Papers

Large language model (LLM) agents are increasingly deployed in tool-augmented environments, but their reliance on external inputs makes them highly vulnerable to prompt injection attacks that can hijack task objectives. Existing safety alignment methods rely on static expert trajectories or preference optimization, limiting their ability to generalize to adaptive attack patterns. In this work, we propose Self-Reflection Fine-Tuning (SRFT), a training framework that enables agents to improve robustness by learning from their own failure experiences under adversarial conditions. Instead of passively imitating expert behaviors, SRFT exposes the agent to compromised trajectories constructed via injected attacks, and leverages an expert model to generate structured self-reflection reasoning that contrasts unsafe and optimal actions. This reflective supervision teaches the agent to identify malicious instructions, reason about their consequences, and maintain alignment with the original user intent. We instantiate this framework in SR-Agent, built on Llama-3.1-8B-Instruct and Qwen3-8B, and evaluate it on both static and adaptive prompt injection benchmarks. Experimental results show that SRFT substantially reduces attack success rates while preserving task performance, and demonstrates strong generalization under adaptive attacks. These findings suggest that learning from failure via self-reflection is a promising direction for building robust and secure LLM agents. Our code is released at https://github.com/Eden-Wang1710/srft-repo.

Generating multiple-choice questions is increasingly scalable, but establishing their assessment quality remains difficult. We present a focused narrative review of automated item-writing flaw detection, revision, psychometric screening, and NLP benchmark auditing. Database searches, citation retrieval, and nominated sources yield fourteen research reports reviewed in full text. We distinguish surface checks from content-sensitive judgments and map a 19-criterion rubric to detection methods and reported evidence. High label-level accuracy often coexists with weak positive case detection, while rubric definitions and reference standards vary. Revision evidence is mixed, and the associations reported in prior work do not establish the effects of repair. We propose evaluating quality assurance as a sequence of independently validated decisions, with criterion-specific reporting, calibrated human review, and outcome-based assessment of revisions.

This paper presents a conformal-seeded hybrid strategy for solving inverse kinematics of offset, redundant 7-DoF robot arms of the humanoid class. Analytical inverse kinematics (AIK) provides closed-form solutions with very low computational cost. However, for offset kinematic structures, the exact closed-form solution is generally unavailable, and practical AIK must rely on an approximate or simplified kinematic model. In contrast, numerical inverse kinematics (NIK) can achieve high-precision solutions on the full kinematic model. However, its convergence is highly sensitive to initialization. To overcome these limitations, we propose a two-stage hybrid inverse kinematics framework with conformal-calibrated seed selection. First, an approximate analytical model efficiently enumerates a finite set of candidate joint solutions. Second, we rank these candidates using a lightweight learned predictor of post-refinement difficulty, wrapped by split-conformal prediction into a calibrated upper bound that serves as the selection score. The best-ranked seed is then refined using a Levenberg-Marquardt solver on the full kinematic model. The proposed method combines fast candidate generation, learned seed ranking with a calibrated difficulty bound, and accurate numerical refinement, achieving real-time performance of less than 40us and a success rate of 100% in our evaluation on reachable targets. We validate the approach through large-scale stochastic simulation across the workspace and experimental demonstrations with motion planning on a humanoid robot arm. Demonstration videos are available at https://youtu.be/aeiBmw1XRbw.

The Gromov-Wasserstein (GW) problem compares structured distributions without requiring a shared feature space or known correspondences, but its nonconvex objective and coupled marginal constraints make computation challenging. Bregman alternating projected gradient (BAPG) uses inexpensive alternating row and column updates, yet its fixed-penalty relaxation leaves a persistent feasibility gap. We propose Adaptive KL-BAPG (A-KL-BAPG), which combines a finite fixed-penalty burn-in with a guarded increasing-penalty phase. At each tail iteration, the method reuses BAPG's alternating updates and backtracks a delayed-power step until a Sinkhorn-inspired projective-diameter safeguard is satisfied. We prove finite termination of the backtracking at each iteration and show that the feasibility gap vanishes asymptotically. We further establish a best-iterate $O(1/\log N)$ bound for the weighted squared corrected residual and, under a support regularity condition, the existence of a stationary accumulation point for the original GW problem. This distinguishes A-KL-BAPG from fixed-penalty BAPG, whose stationarity guarantees are given for the relaxed problem. Experiments show that A-KL-BAPG achieves a favorable balance of accuracy, objective value, feasibility, and stationarity relative to BAPG variants, projection-based methods, and task-specific baselines. For synthetic and real graph alignment problems, it closely matches the accuracy and objective value of fixed-penalty KL-BAPG while reducing the marginal feasibility gap by 62-99% and the projected stationarity residual by 28-98%. Heterogeneous domain adaptation experiments show a similar pattern: A-KL-BAPG maintains comparable target accuracy and objective values while achieving better feasibility and stationarity than fixed-penalty KL-BAPG.

