Computer Science (arXiv)

Machine-generated text (MGT) attribution aims to identify the specific generator responsible for a given text, thereby providing fine-grained evidence for model accountability and misuse investigation. As new large language models continue to emerge, attribution models must continuously incorporate new generators while preserving their ability to recognize previously seen ones. Prior works have shown that this lifelong MGT attribution setting is challenging, and existing methods often struggle to achieve a stable balance between adapting to new classes and retaining old ones. To address this issue, we propose RidgeFT, a lightweight analytic update framework that does not rely on exemplar replay. RidgeFT trains a task-aware encoder on the initial generator set, stores compact class-wise sufficient statistics when each generator class is first observed, and then freezes the encoder for replay-free closed-form updates. It then suppresses generator-irrelevant variation through covariance calibration, improves representation capacity with fixed random features, and updates new classes through closed-form ridge regression based on class-level sufficient statistics. Across multi-topic evaluations with varying initial generator setups, RidgeFT consistently outperforms baselines. It achieves the best macro-F1 across domains, backbones, and incremental protocols, while also improving both old-class retention and new-class adaptation. These results suggest that feature-stable analytic updates provide a simple yet effective approach to lifelong MGT attribution.

Implicit reward hacking is hard to audit when a language model's chain of thought appears benign: a final answer may be anchored by a prompt shortcut while the written reasoning still resembles ordinary problem solving. Verifier-based probes expose such behavior by measuring how early truncated reasoning contexts obtain high reward, but require a task-specific reward signal. This paper proposes a weaker-input alternative, self-commitment latency, which measures how early a prompted reasoning context commits to the model's own final answer. We evaluate the probe in a controlled paired GSM8K setting using Qwen2.5-3B-Instruct-4bit, comparing ordinary prompts with prompts that include an answer hint. Hinted contexts commit substantially earlier and with lower uncertainty than honest contexts. The primary latency metric, first-commitment latency at threshold 0.8, reaches AUROC 0.878; supporting whole-curve summaries reach AUROC 0.926 for commitment range and 0.904 for mean uncommitted mass. The signal is stronger when both prompt conditions answer correctly and remains stable across thresholds. These results show that shortcut-available reasoning contexts can leave an early behavioral commitment signature detectable without a reward model, external judge, or trained classifier.

Text-conditioned 3D human motion models now synthesize plausible motions from prompts, but practical animation and embodied-agent workflows rarely stop at text: a character may need to follow a sketched root path, hit an end-effector target, or satisfy a multi-joint trajectory while still preserving the gait, style, and intent described by language. This exposes a control trade-off. A trajectory controller should be precise without overwriting the pretrained text-conditioned motion prior, yet existing solutions either duplicate large portions of the generator to regain per-layer control access or move much of the cost to test-time optimization. We introduce KV-Control, a compact attention-side control interface for frozen masked text-to-motion transformers. The key idea is to make geometric constraints available as memory inside self-attention rather than injecting them through a global pose token or enforcing them only at the output side. To support this interface, we co-design a part-tokenized motion substrate and controller: \textbf{PartVQ} learns anatomy-aligned part codebooks, T-Concat exposes each frame--part token as an attention-addressable site, and KV-Control injects control-conditioned key/value memories at every self-attention layer while preserving the pretrained query stream, text cross-attention, FFN, and all backbone weights. The resulting adapter adds only trainable injection parameters atop a shared trajectory encoder, yet tracks root and multi-joint constraints with sub-centimeter accuracy under the inherited refinement protocol while retaining text-conditioned motion quality. KV-Control reframes trajectory conditioning as lightweight memory retrieval, providing a small, precise, and transparent control interface for text-to-motion generation.

