Computer Science (arXiv)

We formulate an approximate Cauchy-Schwarz inequality and show that it is satisfied by solutions to the Sherali-Adams linear programming hierarchy (interpreted as ``pseudo-distributions''). As a consequence, we resolve a question left open by the work of O'Donnell and Schramm [OS19] that they had explicitly attributed to the lack of such an inequality. A Cauchy-Schwarz inequality is exactly satisfied by pseudo-distributions satisfying the constraints of the sum-of-squares semidefinite programming hierarchy and already has scores of applications. However, the proof there requires global positive semidefiniteness. Our approximate version, on the other hand, relies only on local positive semidefiniteness satisfied by the Sherali-Adams pseudo-distributions. Our formulation loses an additive error that scales with the L1 norm of the coefficients of the constituent polynomials, and this loss is asymptotically tight. Our proof is elementary and relies on a simple sampling argument. As an application, we resolve a question left open in the work of O'Donnell and Schramm that gives a trade-off between constraint density and the Sherali-Adams degree for refuting random constraint satisfaction problems. Specifically, for odd arity CSPs, we show that the constraint density requirement for a given degree can be improved by a polynomial factor in $n$. Along the way, we observe that by a simple extension, the results in their work extend to a more general semirandom setting.

Reading fiction or encountering narrative generally does not merely add information. The encounter changes the reader. This paper proposes that encounters alter persistent relations among simultaneously active meanings, producing individual and shared histories that population-trained language models do not necessarily retain. A model may be told of an encounter and reproduce its consequences while the history remains in context; this is not the same as being changed by the encounter. This paper formalizes this missing relational state as phase, sets out testable predictions about encounter order, quotation, and suppressed meanings, and argues that future AI agents will need persistent semantic states indexed to particular individuals and relationships. The matching risk is semantic poisoning: an attack that re-signs relations among meanings already present.

Sampling from a diffusion model typically requires many forward passes through a large neural network, making generation computationally expensive. While much work has focused on efficient solvers and samplers, comparatively little attention has been paid to selecting the sampling timesteps themselves. A recent line of work optimizes theoretically derived surrogates for sample quality rather than the quality metric itself. We propose Optimizing Your Sampling (OYS), which instead treats timestep selection as a black-box optimization problem, optimizing the target metric directly with Bayesian optimization. OYS outperforms both the default schedules and those of Align Your Steps on text-to-image generation, and improves over the default schedules on inpainting and other image tasks, in both quantitative and human evaluations. OYS requires no additional training, is applicable even to distilled models, and improves both simple and sophisticated samplers such as Euler and DPM-Solver++. A 5-step OYS schedule retains 89%-94% of the quality of a 50-step schedule while reducing inference cost by 10x.

MongoDB maintains client libraries in a dozen programming languages, used by tens of thousands of organizations and millions of developers. Most are implemented natively rather than as wrappers around a shared core. Ensuring consistent behavior across these libraries, comprising millions of lines of code, is hard but essential. Over eleven years, we developed a specification-based testing approach: tests are written once in YAML and executed by language-specific interpreters for each library. We describe the evolution from many ad-hoc formats to a Unified Test Format, which allowed us to delete over 22,000 lines of test code. The rate of nonconformance bugs fell up to 86% in drivers that adopted YAML tests (though results varied). We report lessons learned about declarative test design, test architecture, schema evolution, and the limits of unification.

MRI reconstruction methods for undersampled k-space data naturally utilize complex-valued measurements. Parallel developments in sparse phase retrieval have shown that magnitude-only measurements may provide complementary information for signal recovery. However, their use in MRI reconstruction remains largely unexplored, due to lack of practical settings where informative magnitude measurements can be obtained without additional scan time. In this work, we investigate the use of auxiliary k-space magnitude information for accelerated steady-state dynamic MRI reconstruction, and demonstrate strong consistency of k-space magnitudes across time-frames. Building on this observation, we propose $\mathbb{C}+\text{Mag}$, a magnitude-informed physics-driven deep learning reconstruction method. The proposed method employs an ADMM-based unrolling framework with a novel magnitude-aware data-fidelity formulation, where quadratically smoothed optimization and momentum-based updates are introduced to address the non-differentiability and non-convexity of the magnitude constraints. Experiments on retrospectively undersampled cine MRI and phase-contrast flow MRI datasets, as well as prospectively undersampled real-time cine MRI acquisitions, demonstrate improved artifact suppression, sharper anatomical recovery, and better preservation of phase information compared to conventional PD-DL methods, which is further supported through blinded expert reader evaluations.