Accurate International Classification of Diseases (ICD) coding is crucial for large-scale clinical research, documentation, and billing. There are three primary problems with current ICD prediction methods: (1) They are unable to comprehend multimodal patient data because they rely on either structured EHR data or unstructured clinical notes. (2) They also struggle with scalability to a larger amount of ICD codes (9K+ codes in ICD-9), as traditional classifiers need dense output layers and often do not generalize well to long tail rare diseases. (3) They lack transparency for clinical use. To address these challenges, this research proposes a two-stage framework that first retrieves ICD codes using a multimodal dual-encoder retrieval model, where structured and unstructured patient data are integrated through gated fusion. The second stage refines the top-k retrieved candidates with an LLM-based re-ranker that provides ranked codes with clinically relevant explanations. Our experiments show that the proposed approach improves Micro-F1 and Precision over a multimodal dual-fusion classifier baseline. These improvements demonstrate that combining a gated multimodal retrieval system with LLM-based re-ranking is a practical alternative to dense multi-label classification for automated ICD coding.

Reconstructing editable parametric CAD models from a single-view image is of great practical value for modern manufacturing, yet remains challenging due to incomplete geometric observations and complex inter-part relationships. To address it, we propose CADForge, an agentic framework that progressively converts a single image into CadQuery programs. CADForge decomposes an object into CAD-meaningful components and performs explicit geometric reasoning for each component, a process that first identifies CAD-relevant constraints and then translates them into precise modeling parameters through mathematical code. The inferred parameters then drive component-wise synthesis of executable CadQuery programs, with a review agent evaluating the resulting geometry and providing targeted feedback for iterative refinement. To further improve robustness and efficiency, CADForge incorporates a failure-guided toolkit construction mechanism to distill accumulated experience into tools, and maintains a compact parametric CAD memory for retrieving modeling context on demand. Experiments on diverse single- and multi-part objects show that CADForge consistently outperforms existing baselines in reconstruction fidelity and perceptual quality, demonstrating an effective approach to accurate single-view CAD reconstruction.

Reinforcement fine-tuning (RFT) is increasingly used in applications where large language models (LLMs) interact with humans and other agents. Here we use social deduction games to study how RFT changes LLMs' social behaviour. We let fine-tuned and base LLM agents play hidden-role games that require hidden-state inference, social reading and vote steering. Our results show that LLM agents do not reliably acquire social-deduction ability by directly optimizing terminal win–loss outcomes, suggesting that final game results provide a sparse and noisy signal for socially interactive learning. However, RFT is particularly effective at improving social reading, including tasks that require agents to infer hidden roles from public discussion, update beliefs over time and predict other agents' future decisions. We further show that RFT can also improve social influence, including tasks that require agents to steer votes, team approvals and collective decisions, although these gains depend more strongly on behaviourally specific rewards and structured interaction settings. Finally, we show that LLMs' ability to play social deduction games can be further improved through multi-agent social-cognitive reinforcement fine-tuning, which combines social-reading and social-influence signals during same-side multi-agent training. These learned behaviours also receive more favourable human evaluations of strategic competence, persuasiveness and social usefulness. Together, these results enrich our understanding of how RFT changes LLMs' social behaviour and provide a step toward a behavioural learning theory for machine social intelligence.