Planning for real-world problems by language models often involves both world and user constraints, which may not be fully specified upfront and are progressively disclosed through interaction. However, existing benchmarks still underexplore adaptive planning under such progressively revealed dual constraints. To address this gap, we introduce AdaPlanBench, a dynamic interactive benchmark for evaluating whether Large Language Model (LLM) agents can adaptively plan and re-plan under progressively revealed world and user constraints. AdaPlanBench is built on 307 household tasks, with a scalable constraint construction pipeline that augments each task with dual constraints. At runtime, agents interact with the environment in a multi-turn protocol where hidden constraints are revealed only when the agent proposes a plan that violates them, requiring iterative plan revision under accumulating feedback. This makes planning challenging, as agents must infer and track constraints from feedback while re-planning effectively. Experiments on ten leading LLMs show that adaptive planning under dual constraints remains challenging, with the best model reaching only 67.75% accuracy. We further observe that performance degrades as more constraints accumulate, with user constraints posing a particularly large challenge and failures often stemming from weaker physical grounding and reduced effectiveness. These results establish AdaPlanBench as a testbed for dual-constrained interactive planning and highlight the challenge of reliable adaptation to dynamically revealed constraints in LLM agents.

Distilling accurate user preferences from noisy implicit feedback remains a fundamental bottleneck in recommendation systems, highlighting the need for recommendation denoising. However, real-world data lack explicit noise annotations, forcing existing methods to rely on unsupervised side information or handcrafted heuristics. These approaches often incur high external costs, generalize poorly, or depend on unreliable priors, causing noise misidentification and corrupting true user preference representations. To address these limitations, we propose a paradigm-level reformulation of recommendation denoising. Instead of indirectly inferring noisy interactions through heuristics, our Creation-Recognition paradigm proactively creates labeled noisy interactions and trains a dedicated recognizer to identify them, transforming denoising from heuristic filtering into supervised learning. Based on this paradigm, we present ANCHOR, an agent-based framework inspired by recent LLM-as-User research. ANCHOR simulates user behaviors to generate realistic noise labels and enables supervised denoising through two stages: noise creation and noise recognition. In the noise creation stage, ANCHOR adopts a recommender-in-the-loop agentic architecture to synthesize both diverse out-of-preference noise and informative boundary-adjacent noise. For out-of-preference noise, it implements five extensible simulation mechanisms to approximate major sources of noisy implicit feedback. For boundary-adjacent noise, an adversarial boundary refinement mechanism generates ambiguous interactions that challenge the recognizer and target the decision boundary. In the noise recognition stage, ANCHOR leverages the generated labels to train a reusable parametric recognizer that integrates collaborative signals and semantic representations to detect noise patterns in real interaction data.

Recursion enables the generation of hierarchical linguistic structures but imposes substantial processing demands during real-time comprehension. While difficulties with complex syntax have been reported in autism spectrum disorder (ASD), the temporal dynamics of recursive processing remain poorly understood. This study used event-related potentials (ERPs) to examine how Mandarin-speaking children with ASD process two-level recursive locative constructions. Twenty-four children (12 ASD, 12 typically developing, TD) participated in a cross-modal sentence-picture matching task. Neural responses were analyzed across three processing stages associated with structural prediction (P200), semantic integration (N400), and syntactic reanalysis (P600), with mental age controlled. Results revealed a systematic divergence between groups. TD children showed clear P200 and P600 modulation in response to structural mismatch, whereas ASD children exhibited attenuated early differentiation and reduced late reanalysis effects. In contrast, ASD children showed enhanced N400 responses under mismatch conditions, indicating increased semantic integration demands. In addition, the ASD group displayed significantly greater inter-individual variability in hemispheric lateralization, although lateralization strength was not associated with receptive vocabulary performance. These findings support a cascading account in which reduced early predictive engagement in ASD leads to increased integration costs and diminished reanalysis efficiency during recursive processing. More broadly, the results highlight the importance of both temporal processing dynamics and neural variability in understanding language differences in ASD.

Extreme events -- such as earthquakes and coronal mass ejections -- are common in many chaotic dynamical systems, yet are difficult to characterize and predict due to the subtle instability mechanisms that drive them. In this work, we develop an interpretable technique that reveals the underlying mechanisms behind extreme events and uses them to build data-driven forecasts and intuitive event suppression controllers. In particular, we utilize the covariance balancing reduction using adjoint snapshots (CoBRAS) method to identify linear oblique projections that best capture the sensitivity of a quantity of interest and reconstruct the original state. Importantly, we bypass the need for cumbersome adjoint calculations, instead using backpropagation via modern automatically differentiable numerical frameworks. To accommodate spatially localized events, we also introduce a new variant of CoBRAS to obtain local sensitivity-balanced projections. We demonstrate the utility of this approach to characterize extreme events across a diverse set of challenging systems, including turbulent bursts of energy dissipation in the 2D Kolmogorov Flow, spontaneous synchronization in networks of coupled FitzHugh-Nagumo oscillators, and the localized formation of ocean rogue waves from a modified nonlinear Schrödinger equation. For each example, we show that our simple forecast models accurately predict extreme events and that the underlying mechanisms may be used to design control laws to prevent these events. Finally, we demonstrate that by learning a neural network surrogate model of the dynamics directly from data, we may extend this approach to experimental systems and systems that are not natively written in an automatically differentiable programming language.

