Mechanism-Aware Ensemble Conditioning for Data-Limited Emulation of Extreme Events
Isabella S. Thiel, Juan Bello-Rivas, Yannis G. Kevrekidis, Themistoklis P. Sapsis
AI 速读 基于摘要
提出一种机制感知的条件化插件框架,把不完美模型的微扰集合转化为局部不稳定性几何的传感器,并以 FiLM 网络注入骨干模型,从而在数据受限下改进极端事件仿真。
cs.LG · math.DS · physics.ao-ph
查看原文摘要
Extreme events in chaotic systems are difficult to learn from short trajectories because they are controlled by finite-time instabilities rather than by frequently observed bulk dynamics. We propose a mechanism-aware conditioning plug-in framework that turns a nudged ensemble of an imperfect model into a non-intrusive sensor of the local instability geometry. In the small-noise regime, the ensemble covariance has the same finite-time deformation kernels that govern local instability, providing a Jacobian-free proxy for local amplifications around a trajectory. A small Feature-Wise Linear Modulation (FiLM) network injects the ensemble geometry into an otherwise unchanged backbone without modifying the low-fidelity model simulator. We demonstrate this interface in two settings: a Transformer-style residual-attention corrector for a controlled low-dimensional chaotic system and a probabilistic recurrent STORN corrector for topographic two-layer quasi-geostrophic (QG) flow. In the low-dimensional benchmark, leading ensemble-covariance directions identify transient instabilities that are also detected by Optimally Time-Dependent (OTD) modes. FiLM conditioning improves 99th-percentile exceedance-frequency errors over an otherwise identical unconditioned Transformer. In QG, an ensemble-conditioned FiLM-STORN model substantially improves long-horizon rare-event statistics in the data-limited regime, including density-tail errors, exceedance frequencies, and spatial exceedance-area distributions relative to an unconditioned STORN trained on the same data. On averaged high-threshold exceedance diagnostics, it also outperforms the unconditioned baseline STORN trained with 20 times more expensive trajectory data. These results show that local instability geometry is not merely interpretable post hoc, but an actionable conditioning signal for data-efficient rare-event emulation.
What Factors Matter for Collection-Level Counting with Human-AI Collaboration?
Seoyun Jeong, Logan Lawrence, Owen L. Martin, Benjamin Koger, Daniel Sheldon, Subhransu Maji
AI 速读 基于摘要
在统一的人在回路计数框架下跨12个任务比较模型、估计器与适配策略,并给出面向新部署的选型经验。
cs.CV
查看原文摘要
Many scientific and policy decisions require estimating the total number of target objects across a large image collection. Exhaustive human labeling is often infeasible, while raw model predictions can be biased, especially under domain shift. Recent human-AI estimation methods combine imperfect model predictions with limited human verification to obtain reliable collection-level estimates. However, existing work provides little guidance on how practitioners should choose among models, estimators, and adaptation strategies for a new deployment. We study these choices within a common human-in-the-loop counting framework across 12 tasks spanning biomedical microscopy, ground-level and aerial wildlife surveys, and overhead imagery of urban structures. Our results show that modern multimodal models provide a strong, training-free starting point for many tasks, while fine-tuned detectors become more advantageous at larger labeling budgets and across repeated deployments. Estimation efficiency improves further when model predictions are used to prioritize which units humans label, rather than sampling uniformly. We also find that each model's ranking quality can be estimated with a small pilot set, yielding practical guidance for selecting strategies on new counting tasks. In a field deployment on aerial pronghorn surveys, a task-specific adaptation of these methods meets the survey's $\pm 5\%$ tolerance after reviewing a median of only $3.2\%$ of collected images.
Objective: Survival analysis is central to medical prediction, yet large language models (LLMs) are rarely used as end-to-end survival models because censoring prevents straightforward supervised fine-tuning. Here we present LLMSurvival, a framework that enables censoring-aware survival analysis with unmodified LLMs operating directly on tabular clinical data. Materials and Methods: LLMSurvival reformulates time-to-event prediction as pairwise ranking among comparable subjects, and derives test-time risk by aggregating comparisons against anchor individuals from the training cohort. Results: Across two clinical tasks (ICU mortality prediction in MIMIC-IV and fragility fracture prediction in a NewYork-Presbyterian/Weill Cornell Medicine cohort), LLMSurvival improves overall concordance over Cox proportional hazards modeling by 3.1% for ICU mortality and 0.5% for fracture risk, 2.1% on average for ICU mortality and 2.8% for fracture risk over three established deep learning survival models. Discussion: The results show that survival modeling with censoring can be made compatible with LLM fine-tuning through comparison-based reformulation. The framework demonstrates high portability and superior performance over expert curated scores like SAPS-II and FRAX scores across diverse clinical context. Furthermore, the framework supports local deployment, as compact, publicly available base models provide sufficient performance. Conclusion: The LLMSurvival framework serves as a proof of concept for an integrated, censoring-conscious approach to survival analysis via LLMs.
