Anthropomorphisation -- the phenomenon whereby non-human entities are ascribed human-like qualities -- has become increasingly salient with the rise of large language model (LLM)-based conversational agents (CAs). Unlike earlier chatbots, LLM-based CAs routinely generate interactional and linguistic cues, such as first-person self-reference, epistemic and affective expressions that empirical work shows can increase engagement. On the other hand, anthropomorphisation raises ethical concerns, including deception, overreliance, and exploitative relationship framing, while some authors argue that anthropomorphic interaction may support autonomy, well-being, and inclusion. Despite increasing interest in the phenomenon, literature remains fragmented across domains and varies substantially in how it defines, operationalizes, and normatively evaluates anthropomorphisation. This scoping review maps ethically oriented work on anthropomorphising LLM-based CAs across five databases and three preprint repositories. We synthesize (1) conceptual foundations, (2) ethical challenges and opportunities, and (3) methodological approaches. We find convergence on attribution-based definitions but substantial divergence in operationalization, a predominantly risk-forward normative framing, and limited empirical work that links observed interaction effects to actionable governance guidance. We conclude with a research agenda and design/governance recommendations for ethically deploying anthropomorphic cues in LLM-based conversational agents.

The rapid evolution of Multi-modal Large Language Models (MLLMs) has advanced workflow automation; however, existing research mainly targets performance upper bounds in static environments, overlooking robustness for stochastic real-world deployment. We identify three key challenges: dynamic task scheduling, active exploration under uncertainty, and continuous learning from experience. To bridge this gap, we introduce \method{}, a dynamic evaluation environment that simulates a "trainee" agent continuously exploring a novel setting. Unlike traditional benchmarks, \method{} evaluates agents along three dimensions: (1) context-aware scheduling for streaming tasks with varying priorities; (2) prudent information acquisition to reduce hallucination via active exploration; and (3) continuous evolution by distilling generalized strategies from rule-based, dynamically generated tasks. Experiments show that cutting-edge agents have significant deficiencies in dynamic environments, especially in active exploration and continual learning. Our work establishes a framework for assessing agent reliability, shifting evaluation from static tests to realistic, production-oriented scenarios. Our codes are available at https://github.com/KnowledgeXLab/EvoEnv

Infrared gas leak detection is important for industrial safety and environmental monitoring, but automatic detection remains challenging because gas plumes are often faint, small, semi-transparent, and weakly bounded. This paper proposes an Edge-Aware and Content-Adaptive Feature Fusion Detector (ECAF-Det) for weak-plume detection in cluttered thermal scenes. ECAF-Det integrates three task-oriented designs: a plume-oriented local-global feature enhancement block to preserve fine boundary cues and capture long-range contextual continuity; a multi-scale edge perception module that transforms directional gradient and phase-consistency cues into hierarchical edge priors for boundary-sensitive plume representation; and a content-adaptive sparse routing path aggregation network that dynamically regulates multi-scale feature propagation to emphasize informative plume features and suppress redundant background responses. Experiments on the IIG dataset show that ECAF-Det achieves 29.8% AP, 84.3% AP50, and 25.3% small-object AP, improving the RT-DETR-R18 baseline by 3.0, 6.5, and 5.4 percentage points, respectively, with 43.7 GFLOPs and 14.9 M parameters. On the LangGas dataset, ECAF-Det achieves 36.3% AP and 68.5% AP50, demonstrating its generalization to different infrared gas plume appearances. The main AI contribution is edge-aware representation learning with content-adaptive sparse feature routing for weak infrared plume perception. The proposed detector can serve as a visual perception component for early warning and remote inspection in industrial gas leak monitoring.