The morphological form of a word can often give cues to its meaning, but purely relying on these mappings can lead to overgeneralization in high-stakes domains. In the medical domain, for instance, LLMs can confidently reason about fictitious drugs from their affixes alone (e.g., wugcillin) and generate plausible-looking clinical content. We present a behavioral and mechanistic study of LLM "affix heuristics" in pharmacology. Using fictitious drug names built from real affixes, we show that affix signals alone elicit class-level pharmacological responses. We introduce a framework for identifying whether a model's drug semantics are driven mainly by the affix, the stem, or the drug name as a whole. Applied across 653 drugs, our framework reveals that models often induce drug meaning primarily through affix cues, yet rarely explicitly indicate this reliance, and sometimes incorrectly conflate properties among affix-sharing drugs. Activation patching across models further localizes this behavior to early-mid layers. These findings show that morphological shortcuts pose a subtle but measurable risk to safety.

Large language models (LLMs) are rigorously aligned to refuse harmful requests, a process that inherently cultivates a latent capacity to evaluate and recognize unsafe content. In this work, we reveal that this advanced safety awareness inadvertently introduces a fatal vulnerability. We introduce Posterior Attack, a single-query jailbreak that bypasses guardrails by prompting the model to generate the exact harmful response its internal classifier would normally flag as unsafe. Through extensive empirical evaluation across 30 open-source LLMs (up to 35B parameters in size) and frontier models (e.g., GPT-5, Claude 4.6), we observe a striking phenomenon: models with superior safety-judgment capabilities are disproportionately more susceptible to this exploitation. To explain this, we formalize the Safety Paradox, analytically showing that monotonic improvements in safety alignment naturally amplify posterior vulnerability. Finally, we establish a causal link via reinforcement learning interventions, exemplifying that artificially degrading a model's safety judgment immunizes it against the attack, whereas enhancing judgment exacerbates the vulnerability. Our findings highlight potential flaws in current alignment paradigms, indicating that defense mechanisms may require further structural refinement.

The rapid evolution of Large Language Models (LLMs) has established cross-lingual versatility as a defining feature of modern systems. However, fine-tuning these models frequently induces negative interference across languages. To address this, we reformulate multilingual fine-tuning as a multi-objective optimization (MOO) problem. Specifically, we introduce Bucket-Level MOO, a scalable distributed framework that applies gradient-based MOO algorithms locally on parameter buckets. This enables conflict-aware updates without the prohibitive communication overhead of reconstructing full gradient vectors. Theoretically, we prove this localized resolution natively enforces Refined Pareto Stationarity, a strictly tighter necessary condition for Pareto optimality. Empirically, Bucket-Level MOO mitigates interference by driving LLMs to construct distinct language-specific dimensions, improving representational separability. Extensive experiments across four base LLMs demonstrate that our method significantly improves both seen and unseen multilingual performance over standard fine-tuning paradigms.

Sow body condition is an important indicator for growers as it has a large impact on lactation performance and piglet survival. However, body condition measures used during production, such as visual scoring and calipers, correlate poorly with underlying tissue composition. Ultrasound scans can provide direct measurements of subcutaneous backfat thickness and loin muscle depth, but their operation is labor intensive and not scalable for production. We present PigFormer, an end-to-end two-stage system that takes raw depth frames from a ceiling-mounted RGB-D camera and predicts subcutaneous backfat thickness, loin muscle depth, and total tissue thickness at the last rib. Stage 1 is a geometric front-end that converts raw depth into a standardized height map via SAM3-to-MaskDINO segmentation distillation, ground-plane removal, and orientation normalization. Stage 2 is a Slice Attention Encoder that treats each height map as a sequence of cross-sectional slices and captures spatial relationships along the full dorsal surface. On a multi-site dataset of 319 sow and gilt instances from two facilities, PigFormer achieves 2.43 mm backfat MAE and 3.87 mm overall MAE. It outperforms strong single-stage ResNet-18 and ViT-small baselines. PigFormer offers a practical path toward continuous, automated, non-contact body condition monitoring in commercial swine production. Code is available at https://github.com/iambashar/Pigformer.