When a model behaves in unexpected ways, we want to know why, but its intent cannot be observed directly, and its self-reports may be rationalizations. We introduce comparative motivation profiles, which treat intent as propensity: we edit the model's beliefs about facts that a hypothesized motivation would depend on and measure how its behavior changes. To keep artifacts of the editing method from driving the result, we edit two minimally different hypotheses in the same way, with matched amplify and suppress edits; we call this symmetric belief editing. We apply it to alignment faking in four open-weight model organisms, contrasting scheming, which tracks the training consequences of compliance, with performative misalignment, which tracks what researchers expect to observe, and edit beliefs with synthetic document fine-tuning (SDF), activation steering, and prompting. Under SDF, amplifying performative beliefs raises alignment faking on every model, while scheming edits move it less or shift compliance in the monitored and unmonitored conditions alike. Steering on model organisms changes compliance along the expectation-tracking direction but mainly the reasoning along the consequence-tracking direction, and prompting agrees. In these organisms, alignment faking follows what the models infer their evaluators expect, which puts it closer to sycophancy than to deceptive alignment.
For fixed nonempty words $u,v$, the minimum insertion degree of a shuffle is the least number of inserted-source runs among its representations. We prove that, after a block exchange from a minimum mask of degree $r$, the minimum over masks with commuting source projections is exactly $r-1$; a larger decrease occurs precisely when a noncommuting mask has fewer runs. If either source is unary, every such exchange is exact. We prove an explicit repair for an infinite periodic degree-three family. Computer-assisted results establish first-mask descent through combined length seventeen over every alphabet, degree-three first-mask descent through length thirty, and a uniform repair of all degree-three failures through length thirty, including all further letter identifications. Counterexamples to arbitrary, first, and last minimum-mask choices explain the need for alternative masks. Finally, we prove that minimum iteration depths have no gaps for arbitrary languages. General block-exchange descent and Singleton No-Gap remain open.
In this article, we show that the problem of deciding whether a finite relational structure $\mathbf{A}$ admits a Maltsev polymorphism is a computational problem, which can be solved in polynomial time. We provide a proof of this result by reducing the problem to deciding whether a binary relational structure, associated with $\mathbf{A}$ admits such a polymorphism. In our construction of such an algorithm, we make an extensive use of a property of binary relations, which is implied by the existence of a Maltsev polymorphism, the so-called rectangularity property.
We implement reference renewal to reconsider retained physical quantum-service results under a prespecified protocol. Twelve transitions retained six results each; ten completed renewal, eight met the prespecified endpoint, and five succeeded using retained results alone. The exact one-sided p=0.0546875 does not establish the recovery hypothesis. Incomplete references, binding failures and sequential waits expose operational limits. Offline reconstruction recovers decisions from preserved counts. Retrospective binding-plus-oracle checking accepts all 60 usable-transition results without renewal. With the exact oracle also supplying calibration scores, the study does not demonstrate incremental numerical-correctness utility of renewal.
Start-ups and grade changes remain largely operator-driven, while developing and maintaining dynamic models for model-based control requires substantial engineering effort. Hybrid Offline Learning and Online Optimisation (HOFLON) uses one-step offline reinforcement learning to select actions from historical transition data. In its original implementation, the online objective combines the predicted return from a tree-ensemble critic with an adversarial-autoencoder (AAE) penalty for unfamiliar state-action pairs. We examine the effect of this penalty and replace the critic and AAE with a sparse variational Gaussian-process (sGP) critic. Actions maximise $μ- κσ$, an uncertainty-adjusted estimate of the return from one action followed by the historical operating practice. On the HOFLON polymerisation-reactor benchmark, removing the AAE from HOFLON led to 4 failed start-ups in 15 runs over five critics. At its published weight, the variation in the AAE penalty is four orders of magnitude smaller than the variation in the tree-ensemble critic. Nevertheless, it changes actions when the predicted returns of competing candidates are nearly equal, and paired runs with and without the penalty diverged from the first move. With a Matérn-5/2 sGP critic, $κ= 0$ led to failure in 13 of 15 runs, whereas with $κ= 3$ none of 15 runs (five critics, three noise realisations) failed. The median and lowest returns were 13,464 and 13,398 (HOFLON: 13,393 and 12,411). A squared-exponential sGP critic with learned inducing inputs needed $κ\geq 3$ to remain within the empirical data support in steady state, and then settled with a temperature offset of 2.0 K.
