AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

arXiv

Metamorphic Testing for Clinical ML Models: A Framework Proposal and Pilot Study

Jie "JW" Wu, Feiyu E, Bo Chen

Machine learning models for clinical prediction tasks, such as in-hospital mortality and sepsis onset, routinely achieve high AUROC scores. However, AUROC measures ranking performance rather than clinical sensibility. A model may rank patients correctly overall while predicting a lower mortality risk when a patient's SOFA score worsens, contradicting established medical knowledge. This paper proposes applying metamorphic testing (MT) to clinical machine learning models to evaluate behavioral correctness without requiring ground-truth labels for individual predictions. We design a catalog of 12 candidate metamorphic relations (MRs) for three ICU prediction tasks using the MIMIC-III and MIMIC-IV datasets, with each MR grounded in an authoritative clinical guideline. We further propose a five-layer validation strategy to ensure that MRs are clinically sound before deployment. As a feasibility study, we evaluate the approach on the UCI Heart Disease dataset. Although the three clinical models achieve strong predictive performance (AUROC = 0.849-0.900), they exhibit MT violation rates ranging from 27% to 87% across five pilot MRs. An injected-fault experiment further shows that a sign-negation error in a blood pressure feature remains undetected by AUROC but increases the MT violation rate by 31-67 percentage points. These findings suggest that metamorphic testing provides a valuable complement to conventional performance metrics for assessing the behavioral correctness of clinical prediction models.

arXiv

Finite-Time Analysis of the Natural Policy Gradient in Finite-Horizon Markov Decision Processes

Asha Barua, Sajad Khodadadian

Natural Policy Gradient (NPG) is a well-established Reinforcement Learning algorithm that underlies widely used methods such as Trust Region Policy Optimization and Proximal Policy Optimization, both of which have demonstrated strong empirical success. In this paper, we study exact NPG in finite-horizon Markov Decision Processes with known dynamics and horizon-dependent transition kernels. We provide the first finite-time convergence guarantees for this algorithm in this setting, for which we consider both constant and increasing step size regimes. With a constant step size $η_t=η$, we prove that NPG converges sublinearly with a rate of $\mathcal{O}(H^{2}/t)$ after $t$ iterations, where $H$ is the horizon length. We also extend this constant step size analysis to linear MDPs in an exact population-projection oracle under a full support projection distribution, recovering the same sublinear rate as in the tabular setting. Furthermore, with increasing step sizes, we prove that this algorithm achieves a linear convergence rate of $\mathcal{O}\left(\left(1-\frac{1}{\vartheta_ρ}\right)^t\right)$ for a problem-dependent constant $\vartheta_ρ> 1$, and the horizon-only robust schedule of the form $η_t=η_0(H/(H-1))^t$ where $η_0>0$ and $H \geq 2$, attains this same geometric rate.

arXiv

Bayesian Complete-Pooling in Cross-Subject Classification for Motor Imagery Electroencephalogram

Ethan Davis

Brain-computer interfaces (BCIs) have long sought calibration-free operation, but classifiers are typically benchmarked by discrimination alone, blind to whether predicted probabilities are well calibrated - a meaningful gap given nonstationary electroencephalogram (EEG) signals and the risk of overconfident point-estimate classifiers under distribution shift. We conducted a large-scale study contrasting Bayesian complete-pooling models against frequentist baselines for cross-subject, left-hand versus right-hand motor imagery EEG classification across 20 datasets. Six frequentist pipelines were each paired with an analogous Bayesian pipeline sharing identical feature engineering, fit via Markov chain Monte Carlo posterior sampling. Our primary metric was the Brier score, decomposed into reliability and resolution, alongside AUROC for discrimination and Shannon entropy for sharpness. Each metric was analyzed via random-effects meta-analysis (REML, Knapp-Hartung adjustment), verified by leave-one-out influence analysis. Bayesian complete-pooling produced statistically but not practically significant improvements in reliability and increases in predictive uncertainty (lower sharpness); Brier score, resolution, and discrimination showed no significant differences. Between-study heterogeneity was low across all metrics, though the reliability result was sensitive to leave-one-out removal. We additionally profiled computational cost, finding that Bayesian pipelines consumed roughly thirteen times more energy than their frequentist counterparts, a cost that remains modest relative to common household appliances. These results suggest that Bayesian complete-pooling alone offers limited practical benefit for cross-subject motor imagery classification, and that partial-pooling across subjects and sessions is a more promising direction for future work.