Subliminal learning is a phenomenon where a student language model acquires a teacher model's behavioral traits by training on semantically unrelated outputs. It is a subtle statistical phenomenon as trait transmission relies on weak statistical patterns in the generated data. To understand trait transmission between teacher-student pairs, we study cross-trait transfer: how data generated under one teacher trait changes the student's preferences of other traits. To this end, we introduce a directed trait-transfer matrix that quantifies these effects using log-probability gains for student answers. We find that the trait-transfer matrix reveals clusters of related traits, with students sometimes developing preferences for traits similar, but not identical, to the teacher's trait. Such cross-trait structure can be partially captured by output distribution metrics and representation-based metrics. Further, we analyze trait development and interaction: learning dynamics shows a progression from broad shared shifts toward more trait-specific transfer, and multi-trait experiments suggest that opposed traits can enhance such differentiation. Together, our findings reveal salient statistical structures over trait transfer and competition, thus providing a broader view of how hidden preferences are transmitted in subliminal learning.

Biomedical imaging modalities often require a trade-off among resolution, field of view (FOV), and acquisition speed. Video mosaicking offers a strategy to overcome this limitation by computationally stitching sequential high-resolution frames into a wide-FOV composite. However, existing methods struggle with non-rigid deformations, and modality-specific artifacts arising in clinical and research imaging. Here, we present FloVMos, a generalizable, optical-flow-based deep learning framework for real-time video mosaicking across diverse biomedical imaging modalities. FloVMos achieves robust, pixel-level registration by fine-tuning an optical flow model on synthetic training data with ground-truth deformation fields. We introduce a pipeline for generating this training data, simulating realistic tissue motion and imaging distortions from existing mosaics or raw videos. Our automated synthetic data generation and optical flow model training based on this data allow users to adapt FloVMos to different imaging modalities. To demonstrate this, we applied FloVMos to seven diverse imaging modalities: reflection confocal microscopy, open-top light-sheet microscopy, fetoscopy, laparoscopy, dermoscopy, sparse spectral microscopy, and endoscopy. FloVMos outperforms conventional baselines in accuracy, robustness, and speed for all the tested modalities. This adaptable and training-efficient framework enables large-area visualization with real-time performance and may support broader use of video-based biomedical imaging in research and clinical workflows.

Exactly computing the maximum function is a standard test case for studying depth in ReLU networks. Two hidden layers are known to suffice for up to twelve inputs through computer-assisted constructions. For six real inputs, we give an explicit hexagon identity whose local structure yields a self-contained analytical proof of this depth bound. The identity was found by computer-assisted search; we prove it through explicit cancellations that can be checked entirely by hand, without executing a verification program. The identity also yields an explicit network with hidden widths $17$ and $41$, zero biases, and rational weights.

Robotic manipulation often requires inferring task-relevant states from past interactions when the current observation alone is insufficient to determine the appropriate action. Despite progress in benchmarking memory-augmented vision-language-action (VLA) models, application-oriented tasks requiring history-dependent semantic inference remain underrepresented. We introduce GiT (Grounded in Time), a dataset and benchmark for grounding manipulation decisions in past events across biolaboratory, household, and industrial scenarios. It includes real-robot and Universal Manipulation Interface (UMI) style demonstrations covering 18 bimanual tasks, together with simulation data and a ManiSkill-based evaluation suite covering nine tasks. Fine-grained subtask annotations and annotated counterfactual task pairs, in which similar current observations require different actions depending on prior events, support policy learning and targeted evaluation of history use. Evaluations of representative end-to-end VLA models in simulation and on selected real-world tasks reveal substantial room for improvement in history-dependent manipulation. The dataset and benchmark are available at the project page.

Generating an executable program does not necessarily mean that it correctly implements the behavioral requirements specified in natural language. To evaluate large language models' ability to realize detailed specifications as complete interactive programs, we introduce Spec2Game, a benchmark that requires models to generate complete Pygame projects from detailed natural-language game specifications. Spec2Game comprises 15 game families and 150 task instances, with one canonical task and nine controlled rule variants per family, spanning three levels of implementation complexity. Using source-code, runtime, and visual evidence, we evaluate generated projects along four dimensions—Executability, Specification Realization, Code Quality, and User-Facing Quality. Across 14 LLMs and 3,330 generated projects, we find that high executability does not imply faithful specification realization. Component-level analysis further shows that models perform substantially better on Game Element Modeling than on Rule and Mechanism Modeling or Goal and Termination Modeling, indicating that faithfully implementing game rules and termination logic remains a major challenge.