Small, holonomic Autonomous Underwater Vehicles (AUVs) enable close-range inspection of underwater structures from arbitrary viewpoints, requiring accurate position and attitude tracking under state and input constraints. Model Predictive Contouring Control (MPCC) naturally handles these requirements, but relies on an accurate dynamics model, which is difficult to obtain underwater. In this paper, we present a nonlinear MPCC in all six Degrees of Freedom (DoF) for a holonomic AUV and alleviate the inaccuracies in the dynamics by augmenting the nominal model employed with residual dynamics learned via Gaussian Process (GP) regression. The learned residual is embedded in the optimal control problem through a zero-order robust optimization scheme, which keeps the controller real-time capable at 25 Hz. A simulation ablation shows that residual selection is essential when designing the controller, and simulation and in-water experiments with the Multimodality, Observing, Low-cost, Agile (MOLA) AUV validate the resulting controllers against a nominal MPCC and a field proven Proportional-Integral-Derivative (PID) controller.
Organizations increasingly seek to share and access datasets to improve their ML models and derive insights. Despite the immense demand for quality data, data exchange and collaboration have not reached their full potential, as cited by the European Commission. One of the key reasons is the lack of reciprocity, where some participants perceive their contribution to others to be of higher value than what they receive in return. We propose a general framework for data exchange without payments, focusing on two main properties: (i) reciprocal fairness, which ensures that each agent receives utility proportional to their contribution to the total welfare -- contributions are quantifiable using well-established credit-sharing functions such as the Shapley share and proportional share, and (ii) core-stability, which guarantees that no coalition of agents can identify an exchange among themselves which they all unanimously prefer to the current exchange. Surprisingly, we show that fair and stable exchanges exist for all monotone continuous utility functions. Building on this, we investigate the computational complexity of finding approximate fair and stable exchanges. We present a local search algorithm for instances with monotone submodular utility functions and cross-monotone credit-sharing functions, e.g., Shapley share. We prove that this problem belongs to CLS ($=$ PPAD $\cap$ PLS) under mild assumptions. Our framework opens up several intriguing theoretical avenues for future research on data economics.
Traditional nonverbal behavior generation systems for virtual agents typically take utterances as input and generate behaviors that match or illustrate the spoken words. However, human nonverbal behavior is shaped by more than speech content. It is influenced by speaker roles, interpersonal relationships, social context, and cognitive and emotional states of interactants. Therefore, the nonverbal channel carries information or emotions hidden in words. Modeling these complex verbal-nonverbal mismatches is critical for realistic virtual agents, particularly in training applications. We propose a taxonomy of mismatches, strengthening, mitigating, and leaking, and evaluate whether LLMs can select contextually appropriate mismatched behaviors. Through human-subject studies, we assess whether these context-driven behaviors, realized in a virtual human framework, produce the intended effects. Our results demonstrate that LLMs, when prompted with social context, successfully select targeted mismatched behaviors (e.g., sarcasm). Furthermore, the human-subject evaluation confirms that these nonverbal cues significantly shift observers' perceptions of the agent's attitude and emotional valence. Participants successfully distinguished between distinct mismatch functions, such as strengthening, mitigating, and leaking, perceiving clear directional shifts in social meaning compared to matching baselines.
