版本更新

One-step generative models construct a static generator through iterative training-time transport. Existing transport objectives primarily assess distributional motion, although a neural generator needs to realize the requested sample displacements jointly through shared parameter updates. The training-time construction raises the question: \emph{once training becomes the iterative process that constructs the final one-step map, what to optimize: the next distributional move, or the route by which the finite generator learns the final map?} To address the question, we introduce \textbf{T}raining \textbf{D}ynamics \textbf{A}ction (\textbf{TDAction}), which selects transport targets according to local shared-parameter realization cost while retaining a prescribed level of distributional progress. We formulate the cost as a soft-terminal control problem and derive a closed-form Batch Tangent Action-to-Go value that accounts for parameter effort and terminal mismatch. The criterion captures cross-sample interactions omitted by independent pairwise costs; under isotropic mobility, the criterion agrees with quadratic Euclidean assignment for deterministic balanced couplings. Randomized tangent probes provide a low-rank implementation that constructs shared detached targets without adding an inference-time trajectory. Controlled studies examine the relationship between generator geometry, transport selection, and realized local action. On ImageNet $256\times256$, TDAction attains an FID below $1.1$ without distillation.

In-sensor processing (ISP) is used in various fields, including autonomous driving automotive systems, wearable healthcare devices, environmental monitoring, wireless sensor networks, smart cities, and industrial control systems. One of the main features of most of these applications is energy and hardware restriction. This restriction amplifies the importance of using high-performance and low-energy consumption computing systems and methods. This paper proposes efficient spintronic stochastic computing modules for in-sensor computing systems to address this challenge. The proposed design utilized the stochastic behavior of the magnetic tunnel junction in the subcritical switching regime to generate a probability-adjustable random stream. Probability-adjustable random stream generation is the most important step in any stochastic system because it determines the quality of the final output. The simulation results indicate that the proposed design offers almost the same peak signal-to-noise ratio and structural similarity while occupying at least 62\% lower area and consuming 60\% lower energy. These advantages made the proposed design a good choice for ISP applications with limited energy.

Weeds compete with crops for light, water, and nutrients, reducing yield and crop quality. Efficient weed detection is essential for site-specific weed management (SSWM). Although deep learning models have been deployed on UAV-based edge systems, a systematic understanding of how different model architectures perform under real-world resource constraints is still lacking. To address this gap, this study proposes a deployment-oriented framework for real-time UAV-based weed detection on resource-constrained edge platforms. The framework integrates UAV data acquisition, model development, and on-device inference, with a focus on balancing detection accuracy and computational efficiency. A diverse set of state-of-the-art object detection models is evaluated, including convolution-based YOLO models (v8-v12) and transformer-based RT-DETR models (v1-v2). Experiments on three edge devices (Jetson Orin Nano, Jetson AGX Xavier, and Jetson AGX Orin) demonstrate clear trade-offs between accuracy and inference latency across models and hardware configurations. Results show that high-capacity models achieve up to 86.9% mAP50 but suffer from high latency, limiting real-time deployment. In contrast, lightweight models achieve 66%-71% mAP50 with significantly lower latency, enabling real-time performance. Among all models, RT-DETRv2-R50-M achieves competitive accuracy (79% mAP50) with improved efficiency, while YOLOv10n provides the fastest inference speed. YOLOv11s and RT-DETRv2-R50-M offer the best balance between accuracy and speed, making them strong candidates for real-time UAV deployment.

Recent work on hallucination detection in large language models has shown that, for a fixed pre-trained model and reasoning task, it is possible to estimate the model's confidence in the correctness of its outputs. Such uncertainty estimates have primarily been used to improve truthfulness by detecting or filtering confabulations. In this work, we ask whether these signals can instead be used more proactively to directly improve the accuracy of model-generated answers. We propose USteer, a simple, training-free steering mechanism that adjusts a model's layer-wise activations during inference using the gradient of a confidence measure with respect to the activations. This procedure nudges generation toward outputs with lower uncertainty at inference time, without modifying model parameters or requiring additional supervision. We show that this approach consistently reduces hallucination across a range of reasoning tasks, demonstrating that confidence signals can be leveraged not only for detection, but also for effective inference-time control of model behavior.