Mathematicians and computer scientists are increasingly leveraging proof assistants to formalize and check complex proofs, a task that demands substantial expertise. Can we lower the bar by automating the conjecturing of helpful, interesting and novel lemmas? We present the first neuro-symbolic lemma conjecturing tool, LEMMANAID, designed to discover conjectures by drawing analogies between mathematical theories. LEMMANAID uses a fine-tuned LLM to generate lemma templates that describe the shape of a lemma, and symbolic methods to fill in the details. We compare LEMMANAID against the same LLM fine-tuned to generate lemmas directly, as well as a fully symbolic conjecturing method. On test sets from Isabelle's HOL library and Archive of Formal Proofs (AFP), LEMMANAID consistently outperforms both neural and symbolic methods. Using DeepSeek-coder-6.7B as a backend, LEMMANAID discovers 50% (HOL) and 29% (AFP) of the gold standard lemmas, increasing to 55% and 35% when ensembling prompting strategies. In a case study on Octonions, LEMMANAID discovers 79% of the gold standard lemmas, compared to 62% for neural-only and 23% for the state of the art symbolic tool. Furthermore, in a targeted comparison, LEMMANAID discovers more gold standard lemmas than both Claude Opus 4.5 and GPT-5.2. Our results show that LEMMANAID can conjecture a significant number of interesting lemmas across complex formalizations in mathematics and computer science.

Knowledge Base Question Answering (KBQA) challenges models to bridge the gap between natural language and strict knowledge graph schemas by generating executable logical forms. While Large Language Models (LLMs) have advanced this field, current approaches often struggle with a dichotomy of failure: they either generate hallucinated queries without verifying schema existence or exhibit rigid, template-based reasoning that mimics synthesized traces without true comprehension of the environment. To address these limitations, we present \textbf{KBQA-R1}, a framework that shifts the paradigm from text imitation to interaction optimization via Reinforcement Learning. Treating KBQA as a multi-turn decision process, our model learns to navigate the knowledge base using a list of actions, leveraging Group Relative Policy Optimization (GRPO) to refine its strategies based on concrete execution feedback rather than static supervision. Furthermore, we introduce \textbf{Referenced Rejection Sampling (RRS)}, a data synthesis method that resolves cold-start challenges by strictly aligning reasoning traces with ground-truth action sequences. Extensive experiments on WebQSP, GrailQA, and GraphQuestions demonstrate that KBQA-R1 achieves state-of-the-art performance, effectively grounding LLM reasoning in verifiable execution.

Conformal prediction quantifies the uncertainty of machine learning models by augmenting point predictions with valid prediction sets. For complex scenarios involving multiple trials, models, or data sources, conformal prediction sets can be aggregated to create a prediction set that captures the overall uncertainty, often improving precision. However, aggregating multiple prediction sets with individual $1-α$ coverage inevitably weakens the overall guarantee, typically resulting in $1-2α$ worst-case coverage. In this work, we propose a framework for the weighted aggregation of prediction sets, where weights are assigned to each prediction set based on their contribution. Our framework offers flexible control over how the sets are aggregated, achieving tighter coverage bounds that interpolate between the $1-2α$ guarantee of the combined models and the $1-α$ guarantee of an individual model depending on the distribution of weights. Importantly, our framework generalizes to data-dependent weights, as we derive a procedure for weighted aggregation that maintains finite-sample validity even when the weights depend on the data. This extension makes our framework broadly applicable to settings where weights are learned, such as mixture-of-experts (MoE), and we demonstrate through experiments in the MoE setting that our methods achieve adaptive coverage.

One of the most striking features of Large Language Models (LLMs) is their ability to learn in-context. Namely at inference time an LLM is able to learn new patterns without any additional weight update when these patterns are presented in the form of examples in the prompt, even if these patterns were not seen during training. The mechanisms through which this can happen are still largely unknown. In this work, we show that the stacking of a self-attention layer with an MLP allows the transformer block to implicitly modify the weights of the MLP layer according to the context. We argue through theoretical analysis and experimentation that this simple mechanism may help explain why LLMs demonstrate capabilities of in-context learning, beyond what is captured during training. Specifically, we show that a standard forward pass with context is mathematically equivalent to a forward pass without context but with the MLP weights updated by a minimal low-rank update representing the context.

