Building sensors are embedded in physical topology, spatial hierarchy, and operational context, yet existing forecasters often treat them as isolated time series or rely on fixed covariate sets. We present TopoBrick, a training-free framework for zero-shot building IoT (Internet-of-Things) forecasting. TopoBrick uses building knowledge graphs to construct a compact structural skeleton and employs an agentic topology sampler to select target-specific exogenous variables. The selected variables are organized by deployment-time availability, separating past-known sensor states from future-known calendar, schedule, and meteorological exogenous variables. Across three real-world buildings, TopoBrick outperforms strong zero-shot foundation-model baselines and remains competitive with fully trained building-specific models. Ablations show that topology-aware sampling is more reliable than random, ontology-only, or fixed-hop selection, especially for physically coupled HVAC and weather-driven sensing variables.
Large language models (LLMs) achieve promising results on medical question answering benchmarks, yet their use in public health is constrained by hallucinations and the rapid evolution of official guidance. Retrieval-Augmented Generation (RAG) mitigates these risks by grounding responses in an explicitly maintained corpus, but end-to-end performance depends critically on retrieval configuration and on evaluation beyond multiple-choice formats. We extend PubHealthBench, a question answering (QA) benchmark of 7,929 questions derived from UK Government public health guidance, into a retrieval-augmented setting and systematically evaluate retrieval and generation choices. We compare dense, sparse, and hybrid retrieval across multiple embedding models and corpus variants, and show that hybrid retrieval consistently improves recall and ranking quality, with chunk length and topic interacting with ranking performance. Providing retrieved context substantially increases multiple-choice accuracy across a diverse set of LLMs, enabling smaller open-weight models to match or outperform larger models used without retrieval, with gains primarily driven by retrieval quality and careful context selection. To assess realistic free-form answering, we introduce a rubric-based LLM-as-a-judge covering faithfulness, completeness, clarity, and factual consistency, and validate it against dual human annotations. Judge-human agreement is strongest for faithfulness and completeness, while factual consistency and clarity are less reliably reproduced, motivating caution when interpreting those dimensions at scale. Overall, our results highlight retrieval as a primary lever for reliable public health QA and provide practical guidance for building and evaluating RAG systems grounded in official guidance.
A learned world model is usually judged by how faithfully it reconstructs its observations or predicts reward, as though quality were something the model simply has or lacks. But what a task actually needs from a model is narrower: the few predictive coordinates its queries depend on, which we call the closure. We show that how much of that closure a latent comes to represent is set not by the model's capacity or its observations but by the dimensionality of the objective it is trained against, and we measure this directly on a DreamerV3 stack in a controlled environment with known ground-truth closure. An aligned scalar value signal -- the objective at the heart of value equivalence -- installs only a one-dimensional projection of a closure that needs several dimensions: read through a single linear probe, the recoverable structure rises from R^2=0.10 to 0.76 as the scalar is replaced by the full objective. Sweeping the objective's dimensionality from one to four installs exactly that many predictive directions through an auxiliary head, and the same staircase appears -- at attenuated magnitude but the same rank -- through the model's own value head, so the dissociation is dimensional rather than an artifact of head form. Capacity-matched comparisons and in-situ pressure checks rule out the obvious alternatives. The law governs a regime, and we measure its boundary: on a companion closed-loop task whose structure is observable frame by frame, reconstruction installs that structure and the scalar objective suffices -- the objective decides what a latent represents exactly where cheaper training signals cannot already recover it. Value equivalence is thus not all-or-nothing but dimensional: the familiar single-reward objective is its rank-one corner, and a model installs as much of a task's structure as the objective it is asked to predict.
On modular arithmetic, a network's embedding keeps compressing for tens of thousands of steps after it has already generalized. Reading effective rank at the grokking transition overstates the converged value by 3-5x on an MLP, and by 1.3-1.5x on a transformer trained to convergence; on the MLP it also erases which cells compress at all. Compression lags the accuracy transition by an amount on the order of the time-to-grok, at least 10,000 steps, rather than coinciding with it. A one-variable ablation shows what sets the lag size: adding LayerNorm to an otherwise identical transformer moves the fraction of compression done by the grok step from 0.87 to 0.25, and a pre-registered control rules out scale invariance as the mechanism. We package this as an audit that separates onset from compression, flags censoring, excludes boundary cells that never fully generalize, and checks that the reference floor has plateaued, with an adversarial suite that caught a false-confidence bug in our own branch. A secondary, MLP-specific depth law linking norm budget to converged floor fails a generality test on a transformer and flips sign under free weight decay. Code and the toolkit are released.