arXiv

Variable Importance Identification Through Lazy Training for Binary Classification

Anand Singh, Luke Pennella, Eshan Kabir, Xiaoxi Shen

Deep neural networks have been widely used in many applications (e.g., computer vision and natural language processing); however, understanding their explainability remains a challenging task. Recently, substantial research has been devoted to improving the explainability of deep neural networks, with most of this work focusing on the regression framework. In this paper, we instead focus on the binary classification framework and adopt a variable-importance framework combined with the idea of lazy training to propose an efficient algorithm for identifying important features. From a theoretical perspective, our method relies on only a minimal set of assumptions and achieves well-controlled error rates. The validity of the proposed method and algorithm is examined through extensive simulation studies and real-data applications.

arXiv

Athena-Brain Technical Report: An Efficient Robot Brain for General Intelligence and Embodied Interaction

Jialian Li, Junhong Liu, Yuchen Cao, Weiran Guo, Jiaming Song, Xutao Wang, Yi Zhao, Jiangpin Liu, Jie Chen

Large language models (LLMs) have demonstrated remarkable capabilities in language understanding, reasoning, and world knowledge. As embodied agents become increasingly capable, there is a growing demand for compact models that can serve as an on-device brain, preserving the broad general intelligence of LLMs while enabling effective high-level interaction with embodied environments. Existing approaches, however, often prioritize either general-purpose intelligence or specialized embodied capabilities, making it challenging to satisfy both requirements within a single model. We present \textbf{Athena-Brain-8B}, an 8B LLM designed to serve as an on-device brain for embodied intelligence for embodied intelligence. Through a multi-stage post-training pipeline consisting of General Supervised Fine-Tuning, General Reinforcement Learning, Embodied Expert training, and Model Merge, Athena-Brain-8B maintains strong general capabilities while acquiring strong high-level embodied interaction capabilities and generating concise responses for efficient embodied interaction. Experimental results demonstrate the effectiveness of Athena across both general and embodied evaluations. Compared with the corresponding Qwen3-8B thinking model, Athena-Brain-8B achieves comparable performance on general language and reasoning benchmarks while generating substantially shorter responses. On in-domain embodied benchmarks, Athena-Brain-8B consistently outperforms models of similar scale and surpasses several substantially larger frontier models evaluated zero-shot, demonstrating that compact language models can effectively integrate strong general intelligence with embodied capabilities.

arXiv

Position: AI/ML Deepfake Research is Misaligned with AI-Generated Non-Consensual Intimate Imagery (AIG-NCII)

Li Qiwei, Wells Lucas Santo, Sarita Schoenebeck, Eric Gilbert

AI-generated non-consensual intimate imagery (AIG-NCII) is not adequately addressed in AI/ML literature regarding AI-generated media, commonly referred to as "deepfakes". While research on deepfakes currently focuses on its epistemic harms -- or harms relating to truth and authenticity -- this is misaligned with the dominant reality of generative AI abuse involving sexualized imagery. We conduct a landscape analysis of highly-cited works to demonstrate that technical interventions addressing deepfakes almost entirely ignore AIG-NCII, limiting the research ecosystem to authenticity detection tools. In this position paper, we argue that existing interventions address viewer-centric epistemic harms, such as fraud or scams, but ignore subject-centric dignity harms, such as AIG-NCII. We illustrate that knowing an image is synthetic does not mitigate harms to subjects and may, in some cases, even exacerbate them. We conclude by offering recommendations to realign the field, including updating threat models to consider subject-centric harms and addressing AIG-NCII in AI safety research. Finally, we caution that researchers should only engage in this high-risk domain if they implement safety guardrails for both subjects and researchers and establish partnerships with domain experts in sexual violence prevention.

arXiv

How Do Practitioners Build SE Agents? Insights from a Mixed-Methods Study

Yunbo Lyu, David Williams, Jieke Shi, Zhensu Sun, Chao Peng, Zhou Yang, Federica Sarro, David Lo

