference-free LongCLIPScore (0.839 vs best baseline's 0.816). For reviews, multi-reference training often under-performs zero-shot inference, and consolidation's gains over multi-reference training hold across Llama3.1, Mistralv0.3, and Qwen2.5. Consolidation uses $\sim$4$\times$ (reviews) and 5$\times$ (captions) fewer individual references during optimization. Dataset and code will be released upon acceptance.

Simulations for learning-based autonomous colonoscopic navigation focus mainly on fully actuated capsule robots, failing to capture the contact-rich navigation of long and flexible clinical colonoscopes. We present the Autonomous Robotic Colonoscopy Gym (ARCGym), an open-source reinforcement learning environment and benchmark for image-based navigation in clinically derived deformable colon anatomies. ARCGym supports multiple types of colonoscope robots, spanning capsule robots and flexible endoscopes, with this work focusing on flexible endoscopes including magnetic-driven tip actuation and clinically used proximally translational actuation. This work includes five CT-reconstructed colons representing typical clinical scenarios, a set of clinically meaningful navigation subtasks, and unified success metrics. We introduce a reward combining depth-based lumen alignment with a lumen-visibility score to improve learning under occlusions. Experiments across tasks, robots, and anatomies show that autonomous navigation remains challenging for both magnetic-driven and proximal-insertion flexible robots, with proximal-insertion actuation remaining an open problem.

Blind and low vision (BLV) screen reader users construct mental models of user interfaces (UIs) through incremental screen reader interaction, a time-consuming and cognitively demanding process complicated by modern interfaces that may not convey dynamic content accessibly. We interviewed eleven BLV screen reader users about UI understanding and derived design objectives that informed Coral, a context-aware browser extension. Coral synthesizes interface and user context to generate screen reader-narrated gists which holistically notify users of interface states and changes relevant to their likely goals and ongoing interaction. In a comparative evaluation with eight BLV screen reader users, participants used Coral to form initial expectations and interpret interface changes, and reported spending less time and effort manually verifying interaction outcomes. Together, our findings provide deeper insight into how BLV screen reader users navigate gaps in their UI understanding, and how intelligent support that combines interface and user context can bridge these gaps.

Expert demonstrations often specify what a robot should do, but not how fast it can do it. Imitation Learning (IL) inherits demonstration timing, while directly accelerating the learned motion can fail when faster execution changes the robot-object dynamics. We study faster-than-demonstration execution as a dynamics-aware control problem and introduce Expert-Play Contouring Control (EPCC), which combines slow expert demonstrations with fast, non-expert play. Expert demonstrations train a latent trajectory generator whose predictions are reparameterized into a time-independent contour of successful task progression, while play trains a world model (WM) of fast-action outcomes. At deployment, our proposed planner uses the WM to optimize actions that makes maximize progress along the expert-derived contour while penalizing deviation from the intended task evolution. Averaged across three visuomotor manipulation tasks, EPCC achieves a $2.0\times$ the throughput of the IL baseline, including $2.2\times$ that of the throughput of the strongest acceleration baseline on a task with interaction-sensitive object dynamics. Our analysis shows that the gains concentrate where faster execution changes robot-object evolution. Together, our results highlight a simple yet effective principle: demonstrations provide task intent, while play data provides the dynamic coverage needed to execute that intent faster.