Random matrix theory has played an important role in various areas of pure mathematics, mathematical physics, and machine learning. From a practical perspective of data science, input data are usually normalized prior to processing. Thus, this study investigates the statistical properties of min-max normalized eigenvalues in random matrices. Previously, the effective distribution for such normalized eigenvalues has been proposed. In this study, we apply it to evaluate a scaling law of the cumulative distribution. Furthermore, we derive the residual error that arises during matrix factorization of random matrices. We conducted numerical experiments to verify these theoretical predictions.

Sparse Mixture-of-Experts architectures are essential for scaling model capacity efficiently, yet the standard Top-$k$ routing imposes a rigid sparsity pattern that ignores the intrinsic variance in token difficulty and layer-specific computational needs. Top-$p$ routing is more adaptive because it selects experts until their cumulative routing probability reaches a threshold, allowing confident tokens to use fewer experts and ambiguous tokens to recruit more. However, we demonstrate that existing naive Top-$p$ implementations with fixed global probability thresholds provide only marginal gains over Top-$k$, suffer from hyperparameter sensitivity, and result in uncontrolled computational costs. In this paper, we propose **DTop-$p$**, a sparsity-controllable dynamic routing mechanism that learns the Top-$p$ probability threshold with a Proportional-Integral controller and uses dynamic routing normalization to support layer-wise expert selection under a global sparsity constraint. Extensive experiments on Large Language Models and Diffusion Transformers demonstrate that **DTop-$p$** consistently outperforms both Top-$k$ and fixed Top-$p$ baselines while matching the average FLOPs of Top-$k$ MoE. Our analysis confirms that **DTop-$p$** exhibits strong scaling properties across expert granularity, total expert capacity, model size, and dataset size, offering a robust and efficient MoE framework for foundation model pre-training.

Scaling test-time computation has been shown to significantly improve large language model (LLM) performance without additional training. However, extending these techniques to multi-agent systems remains challenging: existing approaches lack principled mechanisms for allocating compute to enable effective collaboration, scaling coordination itself, or optimizing compute usage under explicit budget constraints. To address this gap, we propose FutureWeaver, a framework for planning and optimizing test-time compute allocation in multi-agent systems under fixed budgets. It introduces collaboration modules, formalized as modular, callable functions that encapsulate reusable multi-agent workflows and are automatically induced via self-play reflection from recurring interaction patterns. Building on these modules, it employs \emph{a dual-level planning architecture} that jointly performs short-horizon action selection and long-horizon abstract lookahead to optimize inference trajectories under budget constraints. Experiments on complex agent benchmarks demonstrate that FutureWeaver consistently outperforms baselines across diverse budget settings, validating its effectiveness for multi-agent collaboration in inference-time optimization.

We introduce the task of Reconstructing Objects along Hand Interaction Timelines (ROHIT). We first define the Hand Interaction Timeline (HIT) from a rigid object's perspective. In a HIT, an object is first static relative to the scene, then is held in hand following contact, where its pose changes. This is usually followed by a firm grip during use, before it is released to be static again w.r.t. to the scene. We model these pose constraints over the HIT, and propose to propagate the object's pose along the HIT enabling superior reconstruction using our proposed Constrained Optimisation and Propagation (COP) framework. Importantly, we focus on timelines with stable grasps - i.e. where the hand is stably holding an object, effectively maintaining constant contact during use. This allows us to efficiently annotate, study, and evaluate object reconstruction in videos without 3D ground truth. We evaluate our proposed task, ROHIT, over two egocentric datasets, HOT3D and in-the-wild EPIC-Kitchens. In HOT3D, we curate 1.2K clips of stable grasps. In EPIC-Kitchens, we annotate 2.4K clips of stable grasps including 390 object instances across 9 categories from videos of daily interactions in 141 environments. Without 3D ground truth, we utilise 2D projection error to assess the reconstruction. Quantitatively, COP improves stable grasp reconstruction by 6.2-11.3% and HIT reconstruction by up to 24.5% with constrained pose propagation.