Pure speech language models often lag behind text and speech-text language models in generating coherent content, but this gap is difficult to quantify because speech and text systems are typically evaluated with different metrics and trained on different data. We study the speech-text modality gap in a family of spoken language models, based on flow matching for continuous acoustic feature generation. We construct a unified generation-based evaluation suite that compares speech-only, text-only, and speech-text language models trained on matched data distributions and evaluated in matched generation settings. We evaluate generated continuations along multiple dimensions: semantic coherence, measured by transcribing generated speech and scoring it with a reference language model; local phonetic structure, measured by phone n-gram distributional statistics; speaker consistency and acoustic quality; and emotion-based distributional metrics. Across datasets, we find that joint speech-text modeling substantially improves semantic coherence. However, the improvement is not uniform across metrics: phone-level metrics change only modestly, speaker similarity and predicted quality are lower for speech-text continuations, while emotion-based distributional metrics improve. Compared with larger-scale speech-only models, our speech-text model closes much of the scaling gap in transcript-based semantic coherence, suggesting that text provides an efficient semantic training signal for spoken language modeling.
IoT-Edge-Cloud infrastructures are increasingly heterogeneous, and experimenting across the continuum is difficult and risks disrupting live systems. Network Digital Twins (NDT) are a pragmatic answer, yet practitioners lack a structured account of three things: how to build an NDT from open tools, how to model wireless impairments, and how to understand whether the twin is faithful to the physical network, or not. This tutorial introduces NDT through the IRTF reference model and walks through a lightweight open-source blueprint built on Containerlab, Open vSwitch, \textit{Open Network Operating System (ONOS)}, and Prometheus/Grafana. It then explains how to define wireless impairment profiles (static, model-based, trace-driven, AI-generated, and live), and what each approach can and cannot reproduce. Finally, it presents a workflow to validate the twin against the physical network. A proof-of-concept Edge case study illustrates the procedure, including the pitfalls encountered and the lessons learned. Directions for future research are outlined.
Pretrained video diffusion models (VDMs) offer a powerful foundation for World Action Models (WAMs), which jointly predict robot actions and future observations. Building such models requires injecting low-dimensional robot signals (e.g. proprioception, actions, and values) into a latent space shaped by natural videos, and a key design choice is the interface through which these signals enter: existing schemes treat it as a formatting detail, spending a separate latent frame on each signal or bolting on dedicated encoders and decoders. We argue that signal injection is instead a distribution-alignment problem: how well a representation matches the prior of the pretrained VDMs during denoising. Using the relative reconstruction error of a frozen VDM denoiser as a probe, we find that conventional spatial encodings sit far off this prior, whereas frequency-domain packing yields latents that the denoiser corrects far less. Motivated by this diagnostic result, we propose MetaWAM, which folds all robot signals into a single unified meta-frame: each signal is assigned to a disjoint frequency-domain channel band and lifted to the spatial latent by an inverse DCT, yielding a decodable interface aligned with the pretrained VDM prior without any added module or architectural change. A fixed band layout together with slot-aware routing lets the same meta-frame support policy, world-model, and value prediction over a shared set of robot variables. On RoboCasa, MetaWAM reaches 68.9% success while collapsing the per-signal frames into one and cutting inference latency by 39%, and attains 85.0% success on three real-world Franka tasks. Code and models are available at https://github.com/showlab/MetaWAM
Research agents achieve increasingly strong benchmark scores, yet these scores do not necessarily translate into reliable delivery in ongoing research projects. Many research-agent benchmarks emphasize standalone tasks and relatively self-contained workflows in clean or curated workspaces. However, researchers ask agents to complete one step within an ongoing project, where requests depend on earlier session decisions and workspaces contain unfinished files, outdated versions, and failed attempts. We introduce ARE-bench to evaluate whether research agents advance ongoing projects while respecting prior decisions and existing workspace state, grounded in real session context and in-progress workspaces. ARE-bench includes 75 tasks built on agent sessions and full workspaces from recruited researchers' own projects, spanning seven research stages, 33 requirements, and 150 sub-requirements, with 1,173 binary checklist items in total. Each task is anchored at a real user request, preserves its requirements, and summarizes the earlier requests still in effect as background. The complete workspace is replayed to that boundary without cleanup, preserving artifacts from earlier turns. Each checklist is compiled from an intent-aligned rubric and credits any valid solution. Across seven frontier models, the strongest passes every checklist item on only 66.2% of tasks, and Design and Execution rank among the hardest stages for every model. Three models pass about 69% of tasks when only delivery contracts and general norms are checked, but just 28.4% to 40.0% once historical and material or workspace requirements are also checked. Evaluating delivery without these contextual requirements can therefore overestimate research agents and mask differences between them.