Dialectal Arabic machine translation (MT) remains challenging despite recent progress in Arabic language technologies, particularly because effective translation requires modeling not only semantic content but also dialectal variation, conversational context, speaker and addressee characteristics, and sociolinguistic appropriateness. Moreover, conventional MT metrics provide limited insight into the linguistic errors produced by dialectal systems. We present the AlexandriaX 2026 Shared Task on Dialectal Arabic MT, which addresses these challenges through three complementary subtasks: (1) context-aware English-to-Dialectal Arabic dialogue translation across 13 Arabic varieties, (2) cross-dialect Arabic translation in the financial domain covering six Arabic dialects, and (3) span-level MT error detection and classification using linguistically motivated error categories across five Arabic varieties. The shared task attracted 38 registrations for Subtask 1, 33 for Subtask 2, and 35 for Subtask 3. Twelve unique teams submitted their system description papers, all of which we accepted for publication. The best system on Subtask 1 achieved 30.42 spBLEU in the constrained track and 33.49 spBLEU in the unconstrained track. On Subtask 2, the top system obtained 28.40 spBLEU. On Subtask 3, the best system achieved an overall score of 49.82, outperforming the 24.29 baseline. Taken together, the results of the leading systems across the three subtasks highlight the benefits of explicit dialect modeling, context-aware generation, retrieval and reranking, and specialized approaches to interpretable MT error analysis. All the resources of AlexandriaX 2026 shared task are publicly available, including data, baselines, and evaluation code on our project page: https://alexandriax.dlnlp.ai.

Different tasks performed by legged robots impose distinct torque and speed requirements on actuators. Existing robotic actuators are generally optimized at the component level for metrics such as torque or power density, without explicit task guidance. System-level optimization across components such as motors, gearboxes, and sensors is challenging because of the high computational cost and coupling among mechanical, electrical, and electromagnetic behaviors. Consequently, improvements in individual components may not translate into better robot performance in a specific task. To this end, we present a systematic optimization framework for task-oriented co-design of actuator hardware and control. First, surrogate models are employed to accelerate motor evaluation and support global exploration of the coupled design space. Then, a hierarchical mixed-variable optimization strategy is adopted, combining discrete enumeration with continuous search over dimensions and real-valued indices. These indices are rounded to select admissible values for the remaining discrete choices before each evaluation. Within this search, rated output torque density and task performance are jointly optimized, with Bezier-parameterized joint torque profiles determined for each hardware candidate. Finally, the effectiveness of the proposed framework is validated through actuator fabrication and experiments on a two-degree-of-freedom jumping leg. Based on its measured mass, the fabricated prototype achieves a nominal rated output torque density of 35.7 N m/kg, approximately 60% higher than that of a widely used commercial geared joint actuator, while being 18.6% lighter. Under matched bench conditions, it achieves 12.0% greater jump height at twice-rated torque. Together, these results demonstrate a systematic route from task requirements to actuator design and control.

LLM-based machine translation evaluation can closely match human judgments, but in practice it remains largely diagnostic, with the signals rarely translating into direct quality improvements under real production constraints. We propose a two-stage, evaluator-guided automatic post-editing framework that turns MQM-style evaluation into targeted repairs: a retrieval-augmented LLM evaluator outputs structured, span-level MQM diagnoses under an explicit edit contract, and a separate LLM post-editor applies minimal edits restricted to those diagnoses. This separation improves controllability and reduces paraphrastic drift compared to one-stage "judge-and-refine" baselines. In a systematic study involving seven LLMs spanning three model providers and seven languages, our best configuration consistently improves both COMET-22 and COMETKiwi scores over one-stage post-edit methods, while the evaluator's error spans and severities show strong agreement with human MQM annotations and human editor preferences.

LLM agents are increasingly used for security tasks: vulnerability discovery, exploit reproduction, and patch generation. Improving them at the model level demands expert demonstrations or computable rewards, which security tasks rarely offer: traces are costly, failures hard to diagnose, rewards sparse, and non-computable. Efforts thus shift to the harness and context, but manual tuning needs task-specific expertise and scales poorly, while automated methods rely on scarce ground truth, stronger optimizer models, or unguided propose-and-evaluate loops that reduce to costly trial and error. We introduce SelfOp, an algorithm that automatically improves a frozen security agent's task context (instructions, skills, and reference documents), without modifying its execution harness and model weights. SelfOp casts context optimization as chain-rule-inspired textual gradient descent: from a single instance's outcome, it propagates error signals backward through the evaluator, the agent's trajectory, and the context artifacts that shaped its behavior, yielding per-instance textual gradients. Gradients are accumulated across instances by clustering, ranking, and filtering, and committed only under cross-instance consensus. A convergence detector monitors the gradient signal itself and stops once the context has absorbed the generalizable information in the training data, without held-out validation data. We evaluate SelfOp on CyberGym, a benchmark of real-world vulnerability reproduction tasks. With fewer than 200 training examples, SelfOp yields a 17-point self-improvement for GPT-5.4-mini (with Codex), enough to surpass the frontier GPT-5.4 baseline by 6 points, and an 18.5-point self-improvement for GPT-5.4 itself. The optimized skills also transfer across models, highlighting that SelfOp-optimized skills learn generalizable task knowledge not model-specific patterns.