The efficacy of continued pre-training for Large Language Models (LLMs) hinges upon hyperparameter configurations, such as learning rate and batch size. However, current practices often rely on heuristics or grid searches, leading to training instability and excessive costs. In this work, we first empirically discover that optimal hyperparameters follow stable and predictable scaling laws throughout the continued pre-training process. Leveraging these insights, we propose a novel framework to establish quantitative relationships between compute budget and optimal hyperparameters for a given checkpoint. Our approach has two stages: (1) \textit{Empirical Law Discovery}, where we train small-scale proxy models to derive functions mapping compute budget to optimal hyperparameters via standard loss-compute scaling laws; and (2) \textit{State-Aware Hyperparameter Prediction}, where we evaluate an initial checkpoint's validation loss and use the inverse scaling law to estimate its \textit{equivalent pre-training compute} -- the compute needed to achieve the same loss from scratch. Combining this with the planned compute budget, we predict optimal hyperparameters for the target run. Empirical results demonstrate that our method reduces the hyperparameter search overhead by up to 90\% while achieving comparable or superior performance relative to baselines. This model-agnostic framework generalizes across architectures, providing a principled and efficient methodology for diverse continued pre-training scenarios starting from any given point.

As large language models (LLMs) are widely deployed, identifying their vulnerability through jailbreak attacks becomes increasingly critical. Optimization-based attacks like Greedy Coordinate Gradient (GCG) have focused on inserting adversarial tokens to the end of prompts. However, GCG restricts adversarial tokens to a fixed insertion point (typically the prompt suffix), leaving the effect of inserting tokens at other positions unexplored. In this paper, we empirically investigate \emph{slots}, i.e., candidate positions within a prompt where tokens can be inserted. We find that vulnerability to jailbreaking is highly related to the selection of the \emph{slots}. Based on these findings, we introduce the \textit{Vulnerable Slot Score} (VSS) to quantify the positional vulnerability to jailbreaking. We then propose SlotGCG, which evaluates all slots with VSS, selects the most vulnerable slots for insertion, and runs a targeted optimization attack at those slots. Our approach provides a position-search mechanism that is attack-agnostic and can be plugged into any optimization-based attack, adding only 200ms of preprocessing time. Experiments across multiple models demonstrate that SlotGCG significantly outperforms existing methods. Specifically, it achieves 14\% higher Attack Success Rates (ASR) over GCG-based attacks, converges faster, and shows superior robustness against defense methods with 42\% higher ASR than baseline approaches. Our implementation is available at \href{https://github.com/youai058/SlotGCG}{https://github.com/youai058/SlotGCG}

For over half a century, software engineering has operated on a foundational premise: human engineers decompose problems, encode decision logic into static code, and manually adapt that code as requirements evolve. This paper argues that the emergence of AI agents -- systems where large language models serve as the primary reasoning engine, dynamically generating and discarding code as an instrumental resource -- constitutes not an incremental improvement but a fundamental restructuring of the software paradigm. Drawing on first-principles analysis of complexity scaling, we formalize the distinction between traditional software (where code is the carrier of decision logic) and agentic systems (where code is ephemeral tooling for an LLM-driven reasoning loop). We trace the historical arc from licensed software to SaaS to what we term Agent-as-a-Service (AaaS), showing that each shift transferred additional complexity away from end-users. We introduce the concept of Agentic Engineering as an emergent discipline -- distinct from software engineering in its core object of study, control model, and human role. Through analysis of recent benchmark evidence including SWE-bench Verified, EvoClaw, and LangChain's multi-agent coordination studies, we demonstrate both the transformative potential of the agentic paradigm and its current limitations. We conclude with a four-stage roadmap toward self-evolving agent ecosystems and concrete recommendations for practitioners navigating this transition.