Despite rapid progress in large-scale language and vision models, AI agents still suffer from a fundamental limitation: they cannot remember. Without reliable memory, agents catastrophically forget past experiences, struggle with long-horizon reasoning, and fail to operate coherently in multimodal or interactive environments. We introduce MemVerse, a model-agnostic, plug-and-play memory framework that bridges fast parametric recall with hierarchical retrieval-based memory, enabling scalable and adaptive multimodal intelligence. MemVerse maintains short-term memory for recent context while transforming raw multimodal experiences into structured long-term memories organized as hierarchical knowledge graphs. This design supports continual consolidation, adaptive forgetting, and bounded memory growth. To handle real-time demands, MemVerse introduces a periodic distillation mechanism that compresses essential knowledge from long-term memory into the parametric model, allowing fast, differentiable recall while preserving interpretability. Extensive experiments demonstrate that MemVerse significantly improves multimodal reasoning and continual learning efficiency, empowering agents to remember, adapt, and reason coherently across extended interactions.

Thinking Large Language Models (LLMs) used as judges for pairwise preferences remain noisy at the single-sample level, and common aggregation rules (majority vote, soft self-consistency, or instruction-based self-aggregation) are inconsistent when ties are allowed. We study inference-time compute (ITC) for evaluators that generate n independent thinking--rating samples per item, and propose a principled, distribution-calibrated aggregation scheme. Our method models three-way preferences with a Bradley-Terry-Davidson formulation on rating counts, leveraging both polarity (margin among non-ties) and decisiveness (non-tie rate) to distinguish narrow margins from strong consensus. Across various evaluation benchmarks, our approach consistently reduces MAE and increases pairwise accuracy versus standard baselines, and when evaluated against human-consensus meta-labels, matches or exceeds individual human raters. These results show that carefully allocating ITC and aggregating with distribution-aware methods turns noisy individual model judgments into reliable ratings for evaluation.

We present the results of cognitive tests on conceptual combinations, performed using specific Large Language Models (LLMs) as test subjects. In the first test, performed with ChatGPT and Gemini, we show that Bell's inequalities are significantly violated, which indicates the presence of a 'non-classical probability model' with probabilities that do not satisfy Kolmogorov's axioms. In the second test, also performed using ChatGPT and Gemini, we identify the presence of 'Bose-Einstein statistics', rather than the intuitively expected 'Maxwell-Boltzmann statistics', in the distribution of the words contained in large-size texts. Interestingly, these findings mirror the results previously obtained in both cognitive tests with human participants and information retrieval tests on large corpora. Taken together, they point to the 'systematic emergence of non-classical quantum-like structures in conceptual-linguistic domains', regardless of whether the cognitive agent is human or artificial. Although LLMs are classified as neural networks for historical reasons, we believe that a more essential form of knowledge organization takes place in the distributive semantic structure of vector spaces built on top of the neural network. It is this meaning-bearing structure that lends itself to a phenomenon of evolutionary convergence between human cognition and language, slowly established through biological evolution, and LLM cognition and language, emerging much more rapidly as a result of self-learning and training. We analyze various aspects and examples that contain evidence supporting the above hypothesis. We also advance a unifying framework that explains the pervasive quantum organization of meaning that we identify.

Creativity is a complex phenomenon. When it comes to representing and assessing creativity, treating it as a single undifferentiated quantity would appear naive and underwhelming. In this work, we learn the \emph{first type-specific creativity reward model}, coined CREward, which spans three creativity ``axes," geometry, material, and texture, to allow us to view creativity through the lens of the image formation pipeline. To build our reward model, we first conduct a human benchmark evaluation to capture human perception of creativity for each type across various creative images. We then analyze the correlation between human judgments and predictions by large vision-language models (LVLMs), confirming that LVLMs exhibit strong alignment with human perception. Building on this observation, we collect LVLM-generated labels to train our CREward model that is applicable to both evaluation and generation of creative images. We explore three applications of CREward: creativity assessment, explainable creativity, and creative sample acquisition for both human design inspiration and guiding creative generation through low-rank adaptation.

