Meta-Adaptive Beam Search Planning for Transformer-Based Reinforcement Learning Control of UAVs with Overhead Manipulators under Flight Disturbances

Drones equipped with overhead manipulators offer unique capabilities for inspection, maintenance, and contact-based interaction. However, the motion of the drone and its manipulator is tightly linked, and even small attitude changes caused by wind or control imperfections shift the end-effector away from its intended path. This coupling makes reliable tracking difficult and also limits the direct use of learning-based arm controllers that were originally designed for fixed-base robots. These effects appear consistently in our tests whenever the UAV body experiences drift or rapid attitude corrections. To address this behavior, we develop a reinforcement-learning (RL) framework with a transformer-based double deep Q learning (DDQN), with the core idea of using an adaptive beam-search planner that applies a short-horizon beam search over candidate control sequences using the learned critic as the forward estimator. This allows the controller to anticipate the end-effector's motion through simulated rollouts rather than executing those actions directly on the actual model, realizing a software-in-the-loop (SITL) approach. The lookahead relies on value estimates from a Transformer critic that processes short sequences of states, while a DDQN backbone provides the one-step targets needed to keep the learning process stable. Evaluated on a 3-DoF aerial manipulator under identical training conditions, the proposed meta-adaptive planner shows the strongest overall performance with a 10.2% reward increase, a substantial reduction in mean tracking error (from about 6% to 3%), and a 29.6% improvement in the combined reward-error metric relative to the DDQN baseline. Our method exhibits elevated stability in tracking target tip trajectory (by maintaining 5 cm tracking error) when the drone base exhibits drifts due to external disturbances, as opposed to the fixed-beam and Transformer-only variants.

Sustainability Is Not Linear: Quantifying Performance, Energy, and Privacy Trade-offs in On-Device Intelligence

The migration of Large Language Models (LLMs) from cloud clusters to edge devices promises enhanced privacy and offline accessibility, but this transition encounters a harsh reality: the physical constraints of mobile batteries, thermal limits, and, most importantly, memory constraints. To navigate this landscape, we constructed a reproducible experimental pipeline to profile the complex interplay between energy consumption, latency, and quality. Unlike theoretical studies, we captured granular power metrics across eight models ranging from 0.5B to 9B parameters without requiring root access, ensuring our findings reflect realistic user conditions. We harness this pipeline to conduct an empirical case study on a flagship Android device, the Samsung Galaxy S25 Ultra, establishing foundational hypotheses regarding the trade-offs between generation quality, performance, and resource consumption. Our investigation uncovered a counter-intuitive quantization-energy paradox. While modern importance-aware quantization successfully reduces memory footprints to fit larger models into RAM, we found it yields negligible energy savings compared to standard mixed-precision methods. This proves that for battery life, the architecture of the model, not its quantization scheme, is the decisive factor. We further identified that Mixture-of-Experts (MoE) architectures defy the standard size-energy trend, offering the storage capacity of a 7B model while maintaining the lower energy profile of a 1B to 2B model. Finally, an analysis of these multi-objective trade-offs reveals a pragmatic sweet spot of mid-sized models, such as Qwen2.5-3B, that effectively balance response quality with sustainable energy consumption.

The Limits of Learning from Pictures and Text: Vision-Language Models and Embodied Scene Understanding

What information is sufficient to learn the full richness of human scene understanding? The distributional hypothesis holds that the statistical co-occurrence of language and images captures the conceptual knowledge underlying visual cognition. Vision-language models (VLMs) are trained on massive paired text-image corpora but lack embodied experience, making them an ideal test of the distributional hypothesis. We report two experiments comparing descriptions generated by 18 VLMs to those of over 2000 human observers across 15 high-level scene understanding tasks, spanning general knowledge, affordances, sensory experiences, affective responses, and future prediction. Because many tasks lack ground truth answers, we developed a Human-Calibrated Cosine Distance (HCD) metric that measures VLM output similarity to the distribution of human responses, scaled by within-human variability. In Experiment 1, VLMs approached human-level performance on general knowledge tasks, but showed a robust deficit for affordance tasks that resisted prompt engineering and did not improve with newer model releases. In Experiment 2, we tested six mechanistic hypotheses for explaining this affordance gap, finding that the deficit was structural rather than stylistic and was not resolved by providing explicit spatial information. Corpus analyses revealed that image captioning datasets contain sparse agent-addressed affordance language, consistent with Gricean accounts of why embodied knowledge may be systematically underrepresented in language. Together, these findings suggest that distributional learning from images and text is insufficient for affordance-based scene understanding, implying that some dimensions of human visual cognition may require the kind of agent-centered, three-dimensional experience that no photograph or caption can encode.