Traffic elements such as traffic lights and road signs play a fundamental role in human driving decisions and should naturally influence end-to-end driving performance. However, existing end-to-end driving research predominantly focuses on dynamic road participants (e.g., vehicles and pedestrians), while the role of traffic elements remains largely unexplored. The community still lacks a systematic study quantifying their impact, largely because public datasets rarely provide structured traffic-element annotations and modern driving systems vary widely in architecture and training paradigm. In this work, we present the first systematic investigation of traffic element awareness for end-to-end autonomous driving. We construct a unified research infrastructure by augmenting multiple public driving datasets with comprehensive traffic-element annotations. To support diverse model families, we adopt a minimal and universal integration design that incorporates traffic-element signals into existing pipelines in a plug-and-play manner with negligible architectural modification. We evaluate this design across modern paradigms, including perception-prediction-planning pipelines, vision-language-action models (VLA), regression-based planners, diffusion-based policies, and trajectory-scoring frameworks, on nuScenes, NAVSIM-v1, NAVSIM-v2, and Bench2Drive. Across all paradigms and datasets, this simple integration consistently improves driving performance, demonstrating that traffic element awareness provides a robust and generalizable signal for end-to-end driving systems. Notably, on the challenging NAVSIM-v2 benchmark, our approach significantly improves state-of-the-art architectures and data pipelines, establishing a new state of the art.

Academic surveys play a central role in organizing rapidly expanding scholarly literature, yet their construction requires extensive paper analysis, coherent knowledge organization, fine-grained citation support, and reliable manuscript assembly. Existing Deep Research and automated survey generation systems address parts of this process, but typically do not coordinate paper understanding, literature organization, evidence-grounded drafting, and manuscript validation through a shared, revisable state. We introduce DAS, a stateful agentic framework for generating publication-oriented academic surveys. Its key idea is to separate reusable paper analysis from topic-specific manuscript construction. DAS builds on DAS-2M, a dynamically updated metadata lake containing survey-oriented representations of approximately two million papers. Its agents maintain explicit literature, organization, writing, and finalization states through candidate-grounded taxonomy planning, reverse paper-to-section routing, and hierarchical claim and citation planning. Semantic review reactivates only the affected writing states for repair and reevaluation, forming a scoped closed loop with deterministic validation. We further introduce DAS-Bench, a 30-topic benchmark, together with DAS-Eval, which assesses scholarly citation quality, taxonomic synthesis, hierarchical discourse, and manuscript assembly reliability through 16 criteria. Among systems evaluated on all 30 topics, DAS achieves the highest average in all four dimensions, with an overall score of 4.34 compared with 4.03 for the strongest competitor, and the same ordering is preserved on the matched 21-topic CS subset. Blinded expert evaluation further prefers DAS to Naive RAG on 27 of 30 topics and to AutoSurvey on 19 of 21 shared CS topics. The project page is available at https://zhikaixu24.github.io/projects/DAS/.

Categorising invoices into the correct General Ledger (GL) code underpins financial reporting and tax compliance. This is a skilled accounting judgement rather than a routine task: the correct category depends subtly on the nature of the purchasing business, the vendor and the invoice text. Whilst AI is increasingly being adopted across industries to automate tasks, including invoice categorisation, implementations built on in-house small language models (SLMs) can simultaneously reduce cost and improve data security, confidentiality, and interpretability. We investigate this approach by first analysing the pre-trained embedding geometry of a small sentence transformer (SBERT) and classic SLM (DeBERTa). The sentence-embedding space of this financial corpus is globally anisotropic but composed of locally isotropic clusters, extending prior token-level findings to sentence embeddings in a financial setting, and these clusters are strongly correlated with the vendor identity. SBERT fine-tuned on a single GPU reaches 0.96 accuracy on invoice classification, above both a zero-shot LLM and a vendor identity baseline, increasing performance for smaller, challenging categories and new clients. For this important generalisation problem, SBERT reaches 0.9 F1 with roughly 100 client-specific invoices, showing that an in-house SLM implementation is promising. Combining these results with geometric analysis shows that pre-trained embedding geometry is associated with classification performance and reveals a counterintuitive finding that a structured input that would help a human reader does not improve the SLM performance.