Federated learning (FL) has been extensively studied as a privacy-preserving training paradigm. Recently, federated block coordinate descent scheme has become a popular option in training large-scale models, as it allows clients to train only a subset of the model locally instead of the entire model. However, in the era of large language models (LLMs), even a single block can contain a significant number of parameters, posing substantial communication latency, particularly for resource-constrained clients. To address this challenge in federated training/fine-tuning LLMs, we propose ParaBlock, a novel approach that establishes two parallel threads for communication and computation to enhance communication efficiency. We theoretically prove that the proposed ParaBlock achieves the same convergence rate as the standard federated block coordinate descent methods. Empirical evaluations on fine-tuning LLMs on general instruction following and mathematical reasoning confirm that ParaBlock not only maintains strong performance but also significantly improves communication efficiency.

Text-to-Image (T2I) models are capable of generating high-quality artistic creations and visual content. However, existing research and evaluation standards predominantly focus on image realism and shallow text-image alignment, lacking a comprehensive assessment of complex semantic understanding and world knowledge integration in text-to-image generation. To address this challenge, we propose \textbf{WISE}, the first benchmark specifically designed for \textbf{W}orld Knowledge-\textbf{I}nformed \textbf{S}emantic \textbf{E}valuation. WISE moves beyond simple word-pixel mapping by challenging models with 1000 meticulously crafted prompts across 25 subdomains in cultural common sense, spatio-temporal reasoning, and natural science. To overcome the limitations of traditional CLIP metric, we introduce \textbf{WiScore}, a novel quantitative metric for assessing knowledge-image alignment. Through comprehensive testing of 20 models (10 dedicated T2I models and 10 unified multimodal models) using 1,000 structured prompts spanning 25 subdomains, our findings reveal significant limitations in their ability to effectively integrate and apply world knowledge during image generation, highlighting critical pathways for enhancing knowledge incorporation and application in next-generation T2I models. Code and data are available at \href{https://github.com/PKU-YuanGroup/WISE}{PKU-YuanGroup/WISE}.

Although hyperspectral imaging offers unparalleled non-invasive physiological insight, its bulky hardware, slow acquisition, and regulatory burden severely limit its clinical availability. A natural workaround is to reconstruct hyperspectral information from ubiquitous RGB or CASSI measurements. However, existing paradigms, developed for object-centric scenes, rely on reflectance-based feature alignment, assuming that spectral similarity preserves semantic meaning. This assumption breaks down in physiological imaging, where visually similar RGB responses may arise from distinct and entangled physiological states. This mismatch motivates a shift from reflectance alignment to physiology-aware representation learning, grounded in shared light-matter interaction principles -- a shift that introduces fundamental challenges from cross-channel semantic shifts (C1) and irreversible information loss in RGB-based acquisition (C2). We therefore design PHASE, a physiology-aware hyperspectral reconstruction paradigm that fundamentally redefines object-to-human transfer by disentangling cross-channel physiological semantics via Physiological Channel Reinterpretation and restricting reconstruction to physiologically plausible solutions through Physiologically Constrained Alignment. Under two source-to-target transfer protocols, PHASE consistently outperforms state-of-the-art methods by up to +2.20 SSIM and -3.06 in SAM with merely 1.5% labeled supervision.

Multi-token prediction (MTP) is a prominent strategy to significantly speed up generation in large language models (LLMs), especially in byte-level LLMs, which are tokeniser-free but prohibitively slow. However, many existing MTP methods either assume independence between future tokens, sacrificing expressiveness, or generate tokens one at a time within the window, increasing latency. In this work, we investigate the trade-off between expressiveness and latency in MTP within the framework of probabilistic circuits (PCs). Our framework, MTPC, allows one to explore different ways to encode the joint distributions over future tokens by selecting circuit architectures, generalising classical models such as (hierarchical) mixture models, hidden Markov models, and tensor networks. We show the efficacy of MTPC by retrofitting existing byte-level LLMs, such as EvaByte, and byte-fied subword models, such as Llama3.2 3B. Our experiments show that, when combined with speculative decoding, MTPC substantially speeds up generation compared to MTP with independence assumptions, while guaranteeing to retain the performance of the original verifier LLM. We also rigorously study the optimal trade-off between expressiveness and latency when exploring the possible parameterisations of MTPC, such as PC architectures and partial layer sharing between the verifier and draft LLMs.