Undergraduate programmes in intelligent medical engineering are expanding, yet laboratory curricula lag behind the multimodal, long-tailed, and distributionally shifting realities of clinical AI. This design paper presents an advanced experimental teaching system that translates an ongoing multimodal deep learning research project on endometrial carcinoma into a structured undergraduate lab sequence. We identify three educational gaps (modality, authenticity, and deployment) and derive four pedagogical principles from constructive alignment, experiential learning, the research teaching nexus, and the CDIO framework. The curriculum comprises four progressive tiers plus an engineering layer, with 32 laboratory units over 64 contact hours, delivered via a custom virtual clinical workstation using de-identified multi-institutional data. Each tier maps to a specific technical bottleneck, prerequisite coursework, and criterion-referenced deliverables. Data governance, safety, and assessment protocols are specified. Learning outcome data will be collected across two implementation cycles.

Image-to-layer decomposition converts a flattened image into editable RGBA layers, enabling element-level editing in design workflows. Existing diffusion-based systems typically adapt large pretrained text-to-image (T2I) models and introduce RGBA autoencoders or variable-layer architectural modules. We revisit this design choice and ask whether layer decomposition truly requires these heavyweight components. We introduce PixelART, a pixel-space rectified-flow Transformer trained from scratch for image-to-layer (I2L) decomposition. PixelART directly denoises regional RGBA pixel patches using a single-stream multi-modal diffusion Transformer, avoiding RGBA-VAEs, pretrained T2I backbones, and layer-specific decoders. We identify a key property of the task: high-noise timesteps determine layer assignment and coarse layer organization, while low-noise timesteps mainly refine color, alpha, texture, and boundaries. Based on this observation, we propose a terminal-boosted timestep sampling strategy to increase training coverage in the high-noise layer assignment regime. Trained on 4M multi-layer design templates, PixelART achieves state-of-the-art layer decomposition and composite reconstruction on Design-Multi-Layer-Bench and LICA with over 80% fewer parameters, 98% lower latency, and 85% lower memory than the recent Qwen-Image-Layered model. Ablation experiments show that pixel-space $\mathbf{x}$-prediction, terminal-boosted timestep sampling, and data/model scaling are critical, while T2I pretraining brings marginal benefits to the I2L task.

Video foundation models now reach human-level accuracy on physical-reasoning benchmarks, yet such tasks require predicting unobserved physical outcomes. Do these models perform human-like forward simulation, or do they exploit statistical regularities in visible scenes? Accuracy alone cannot distinguish these strategies. We introduce a distributional evaluation framework that treats model seeds and human raters as populations, enabling comparison of consensus, uncertainty, and strategy. On the Physion benchmark, we evaluate three ViT-L architectures (V-JEPA2, VideoMAEv2, DINOv2). V-JEPA2 narrows the accuracy gap to ~1 percentage point (73.2% vs. 74.2%), yet model-human disagreement reaches 26.4%, far exceeding human-human disagreement (4.8%), with substantially lower agreement (kappa ~ 0.48 vs. 0.91). The divergence follows forward-simulation demands: models outperform humans on geometric reasoning (linking, +11.8 pp) but underperform on gravitational dynamics (rolling, -11.8 pp) and causal chains (dominoes, -10.5 pp). Strategy fingerprinting confirms all three architectures share non-human strategies while none aligns with humans. Attribution analysis suggests that unobservable outcome features, rather than visible scene properties, predict this divergence, consistent with models relying more on scene-level statistical regularities than on explicit forward simulation, a systematic divergence that accuracy alone cannot reveal. Code is available at https://github.com/fanhong-li/model-human-divergence.