Beyond MACs: Hardware Efficient Architecture Design for Vision Backbones

Vision backbone networks play a central role in modern computer vision. Enhancing their efficiency directly benefits a wide range of downstream applications. To measure efficiency, many publications rely on MACs (Multiply Accumulate operations) as a predictor of execution time. In this paper, we experimentally demonstrate the shortcomings of such a metric, especially in the context of edge devices. By contrasting the MAC count and execution time of common architectural design elements, we identify key factors for efficient execution and provide insights to optimize backbone design. Based on these insights, we present LowFormer, a novel vision backbone family. LowFormer features a streamlined macro and micro design that includes Lowtention, a lightweight alternative to Multi-Head Self-Attention. Lowtention not only proves more efficient, but also enables superior results on ImageNet. Additionally, we present an edge GPU version of LowFormer, that can further improve upon its baseline's speed on edge GPU and desktop GPU. We demonstrate LowFormer's wide applicability by evaluating it on smaller image classification datasets, as well as adapting it to several downstream tasks, such as object detection, semantic segmentation, image retrieval, and visual object tracking. LowFormer models consistently achieve remarkable speed-ups across various hardware platforms compared to recent state-of-the-art backbones. Code and models are available at https://github.com/altair199797/LowFormer/blob/main/Beyond_MACs.md.

Entanglement as Memory: Mechanistic Interpretability of Quantum Language Models

Quantum language models have shown competitive performance on sequential tasks, yet whether trained quantum circuits exploit genuinely quantum resources -- or merely embed classical computation in quantum hardware -- remains unknown. Prior work has evaluated these models through endpoint metrics alone, without examining the memory strategies they actually learn internally. We introduce the first mechanistic interpretability study of quantum language models, combining causal gate ablation, entanglement tracking, and density-matrix interchange interventions on a controlled long-range dependency task. We find that single-qubit models are exactly classically simulable and converge to the same geometric strategy as matched classical baselines, while two-qubit models with entangling gates learn a representationally distinct strategy that encodes context in inter-qubit entanglement -- confirmed by three independent causal tests (p < 0.0001, d = 0.89). On real quantum hardware, only the classical geometric strategy survives device noise; the entanglement strategy degrades to chance. These findings open mechanistic interpretability as a tool for the science of quantum language models and reveal a noise-expressivity tradeoff governing which learned strategies survive deployment.

Maintaining Difficulty: A Margin Scheduler for Triplet Loss in Siamese Networks Training

The Triplet Margin Ranking Loss is one of the most widely used loss functions in Siamese Networks for solving Distance Metric Learning (DML) problems. This loss function depends on a margin parameter μ, which defines the minimum distance that should separate positive and negative pairs during training. In this work, we show that, during training, the effective margin of many triplets often exceeds the predefined value of μ, provided that a sufficient number of triplets violating this margin is observed. This behavior indicates that fixing the margin throughout training may limit the learning process. Based on this observation, we propose a margin scheduler that adjusts the value of μ according to the proportion of easy triplets observed at each epoch, with the goal of maintaining training difficulty over time. We show that the proposed strategy leads to improved performance when compared to both a constant margin and a monotonically increasing margin scheme. Experimental results on four different datasets show consistent gains in verification performance.