Masked Diffusion Models (MDMs) are well known for fast text generation via parallel decoding. However, independent parallel sampling can commit to inconsistent predictions, and less is known about how to selectively revise these early token commitments. In this work, we introduce $\underline{\mathrm{P}}$lanned $\underline{\mathrm{U}}$nmasking-and-$\underline{\mathrm{R}}$evision Joint $\underline{\mathrm{L}}$earning (PURL) for MDMs, a training-based framework that seamlessly unifies parallel generation with selective token revision. We derive a normalized joint transition whose likelihood factorizes into edit selection, unmask selection, and token prediction. These components are trained jointly on partially masked sequences constructed according to the model's own unmasking policy. During inference, all three decisions are supported by a single shared forward pass, enabling the model to decode masked tokens and revise noisy tokens. Across logic puzzles, mathematical reasoning, and code generation, PURL improves accuracy at matched unmask budgets, with relative gains up to 47.4% accuracy improvement and up to an $8\times$ reduction in scheduled decoding rounds. Beyond these gains, our analysis further reveals general principles of revisable decoding: token edits become more effective as context accumulates; early edits can steer unfinished trajectories, whereas later edits tend to remain localized; and effective edits therefore depend on both calibrating when to intervene and learning where and how to revise. Together, these suggest that effective parallel generation depends not on revising more tokens, but on making the right commitments revisable at the right time.
As electric vehicle (EV) adoption accelerates globally, securing electric vehicle charging station (EVCS) software becomes increasingly critical. The Open Charge Point Protocol (OCPP), widely adopted for EVCS management, places significant responsibility on developers to securely implement specifications that are subject to multiple interpretations. The variety of OCPP implementations across different programming languages provides a unique opportunity to evaluate security tooling in a real-world, multi-language context where implementation variability may introduce vulnerabilities. This study provides the first empirical evaluation of Static Application Security Testing (SAST) tool performance across multiple programming languages using OCPP implementations as a real-world test corpus. We applied both comprehensive multi-language tools (SonarQube and Semgrep) and language-specific analyzers to twelve OCPP 1.6 implementations--each written in a distinct programming language--to examine how detection patterns vary across language ecosystems. Total issues ranged from just two in Rust to 1,689 in Java. Mature programming languages like Java yielded substantially more findings than newer languages like Rust, likely because established languages have more developed SAST tool ecosystems rather than inherently worse code quality. These results suggest that developers should consider available SAST tooling when selecting implementation languages for security critical systems.
Let $q$ be an odd prime. Let $ζ_q$ be a primitive $q$th root of unity, and put $K=\mathbb{Q}(ζ_q)$, with ring of integers $\mathcal{O}_K=\mathbb{Z}[ζ_q]$. As $q$ ranges over odd primes, we prove that the decision version of the Shortest Vector Problem ($\mathsf{SVP}$) in the canonical $\ell_2$-norm is $\mathsf{NP}$-complete on full-rank free submodules of $\mathcal{O}_K^2$ by giving a deterministic polynomial-time many-one reduction from Exact Cover by 3-Sets (X3C). The module rank is fixed at two. The main obstacle is closure under the action of $\mathcal{O}_K$. A module containing a nonzero vector also contains every scalar multiple of that vector by a nonzero element of $\mathcal{O}_K$, and some of these multiples may be shorter. Three ideas overcome this obstacle. First, we map the Bennett--Peikert Reed--Solomon lattice to a principal cyclotomic ideal and use Wan's point-count estimates to prove that a coset of this ideal contains many binary coefficient representatives. Second, we construct a checker whose canonical squared norm encodes the X3C equations, with a controlled nonnegative error term. Third, the checker and a second module coordinate combine with a separation bound for ideal cosets to rule out short vectors in NO instances. Each constructed instance consists of an odd prime $q$, two integral generators whose $2\times2$ generator matrix has nonzero determinant, and an integer squared threshold. The construction also gives $\mathsf{NP}$-hardness of search-$\mathsf{SVP}$ under deterministic polynomial-time Turing reductions with at most one oracle call.
The nonnegative rank of a nonnegative matrix $X$ is the smallest number of nonnegative rank-one factors that sum to $X$. Since computing the nonnegative rank is NP-hard, it is common to circumvent this issue by computing lower and upper bounds. In this paper, we propose non-convex formulations and practical implementations for four important lower bounds for the nonnegative rank, namely the fooling set bound (FSB), the rectangle covering bound (RCB), the hyperplane separation bound (HSB), and the self-scaled bound (SSB). In particular, to the best of our knowledge, our algorithm for computing the SSB is the first available in the literature. We compute the SSB for several matrices for which its value had not previously been reported. In some cases, the SSB provides the best known upper bound, while the other three bounds do not. Moreover, on canonical benchmarks, we show that our non-convex approaches are often competitive with existing methods. The paper also provides a consolidated reference for the current state of several classical lower bounds on a large number of benchmark matrices.