A popular class of Byzantine fault-tolerant atomic broadcast protocols rely on directed acyclic graphs (DAGs) that represent causal relations between broadcast messages. Each process applies a protocol-specific \emph{commit rule} on its local DAG to determine which vertices can be delivered in a total order. Intuitively, commit rules that impose fewer conditions on the DAG to order its vertices imply more efficient protocols, as the broadcast messages are delivered with lower latency. In this paper, we define commit rules on an uncertified round-based DAG construction, and introduce a sub-rule relation between them: a commit rule $cr_1$ is a sub-rule of a commit rule $cr_2$ if, for any DAG, the set of vertices committed by $cr_1$ contains all vertices committed by $cr_2$. We use the sub-rule relation to determine a minimal commit rule in an eventually synchronous model and a minimal commit rule in an asynchronous model, namely, two commit rules that require the least conditions on the DAG to safely commit any set of vertices in their respective models. To the best of our knowledge, no existing DAG-based atomic broadcast protocol relies on such minimal commit rules: we introduce \emph{Minnow}, a new protocol for DAG-based atomic broadcast, which can be instantiated in both eventually synchronous (S-Minnow) and asynchronous networks (A-Minnow).

Initialization-free bundle adjustment (InitFree BA) aims to recover camera poses and scene structure directly from image observations, avoiding the geometric initialization stages of conventional structure-from-motion pipelines. Recent methods based on Object-Space Error (OSE) formulations and Variable Projection (VarPro) show encouraging optimization behavior from random camera configurations. However, existing evaluations primarily measure optimization success, leaving unclear whether a low OSE objective yields a valid metric 3D reconstruction. We revisit InitFree BA experimentally through a unified evaluation framework combining a C++ implementation of existing OSE formulations with a Blender-based dataset generator providing exact ground truth and controlled camera configurations and observation densities. Our experiments reveal a previously overlooked optimization--reconstruction gap: projective solutions with similarly low OSE values can lead to substantially different Euclidean reconstructions after metric upgrade. We identify initialization priors, landmark observation density, and metric-upgrade stability as key factors governing reconstruction success. Overall, our results suggest that the main challenge of InitFree BA is not merely minimizing OSE objectives, but obtaining projective reconstructions that admit reliable metric upgrade. We believe that the proposed benchmark, implementation, and analysis establish stronger experimental foundations for future research on initialization-free bundle adjustment, a problem largely unexplored within the computer vision community. Project page is available at https://github.com/simonwebertum/InitFreeBA.git.

Humans continuously learn from experience, whereas conventional large language model (LLM) evaluations ignore the models' ability to improve through inference-time interaction. In this paper, we study how LLMs learn from iterative experience at test time, a setting we refer to as Chain-of-Experience (CoE), where models accumulate experiential traces through iterative interactions with self or environmental feedback to form a continual improvement loop beyond zero-shot inference. We instantiate CoE with diverse feedback mechanisms, including model self-feedback and environmental signals such as correctness or public coding test pass rates, and evaluate across math, coding, and knowledge domains using 8 LLMs, including GPT-5, Gemini-2.5 Pro, Claude-4.5 Sonnet. Our study shows that leveraging iterative experience consistently outperforms feedback-free baselines, achieving substantial gains with self feedback alone, alongside a 5.6% overall improvement and 19% lower API cost across tasks and models. We further show that combining complementary feedback channels (e.g., model and correctness signals) yields additional gains, and that CoE delivers higher accuracy per token than existing test-time strategies. We observe a positive correlation between LLM base ability and improvement capacity, and show that models remain robust under weak or spurious feedback, with different feedback contributing to distinct improvement aspects and most gains emerging early in the iterations.