Large language models (LLMs) sometimes refuse to follow benign instructions, such as declining to argue a political position or adopt a stated persona, and such refusals are commonly read as safety guardrails at work. We ask whether they can instead signal a **capability deficit**: a shortage of the internal representations a model needs to reason from the instructed perspective. To investigate, we introduce **ideological depth**, a property with two components: (i) a model's ability to follow political instructions without *failure* (steerability), and (ii) the **feature richness** of its internal political representations, measured with sparse autoencoders (SAEs). Using two widely used openweight LLMs as candidates, we compare interventions based on prompts and activation-steering, and probe political features with publicly available SAEs. We find large, systematic differences: a model that is more steerable in both ideological directions activates **~7.3x** more distinct political features, while the other model instead responds with increased refusals. Causally ablating a small, targeted set of political features from the former model reproduces the same feature-poor behavior and drives up refusals. Together, these results indicate that refusals on benign prompts can arise from **capability deficits** rather than fixed safety rules, and that ideological depth is a measurable property of LLMs that helps predict when a model will refuse.

The performance of image generation has been significantly improved in recent years. However, the study of image screening is rare, and its performance with Multimodal Large Language Models (MLLMs) is unsatisfactory due to the lack of data and the weak physical plausibility reasoning ability in MLLMs. In this work, we propose a complete solution to address these problems in terms of data and methodology. For data, we collect a comprehensive image screening dataset with over 128k samples, comprising about 640k images. Each sample consists of an original image and four generated images. The dataset evaluates the physical plausibility reasoning ability under four aspects: appearance deformation, physical shadow, placement layout, and extension rationality. Regarding data annotation, we investigate multiple approaches, including purely manual, fully automated, and answer-driven annotations, to acquire high-quality chains of thought (CoT) data in the most cost-effective manner. Methodologically, we introduce a Hard Cases Mining (HCM) strategy with a Dynamic Proportional Accuracy (DPA) reward into the Group Relative Policy Optimization (GRPO) framework, called HCM-GRPO. This enhanced method demonstrates superior physical plausibility reasoning capabilities compared to the original GRPO. Our experimental results reveal that even state-of-the-art closed-source MLLMs, such as GPT5.2 and Gemini3-Pro, exhibit unsatisfactory performance in physical plausibility reasoning. In contrast, by leveraging the HCM-GRPO, we are able to surpass the scores of both large-scale open-source and leading closed-source models with a much smaller model.

Parliamentary speech generation presents specific challenges for large language models beyond standard text generation tasks. Unlike general text generation, parliamentary speeches require not only linguistic quality but also political authenticity and ideological consistency. Current language models lack specialized training for parliamentary contexts, and existing evaluation methods focus on standard NLP metrics rather than political authenticity. To address this, we present ParliaBench, a benchmark for parliamentary speech generation. We constructed a dataset of speeches from UK Parliament to enable systematic model training. We introduce an evaluation framework combining computational metrics with LLM-as-a-judge assessments for measuring generation quality across three dimensions: linguistic quality, semantic coherence, and political authenticity. We propose two novel embedding-based metrics, Political Spectrum Alignment and Party Alignment, to quantify ideological positioning. We fine-tuned five large language models (LLMs), generated 28k speeches, and evaluated them using our framework, comparing baseline and fine-tuned models. Results show that fine-tuning produces statistically significant improvements across the majority of metrics and our novel metrics demonstrate strong discriminative power for political dimensions.