Learning to generalise from limited data is a fundamental challenge for both artificial and biological systems. A common strategy is to extract reusable structure from abundant unlabelled data, enabling efficient adaptation to new tasks from limited labelled data. This two-stage paradigm is now standard in modern training pipelines, where pretraining is followed by fine-tuning or linear probing. We provide an analytical model of this process: structure extraction is formalized as principal component analysis on unlabelled data, and downstream learning as linear regression on a separate labelled dataset. In the high-dimensional regime, we derive exact expressions for training and generalisation error showcasing their dependence on representation dimensionality, unlabelled and labelled sample sizes, and task alignment. Our results show that pretrained representations strongly influence downstream generalisation, and we characterize the optimal representation size as a function of task parameters: with abundant pretraining data but scarce downstream data, maximally compressed representations are optimal, whereas with limited pretraining data, higher-dimensional representations generalise better. Furthermore, we establish an exact trade-off between pretraining and supervision, quantifying how much unlabelled data is required to replace a single labelled sample. Beyond our idealised model, we observe similar phenomenology in autoencoders and pretrained LLMs. Altogether, we highlight that optimising representation size is critical, giving conditions for when compression during pretraining improves generalisation.

Selecting an energy-efficient model for periodic sensing requires accounting for time between inferences. Hardware-aware model search typically measures inference alone, even when the application cares about energy per release. We present CREST (Cross-platform Runtime Evaluation and Search Tool), an open-source hardware-in-the-loop experimentation system that evaluates model and hardware configurations under a specified release schedule. Researchers can vary the objective, schedule, target and candidate proposer while reusing evaluation and replay. Records preserve comparison conditions and separate valid measurements from deployable candidates. Three case studies demonstrate the system. First, searches and controlled replay on STM32 N657 show how waiting changes model and clock selection. For one architecture, continuous inference favors 800 MHz over 300 MHz at 8.0 versus 17.1 mJ per inference, but additional waiting offsets 97% of this saving in a fitted decomposition. With STOP between releases, 300 MHz uses about 0.3-0.4% less board energy per release at 100 and 500 ms. At a fixed clock, the preferred architecture changes between release periods, which a model with shared waiting parameters cannot produce. Latency predicts continuous energy within a median 1.7% on held-out observations, yet most release-energy error remains in scheduled terms. In paired replay, one of six randomly selected near-latency pairs reverses its continuous-energy order by 5.8 mJ per release. Second, replay on three Arduino targets shows proxy-selected inertial-odometry candidates can fail to fit or use more energy than measured selections, with only 9 of 16 FLOPs-selected candidates fitting the most memory-constrained board. Third, an audio classification study reuses the evaluator with LLM-based candidate proposers, and cross-target replay moves a selected configuration from third to last in energy rank.

Legal information retrieval in Portuguese remains difficult to evaluate systematically because available datasets differ widely in document type, query style, and relevance definition. We present JUÁ, a public benchmark for Brazilian legal retrieval designed to support more reproducible and comparable evaluation across heterogeneous legal collections. More broadly, JUÁ is intended not only as a benchmark, but as a continuous evaluation infrastructure for Brazilian legal IR, combining shared protocols, common ranking metrics, fixed splits when applicable, and a public leaderboard. The benchmark covers jurisprudence retrieval as well as broader legislative, regulatory, and question-driven legal search. We evaluate lexical, dense, and BM25-based reranking pipelines, including a domain-adapted Qwen embedding model fine-tuned on JUÁ-aligned supervision. Results show that the benchmark is sufficiently heterogeneous to distinguish retrieval paradigms and reveal substantial cross-dataset trade-offs. Domain adaptation yields its clearest gains on the supervision-aligned JUÁ-Juris subset, while BM25 remains highly competitive on other collections, especially in settings with strong lexical and institutional phrasing cues. Overall, JUÁ provides a practical evaluation framework for studying legal retrieval across multiple Brazilian legal domains under a common benchmark design.

Large Language Models increasingly suppress biased outputs when demographic identity is stated explicitly, yet may still exhibit implicit biases when identity is conveyed indirectly. Existing benchmarks use name based proxies to detect implicit biases, which carry weak associations with many social demographics and cannot extend to dimensions like age or socioeconomic status. We introduce ImplicitBBQ, a QA benchmark that evaluates implicit bias through characteristic based cues, demographically associated attributes that signal implicitly, across age, gender, region, religion, caste, and socioeconomic status. Evaluating 11 models, we find that implicit bias in ambiguous contexts is over six times higher than explicit bias in open weight models. Notably, this bias is distributed unevenly across demographics: caste emerges as the most severe while gender is the least affected. Safety prompting and chain-of-thought reasoning fail to substantially close this gap; even few-shot prompting, which reduces implicit bias by 79%, leaves caste bias at four times the level of any other dimension. These findings indicate that current alignment and prompting strategies address the surface of bias evaluation while leaving demographically associated stereotypic associations largely unresolved. We publicly release our code and dataset for model providers and researchers to benchmark potential mitigation techniques.