Reinforcement learning for embodied control remains constrained by the difficulty of reward specification. Although recent large language model (LLM)-based methods can synthesize reward functions from natural-language descriptions, they often fail to capture subtle behavioral properties that humans care about, such as natural gait, posture, and movement style. This limitation arises because many desired behaviors are easier to recognize visually than to encode in a reward function. We introduce Reward Optimization via Observable Trees (ROOT), a framework for discovering reward functions that align learned policies with user-specified embodied behaviors. Rather than relying solely on scalar training statistics, ROOT casts reward design as an observation-guided search over a persistent experiment tree that stores reward programs, trained policies, and rollout observations, together with behavioral insights distilled by a video-language model, to diagnose behavioral failures and guide subsequent reward refinements. We evaluate ROOT on seven tasks across four embodiments: simulated Hopper, HalfCheetah, Ant, Unitree Go2, and as well as the real-world Unitree Go2. ROOT produces behaviors that better align with user intent than those generated by existing LLM-based reward-generation methods, achieving up to 86.8% locomotion-completeness accuracy and improving Vid-LLM behavioral alignment from 3.56/5 to 4.14/5, a 16.5% improvement over baselines. Human evaluations further support these results, with ROOT preferred in 51-63% of pairwise comparisons.

Recent successes of matrix- and curvature-based optimizers have renewed interest in how update geometry shapes learning. These methods normalize or precondition updates, changing how different components progress during training. In deep matrix factorization, the geometry that slows gradient descent (GD) favors low-rank solutions by delaying the emergence of small singular modes. This raises the question of what remains of that spectral bias when normalization or curvature correction weakens or removes the slowdown. We study how optimizer geometry and depth jointly govern this behavior through a common framework for singular mode dynamics. Under explicit balance and alignment assumptions, we derive birth, saturation, and decay laws for Euclidean GD, coordinate-wise updates of SignGD and an instantaneous Adam approximation, spectral updates of Muon and cumulative Shampoo, and a block curvature model of K-FAC. The resulting picture is not a simple ordering from stronger to weaker low-rank bias. To highlight, SignGD and ideal Muon eliminate the divergent birth barrier and drive unsupported modes to zero in finite time. Cumulative Shampoo initially retains GD's depth-dependent barrier, then accumulated gradients produce a catch-up phase while making previously active modes increasingly persistent. Undamped K-FAC cancels the factorization-induced slowdown while preserving the ordering of the target singular values, whereas positive damping introduces a spectral threshold below which the slow GD phase laws reappear. These results give normalization, accumulated state, damping, and depth a direct interpretation as controls determining when modes emerge, persist, and disappear during training.

Large language models (LLMs) are increasingly deployed to simulate human behavior, acting as computational replicas of human subjects. Yet the lived psychological experience of humans is difficult to benchmark, particularly as it unfolds over time. We introduce a psychometric benchmark for computational replicas: personas that carry a fixed identity through an evolving sequence of events. Built entirely from published norms and meta-analytic effects, the benchmark scores two dimensions of psychological realism. The first, internal validity, quantifies whether generated trajectories reproduce the internal structure of repeated human measurement: distributions, the between- versus within-person variance partition, temporal dependence, and range. The second, external validity, quantifies whether replicas recover established trait, state, and indicator relations. Across 36 open-weight and proprietary LLMs from nine developers (1B-671B parameters), most recover the direction of established relations (84.3% mean agreement) and the variance partition (26 of 34), yet the within-person correlation and distributional structure elude recovery. Internal validity is independent of scale and capability: a mid-size open LLM (Gemma-3-27B) strikes the best trade-off between the two dimensions. The benchmark is a precondition for using computational replicas in causal inference across domains (e.g., marketing, healthcare), and identifies within-person grounding as the central challenge ahead.