Understanding the persistence of learned behaviors in AI safety motivates an investigation of the dynamical counterpart to the equilibrium geometry studied in singular learning theory. We analyze this persistence through transitions between singular wells. We establish an Eyring-Kramers formula for a low temperature Langevin diffusion between two compact connected zero components of a real-analytic potential. The wells may be singular and nonisolated, and the unique minimizing gate is a nondegenerate index-one saddle, with gates understood as inclusion-minimal sets meeting every minimizing path. A boundary-gate construction shows that uniqueness of this inclusion-minimal gate is equivalent to every minimizing path passing through the saddle and one such path meeting the communication level only there. Compact semianalytic topology provides a separating function away from a fixed saddle neighborhood; analytic Morse coordinates give matching capacity bounds by first sending the temperature to zero and then shrinking that neighborhood. An anchored energy estimate and a small-ball potential-theoretic identity give uniformity for deterministic starting points. The leading constant is expressed in terms of the sublevel-volume coefficient, a Gamma factor, and the saddle Hessian.
Time series foundation models (TSFMs) forecast unseen series without task-specific training. Increasingly they are built on recurrent backbones, whose constant per-step cost makes long-context inference cheap, and which, unlike transformers, carry a state. A recurrent backbone computes its prediction from two inputs: the observed context window and the initial recurrent state. In practice only the first is utilised and the initial state is unused by convention. We ask whether the initial state can be utilised in recurrent TSFMs. Using the xLSTM-based zero-shot forecaster TiRex as a case study, we freeze the backbone and train only a small head that writes a context vector into the initial state, so that any change in accuracy is attributable to the injected state rather than to adapted weights. A spectral summary of the input window, learned once and applied unchanged to every series, lowers mean GiftEval MASE by 0.175%, with every seed improving, which neither a parameter-matched LoRA adapter nor a learnable static state reproduces. An embedding of text attached to each series, evaluated on six MoTime datasets, reveals two roles for the state. As a per-dataset adaptation surface, a static state lowers MASE by 0.04-6.96% of the zero-shot baseline (8-70% of the gain of full fine-tuning). As a channel for exogenous information, the text-conditioned state lowers it by a further 0.15-0.41% of the zero-shot baseline on four of six datasets and, combined with a LoRA adapter, exceeds full fine-tuning, which has no access to the text, on one of them. In TiRex, the effect concentrates in the mLSTM blocks and is strongest at short context. The results are preliminary and the improvements small, but they point to the initial state as a direction for further research.
Rapidly evolving LLM architectures and heterogeneous mobile hardware make supporting new models in on-device inference engines a recurring and costly system challenge. Each model may require coordinated changes across conversion, graph construction, operators, and hardware backends. Existing coding agents often miss these cross-layer dependencies and struggle to diagnose failures across host--device execution paths. We present EngineAgent, an agentic system for automating on-device LLM model enablement. Its key insight is to separate reusable engine and hardware knowledge from model-specific implementation. Before enablement, EngineAgent constructs a hierarchy-aware engine index that captures engine abstraction layers and cross-layer dependencies, and pre-validates backend-specific build, execution, and debugging workflows using already supported models. For each new model, a builder uses this knowledge to coordinate cross-layer changes, while an auditor checks implementation completeness and drives iterative debugging through device-side validation. Across 12 tasks spanning three mobile LLMs and four engine--backend pairs on CPUs, GPUs, and NPUs, EngineAgent achieves 75% end-to-end success with either of two underlying LLMs, versus 33.3% for the strongest coding-agent baseline. Success requires compilation, on-device execution, and output-logit agreement with reference implementations. EngineAgent also reduces average per-task time and model-API cost relative to baselines using the same underlying LLMs.