Large-scale, high-dimensional tabular regression remains challenging: tree-based models are robust but lack end-to-end representation learning, while deep models enable flexible feature learning but often incur costly interaction modeling and sensitivity to noisy or redundant features. We propose TabNSM, a scalable regression framework that extends our earlier sparse-attention and mixer architectures. At its core, the Adaptive Sparse Interaction Module (ASIM) integrates foreground feature discovery, sparse local interaction encoding, and Feature-Token Mixing, providing near-linear complexity under fixed sparse configurations. For regression, TabNSM introduces three complementary components: a Multi-Stage Regression Head for progressive prediction refinement; GridLoss, an ordinal-aware soft-binning objective that incorporates target structure into representation learning; and RISE (Reweighted Instance Sampling by Error), a difficulty-aware sampling strategy based on loss-quantile bins. Across nine real-world regression benchmarks, TabNSM delivers strong predictive performance and practical scalability, with particularly consistent gains on high-dimensional and heterogeneous datasets. These results demonstrate that selective interaction modeling, structured regression supervision, and difficulty-aware sampling provide an effective and scalable approach to deep tabular regression.

GPT-style models achieve strong performance by representing language with finite vocabularies of reusable discrete tokens. This success has motivated symbolic music tokenizations to treat recurring musical structures, such as chords, motifs, and phrases, as reusable units analogous to linguistic tokens. However, tokenization derives its advantage not from reusable combinations alone, but from compression: effective compression requires coordinates in which recurring regularities form stable and predictable conditional distributions. The key problem is therefore not to find larger musical combinations, but to discover the coordinate system in which musical facts become predictively compressible. We formulate the Effectiveness--Losslessness Framework and define tokenization as the construction of a predictively effective and relationally lossless coordinate system. The Predictive Effectiveness Principle defines the Fact--Token Boundary: decoupling and denesting construct coordinate interfaces that expose predictive regularities. The Relational Losslessness Principle defines the Token--State Boundary: tokenization stops before context-dependent relations are fixed, leaving their computation to model states. Controlled symbolic-music experiments validate these boundaries. Effective coordinate construction improves predictive compressibility, while fixed relational projections constrain contextual modeling. Sequence compaction alone does not guarantee predictive compression, while preserving contextual freedom allows higher-order musical organization to emerge without explicit structural labels. These results reveal why GPT-style models do not transfer directly across modalities: architectures transfer, but tokenization interfaces do not. Tokenization must discover effective representations while preserving the relational freedom from which contextual structure can emerge.

WEASEL 2.0 is a dictionary-based time series classifier that combines dilated sliding windows with a randomised hyperparameter ensemble and a fixed-size dense feature representation. Two of its hyperparameter choices, the maximum ensemble size and the maximum window size, are specified by simple thresholding rules whose chosen thresholds are not empirically justified in the original paper. In this work we reproduce WEASEL 2.0 on 114 UCR datasets, achieving a mean accuracy of 0.865 and median of 0.928, closely matching the published values (Wilcoxon signed-rank, p = 0.655). We then test the sensitivity of four design choices: the downstream classifier, the absence of feature weighting, the maximum window-size rule, and the maximum ensemble-size rule. The first three are robust to perturbation. The fourth is over-provisioned for long-series datasets, motivating an adaptive rule that sets the maximum ensemble size from series length and number of classes. Evaluated on fixed-length datasets, the adaptive rule reduces peak fit memory by a median of 37 MB (mean 395 MB) and fit time by a median of 0.4 s (mean 4 s), with a median accuracy change of 0% (mean -0.11%). Memory and time savings concentrate on long-series datasets where the original rule allocates the largest ensemble size.