Existing activation steering methods often assume that a high-level concept can be mediated by a single steering direction. To support this, two complementary interventions should be achieved: additive steering should induce the target behavior, while directional ablation should suppress it. Yet behaviors may occupy richer activation geometries beyond a single direction, and semantically similar behaviors may be represented by distinct directions. In this work, we study how many directions can reliably control two different types of refusal behaviors: refusal triggered by the safety alignment and refusal in general contexts. Given the limited expressive capability of a single steering vector, we study the general setting of steering subspaces and introduce the notion of steering dimensionality as the minimum subspace dimensionality required to reliably control a behavior. We characterize sufficient steering subspaces that cover the full extent of the target behavior through both the (monotonic) improvement before the sufficient dimensionality, and the saturation beyond it. Empirically, we find that refusal triggered by safety alignment is 1-dim steerable, while multiple distinct steering directions can achieve comparable control. In contrast, refusal in general contexts exhibits substantially richer activation geometry where even 5-dim steering subspaces fail to reliably capture its full steerable variation. Our results reveal that the activation geometry underlying refusal is highly context-dependent and can be substantially more complex than a single linear steering direction.

Active Directory (AD) remains the predominant identity and access management infrastructure in enterprise environments, and its compromise represents the highest-impact outcome in internal penetration tests. Recent work has shown that large language models (LLMs) can autonomously conduct assumed-breach penetration testing against AD, but these studies employ standalone agents lacking structured guardrails, deterministic validation, and multi-stage chain orchestration. We present a benchmark evaluation of NeuroSploit v4.2.0, an open-source Rust-based autonomous pentest harness, against the Game of Active Directory (GOAD), a deliberately vulnerable multi-forest AD lab maintained by Orange Cyberdefense comprising five virtual machines, two forests, and three domains. The harness orchestrates 22 AD-specific agents and 7 multi-stage attack-chain playbooks covering the full AD kill chain: enumeration, Kerberoasting, AS-REP roasting, NTLM relay and coercion, Kerberos delegation abuse, AD CS exploitation (ESC1-ESC8), MSSQL linked-server pivoting, DCSync, cross-forest trust abuse, and persistence detection. We benchmark nine frontier LLMs (Claude Opus 4.6/4.7/4.8, GPT-6 Astra, GPT-5.6 Sol, Grok 4.6, Qwen 3.8, GLM 5.3, Kimi k3) within the harness, comparing against direct invocation across 14 technique categories and 7 chains. The harness achieves 96-100% technique coverage with 90-97% precision, while direct invocation covers only 21-54% and produces 3.2x more false positives. Time to full three-domain compromise with Opus 4.8 was 134 minutes with guardrail activations preventing lockout-triggering sprays, unauthorized DCSync dumps, and out-of-scope reconnaissance. Results demonstrate that structured harness orchestration with domain-specialized agents, POMDP belief tracking, and cross-model voting substantially outperforms unstructured LLM usage for AD penetration testing.

The clinical management of chronic disease is naturally structured as a feedback control problem. Physicians observe the disease state at clinic visits and make decisions based on the patient's history and current state. We propose a framework that models the dynamics of chronic disease in response to therapy as an event-based controlled stochastic system, in which treatment decisions are made at discrete, irregularly spaced events while the disease evolves between events as a continuous-time Markov chain (CTMC) with state and input dependent transition rates. We demonstrate this framework in the setting of ulcerative colitis, where we identify the model from real-world clinical data in the electronic health record (EHR) of more than 3,000 patients with ulcerative colitis. Using the learned model, we formulate therapy selection as a model predictive control problem (MPC) that maximizes the expected time spent in inactive disease states, and we evaluate the resulting policy. In closed-loop simulation on 10 patients, the MPC achieves a cost at or below the observed clinical course in the majority of its realizations for 4 of the 10 patients, and its outcomes in all cases are comparable to observed care and within clinical guidelines.