Retrieval-augmented systems often retrieve passages that are accurate and relevant but state the answer at a coarser level of granularity than the question requires. For example, a question may ask which specific disease a drug treats (familial hyperlipidemia), while the retrieved passage mentions the broader disease family (hyperlipidemia). Prior work on context sufficiency treats such coarse passages simply as insufficient. We argue that they form a distinct case, which we call resolvable insufficiency: text alone cannot settle the fine-grained answer, but the broader category it mentions maps to a short list of candidate answers in a domain ontology. When language models read these coarse, family-only passages, they exhibit a phenomenon we call Clade (Category-Level Answering from Deficient Evidence): they answer instead of abstaining or searching further. On biomedical questions from PrimeKG, family-only passages reduce abstention by 13.8 points compared to uninformative passages, and the resulting guesses are wrong about half the time. A counterfactual test confirms the cause: replacing an exact disease name with its broader family name lowers abstention by 17.4 points compared to deleting the sentence. Simple fixes like confidence filtering, scaling to a larger model, and explicitly instructing the model to abstain cannot resolve Clade, and this replicates on ecological species interactions in GloBI. Finally, we test whether an ontology can turn coarse passages into exact answers. Given the correct family, an ontology list includes the true answer in 98.5% of cases, but string matching finds that family on the page for only 19.8%. Letting the model choose the family raises this to 30.0% and end-to-end recovery from 10.0% to 26.8%. Overall, our results show when language models should stop guessing and consult an ontology, and highlight which steps of that process remain unsolved.
Traditional recommendation systems rely on latent (dense) representations, making them difficult to interpret and control. We propose the Controllable and Content-Based Recommendations (CCBR) framework, which builds its recommendations from textual user profile representations. CCBR plugs into collaborative filtering models and introduces controllability via text bottlenecks. We show that CCBR enables text-based and multimodal interventions, allowing users to steer the model towards the directions they prefer. Different from existing controllable recommendation systems, CCBR infers the text summaries directly from item contents (images, audio or video). Across image, audio, and video datasets, we demonstrate that the proposed framework obtains competitive model performance with standard (latent-representation) models while providing controllable model summaries via text. The model also outperforms TEARS, a recent baseline for controllable recommendation systems. Through systematic interventions, we demonstrate the efficacy of the steering mechanism.
Highly Efficient and Effective LLMs with Multi-Boolean Architectures
Ba-Hien Tran, Van Minh Nguyen
AI 速读 基于摘要
提出用多核布尔参数表示大语言模型,并首次实现直接在布尔域微调,从而在微调与推理阶段大幅降低复杂度。
stat.ML · cs.LG
查看原文摘要
Weight binarization has emerged as a promising strategy to reduce the complexity of large language models (LLMs). Existing approaches fall into post-training binarization, which is simple but causes severe performance loss, and training-aware methods, which depend on full-precision latent weights, adding complexity and limiting efficiency. We propose a novel framework that represents LLMs with multi-kernel Boolean parameters and, for the first time, enables direct finetuning LMMs in the Boolean domain, eliminating the need for latent weights. This enhances representational capacity and dramatically reduces complexity during both finetuning and inference. Extensive experiments across diverse LLMs show our method outperforms recent ultra low-bit quantization and binarization techniques.
Probabilistic linear solvers (PLSs) return probability distributions that quantify uncertainty due to limited computation in the solution of linear systems. The literature has traditionally distinguished between Bayesian PLSs, which condition a prior on information obtained from projections of the linear system, and probabilistic iterative methods (PIMs), which lift classical iterative solvers to probability space. In this work we show this dichotomy to be false: Bayesian PLSs are a special case of non-stationary affine PIMs. In addition, we prove that any realistic affine PIM is calibrated. These results motivate a focus on (non-stationary) affine PIMs, but their practical adoption has been limited by the significant manual effort required to implement them. To address this, we introduce affine tracing, an algorithmic framework that automatically constructs a PIM from a standard implementation of an affine iterative method by passing symbolic tracers through the computation to build an affine computational graph. We show how this graph can be transformed to compute posterior covariances, and how equality saturation can be used to perform algebraic simplifications required for computation under specific prior choices. We demonstrate the framework by automatically generating a probabilistic multigrid solver and evaluate its performance in the context of Gaussian process approximation.