Improving flight safety with flight data requires not only accurate detection of risk events, but more importantly, clear interpretation of their underlying causes at the level of pilot control behavior. Existing explainable AI techniques, such as feature importance maps, often require considerable domain knowledge to translate them into operationally meaningful explanations. Large Language Models (LLMs), which excel at language reasoning, bring a promising solution to this issue. However, applying LLMs in this domain presents key challenges such as modal inconsistency, limited classification ability, scarcity of task-specific data for fine-tuning, and lack of domain knowledge. To overcome these challenges, we propose FlightLLM, a prior-guided semantic LLM-based approach for interpretable flight safety analysis. Specifically, we first perform feature engineering to address modal inconsistency, combining statistical descriptors with physically meaningful flight indicators. This representation is further processed by a Semantic Discretization module, which converts abstract numerical patterns into qualitative descriptions that are more compatible with language reasoning. In addition, since LLMs are not inherently strong classifiers, CatBoost is incorporated as a statistical expert, and its prediction results are injected into the prompt as prior guidance. A contrastive few-shot learning strategy is further adopted to compensate for limited data. Finally, we design structured prompts to embed aviation-specific knowledge into the inference process. Using hard landing, a representative risk event with complex causal mechanisms, as an anchor point, we evaluate FlightLLM on a dataset of 704 real-world A320 flight samples. Experimental results show that the proposed approach achieves competitive classification performance while generating direct and reasonable explanations for event causes.

One of the most common reasons for anterior cruciate ligament (ACL) reconstruction failure is femoral tunnel malpositioning (ACL footprint center and tunnel orientation). Such failures may lead to the development of meniscal pathology and osteoarthritis. Accurate ACL femoral footprint identification is therefore essential for precise tunnel placement, restoration of the native knee joint mechanics, post-surgical knee joint health and prevention of graft failure. Recent advances in artificial intelligence (AI) bring new opportunities to improve image-guided orthopedic surgery. However, at present, existing AI research focuses primarily on ACL segmentation and rupture classification based on pre- and post-operative magnetic resonance (MR) images. Identification of the ACL footprint center using deep learning methods has not been thoroughly researched. Thus, the purpose of this study is to explore 3D deep learning models for ACL femoral footprint identification directly from 3D MR images. Two comprehensive 3D deep learning architectures were developed: a 3D graph convolutional neural network-based geometric model applied to 3D femoral meshes; and a 3D landmark-enhanced identification model based on 3D MR images. A total of 4883 right and 3087 left knee image sets were used from a publicly available database. Eighty percent (80%) were applied to model generation, and twenty percent (20%) were preserved for model testing. Both models achieved excellent performance; however, the image-based method outperformed the model-based method (average error of 2.1mm vs 2.8 mm). Thus, 3D deep learning provides a feasible clinical approach for ACL footprint localization and has the potential to improve ACL reconstruction footprint accuracy.

Reasoning in LLMs is overwhelmingly studied in domains that provide a model with rules: mathematics and code. Linguistic puzzles invert this: the solver must first discover the system before reasoning within it. We present the IOL-AI Challenge, an open-science competition run on the unseen problems of the International Linguistics Olympiad (IOL) 2026 Individual Contest, evaluated both automatically and, for the first time, by members of the official IOL Jury under the same rubrics applied to human contestants. The challenge drew 731 submissions from 46 teams under a strict compute budget (one T4, 30 mins). We additionally benchmark 15 unconstrained frontier and open models, with Claude Opus 4.8 earning a jury score equivalent to a gold medal, while both resource-constrained systems we submitted for jury grading scored in the range of the bottom 5% of contestants. Capability was not determined by scale: 14B submissions outperform models twice their size, and gains come from decoding and output-handling rather than model capacity. We also found that automatic metrics rank systems exactly as the jury does, but compress the scale, upscoring weak systems by ~13 points and understating strong ones. Our analysis shows that while frontier models might have prior knowledge about some of the problem languages, it does not significantly help them solve the linguistic reasoning tasks, leaving linguistic reasoning as a strong benchmarking proxy for generalizable reasoning skills.