Fourier Neural Operators (FNOs) offer an efficient paradigm for solving partial differential equations (PDEs). However, FNOs rely on a fixed Fourier basis and hard frequency truncation, which inherently limit their ability to model non-periodic, localized, and fine-scale solution structures. We propose the Stochastic Adaptive Fourier Decomposition Neural Operator (SAFDNO), a spectral neural operator that replaces predefined Fourier modes with an adaptive Takenaka-Malmquist (TM) orthonormal system derived from the theory of Stochastic Adaptive Fourier Decomposition (SAFD). Instead of performing an expensive greedy pole search in classical SAFD, SAFDNO amortizes stochastic pole selection through a neural pole predictor and constructs the adaptive TM system directly from latent features. The resulting operator performs learned filtering on coefficients of analytic branches in the Hardy space with respect to the input-adaptive TM system, preserving the global receptive field of spectral operators while providing a more flexible representation than using fixed spectral bases. Across nine PDE benchmark problems, SAFDNO achieves the best performance on all six regular-grid problems among strong neural operator baselines, with especially notable gains on Darcy, Burgers, and Navier-Stokes, where fixed Fourier modes are often less effective at modeling localized oscillations, sharp transitions, and multiscale structures. SAFDNO also exhibits stronger zero-shot super-resolution performance and shows less performance degradation when deployed on finer discretizations. These results suggest that the input-adaptive TM system provides a promising alternative to fixed spectral representations for neural operator learning.

For ground robots operating in outdoor environments, understanding the properties of the underlying terrain is essential for ensuring reliable operation. In most perception-based studies, this problem is formulated as categorical classification with a fixed number of classes defined during training. We propose an approach that enables new surface classes to be added as trainable vectors, which can subsequently be used to address higher-level tasks. By employing a learning paradigm based on predicting the robot's next state in time and using attention blocks, we improved classification accuracy to 98.56% on the Belyaev-Kushnarev dataset and 94.8% on BorealTC.

Uncertainty quantification (UQ) for large language models (LLMs) aims to provide reliable measures of predictive confidence, yet current methods are often unstable under meaning-preserving perturbations. Semantically equivalent paraphrases can induce substantial variability in predictive confidence, even for methods with formal guarantees, such as conformal prediction. To address this issue, we propose a paraphrase-aware UQ framework robust to semantic rewordings. Our approach trains a lightweight proxy model on LLM hidden states and aggregates its predictions across paraphrases to construct label-wise nonconformity scores. Under score exchangeability, conformal calibration retains marginal coverage. This guarantee can also hold under test-only rewording, provided that the paraphrase pipeline satisfies an additional distributional alignment condition. We evaluate three settings (normal, fully reworded, and semi-reworded) which apply rewording to neither dataset, both calibration and test datasets, or only the test dataset, respectively. Across seven multiple-choice QA benchmarks and multiple model families, our method produces compact prediction sets with empirical coverage generally near the nominal target, even in the semi-reworded setting. Ablation studies show that the learned proxy accounts for most of the reduction in set size, while paraphrase-augmented training and inference-time aggregation improve stability under rewording. Code is available at https://github.com/Raina-Xin/PA_Score.

Humanoid robots could transport payloads substantially heavier than themselves by pulling passive wheeled vehicles instead of carrying the load. This capability, however, creates a coupled locomotion problem: the robot must maintain persistent upper-body contact while adapting to unknown, configuration-dependent forces arising from the payload, vehicle, and terrain. We present a whole-body control framework for humanoid rickshaw pulling that tracks commanded vehicle motion while preserving balance and stable grasps under uncertain load dynamics. During training, a privileged teacher exploits vehicle states, interaction forces, and load properties. Its actions and latent are distilled into a history-conditioned student that implicitly infers coupled dynamics from proprioceptive responses, followed by reinforcement-learning fine-tuning. Comparisons with No History and Only History baselines show that the resulting policy achieves accurate vehicle tracking while reducing vehicle oscillation, torso tilt, and actuation cost. Behavioral analysis shows that Unitree G1 propels the rickshaw and generates gait-synchronized whole-body reactions that stabilize its lateral and roll motions. Moreover, pulling redistributes joint effort and yields a lower robot-normalized cost-of-transport proxy than unloaded walking over most tested load–speed conditions. On hardware, a single policy performs starting, sustained pulling, turning, and stopping with both rigid payloads and human passengers, handling a loaded rickshaw mass of up to 115~kg without load-specific retuning. These results demonstrate robust heavy-load transportation through coordinated and persistent humanoid–vehicle interaction.