While personalisation is becoming a defining capability in human-robot interaction (HRI), the existing literature on responsible personalisation remains fragmented, offering isolated accounts of ethical risks without a structured understanding of how they emerge across interaction contexts. This gap is particularly critical in HRI, where robots' embodiment and social presence can amplify and reshape such risks or generate new types of risks. We present a lifecycle-based and context-sensitive framework for personalised HRI, grounded in an embodiment-aware perspective. The framework combines stages of the personalisation process with interaction characteristics (short-term vs. long-term, open-domain vs. closed-domain), enabling systematic analysis of how risks arise and evolve. Building on this, we conduct an integrative analysis of key ethical risks, including autonomy erosion, biased user modelling, manipulation, dehumanisation, and privacy violations, and examine how they manifest across contexts. We translate these insights into actionable design recommendations and outline open research challenges. By structuring both the design space and risk landscape of personalised HRI, this work provides a foundation for more systematic, transparent, and ethically grounded approaches to personalised robot behaviour.
Formal verification offers the strongest guarantee of software correctness, but it does not scale: the proofs demanded by interactive theorem provers such as Coq require enormous expert effort. Large language models (LLMs) promise to generate these proofs automatically, yet existing approaches wire a fixed, human-designed proof strategy into the system and constrain the model to follow it (retrieving premises and predicting tactics one step at a time, or splitting goals by divide-and-conquer), and still prove only a fraction of their target theorems. We show that imposing such a strategy is unnecessary and limiting. Handing the whole lemma to a general LLM code agent (for example, Claude Code), free to choose its own approach, and wrapping it in a verification harness is both simpler and more effective, achieving full coverage: every targeted lemma proved, with no failures and no Coq expert intervention. The agent writes the proofs under feedback and hard constraints from the harness that keep each one sound (accepted only when the prover's kernel closes it), complete (no obligation left unproved or silently dropped), and terminating (no divergent tactics). We evaluate this harness plus code agent along three dimensions. (1) Core logic: on Iris, the state-of-the-art separation logic for concurrent and memory-manipulating programs, Aria proves all 4,257 lemmas of the four core modules and the 217 lemmas verifying Rust's standard libraries built on it, fully automatically. (2) Comparison with prior LLM provers: on reglang, where prior provers manage barely one in eight, Aria proves all 318. (3) Generality: on iris-lean, the unfinished Lean 4 port of Iris, it proves 72 not-yet-ported lemmas, showing the approach is not specific to Coq. A state-of-the-art model (Claude Opus 4.7) can write proofs for verified software development fully and automatically.
Robotic tree-fruit harvesting is a flagship problem for agricultural automation, but progress is bottlenecked by the cost and irreproducibility of field experiments: an orchard is available only weeks a year, every tree is different, and a control error can permanently damage the crop or the plant. The tree models used in graphics and agronomy are geometrically detailed but physically inert, while the GPU-parallel simulators used in robot learning contain no plausible trees. We present OrchardBench, a physically-grounded, GPU-parallel simulation of apple-orchard trees on the Newton engine. Each tree is grown by a stochastic L-system and instantiated as a fully articulated body: branches are compliant torsional spring-dampers whose stiffness follows Euler-Bernoulli beam theory, they break at a wood modulus of rupture and fall as free hinges, and apples are independent bodies on stem tethers that detach at literature-grounded pull forces and load the branch when pulled. A moving, density-controllable foliage layer occludes the canopy as real leaves do. Every physical parameter is tied to a published source. Per-environment domain randomization makes each batched world a distinct tree, and a mobile manipulator with a wrist depth camera closes the loop with geometric fruit perception and an autonomous harvesting baseline. Careful engineering of the solver and the model lets OrchardBench run many parallel environments at interactive rates on a laptop GPU. We define the tasks and a metric suite spanning harvest completeness, throughput, and plant damage (with a per-canopy-zone breakdown), and report baseline results across foliage, fruit load, terrain, canopy zone, and parallelism. The analytic baseline succeeds on about 40% of the fruit it detects and harvests only about an eighth of the reachable fruit on a tree, leaving clear headroom for novel autonomy approaches.
Diffusion models generate high-quality images, but their inference cost comes from two sources: large denoising networks and repeated denoising steps. Existing compression pipelines usually attack these costs separately. Pruning reduces the network, but most pruning methods still rely on a long post-pruning retraining stage to recover a many-step sampler. Step distillation reduces the number of denoising steps, but it usually assumes a student that can already follow the teacher well enough to receive useful distillation gradients. This paper asks whether post-pruning retraining can be replaced by step distillation. We find that the direct replacement fails: after pruning an EDM2-XS teacher, starting SiDA from the pruned checkpoint produces unusable samples. We introduce a short teacher-alignment repair stage as a bridge between pruning and step distillation. The bridge matches the pruned generator to the teacher on noisy real-image latents, then hands the repaired checkpoint to one-step distillation. On ImageNet-512, the original EDM2-XS baseline uses 124.713M parameters and 63 network evaluations, reaching an FID of 3.53. With a suitable distillation objective, our 20% pruned one-step generator uses 98.826M parameters and one network evaluation, reaching an FID of 3.12. With 30% pruning, the model uses 88.029M parameters and one network evaluation, with an FID of 4.26.