There are renewed efforts to build a lunar base and house a team of astronauts on the Moon for extended periods. However, important challenges remain, such as a rapid-response fire-hazard management system. In the event of a fire or toxic leak inside an early crewed lunar habitat, a single pressurized cylinder must be handled within minutes. However, suited astronauts and radio-delayed support from Earth cannot guarantee such response times. We describe a prototype fire-fighting and emergency response safety technology that embeds intelligence in the habitat itself: using thin ceramic QR codes affixed every few meters, each carries a local floor map, safe sensor limits, and step-by-step hazard responses. A low-power rover decodes a plate in a matter of seconds, polls the adjoining temperature-gas sensor cluster, and acts immediately, eliminating the need for a global map . In a representative layout, the interior is divided into roughly one code per two square meters. Simulations show that rapid-response firefighting both simplifies the task and avoids costly resource use and indeterminate outcomes. Because knowledge is spread across passive plates, damage is localized, procedures can be updated by replacing a single code, and processor demands remain minimal. However, important challenges remain, such as a rapid-response fire-hazard management system. In the event of a fire or toxic leak inside an early crewed lunar habitat, a single pressurized cylinder must be handled within minutes. However, suited astronauts and radio-delayed support from Earth cannot guarantee such response times. We describe a prototype fire-fighting and emergency response safety technology that embeds intelligence in the habitat itself: using thin ceramic QR codes affixed every few meters, each carries a local floor map, safe sensor limits, and step-by-step hazard responses.

Market-making strategies in real limit order book markets face substantial model uncertainty and regime-shift risk. Existing adversarial reinforcement learning approaches improve robustness by formulating the Avellaneda–Stoikov market-making problem as a zero-sum game between a market maker and an environmental adversary. However, these approaches typically rely on Poisson order arrivals and neglect trade-induced price impact, limiting their ability to capture important high-frequency market microstructure effects such as clustered order flow, self-excitation, and post-trade price feedback. We extend adversarial reinforcement learning for market making to a more complex environment with Hawkes self-exciting order arrivals and trade-induced price impact. To mitigate the increased non-stationarity introduced by the expanded regime space, we incorporate an LSTM module that explicitly models the temporal structure of recent observations. We further characterize the equilibrium properties of the proposed framework through both game-theoretic analysis and numerical experiments, and introduce a robustness evaluation protocol focused on improvements in the left tail of the return distribution. Experimental results across a range of market regimes show that the proposed method achieves improved left-tail performance in most complex microstructure environments. In particular, the gains are pronounced in regimes with strong Hawkes excitation and low-to-moderate price impact. Bootstrap tests provide no evidence that these improvements are obtained through a stronger terminal directional inventory bias. These results suggest that combining adversarial training with temporal state representation can improve the robustness of reinforcement-learning-based market-making strategies under order-flow self-excitation, price impact, and regime uncertainty.

We study differentially private covariance estimation in operator norm for mean-zero sub-Gaussian distributions with unknown covariance support and at most $k$ nonzero entries per row. We develop a multiscale random-threshold algorithm with sample complexity $\ot(k^2/\alpha^2+k\sqrt d/(\alpha\varepsilon))$ for $(\varepsilon,\delta)$-differential privacy and error at most $\alpha\sigma^2$, where $d$ is the dimension and $\sigma$ is a known sub-Gaussian scale. The bound improves the privacy-dependent term of the existing $\ot(k^2/\alpha^2+k^{3/2}\sqrt d/(\alpha\varepsilon))$ \citep{kumar2026curse} upper bound by a factor of $\sqrt k$, and matches the lower bound of $\widetilde{\Omega}(k^2/\alpha^2 + k\sqrt{d}/(\alpha\varepsilon))$ in its applicable parameter regime. Our key technical ingredient is a direct operator-norm bound on the centered fluctuations of an ideal reconstruction, exploiting conditional independence rather than accumulating entrywise errors across each row. A multiscale allocation of threshold tests balances reconstruction variance against query sensitivity. Together, these ingredients sharpen the trade-off between approximation error and privacy protection, removing the additional $\sqrt{k}$ factor from the privacy-dependent sample complexity.