LLM post-training often relies on reinforcement learning methods that sample multiple rollouts per prompt, yet most existing approaches use a fixed rollout budget for every prompt, despite large differences in the training signal different prompts provide. In this paper, we study adaptive rollout allocation under a fixed global budget and formulate the problem as online resource allocation with prompt-level diminishing returns. Our method, CERO, maintains a Beta posterior over each prompt's success probability and uses the posterior expected Bernoulli variance as a Bayesian estimate of the value of additional rollouts. We use this estimate to construct a concave, saturating utility over cumulative allocations, yielding an objective in which decisions across prompts and epochs are coupled by the global budget. Since the resulting objective is temporally nonseparable, we derive a Fenchel-dual reformulation and update both prompt-level and budget-level dual variables via projected online gradient descent. Under fixed prompt utilities, we prove an $O(\sqrt{K})$ regret bound against the offline allocation benchmark. Experiments on mathematical-reasoning problems show that CERO consistently outperforms GRPO across multiple open-weight LLMs and benchmarks, demonstrating that adaptive rollout budgeting can improve sample efficiency.

How does a system that merely predicts the world come to distinguish its own causal influence from everything else? We trace this transition in a minimal 192-dimensional GRU through 40 controlled experiments arranged as a developmental sequence, adding components one at a time and tracking whether the system can distinguish self-caused from world-caused changes. The developmental path reveals four conditions that must be satisfied in strict order: (1) persistent state forming stable attractors, (2) a causal action loop linking output to input, (3) proprioceptive feedback that makes implicit causal knowledge explicit, and (4) asynchronous awakening - perceptual learning must consolidate before action learning begins. We propose agency gain (A = Err_world - Err_self), the predictive advantage of knowing one's own action, as a metric to track this process. The self-aware predictor consistently outperforms the self-blind predictor across periodic (sinusoidal) and chaotic (Lorenz) environments, and the metric survives ablation of all auxiliary components. Only forward-sampled action selection produces meaningful agency gain; two gradient-based alternatives degenerate. Equally significant are 12 falsified hypotheses mapping where development stalls: predictive coding alone does not produce self-represent

AI assistants in human-AI collaboration often correct suboptimal human actions through behavioral feedback (e.g., alerts or steering-wheel nudges in assistive driving). Such interventions can mitigate immediate errors, but long-term improvement requires addressing the underlying misconceptions that cause repeated mistakes. We introduce SENSEI, a framework that infers user misconceptions from interaction behavior and provides targeted, minimal yet sufficient suggestions to correct them. Our approach departs from action- or trajectory-level interventions by operating over a structured knowledge representation to localize and correct the sources of erroneous behavior. Across three long-horizon tasks with diverse misconceptions and corresponding behaviors, SENSEI demonstrates zero-shot compositional generalization, disentangling multiple overlapping misconceptions despite training only on single-misconception cases. A user study further shows that our method identifies real human misconceptions and provides effective guidance that improves long-horizon task performance, successfully correcting $90\%$ of student misconceptions. Code and project page are available at https://misoshiruseijin.github.io/SENSEI/.

This paper investigates a rotatable antenna (RA)-enabled uplink non-orthogonal multiple access (NOMA) system, where a base station equipped with multiple independently RAs serves both ground and aerial users. Specifically, we formulate an energy efficiency (EE) maximization problem by jointly optimizing receive beamforming, user power allocation, and RA rotation. To make the problem tractable, a new block coordinate descent-based algorithm is developed, in which the receive beamforming is updated via the minimum mean square error criterion, while the power allocation and RA rotation are handled by fractional programming and successive convex approximation. Numerical results demonstrate the EE superiority of the proposed RA-NOMA scheme over several benchmarks.