We introduce LOREN, a curvature-aware zeroth-order (ZO) optimization method for fine-tuning large language models (LLMs). Existing ZO methods, which estimate gradients via finite differences using random perturbations, often suffer from high variance and suboptimal search directions. Our approach addresses these challenges by: (i) reformulating the problem of gradient preconditioning as that of adaptively estimating an anisotropic perturbation distribution for gradient estimation, (ii) capturing curvature through a low-rank block diagonal preconditioner using the framework of natural evolution strategies, and (iii) applying a REINFORCE leave-one-out (RLOO) gradient estimator to reduce variance. Experiments on standard LLM benchmarks show that our method outperforms state-of-the-art ZO methods by achieving higher accuracy and faster convergence, while cutting peak memory usage by up to 27.3% compared with MeZO-Adam.

Second-order optimization methods for training neural networks, such as KFAC, exhibit superior convergence by utilizing curvature information of loss landscape. However, it comes at the expense of high computational burden. In this work, we analyze the two components that constitute the layer-wise Fisher information matrix (FIM) used in KFAC: the Kronecker factors related to activations and pre-activation gradients. Based on empirical observations on their eigenspectra, we propose efficient approximations for them, resulting in a computationally efficient optimization method called MAC. To the best of our knowledge, MAC is the first algorithm to apply the Kronecker factorization to the FIM of attention layers used in transformers and explicitly integrate attention scores into the preconditioning. We also study the convergence property of MAC on nonlinear neural networks and provide two conditions under which it converges to global minima. Our extensive evaluations on various network architectures and datasets show that the proposed method outperforms KFAC and other state-of-the-art methods in terms of accuracy, end-to-end training time, and memory usage.

Backpropagation (BP) remains the dominant and most successful method for training parameters of deep neural network models. However, BP relies on two computationally distinct phases, does not provide a satisfactory explanation of biological learning, and can be challenging to apply for training of networks with discontinuities or noisy node dynamics. By comparison, node perturbation (NP), also known as activity-perturbed forward gradients, proposes learning by the injection of noise into network activations, and subsequent measurement of the induced loss change. NP relies on two forward (inference) passes, does not make use of network derivatives, and has been proposed as a model for learning in biological systems. However, standard NP is highly data inefficient and can be unstable due to its unguided noise-based search process. In this work, we develop a modern perspective on NP by relating it to the directional derivative and incorporating input decorrelation. We find that a closer alignment with directional derivatives together with input decorrelation at every layer theoretically and practically enhances performance of NP learning with large improvements in parameter convergence and much higher performance on the test data, approaching that of BP. Furthermore, our novel formulation allows for application to noisy systems in which the noise process itself is inaccessible, which is of particular interest for on-chip learning in neuromorphic systems.

Action chunking is a widely adopted approach in Learning from Demonstration (LfD). By modeling multi-step action chunks rather than single-step actions, action chunking significantly enhances modeling capabilities for human expert policies. However, because action chunking makes a single decision only after a complete action block has been executed, the resulting reduction in decision frequency restricts the utilization of real-time observations, impairing reactivity in dynamic or noisy environments. Existing efforts to address this issue have primarily resorted to trading off reactivity against decision consistency, without achieving both. To address this limitation, we propose a novel algorithm, Temporal Action Selection (TAS), which caches predicted action chunks from multiple timesteps and dynamically selects the optimal action through a lightweight selector network. TAS achieves balanced optimization across both reactivity and decision consistency. Experiments across multiple tasks with diverse base policy architectures show that TAS significantly improves success rates. Furthermore, integrating TAS as a base policy with residual reinforcement learning (RL) improves both training efficiency and the performance ceiling. Experiments in both simulation and physical robots confirm the method's efficacy.