The rise of Software Engineering (SE) agents, i.e., LLM-based agents that can understand large codebases and carry out engineering tasks with limited human intervention, has been marked by rapid advances and adoption, but little is known about how developers build these systems in practice: existing studies mine repositories or examine deployment, but few investigate how SE agents are constructed. Through semi-structured interviews with 20 practitioners from 12 organizations and an online survey of 80 practitioners, this paper is the first to study how SE processes are changing in the development of SE agents and what challenges developers face. We find that as implementation becomes cheaper, bottlenecks shift rather than disappear: long-standing work in requirements, coordination, and deployment becomes more visible, while reviewing generated code and evaluating agent behavior become new and increasingly central forms of work. We characterize a seven-stage workflow and five process shifts, including a move toward evaluation-driven development, in which evaluation is increasingly defined early and steers iteration, and the emergence of specifications as first-class artifacts that teams test and version alongside code. We further identify six challenges that teams face, together with 12 corresponding practices they use or propose to address them, including unreliable evaluation signals, comprehension debt as code outpaces understanding, and behavioral changes introduced by provider-side model updates.

arXiv

A Self-Evolving Default Action for Cooperative Tasks with Continuous Action Space

Shuangyao Huang

Counterfactual credit assignment has proven effective in multi-agent reinforcement learning (MARL) for discrete action spaces, yet its extension to continuous-action cooperative tasks remains challenging. Existing methods that approximate the counterfactual baseline via Monte Carlo sampling often introduce bias into policy gradients and fail to guarantee convergence to local optima, as the sampled actions may not have been sufficiently trained. To address these limitations, we propose SAFE, a novel MARL framework that employs a counterfactual baseline conditioned on a self-evolving default action sampled from each agent's experience buffer. This design naturally extends to continuous action spaces without relying on additional simulations, reward models, or environment-specific prior knowledge. The baseline accurately quantifies each agent's contribution, and introduces no bias into the deterministic policy gradient, ensuring convergence to local optima. Extensive experiments on cooperative vehicular tasks demonstrate that SAFE consistently outperforms state-of-the-art models.

arXiv

Interpreting Quantum Learning Models via Stochastic Processes

Johannes Fankhauser, Lukas J. Fiderer, Hans J Briegel

Quantum machine learning models define probabilistic input--output maps through coherent quantum evolution and measurement. While such models can exhibit computational advantages, their internal functioning and decision making generally resists interpretation in terms of stochastic trajectories through intermediate configurations. In contrast to classical (Markovian) stochastic processes, quantum dynamics generically violates the Chapman--Kolmogorov divisibility condition, preventing a decomposition into probabilistically meaningful intermediate transitions. We develop a probabilistic framework for representing quantum learning models as stochastic processes over configuration spaces where the dynamics are modeled as linear maps on probability distributions. Starting from a fixed POVM, arbitrary quantum channels induce transition kernels on the associated probability representation. For informationally complete POVMs, and in particular SIC-POVMs, these kernels are Markovian but generally quasi-stochastic, with non-classicality appearing as negativity. By contrast, projective spaces admit positive stochastic kernels but generally require non-Markovian dynamics due to the failure of Chapman--Kolmogorov divisibility. This yields a trade-off between negativity and dependence on past configurations, i.e. quantum dynamics can be represented either by Markovian quasi-stochastic maps or by positive stochastic processes with higher Markov order. We discuss how such representations of quantum dynamics can be interpreted as stochastic walks through a memory space in the spirit of Projective Simulation, a model of learning and agency in which decisions arise from random walks over an episodic memory network. We further outline how finite-order stochastic kernels can approximate such quantum deliberation processes and show in what regimes the classical machine learning model is recovered.

arXiv

Knowledge-Guided Cross-Modal Fusion for Adult-to-Pediatric ECG Transfer via Label-Conditioned Contrastive Alignment

Xinran Liu, Yuwen Li, Hongxiang Gao, Heyang Xu, Jianqing Li, Zongmin Wang, Chengyu Liu