This paper establishes a theoretical framework for the uniform convergence of smoothly activated deep neural network (DNN) estimators. While standard ReLU networks achieve minimax-optimal rates in the $L^2(P)$ norm for various nonparametric regression tasks, we establish a theoretical lower bound demonstrating that least-squares ReLU estimators can suffer from the curse of dimensionality in their uniform convergence behavior. Motivated by the need for reliable uniform guarantees in downstream tasks requiring worst-case reliability, we address this limitation by analyzing smoothly activated DNNs (smooth DNNs), encompassing both feedforward and residual structures. We establish novel pseudo-dimension bounds, non-asymptotic approximation guarantees, and Hölder-norm bounds for the approximators of these models. Leveraging these results, we derive non-asymptotic uniform convergence rates for smooth DNN estimators across multiple statistical contexts, including Huber, least-squares, quantile, and logistic regression. We prove that smooth DNNs can mitigate the {curse of dimensionality} in uniform convergence by adaptively exploiting the low-dimensional hierarchical composition structure of the target function. Supported by both simulation studies and a real-world application, our results position smooth DNNs as a theoretically grounded and practically viable alternative to ReLU networks for statistical learning tasks requiring uniform guarantees.

Training vision-language web agents with multi-step RL is compute-intensive, with two dominant forms of inefficiency: idle GPUs in synchronous RL, and trajectories that use more steps and tokens than necessary. We present AsyncWebRL, which addresses both. On the system side, an asynchronous design overlaps rollout, gradient update, and policy refresh across iterations, paired with two web-agent-specific adaptations, namely an everlasting rollout pool and lightweight screenshot handling, that together deliver up to a $2.9\times$ end-to-end training-throughput speedup over the previously fastest open synchronous pipeline (WebGym). On the algorithmic side, we identify the per-trajectory normalizer $1/|τ_i|$ in multi-step GRPO as the root cause of trajectory-level and token-level inefficiency: because failures are systematically longer than successes, it down-weights the negative gradient on failed tokens, so the policy keeps producing verbose memory schemas. Replacing $1/|τ_i|$ with a constant $1/k$ breaks this coupling, contracting trajectories while preserving aggregate success. Together, these contributions set a new open-source state of the art on the WebGym out-of-distribution test split (+5.8% relative over the 42.9% prior best), with the largest gains on the harder slices (+42% relative on Medium, +48% relative on Hard).

In this paper, we study multi-objective submodular maximization (MOSM) subject to a cardinality constraint under differential privacy (DP). Specifically, we aim to select a set of at most $k \in \mathbb{Z}_{+}$ elements to maximize the minimum of $d > 1$ monotone submodular functions while satisfying $\varepsilon$-DP. Although extensive studies have been conducted on both differentially private single-objective submodular maximization on sensitive data and non-private MOSM, to the best of our knowledge, there has not yet been any prior work on MOSM with DP. We propose two novel algorithms: the first extends the classic greedy algorithm and the second employs a truncation technique, both of which are integrated with DP mechanisms for privacy protection and achieve approximation guarantees for MOSM. Finally, we conduct numerical experiments on two submodular maximization applications, namely maximum coverage and facility location, in multi-objective settings to validate the efficacy and efficiency of our proposed algorithms.

We introduce the Coverage Gap as a measurable distance between the observable public exposure of critical-infrastructure operators and their declared capability to coordinate vulnerability disclosure. We instantiate it against the 915 Chilean Operadores de Importancia Vital (OIVs -- Operators of Vital Importance) designated by the National Cybersecurity Agency (ANCI) under Ley 21.663 (Resolucion Exenta No. 87, 16 December 2025). Using a passive-only, OSINT-based method consistent with the principles of ISO/IEC 29147:2018 and Chile's computer-crimes safe harbour (Ley 21.459), we conduct a full-universe census of the foundational disclosure-capability layer (Layer 1, verifiable disclosure contact) across approximately 98.7% of the official catalogue. Only 16 of 915 OIVs (1.7%) publish a verifiable RFC 9116 disclosure channel; among operators of physical-world infrastructure -- energy, health, banking, telecommunications, fuel, water, transport, and state administration -- fewer than ten do so, and all four major banks and both telecommunications incumbents lack one entirely. This compares with over 99% adherence in the U.S. federal civilian branch under CISA Binding Operational Directive 18-01. Email-authentication misconfiguration affects 766 of 915 (84%) OIVs, and end-of-life or known-vulnerable stack components an estimated 23.5% (Wilson 95% CI [12%, 38%]). Cross-jurisdictional benchmarking situates Chile roughly eight years behind the USA, the UK, and the Netherlands on email-authentication mandates, and three years behind Denmark. We propose a four-stage roadmap modelled on BOD 18-01 and the UK Public-Sector DMARC Toolkit, and release the open-source tool anci-oiv-resolver (Apache 2.0) to enable independent reproduction of the OIV-domain mapping that underpins universe-scale auditing.