Answering questions accurately and efficiently in embodied scenarios presents significant challenges due to limited computational and memory resources for Vision Language Model (VLM) inference. Existing methods adopt visual search key frame retrieval method to select critical question-related key frames for VLM input. However, visual search methods are inefficient because they require visual search among thousands of video frames for each individual user query. In this work, we propose a memory tree guided key frame selection paradigm for efficient 3D question answering in embodied scenarios. Our method leverages a compact and reusable 3D scene representation, termed MemTree3D, which supports real-time online construction leveraging camera 6-DoF poses. MemTree3D captures multi-level 3D scene information, enabling a Large Language Model to efficiently query and retrieve question-relevant key frames through our scoring-based frame selection without reprocessing the entire video stream. On OpenEQA, our method improves the LLM-Match of GPT-4o by 17.4%, LLaVA-OneVision-7B by 5.8%, outperforms existing visual search methods. Our code is available at https://github.com/hsiangwei0903/MemTree3D

Combining large language models with reinforcement learning is increasingly explored, yet the theoretical status of LLM-derived reward signals is often left implicit. We formalize the hybrid LLM-planner and RL-controller architecture as a Goal-Augmented Markov Decision Process and show that when the LLM per-state progress score is used as a bounded potential function, the resulting shaping term preserves the optimal policy set even when the LLM scores are inaccurate. This guarantee is stronger than what general LLM-as-reward approaches provide. We verify the result numerically on a small MDP under four potential configurations, including an adversarial one scaled to twenty times the base reward magnitude.

Pure and full synchronized regular expressions (pure sregex and full sregex ) extend regular expressions by adding labels to the operators (Kleene star and alternation). Operators within the same scope are synchronized if they have the same label. We show that a regular expression with backreferences (known from practical regex engines) can be translated into a full sregex. Previous work did not consider synchronized alternations or nested star synchronization. Within the same scope, stars with the same label match the same number of iterations, alternations with the same label match the same choice. The scope may depend on the current iteration of an outer star. Pure sregexes restrict synchronization to the local scope, while full sregexes also allow synchronization across iterations. In contrast to operational semantics in previous work on backreferences, we present a denotational semantics, where concretizations act similarly to valuations in logic. As with backreferences, we show that matching a word is NP-complete. Pure and full synchronized languages are considered and we show that they are closed under concatenation, union and star. By a pumping lemma, they are not closed under intersection. Relationships to other language models are discussed.

Probabilistic modeling of physical fields benefits from both a data-driven prior and known physical structure such as the governing equations. Energy-based models (EBMs) are a natural fit since energies compose additively, which enables augmenting physics information during inference. However, EBMs have been difficult to train and sample from due to the intractable partition function. We show in this work that flow matching models with a potential-induced velocity yield an explicit scalar energy at all transport times, whose gradient is exactly the converted learned score and which recovers the marginal negative log-density at the population optimum. The time-dependent energy functions are obtained purely from the matching regression objective on an independent linear Gaussian interpolation, without a variational form or additional MCMC steps, and the sampling retains the flow ODE. Access to the energy function from a trained model serves three roles: energy-corrected data generation, energy as a scoring function for out-of-distribution (OOD) detection, and energy compositional posterior sampling for inverse problems. In particular, we show the explicit energy permits general MCMC samplers in the predictor-corrector sampling framework, reducing PDE residual and spectral distance compared to the flow ODE baseline. Furthermore, we demonstrate utilizing the data energy and physics-based energy (e.g., PDE residuals) as complementary mechanisms to improve detection accuracy for OOD tasks. In addition, we explore the connection to MCMC-based inference for inverse problems by composing the energy with a quadratic observational likelihood that yields a posterior energy, used as an explicitly chosen family of inference-time targets.

We study $n$-party fault-tolerant consensus against general (non-threshold) adversaries. We describe an infinite family $Z_\mathsf{proj}^{n,d}$ of $Q^d$-satisfying $n$-party adversary structures based on finite projective geometry which cause error-free $R$-round protocols for interactive consistency on $L$-bit inputs to require $Ω(Ln^{2+1/d})$ bits of expected communication. Likewise, $Z_\mathsf{proj}^{n,d}$ causes error-free byzantine agreement and broadcast to cost $Ω(Ln^{1+1/d})$ bits. In every case, the lower bound is $Ω(L_{\mathsf{out}} \cdot n^{1+1/d})$ bits, where $L_{\mathsf{out}}$ is the output length. The family $Z_\mathsf{proj}^{n,d}$ also causes reliable broadcast and byzantine agreement to cost $Ω(Ln^{1+1/d})$ bits of expected communication in asynchronous networks. Moreover, there exists a related family $Z_\mathsf{2\textsf-proj}^{n,d}$ of $Q^d$-satisfying adversary structures that make core set agreement cost $Ω(Ln^{2+1/d})$ bits. These asynchronous lower bounds hold against send-omission adversaries, even if the protocol uses cryptography. Their basis is that if a quorum of non-faulty parties agree on an output and terminate, then the messages they sent before terminating must suffice for the parties outside the quorum to also terminate with the same output. Surprisingly, if we do not require the parties to terminate (stop sending messages) after they output, then these bounds no longer hold. We show this by designing a non-terminating omission-tolerant reliable broadcast protocol that can for any parameter $δ> 1$ be tuned to cost $(1 + \frac{1}{δ- 1})Ln + O(δn^2\log(δn))$ bits, which is of independent interest. Lastly, we show how to get termination with $O(Ln^{1+1/d} + n^2\log n)$ bits (assuming the $Q^d$ condition), and thus prove our asynchronous lower bounds tight.