Adult and pediatric electrocardiogram (ECG) interpretation relies on age-sensitive criteria, and models pretrained mainly on adult ECGs often transfer poorly to pediatric populations when pediatric labels are scarce. Existing multimodal ECG--text methods typically align waveforms and text at the global sample level, entangling evidence from co-occurring diagnoses and limiting transfer under this gap. We propose Pediatric-Adult ECG Alignment via Cross-modal Enhancement (PEACE), a knowledge-guided framework pretrained on the largely adult MIMIC-IV ECG corpus. PEACE describes each diagnosis along rhythm, morphology, and ST--T axes and, per recording, composes only positive-label descriptors into three axis tokens and a fused embedding. A label query network (LQN) uses diagnostic labels as queries to cross-attend over ECG tokens and axis tokens, while label set aware bidirectional contrastive learning (LSBC) aligns pooled ECG features with the fused embedding when recordings share diagnoses. Curriculum adaptive fusion (CAF) gates alignment strength according to smoothed classification loss and training progress, limiting disruption during early optimization. The knowledge branch is used only for training supervision; inference uses ECG signals alone. On ZZU-pECG, PEACE reaches macro average AUCs of 59.39%, 81.74%, and 91.56% under zero-shot, 50-shot, and full fine-tuning, with the clearest gains over foundation and knowledge-pretraining baselines under limited supervision; versus domain adaptation initializations, zero-shot improves substantially while 50-shot AUC is comparable to DANN. After fine-tuning on PTB-XL, PEACE reaches 96.90% macro average AUC over nine harmonized labels. Ablations confirm that label-conditioned knowledge alignment, rather than global text fusion, is the key driver of pediatric transfer gains.

arXiv

Infinitesimal Causality

Sridhar Mahadevan

Interventions can be varied continuously in many causal models. Differentiating a specified smooth intervention protocol produces vector fields on a statistical model, and their Lie brackets describe the noncommutativity of the corresponding local perturbations. We formulate this differential geometry of interventions on smooth statistical models and call the resulting framework infinitesimal causality (IC). Given a constant-rank distribution spanned by visible intervention fields, we define the normal Lie-bracket residual and show that its vanishing is exactly the involutivity condition in the classical Frobenius theorem. We establish the coordinate invariance of the zero-residual property and characterize its dependence on the intervention protocol, visible span, and metric. Fully observed and latent-variable examples delineate the additional structural assumptions needed to interpret bracket residuals causally. We also distinguish tangent vectors on a statistical parameter manifold from derivatives of stochastic kernels. In the finite-state linearization of a Markov category, normalization and copy compatibility yield well-typed first-order defects. Normalization is automatic for differentiable paths of stochastic kernels, whereas copy compatibility characterizes a more restrictive deterministic or comonoid-preserving perturbation. Together, the geometric and kernel-level constructions make IC a precise foundation for Lie-bracket-based causal diagnostics and identify the assumptions required to pass from local intervention geometry to causal conclusions.

arXiv

Multi-dimensional training-priority weighting based on physical information propagation paths: a unified residual-weighting framework for physics-informed neural networks

Zhangyi Lian, Xinda Dong, Wenxuan Huo, Weifeng Huang, Greg Zhu, Qiang He

Physics-informed neural networks (PINNs) have shown promise for solving partial differential equations (PDEs); however, their synchronous optimization treats residuals of different regions and constraints equally, which is inconsistent with the progressive "from source to response" physical information propagation path, degrading training stability and accuracy. Existing causal training methods focus mainly on the temporal dimension, lacking a unified characterization of spatial and boundary dimensions. To address this, we define a unified class of training priorities according to the physical information propagation path: premise regions should be learned before dependent regions; temporal, spatial, and boundary priorities are instances of this principle. Using neural tangent kernel (NTK) dynamics, we theoretically analyze why standard PINNs do not obey this priority: their residual convergence order is governed by the NTK spectrum and is independent of the propagation path. Accordingly, we propose a unified multi-dimensional priority-constraint framework that partitions the domain along the propagation path and constructs negative-exponential residual weights, converting the physical propagation order into a training priority. For cases with coexisting priorities, we introduce a directional compatibility coefficient to clarify that "orthogonal directions can be coupled multiplicatively in synergy, whereas coaxial opposite directions cannot." Benchmark cases show that this method consistently improves the convergence behavior and prediction accuracy of PINNs on problems with clear propagation paths or constraint-dominated structures, without modifying the network architecture and with controllable additional computational cost.