Spiking Neural Network (SNN) simulation serves as a crucial tool for understanding brain dynamics and advancing neuromorphic computing, but faces significant scalability challenges in large-scale distributed implementations. The primary bottlenecks arise from frequent synchronization overhead in time-driven simulators and extensive secondary rollbacks in optimistic PDES approaches, compounded by inefficient communication patterns that underutilize network bandwidth. In this paper, we propose OACM, an Optimistic Asynchronous Communication Model that addresses these challenges through three key innovations. First, we design Optimistic Hybrid SNN Simulation that combines the implementation simplicity of time-driven approaches with reduced synchronization frequency through strategic rollback mechanisms within synchronization windows. Second, we implement asynchronous one-sided communication using the UNR library, eliminating handshake latency and achieving complete computation-communication overlap. Third, we develop adaptive message aggregation and routing strategies within a 2D-HyperX virtual topology to optimize bandwidth utilization for small message traffic. Experimental evaluation on a high-performance computing cluster demonstrates that OACM achieves up to 1.4x speedup over the original CORTEX simulator and over 22.6x speedup compared to NEST when simulating a multi-area marmoset brain model at scales of up to 174 compute nodes.

Modern TTS systems increasingly generate synthetic speech at scale for diverse users. This setting calls for content-level provenance that can verify the origin of released speech and attribute it to the requesting user, which generative watermarking can support by embedding multi-bit identifiers directly into synthesized speech. Once released, however, speech may undergo heterogeneous learned transformations during distribution and editing, with reconstruction objectives that can preserve speech utility while affecting watermark recoverability differently. We find that no single watermark carrier remains consistently reliable across reconstruction models, as its survival depends jointly on the embedded structure, reconstruction mechanism, and observation representation. To this end, we propose Thrive, a multi-bit generative speech watermarking framework for modern autoregressive TTS, covering both discrete-token and continuous-representation generation under reconstruction attacks. Specifically, Rise synchronizes watermark injection into intermediate representations with its continued integration into subsequent generation, while Care combines waveform and spectral experts using bit-wise reliability selection. Experiments on both autoregressive paradigms show that Thrive preserves synthesis fidelity, achieves 87.6% average recovery accuracy under reconstruction attacks, and supports source attribution over candidate sets of up to 10,000 identities.

Humanoid whole-body controllers can now track a diverse set of dynamic motions, but they are typically trained offline and then frozen, so teaching such a controller a new skill tends to erode the skills it already mastered. We study continual learning for humanoid whole-body motion, where a single controller must acquire skills from a sequential task stream without revisiting past data. We introduce Similarity-guided LoRA-PNN, a progressive neural network (PNN) policy that prevents catastrophic forgetting by construction while reusing knowledge across skills through lightweight low-rank adaptation. A two-level motion-similarity measure, built from dynamic time warping aggregated by optimal transport, decides which prior skill to build on and how much new capacity to allocate, yielding strong forward transfer and large efficiency gains. Across six sequentially learned skill categories, our similarity-guided LoRA policy attains the best forward transfer (0.125 vs. 0.079) and the highest average accuracy among all methods, while saving up to 94.5% of trainable parameters and 40.8% of training time. The resulting controller reaches 96.13% sim-to-sim transfer and is deployed on a physical Unitree G1. Our code is available at https://anonymous.4open.science/r/continual-humanoid-learning-35D3.

Shininess is one of the main theory combination methods in Satisfiability Modulo Theories. We present two infinite families of generalizations of it: one involving a property between gentleness and shininess, which helps us see gentleness itself as a variation of shininess; and another having no further computability requirements on the weaker theory, in addition dropping the need for smoothness. We prove these methods sharp, and compare them with existing methods.

Open-pit mining operational planning involves allocating limited resources while satisfying production, equipment, and ore-quality requirements. Existing approaches often assume deterministic ore grades or rely on simulation-based evaluation under uncertainty. In this paper, we propose a chance-constrained bi-objective formulation of the open-pit mining operational planning problem under uncertain ore grades. We aim to maximize ore production and minimize fleet cost while satisfying stochastic quality requirements through chance constraints. We model ore grades as independent normally distributed random variables and derive a deterministic reformulation of the two-sided chance constraints, avoiding sampling or simulation during fitness evaluation. We evaluate four multi-objective evolutionary algorithms on benchmark instances under different levels and structures of uncertainty. Our results show that NSGA-II and NSGA-III generally obtain the best feasible ore-production values, with NSGA-II requiring less computational time. GSEMO has the lowest computational cost but obtains feasible solutions less consistently and generally provides lower solution quality. We also observe that higher confidence and uncertainty levels reduce feasibility, with the effect depending on the uncertainty structure. The results highlight the importance of considering both the magnitude and structure of uncertainty in short-term open-pit operational planning.