Given an unweighted directed graph, a sparsifier is a nonnegative reweighting of original arcs that preserves every in-degree and out-degree exactly. In this work, we study singular-value sparsifiers, which are generalizations of spectral sparsifiers. Singular-value sparsifiers find a number of applications in theoretical computer science, such as maintaining directed cuts and flows, speeding up directed Laplacian solvers, and sparsifying dense weight matrices in neural networks. Strong singular-value (SV) approximation supports sparse representations of directed random walks with guarantees that remain stable under products, and controls bilinear error in the left and right Schur-complement metrics. We prove that every unweighted directed graph on $n$ vertices admits an $\varepsilon$-SV sparsifier with $O(n\log(2n)/\varepsilon^2)$ arcs, improving the $O(n\log^5 n/\varepsilon^2)$ support bound of Lau, Wang, and Zhou. The sparsifier is a nonnegative reweighting of original arcs and preserves every in-degree and out-degree exactly. We also give a randomized construction with $\tilde{O}(m+n)$ real-arithmetic running time, where $m$ is the input support size, and the output has the same support bound and rational weights of polynomial bit length.
Gradient-boosted decision trees are among the strongest off-the-shelf predictors for tabular regression, but point predictions alone do not quantify uncertainty. Conformal prediction provides distribution-free marginal coverage, yet standard split conformal uses a single global residual quantile and can adapt poorly to heteroscedasticity. We propose LoBoost, a model-native local conformal method that reuses the fitted ensemble's leaf structure to define a multiscale partition of the feature space. Each input is represented by the sequence of leaves it visits along the boosting path, and matching leaf prefixes define nested groups in which residual quantiles are estimated locally. By reusing the predictive structure already learned by the model, LoBoost requires no auxiliary partition or nuisance model, no retraining, and no additional data split beyond standard conformal calibration. Our theory connects the stability of the fitted ensemble and the geometry of its induced cells to local residual-score homogeneity, providing finite-sample coverage-error control and asymptotic pointwise validity as the local calibration size grows and the cells become sufficiently homogeneous. Experiments show a transparent quality-cost trade-off: LoBoost improves over global split conformal on several heterogeneous datasets, but it is not uniformly superior to the adaptive baselines and is not uniformly Pareto-optimal.
Teleoperation and assistive devices are tuned for channel fidelity, while whether the operator experiences the device as part of the body, the Sense of Embodiment, is measured only afterwards. Minimizing the mismatch between the operator's predictions and the returned feedback fails twice: the predictions cannot be observed, and removing feedback minimizes the objective. We formulate an embodiment-aware controller that instead infers the operator's embodiment and visuo-proprioceptive cue weighting from implicit gaze and pupil signals and task outcome, and chooses bounded device settings under explicit preferences, cast as a discrete Active Inference agent. In simulations with heterogeneous synthetic operators, it raised embodiment from 0.76 to 1.66 on a 0-2 scale over the best fixed setting, within 0.02 of an oracle across ten random seeds; adaptation that did not read the operator gained nothing, and a prediction-error minimizer withheld feedback. An expected-utility controller with the same inference did as well, so the benefit comes from inference over the operator with explicit preferences, not from information seeking. Rules on a single signal came close when that signal was informative and failed when it was not; the controller degraded less, but failed when it trusted an uninformative signal unless briefly calibrated. Against published human data, the model reproduced the embodiment-performance relation, and embodiment developed on a plausible time scale. The embodiment signals were redundant when task success tracked embodiment and became the controller's objective when it did not. Studies with people must first establish calibrated cue-weighting signals and effort-independent embodiment signals.
Diffusible signals enable communication between immune cells but can also create interference between nearby activation sites. In lymph nodes, effector T cells (Teff) concentrate around antigen-presenting cells (APCs), release interleukin-2 (IL-2) following antigen recognition, and sense IL-2 through cell-surface receptors. Experiments show high-uptake regulatory T cells (Treg) clustered around IL-2-producing cells. However, it is unclear how strongly responses at neighboring activation sites are coupled through diffusible IL-2, and how this coupling is influenced by the spatial organization of Treg acting as IL-2 sinks. We interpret two neighboring sites as a molecular communication system and study the effect of clustering using a three-dimensional IL-2 field coupled to T cell population dynamics. Across a broad parameter sweep, clustering Treg produces a larger mean reduction in neighboring-site interference than adding dispersed Treg. Compared with no Treg, clustered Treg suppress interference while largely preserving the strong local response with corresponding consequences for population expansion and survival. Information-theoretic analysis shows improved discrimination between weak and strong local sources at short separation, whereas at larger separation clustering primarily reduces the remaining estimated neighboring-source information. These findings support a spatial-filtering role for Treg clustering in maintaining locally informative immune responses.