Steering with SAE features requires per-feature coefficient tuning, which currently demands intervention sweeps. We ask whether properties of the SAE itself, computable before any forward pass, predict which features will be cheap or expensive to steer. We show that variation in SAE feature steerability is partially predicted by decoder-space geometry: neighbor density and maximum cosine similarity to nearby decoder directions, both computable from the SAE weight matrix before any intervention, rank features by how much steering they require for a fixed behavioral effect ($\rho$ up to $-0.546$, $p < 10^{-6}$, AUROC 0.610-0.822 across conditions; the signal is rank-based, consistent with grid discreteness). This geometry-steerability relationship replicates across two Gemma-2 model scales (2B and 9B), two SAE widths (16K and 65K), and is detectable cross-architecturally on Llama-3.1-8B-Instruct ($\rho = -0.266$, $n = 300$). On Qwen3-8B with BatchTopK SAEs, geometry predicts whether a feature is steerable at all but not the continuous ordering among responsive features, revealing a boundary condition tied to SAE training regime. The signal weakens at deep proportional layer depth in both models, where the cost of steering exceeds our intervention budget, a consistent depth boundary. These results provide preliminary evidence that pre-steering geometry can partially inform coefficient selection, offering a path toward screening features for controllability before deployment.

We describe the integration of io_uring into Oracle Database's storage layer and the architectural decisions required to deploy it in a production multi-process RDBMS. Our design uses per-process ring contexts that eliminate inter-process synchronization, a shared buffer registration mechanism now part of the mainline Linux kernel, and a transparent fallback to libaio on error. Evaluation on an internal development build of Oracle Database 26ai shows that io_uring's benefits concentrate on asynchronous batched I/O paths: on a mixed OLTP workload (TPC-C), io_uring delivers identical throughput while reducing server CPU utilization by 1.2 percentage points through more efficient background writes; on analytical queries (TPC-H), CPU per query drops by 8.5% (geometric mean). Isolating the write path alone shows 29% lower CPU per write and 34% higher throughput. Synchronous read paths – the dominant I/O in OLTP – show no improvement and even increased CPU usage for very large I/O sizes. These results motivate a hybrid I/O architecture that retains pread/pwrite for synchronous operations, adopts io_uring for asynchronous batched I/O, and falls back transparently to libaio – a selective strategy that may also be relevant to other database systems facing the same integration question.

Multimodal large language models (MLLMs) are increasingly used as evaluators, yet their reliability in professional assessment tasks that require expert judgment remains unclear. We investigate this challenge in the context of assessing psychotherapeutic interpersonal skills and introduce MIS-Bench, a Multimodal Interpersonal Skills (MIS) benchmark comprising 996 psychotherapy response videos annotated across 8 dimensions of Facilitative Interpersonal Skills. Across 9 MLLMs with multiple modality and prompting settings, we find that current models show only modest agreement with human experts, inconsistent gains from multimodal input, and limited benefits from reasoning-based prompting. To mitigate this gap, we propose MIS-RAFT, a regression-aware fine-tuning method inspired by RAFT and tailored to fine-grained interpersonal skill scoring at one-decimal precision. MIS-RAFT addresses the mismatch between autoregressive token prediction and scalar-valued expert assessment, significantly improving agreement with human ratings. Overall, MIS-Bench reveals a clear gap between general multimodal capability and expert-level interpersonal judgment, while MIS-RAFT offers a promising path toward more reliable model-based assessment.