LoRA-based continual learning methods mitigate catastrophic forgetting through various mechanisms, yet nearly all complement these with small learning rates as a heuristic to restrict gradient scaling magnitude. Such fixed heuristics lack theoretical guidance on how the strength of this restriction should evolve as tasks accumulate. We reveal that even under directional constraints such as nullspace projection, finite-precision updates inevitably leak into the subspace of accumulated prior knowledge along multiple directions. While small learning rates attenuate such leakage, they cannot prevent the accumulated forgetting from intensifying as the effective rank of historical knowledge grows. We show that the optimal magnitude restriction should adaptively increase with this effective rank to balance stability and plasticity, i.e., preservation of previous knowledge and acquisition of new task information. Under an anisotropic leakage model, we derive a pacing law $s^*=\sqrt{R/c}$ that characterizes the optimal scaling of gradient steps, i.e., the magnitude restriction itself, where $R$ is the effective rank of past updates. Based on this insight, we propose PaLoRA, which compresses historical knowledge via adaptive SVD truncation, projects gradients onto the nullspace of prior tasks, and applies rank-aware adaptive pacing. Experiments demonstrate consistent improvements over prior methods, with particularly strong performance in long-horizon settings, achieving substantial gains of 4% accuracy on challenging 50-task ImageNet-A and ImageNet-R benchmarks.

Multimodal Large Language Models (MLLMs) have demonstrated strong performance in video understanding, yet efficiently processing long, high-resolution videos remains challenging. Such videos often contain substantial spatiotemporal redundancy, and processing redundant visual tokens can incur avoidable computational overhead. Many existing methods prune visual tokens during or after vision transformer (ViT) encoding, leaving much of the encoding cost unaddressed. Some approaches prune patches before encoding but rely on learned auxiliary networks for patch selection, incurring additional training and inference overhead. To address these limitations, we propose FlashGaze, a training-free method that reduces spatiotemporal redundancy before ViT encoding without introducing auxiliary networks. FlashGaze uses pixel-space differences as a proxy for information loss and employs Quadtree Dynamic Programming to jointly optimize patch dropping, merging, and keeping under a fixed budget. Experiments on two MLLM backbones across multiple benchmarks demonstrate substantial efficiency gains while largely preserving accuracy. On Qwen3-VL-8B, FlashGaze retains 98% of the full-input baseline accuracy on LongVideoBench while achieving up to 5.4x and 17x speedups in ViT encoding and MLLM prefill, respectively, and reducing peak GPU memory usage by a factor of 1.8. These efficiency gains enable the model to process videos with more frames and higher resolutions on the same GPU hardware, unlocking video understanding at scales previously out of reach.

Life support equipment coupled to the human lungs forms a complex, nonlinear dynamic system. Current respiratory mask test standards rely on sinusoidal breathing machines and surrogate trachea geometries that substantially reduce physiologically relevant airway inertance. This paper shows that the ISO 16900-5 trachea does not generate physiologically meaningful exhalation momentum, limiting the ability of standard test configurations to reveal valve dynamics relevant to human use. A physiologically motivated “lip-nozzle” surrogate is introduced as a diagnostic tool to restore realistic momentum transfer, enabling observation of exhalation behavior that is not observable under existing test conditions. Nonlinear dynamic simulations incorporating this surrogate reveal a force-balanced operating regime in which exhalation-jet momentum can offset flow-induced valve resistance, in one representative case reversing exhalation mean effective pressure from resistive to assistive. This effect depends on the relationship between the valve's restoring force and lift, representing a design consideration relevant to future valve development. Implications for mask design, valve placement, and future test methods are discussed. This work does not propose new performance limits or acceptance criteria; rather, it demonstrates how current test fixtures suppress inertance- and momentum-driven effects that can materially influence exhalation valve dynamics.