HINT: Composed Image Retrieval with Dual-path Compositional Contextualized Network

Composed Image Retrieval (CIR) is a challenging image retrieval paradigm. It aims to retrieve target images from large-scale image databases that are consistent with the modification semantics, based on a multimodal query composed of a reference image and modification text. Although existing methods have made significant progress in cross-modal alignment and feature fusion, a key flaw remains: the neglect of contextual information in discriminating matching samples. However, addressing this limitation is not an easy task due to two challenges: 1) implicit dependencies and 2) the lack of a differential amplification mechanism. To address these challenges, we propose a dual-patH composItional coNtextualized neTwork (HINT), which can perform contextualized encoding and amplify the similarity differences between matching and non-matching samples, thus improving the upper performance of CIR models in complex scenarios. Our HINT model achieves optimal performance on all metrics across two CIR benchmark datasets, demonstrating the superiority of our HINT model. Codes are available at https://github.com/zh-mingyu/HINT.

DiffusionAnything: End-to-End In-context Diffusion Learning for Unified Navigation and Pre-Grasp Motion

Efficiently predicting motion plans directly from vision remains a fundamental challenge in robotics, where planning typically requires explicit goal specification and task-specific design. Recent vision-language-action (VLA) models infer actions directly from visual input but demand massive computational resources, extensive training data, and fail zero-shot in novel scenes. We present a unified image-space diffusion policy handling both meter-scale navigation and centimeter-scale manipulation via multi-scale feature modulation, with only 5 minutes of self-supervised data per task. Three key innovations drive the framework: (1) Multi-scale FiLM conditioning on task mode, depth scale, and spatial attention enables task-appropriate behavior in a single model; (2) trajectory-aligned depth prediction focuses metric 3D reasoning along generated waypoints; (3) self-supervised attention from AnyTraverse enables goal-directed inference without vision-language models and depth sensors. Operating purely from RGB input (2.0 GB memory, 10 Hz), the model achieves robust zero-shot generalization to novel scenes while remaining suitable for onboard deployment.

Line-of-Sight-Constrained Multi-Robot Mapless Navigation via Polygonal Visible Regions

Multi-robot systems rely on underlying connectivity to ensure reliable communication and timely coordination. This paper studies the line-of-sight (LoS) connectivity maintenance problem in multi-robot navigation with unknown obstacles. Prior works typically assume known environment maps to formulate LoS constraints between robots, which hinders their practical deployment. To overcome this limitation, we propose an inherently distributed approach where each robot only constructs an egocentric visible region based on its real-time LiDAR scans, instead of endeavoring to build a global map online. The individual visible regions are shared through distributed communication to establish inter-robot LoS constraints, which are then incorporated into a multi-robot navigation framework to ensure LoS-connectivity. Moreover, we enhance the robustness of connectivity maintenance by proposing a more accurate LoS-distance metric, which further enables flexible topology optimization that eliminates redundant and effort-demanding connections. The proposed framework is evaluated through extensive multi-robot navigation and exploration tasks in both simulation and real-world experiments. Results show that it reliably maintains LoS-connectivity between robots in challenging environments cluttered with obstacles, even under large visible ranges and fragile minimal topologies, where existing methods consistently fail. Ablation studies also reveal that topology optimization boosts navigation efficiency by around $20\%$, demonstrating the framework's potential for efficient navigation under connectivity constraints.

TaxaAdapter: Vision Taxonomy Models are Key to Fine-grained Image Generation over the Tree of Life

Accurately generating images across the Tree of Life is difficult: there are over 10M distinct species on Earth, many of which differ only by subtle visual traits. Despite the remarkable progress in text-to-image synthesis, existing models often fail to capture the fine-grained visual cues that define species identity, even when their outputs appear photo-realistic. To this end, we propose TaxaAdapter, a simple and lightweight approach that incorporates Vision Taxonomy Models (VTMs) such as BioCLIP to guide fine-grained species generation. Our method injects VTM embeddings into a frozen text-to-image diffusion model, improving species-level fidelity while preserving flexible text control over attributes such as pose, style, and background. Extensive experiments demonstrate that TaxaAdapter consistently improves morphology fidelity and species-identity accuracy over strong baselines, with a cleaner architecture and training recipe. To better evaluate these improvements, we also introduce a multimodal Large Language Model-based metric that summarizes trait-level descriptions from generated and real images, providing a more interpretable measure of morphological consistency. Beyond this, we observe that TaxaAdapter exhibits strong generalization capabilities, enabling species synthesis in challenging regimes such as few-shot species with only a handful of training images and even species unseen during training. Overall, our results highlight that VTMs are a key ingredient for scalable, fine-grained species generation.