Imitation-learning policies inherit the quality of the demonstrations they are trained on, and a growing set of curation metrics promise to score and filter low-quality demonstrations automatically. These metrics are each validated on different data with different protocols, so it is unclear which of them actually identify the demonstrations that harm a policy. We build a controlled testbed in which demonstration defects are injected with known type, and audit seven curation metrics along two axes: how well each separates defective from clean demonstrations, and whether training a behavior-cloning policy on each metric's curated subset improves task success. We study two defect regimes. Subtle perturbations (correlated action noise, tremor, truncation) are detectable by multivariate outlier scoring and, once removed, recover the full downstream gap. Structural errors, where the demonstration executes a wrong action at a key moment, are invisible to every action-only metric we test, and two of them are inverted: they score defective demonstrations as higher quality and, used for curation, tend to leave the policy at or below the uncurated baseline rather than above it. Only metrics that examine the state trajectory detect structural errors, and even the best of them recovers just a third of the downstream gap. High detection accuracy does not guarantee downstream improvement. We release the testbed and all curation implementations.

Multi-object tracking (MOT) from UAV imagery presents unique challenges: altitude varies across sequences, objects are small and densely packed, and frequent occlusion causes identity switches. Existing graph-based trackers assume fixed spatial context and treat all objects uniformly, ignoring the heterogeneous lifecycle states of detections, active tracklets, and lost targets. We propose HDST-GNN, a Heterogeneous Dynamic Spatiotemporal Graph Neural Network with three novel contributions. First, Altitude-Adaptive Edge Construction estimates a camera-altitude proxy from mean object area and adjusts the graph connectivity radius accordingly. Second, Heterogeneous Node Representation models detections (Type-D), confirmed tracklets (Type-T), and lost tracklets (Type-L) as distinct node types with dedicated projections and typed edge relations. Third, Occlusion-Gated Temporal Aggregation gates each node's attention contribution by its occlusion confidence, preventing occluded nodes from corrupting neighbour embeddings. HDST-GNN is trained end-to-end with a differentiable Sinkhorn head using joint cross-entropy and triplet loss. On VisDrone2019-MOT with oracle detections, HDST-GNN achieves 94.51% MOTA and 97.24% IDF1, outperforming SORT by +5.0 MOTA points and reducing identity switches by 81%. With real YOLOv8n detections, HDST-GNN reduces identity switches by 49% vs. SORT. Ablation studies confirm the independent contribution of each component.

In remote sensing object detection, Convolutional Neural Networks (CNNs) excel at capturing local details while Vision Transformers (ViTs) are better at global context modeling. However, existing detectors typically rely on a single fixed backbone or a manually designed hybrid architecture, and thus fail to adaptively exploit these complementary strengths across inputs of diverse complexity. To address this limitation, we propose Backbone Module Composition via Reinforcement Learning (BMCR). BMCR dynamically assembles input-adaptive inference paths from reusable modules decomposed from off-the-shelf CNN and ViT backbones. To enable such cross-family composition, we first construct an extensible module toolbox. Specifically, we decompose representative CNN and ViT backbones into reusable functional modules and encapsulate each module with explicit structural, semantic, and computational metadata for compatibility-aware assembly. To bridge the gap between grid-based CNN features and token-based ViT representations, we design a lightweight Optimal Transport (OT) based transition interface that ensures distribution-aware alignment while respecting spatial consistency. The backbone composition process is then formulated as a sequential decision problem, in which a policy network progressively selects task-relevant modules according to intermediate multi-scale observations. To stabilize the joint optimization of reusable modules and the routing policy, we further develop an Adaptive Module Cooperative Optimization (AMCO) strategy that coordinates module updating, routing exploration, and reward assignment during training. On DOTA-v1.0, DOTA-v1.5 and DIOR-R, BMCR achieves 79.31\%, 73.41\% and 71.86\% mAP, respectively, surpassing strong static and dynamic baselines by up to 2.5 points while maintaining competitive efficiency.