Artificial intelligence (AI) is becoming part of the working infrastructure of the biosciences. AI models can predict biomolecular structures, design proteins, rank variants, annotate images, recommend strains and optimise experimental conditions. We argue that the decision to use an AI output to guide laboratory action is a key juncture for trustworthy research and should follow a defined, reviewable process. We propose Traceable Trust as a proportionate assessment-and-design framework for this output-to-action boundary. It asks what evidence supports the output, what capability is being claimed, what agency has been delegated, what threshold authorises action, who can override it and how outcomes inform later decisions. We illustrate the framework through three case studies spanning ecosystem resources, project design and laboratory action. Together, the cases show how trust can be documented where AI outputs begin to shape scientific work.

Diffusion Transformers (DiTs) achieve high-quality generation but are costly due to iterative sampling. Dynamic-resolution sampling reduces early-stage cost by denoising at low resolution; however, uniformly upsampling all latent tokens at resolution transitions incurs redundant computation and may degrade fine-detail consistency. Existing partial upsampling strategies typically rely on local latent structure cues or single-step statistics, making it difficult to jointly capture token-text semantic relevance and token-wise representation dynamics across diffusion steps. We propose AViTS, an adaptive spatiotemporal token selection framework for dynamic-resolution DiTs. AViTS models spatial importance via latent-text attention and temporal importance via token-level feature variation across diffusion timesteps, and fuses them to enable spatiotemporal importance-aware selective upsampling: it prioritizes resolution refinement for critical tokens while deferring less important ones, thereby reducing redundant high-resolution computation and improving the quality-efficiency trade-off. AViTS achieves up to 6.34x on FLUX and nearly 9x FLOPs reduction on Qwen-Image-Edit and FLUX.1-Kontext-dev, orthogonal to distillation, quantization, and feature caching, and reaching 14.76x with distilled models. Code: https://github.com/QHR69/AViTS

Using LLMs as judges has become standard practice for evaluating model outputs at scale. This is particularly common for subjective, open-ended tasks such as assessing helpfulness or alignment, where no single reference answer exists. However, objective tasks introduce a distinct reliability challenge for reference-free LLM judging. In the absence of a reference answer, the judge evaluates factual correctness either through its parametric knowledge or through tool augmentation. Although the former enables efficient evaluation, the judge may hallucinate or lack sufficient evidence for its verdict. Conversely, tool augmentation can provide additional evidence but introduces extra computational cost and requires an appropriate mechanism to determine when and how that evidence should be used reliably. More importantly, neither approach alone provides formal control over the risk of accepted verdicts or guarantees their reliability at a specified level. We propose a risk-controlled framework that calibrates uncertainty thresholds on a held-out set so that the false discovery rate among accepted verdicts remains below a user-specified level~$α$ with high probability, using finite-sample Clopper--Pearson intervals. When the parametric mode is not sufficiently confident, the instance is routed to a retrieval-augmented mode, where the judge gathers web evidence and re-evaluates the instance under a second calibrated threshold. The finite-sample guarantee carries over to this two-threshold routing without additional assumptions. Across open-domain QA benchmarks and judges of varying scales, the framework maintains the target error rate while achieving substantially higher coverage than single-mode baselines.