The increasing adoption of end-to-end learning for autonomous driving introduces increased model complexity and opacity, raising the risk of learning undesired or erroneous behavior. In this work, we integrate unsupervised dictionary learning as a post hoc interpretability module within state-of-the-art driving models to decompose driving behavior into semantically meaningful concepts while demonstrating their causal influence on the model's driving decisions. We propose a stepwise framework for extracting and interpreting meaningful concepts from the end-to-end model and connecting them to the multifaceted model outputs, thereby revealing the underlying decision-making logic for the prediction of future trajectories. Furthermore, targeted interventions at the concept level allow us to manipulate and correct driving decisions, resulting in measurable improvements in overall driving performance. We thus demonstrate how interpretability can effectively be used to reduce model opacity, uncover erroneous behavior, and enable targeted mitigation, ultimately boosting model performance.
Uncertainty estimation (UE) enables LLM-powered systems to recognize when to abstain, yet existing research has predominantly focused on English. We present the first large-scale evaluation of UE methods across 22 languages, spanning high-, mid-, and low-resource settings. Using two human-curated Q\&A datasets, we compare open and closed box UE methods (nine in total) across different model sizes and architectures while eliciting long-form reasoning, avoiding LLM-as-a-judge and embedding-based scoring, which can introduce evaluation noise. We report three main actionable findings. First, we find that prompting models to reason in English while keeping questions in low-resource languages substantially improves UE performance, suggesting that comprehension of low-resource languages is largely intact, and that the reliability bottleneck lies in generation rather than understanding. Second, prompting models to reason in English closes the UE performance gap between low and high-resource languages, demonstrating that generation language matters more than the question language. Third, the choice of UE method should depend on model scale: at smaller scales, open-box probability-based methods outperform alternatives; at larger scales, closed-box self-verbalized uncertainty becomes superior. Finally, we provide an analysis of threshold selection for selective prediction, offering guidance on calibrating abstention in multilingual settings.
Large language models deployed in open-world applications require safety guardrails that are both robust to complex risks and efficient enough for low-latency runtime moderation. Existing guardrails face a practical trade-off between lightweight classification-based models, which are efficient but often struggle with concealed intent, ambiguous semantics, and borderline safety decisions, and reasoning-based guards, which improve judgment quality but introduce additional token generation and inference latency. We present DT-Guard, a content safety guardrail model based on a Reasoning-Active Training, Reasoning-Free Inference paradigm. The key idea is to use reasoning supervision during training while emitting only structured safety labels at inference time. DT-Guard formulates safety judgment as a progressive decision process, Intent - Category - Safety, and constructs an intent-driven dataset with intent labels, risk categories, safety labels, and structured reasoning trajectories. To further improve hard-case robustness, we propose Rollout-Guided Progressive Hard-Case Optimization (RG-PHO), which uses multi-rollout consistency to identify stably mastered, persistently failed, and preference-unstable samples, and applies targeted supervised and preference optimization accordingly. At inference time, DT-Guard directly generates structured labels without explicit reasoning traces, preserving deployment efficiency. Experiments on prompt-side and response-side safety benchmarks show that DT-Guard achieves average F1 scores of 0.886 and 0.870, respectively. With only a 4B backbone, it reaches a dual-side average F1 of 0.878, outperforming strong 8B guardrail baselines. These results demonstrate that reasoning supervision can be effectively internalized into low-latency safety discrimination.
Motion understanding is critical for ensuring safety and robustness in autonomous driving systems, driving increasing interest in motion prediction. A key challenge in this domain is the high cost associated with acquiring real-world motion labels. It is therefore ideal if we could transfer motion knowledge from synthetic data to real data. In this context, we explore the potential of synthetic-to-real translation for motion prediction (SRMP). However, the most used naive motion regression methods are notably sensitive to the synthetic-to-real domain shift, resulting in unreliable knowledge translation. To address this, we propose a novel approach integrating a motion knowledge translation framework with two key components: (1) objectness-aware motion prediction, which explicitly models the joint distribution of motion patterns and objectness priors to improve domain-invariant feature learning, and (2) objectness-aided motion enhancement, a motion label refinement mechanism that leverages learned objectness priors to filter motion noise. Furthermore, we present a physically-based pipeline for generating Motion4D, the first synthetic 4D LiDAR dataset tailored for SRMP research, addressing the lack of synthetic motion datasets. Experimental results demonstrate that our approach effectively bridges the domain gaps and yields superior performance on real scenes.