Spiking Neural Networks (SNNs) offer a promising path toward ultra-low-power artificial intelligence inference by emulating the event-driven computation of biological neurons. However, two challenges limit their practical deployment. First, fixed-parameter Leaky Integrate-and-Fire (LIF) neurons lack the adaptation mechanisms observed in biology, where neurons modulate their excitability based on firing history. Second, scaling from single neurons to multi-neuron networks introduces challenges in synaptic weight distribution and inter-neuron spike routing that are absent in isolated designs. This paper addresses both issues through the extension, verification, and physical implementation of adaptive LIF neurons at three architectural scales. This work contributes: a 2nd-order neuron with two-stage synaptic filtering for richer temporal dynamics; a fully-connected 6-neuron spiking network with configurable weights (100 to 5) demonstrating weight-based inter-neuron communication; and a direct verification methodology enabling per-cycle observation of all internal states. All designs were synthesized targeting Selected Area Electron Diffraction (SAED) 14 nm Complementary Metal-Oxide-Semiconductor (CMOS) technology at 1 GHz and verified with Cocotb-based Python testbenches under pulsed current stimuli (amplitude 80, ISI=3). The results show that adaptation effectively modulates firing: 31% suppression in the 2nd-order neuron (25 vs.\ 36 spikes) and 31% reduction in postsynaptic firing in the network (18 vs.\ 26 spikes). Physically, the 2nd-order neuron costs 1.77x more area and 1.52x more power than the 1st-order baseline, while the 6-neuron network demonstrates near-linear scaling (5.7x area, 5.3x power). Seven verification bugs spanning testbench connectivity, fixed-point overflow, and Verilog expression-width semantics are documented.

This paper presents our system for Track 2 of the NLPCC 2026 Shared Task 10 on citation-level faithfulness in AI-assisted scientific reporting. Given an atomic scientific claim and the structured full text of its cited paper, the task requires both a four-way relation label and up to three evidence paragraph identifiers. The label head ensembles a paragraph-aware cross-encoder with a document-level DeBERTa-large classifier, followed by class-wise decision calibration. Probability-level fusion is motivated by an out-of-fold tendency to over-predict Topical Match. The evidence head combines paragraph scores from top-20 and top-30 joint models with BM25 scores. The system runs fully offline without external retrieval or LLM prompting. On the final leaderboard, our system achieved 82.9898 overall (89.5491 Macro-F1 and 76.4305 Joint@3), ranking second in Track 2. Ablations and error analysis show that model complementarity and calibration drive the label gains. Gold-evidence inference changes label Macro-F1 negligibly, whereas evidence ranking remains important for Joint@3.

Synthetic biology enables the design of genetic circuits that act as feedback controllers. These controllers are typically designed using computational models, but mismatch between model and real dynamics can lead to controllers that fail in practice. While methods to address this issue exist, synthetic biology introduces additional structural constraints. Genetic circuits are often highly constrained by experimental limitations, reducing controller design to selection among a limited set of implementable circuits rather than an optimization over a continuous space. As a result, multiple system hypotheses may lead to the same optimal controller within the implementable set. Reducing model uncertainty may therefore be irrelevant when the models lead to the same optimal controller. In this paper, we exploit this structure to develop an algorithm for controller selection in synthetic biology, formulating the problem as a decision-oriented experimental design problem over a finite controller set. We represent plant uncertainty using a set of hypotheses and select experiments to minimize the posterior controller selection risk, rather than global model uncertainty. Across three mechanistic case studies, our method reaches the stopping criterion in fewer experimental rounds than model uncertainty and random experiment selection policies, while maintaining a comparable success rate.

Recent advances in Audio LLMs have achieved human-level speech recognition, yet existing systems struggle to capture paralinguistic aspects such as speaker traits, expressive variations, and environmental acoustic conditions. To address this, we design a framework of 22 paralinguistic characteristics and create a dataset of over 1.2M Audio-QA pairs. We develop ParA-LLM, trained with a two-stage curriculum: first on single-attribute questions to build foundational knowledge, then on multi-attribute questions for joint reasoning over speaker and acoustic characteristics. We also release ParA-Bench, a benchmark of 6,000 multiple-choice questions across speaker-speech, acoustic, and mixed categories, where frontier models like GPT-4o-Audio achieve only 36% accuracy. ParA-LLM surpasses state-of-the-art Audio LLMs like GPT-4o-Audio by 7.5% on ParA-Bench, with additional gains of 1.13% on MMAU-Pro Speech and 7.49% on MMAR Speech.