The adoption of agroecological practices in modern agriculture requires robotic systems capable of operating in highly diverse and complex field environments. Developing and evaluating such systems relies heavily on simulation, yet generating realistic and configurable 3D environments representative of agroecological diversity remains a major challenge. This paper presents CropCraft, an open-source procedural world generator built on Blender and Python, designed to produce 3D simulation environments tailored to agricultural robotics. CropCraft generates crop fields from a simple YAML configuration file, supporting a wide range of scenarios including intercropping, vineyards, and weed-infested fields. The tool includes a library of 3D plant models (crops, grasses, and weeds) at multiple growth stages, and uses stochastic placement algorithms to realistically reproduce the spatial variability observed in real fields. Generated worlds are directly importable into the Gazebo simulator and include ground-truth annotations for all placed elements, supporting both perception and navigation algorithm development. To demonstrate the practical utility of CropCraft, we apply it to the task of crop-weed semantic segmentation using deep learning. A dataset of 10,000 synthetic images of maize fields with varying weed densities, growth stages, and lighting conditions was generated and used to train several segmentation architectures. Models trained exclusively on synthetic data achieve a sim-to-real gap of approximately 10% mean Intersection over Union (mIoU) on real field images, outperforming previous state-of-the-art synthetic generation approaches. We further show that combining even a few real images with synthetic data improves generalization across domains, providing new insights into the effective use of synthetic data for agricultural perception tasks.

While several high profile video games have served as testbeds for Deep Reinforcement Learning (DRL), this technique has rarely been employed by the game industry for crafting authentic AI behaviors. Previous research focuses on training super-human agents with large models, which is impractical for game studios with limited resources aiming for human-like agents. This paper proposes a sample-efficient DRL method tailored for training and fine-tuning agents in industrial settings such as the video game industry. Our method improves sample efficiency of value-based DRL by leveraging pre-collected data and increasing network plasticity. We evaluate our method training a goalkeeper agent in EA SPORTS FC 25, one of the best-selling football simulations today. Our agent outperforms the game's built-in AI by 10% in ball saving rate. Ablation studies show that our method trains agents 50% faster compared to standard DRL methods. Finally, qualitative evaluation from domain experts indicates that our approach creates more human-like gameplay compared to hand-crafted agents. As a testament to the impact of the approach, the method has been adopted for use in the most recent release of the series.

Self-supervised pre-training on unlabeled graph data has become a common paradigm for Graph Neural Networks (GNNs). However, an objective gap often remains between pre-training objectives and downstream tasks. To bridge this gap, graph prompting methods adapt frozen pre-trained GNNs to specific downstream tasks through learnable prompts. Despite its effectiveness, most existing graph prompting methods primarily focus on improving model performance and largely overlook fairness concerns. As downstream graph data inherently contains biases in both node attributes and graph structures, pre-trained GNNs may produce representations that differ across demographic subgroups. To address this limitation, we propose Adaptive Dual Prompting (ADPrompt), a fairness-aware graph prompting framework for adapting pre-trained GNNs. ADPrompt incorporates two complementary components: Adaptive Feature Rectification, which learns personalized attribute prompts to suppress sensitive information at the input level, and Adaptive Message Calibration, which introduces layer-wise structure prompts to dynamically regulate information propagation from neighboring nodes. By jointly optimizing these two modules, ADPrompt adapts the pre-trained GNN while mitigating both attribute-level and structural bias. Experiments on four benchmark datasets with multiple pre-training strategies demonstrate that ADPrompt consistently outperforms seven competitive baselines in node classification tasks.

Personalized large language models (LLMs) tailor content to individual preferences using user profiles or histories. However, existing parameter-efficient fine-tuning (PEFT) methods, such as the ``One-PEFT-Per-User'' (OPPU) paradigm, require training a separate adapter for each user, making them computationally expensive and impractical for real-time updates. We introduce Profile-to-PEFT, a scalable framework that employs a hypernetwork, trained end-to-end, to map a user's encoded profile directly to a full set of adapter parameters (e.g., LoRA), eliminating per-user training at deployment. This design enables instant adaptation, generalization to unseen users, and privacy-preserving local deployment. Experimental results demonstrate that our method outperforms both prompt-based personalization and OPPU while using substantially fewer computational resources at deployment. The framework exhibits strong generalization to out-of-distribution users and maintains robustness across varying user activity levels and different embedding backbones. The proposed Profile-to-PEFT framework enables efficient, scalable, and adaptive LLM personalization suitable for large-scale applications.