Vision-language models (VLMs) exhibit strong zero-shot generalization but remain vulnerable to adversarial attacks. Existing adversarial fine-tuning methods often use pre-trained model guidance to preserve image--text alignment while improving robustness. Our analysis of visual representation drift reveals complementary limitations of two representative forms of guidance. Matching visual features constrains all directions equally, providing broad coverage without semantic emphasis. Matching prediction distributions prioritizes semantically relevant directions, but remains limited by the candidate texts and prediction probabilities. These limitations can hinder preservation of pre-trained image--text relationships and degrade zero-shot performance. We therefore propose Textual Response-Aware Guidance (TRAG), which constrains visual representation drift using the pre-trained text encoder's responses to local variations in input embeddings. TRAG constructs anchor-level constraints from the response directions and magnitudes around semantic anchors, then aggregates them using pre-trained image--anchor relevance, yielding an image-adaptive constraint. Extensive experiments across architectures and tasks demonstrate state-of-the-art clean and robust performance. Further analysis shows that TRAG helps preserve pre-trained image--text relationships.

Modelling opinion dynamics typically relies on hand-crafted local interaction rules to study emergent macroscopic phenomena such as consensus and polarisation. In contrast, multi-agent reinforcement learning (MARL) enables agents to learn such behaviours directly by optimising simple rewards. To explore the potential of MARL for opinion dynamics, we introduce a GPU-accelerated consensus and truth-finding game that scales to populations of up to 1000 agents, comparable to many real-world social sub-networks. To prevent unrealistic conventions, we extend other-play to general-sum social interactions. We next validate our model on a subset of the Bluesky network by recovering agent importance structures from graph topology alone via a learned attention layer, finding that highly conforming populations most closely match human data. In large social media networks, such high levels of conformity significantly reduce collective accuracy and promote dishonest agents that lie to fit in. By contrast, small hunter-gatherer networks are less affected; here, conformity can even improve collective agreement. This suggests a mismatch between evolved human conformity heuristics and modern social media environments as a potential contributor to misinformation.

In finance, the answer that matters is usually the current one: prices, rates, and disclosures hold only as of a given day, so retrieving up-to-date facts is a core capability of a financial agent. Yet most financial benchmarks overlook timeliness. They fix each answer at annotation time, so the gold goes stale as markets move and, once leaked into training data, rewards recall rather than search and analysis. We introduce LiveSearch, a live benchmark that stores each question as executable verifier code: a typed program of calls to a professional financial data service, followed by a declarative extractor. The question is frozen, while its gold answer is determined by executing the program against professional financial data at evaluation time, and a daily job re-executes it with no human or language model in the loop. A memorized answer is thus likely outdated, and a model must reach the current one through tools and analysis. Construction is equally automatic: a language model only verbalizes programs enumerated from real tool responses and never chooses an answer. Under general web search, six contemporary tool-calling models reach 70.9% to 76.7% answer accuracy. Over three consecutive days, 70% of served questions change their gold value, and even under tolerance-aware matching, a literally reused earlier snapshot fails on a majority of questions within a single day. Per-question tracking uncovers dynamic shifts in correctness masked by aggregate accuracy.

The Deep Tensor Network is a family of sequence operators built from contractions of queries, keys, and values. Tensor Attention mixes tokens through the Gram operators $Q(K^\top K)Q^\top$ and $K(Q^\top Q)K^\top$; Tensor Interaction mixes channels through operators derived from $C=Q^\top K$. Associativity lets us evaluate these products exactly without forming $n\times n$ token matrices. For query/key width $d$ and value width $d_v$, the Gram constructions use $O(d^2+dd_v)$ work and summary state per causal token, or $O(d^2)$ when $d_v=O(d)$. We derive prefix recurrences and distinguish trace, diagonal, and row normalization, including the conditions under which the weights are nonnegative and row-stochastic. The unmasked token operators are positive semidefinite with rank at most $d$, but their entries can be negative. We also give exact evaluations and costs for Hadamard and matrix-exponential variants.