We study a parameterized hybrid ranker that fuses a dense embedding list and a sparse lexical list. The method has a small, explicit parameter vector: a dense prior $\alpha \in [0,1]$, a score-versus-rank mix $\lambda \in [0,1]$, an RRF smoothing parameter $\kappa > 0$, optional list-geometry coefficients that move $\alpha$ per query, and a router margin $\tau$ that can turn sparse search off. We grid-search those ranges on SciFact train (809 queries) and freeze the chosen values on SciFact test (300). The tuned rank-score mix ($\alpha = 0.8$, $\lambda = 0.75$, $\kappa = 20$) reaches 0.753 nDCG@10 and 0.889 recall@10, outperforming dense BGE (0.742 / 0.871) and equal-weight RRF (0.707 nDCG@10) on that test split. A list-conditioned $\alpha$ adds +0.0006 nDCG; a sparse-off router is rejected by the same train split (any $\tau$ that skipped approximately 50% of queries lost nDCG). These coefficients are dataset-specific. Equal RRF with the same models does not beat dense on a nine-zip BEIR macro-average (0.479 vs. 0.519 nDCG@10). Repeating the same train-then-freeze sweep independently on all 20 indexed units beats equal RRF on 20/20 and dense on 16/20 (unit-mean nDCG@10 0.467 vs. 0.462 dense vs. 0.420 RRF). Other corpora should reuse the ranges, not a copy of the SciFact point.

The IEEE BigData Cup benchmark combines three prediction problems with different output structures: ordinal suicide-risk classification, multi-label psychosocial factor detection, and extraction of supporting phrases. We introduce heterogeneous readout decomposition (HRD), which separates semantic verification from output realization. A locally deployed Qwen3.8-27B model, adapted with task-specific QLoRA adapters, produces both answer-token margins and layer-63 answer states for card-conditioned queries. HRD compares four latent scores for ordinal risk, retains token margins for most factors while routing seven labels through one shared latent probe, and constructs evidence sets from verbatim span candidates with calibrated, risk-conditional constraints. On two held-out user-grouped confirmation folds, the latent risk readout improves weighted F1 from 0.8237 to 0.8372 and macro F1 from 0.7965 to 0.8185. Selective factor routing improves macro F1 by 0.0105 and tail-label macro F1 by 0.0189; in contrast, global latent replacement and independent label-specific probes fail. The constrained evidence decoder raises pooled phrase F1 from 0.7488 to 0.7609 in row-level out-of-fold evaluation. Lenormand's best public result is 0.8052 on Subtask 1 and 0.6636 on Subtask 2, giving a composite score of 0.7627. These results identify the answer-token boundary, rather than semantic representation alone, as a measurable source of error in this benchmark.

Large Language Models (LLMs) have shown remarkable potential in Verilog code generation, yet existing datasets contain con siderable noise and redundancy. Prior data selection methods address only isolated quality aspects, neglect the global diversity of the training set, and cannot capture Verilog-specific structural semantics. To bridge this gap, we propose VeriSelector, the first data selection framework for Verilog code generation that jointly optimizes quality and diversity. We formulate the selec tion problem as a constrained bi-objective subset selection problem and solve it via a three-stage approximation. For quality, a multi-granularity pipeline first verifies functional correctness through testbench simulation and then filters misaligned samples via Instruction-Following Difficulty (IFD) scoring. For diversity, 109-dimensional Verilog-specific structural features (AST, CFG, and Netlist) are fused with textual embeddings for clustering-based diversity modeling. A proportional adaptive sampling strat egy then allocates per-cluster quotas guided by IFD ranks, with a provable distribution preservation guarantee. Experiments on three LLMs and three benchmarks show that VeriSelector outperforms full-dataset training and state-of-the-art baselines us ing only 20%-25% of the data, achieving Performance Retention Rates above 118% and reducing training time by over 80%. Notably, VeriSelector improves average Pass@1 by 18.49%-29.43% over full-dataset training and by 1.36%-7.95% over the best-performing baseline across all evaluated models.