arXiv

CollabSkill: Evaluating Human-Agent Collaboration On Real-World Tasks

Yijia Shao, Zora Zhiruo Wang, Neel Ahuja, Yicheng Wang, Bowen Liu, Diyi Yang

AI agents are reshaping the workspace, leading to drastic change of how humans work. Despite the considerable potential of human-agent collaboration both in preserving human agency and generating economic value, this paradigm remains largely absent from occupational task evaluation, hindered by the difficulty of gathering real human data and accounting for inter-human variability. We introduce CollabSkill, a framework for evaluating human-agent collaboration on real-world occupational tasks. CollabSkill pairs real human workers with AI agents on tasks matched to their occupational background, collecting data that capture the complexity of economically valuable tasks and the usage patterns of real workers. To account for inter-human variability, CollabSkill employs a Bayesian skill rating system to disentangle and quantify the skill contributions of both humans and AI agents. Drawing on over 1,500 prompts from 386 working sessions contributed by 93 human workers, our analysis yields insights on two fronts: on the agent side, rankings on CollabSkill diverge meaningfully from those of existing fully autonomous benchmarks where Codex leads, with Claude Code ranking first; on the human side, CollabSkill reveals that practical experience emerges as the primary driver of collaboration skill, with hands-on collaboration meaningfully shifting workers' AI literacy. Together, we hope CollabSkill enables the community to invest in systematic evaluation of human-agent collaboration and spurs development efforts aimed at building AI agents that genuinely augment human workers.

arXiv

Tree-Based Formalization of Multi-Agent Complementarity in Human-AI Interactions

Andrea Ferrario

Complementarity is the case in which a human--AI interaction (HAI) outperforms the best prediction benchmark available among its members. Although this idea is central in HAI research, formal work on complementarity remains limited. Existing frameworks do not model how agents' predictions compose into workflow-sensitive multi-agent protocols. We close this gap by introducing a tree-based formalization of complementarity in multi-agent HAI. An HAI protocol is represented by an ordered agent-role configuration together with a rooted planar binary tree whose leaves are decorated by prediction vectors. A local binary composition rule is evaluated recursively along the tree, yielding a tree-relative complementarity functional relative to a pointwise-min benchmark. We prove four results. First, selector-based HAIs, including reliance, cannot achieve complementarity regardless of task, loss, or prediction quality. Second, in regression under squared loss, complementarity is equivalent to Euclidean distance minimization from the ground-truth vector; for $N=2$, the optimal linear-pooling weight has a closed form and a residual-correction interpretation. Third, under linear local composition, every protocol tree defines a barycentric coordinate chart on the simplex of leaf weights; Tamari-cover reparameterizations of protocol trees preserve complementarity, and for all $N$, any two Tamari paths with the same initial and terminal trees preserve the protocol output and complementarity. Fourth, in binary classification, no internal local composition can achieve complementarity under endpoint-monotone losses, including standard Bregman and many finite Bernoulli $f$-divergence losses; an analogous obstruction holds for multiclass aggregation under cross-entropy. In summary, our framework shows that complementarity is attainable in multi-agent regression, but obstructed in classification.

arXiv

Latent Confounded Causal Discovery via Lie Bracket Geometry

Sridhar Mahadevan

We study causal discovery from observational and interventional regimes when latent variables may affect the measured system. Our first algorithm, BRIDGE (Bracket Residuals for Interventional Discovery and Geometric Estimation), combines a density-ratio or transport engine with a high-recall geometric screen and passes the retained arrows to a score-based or differentiable discovery method. The main formulation and experiments use known single-node intervention targets; in that regime the screen is designed to retain candidate directed effects, while a downstream learner determines the final graph or equivalence-class representation. Our second algorithm, Spectral Kernel Flow Matching (SKFM), amortizes the response fields, summarizes residual nonclosure by a spectral visible-footprint subspace, and applies an order-dependent graph extractor. Direct extraction succeeds on calibrated chains and selected motifs, but is unstable on harder random DAGs when the order must be learned. On ten-node nonlinear random DAGs, the more reliable hybrid role of the geometry is as a candidate generator: calibrated SKFM/Bridge fields followed by local BIC scoring achieve mean directed $F_1\simeq0.86$. Sachs protein signaling provides a real-data stress test and supports a diagnostic, not fully identified, interpretation. The contribution is therefore a practical interventional screening pipeline, explicit guarantees for screen retention and residual-footprint rank under stated assumptions, and a falsifiable account of the boundary between geometric diagnostics and causal identification.

arXiv

KBF: Knowledge Boundary as Fingerprint for Language Model and Black-Box API Auditing

Yijia Fang, Yiqing Feng, Bingyu Li, Mingxun Zhou

Relay and reseller APIs increasingly intermediate access to large language models (LLMs), but users have no direct way to verify that a claimed endpoint is actually serving the advertised model. We introduce KBF, a low-cost black-box auditing protocol that fingerprints model APIs using stable numerical recall near the knowledge boundary. Across 16 production LLM endpoints, KBF flags all 155 economically relevant substitutions without rejecting any same-model controls, remains stable under deployment variation, detects high-separation mixed-routing attacks when only 5-10% of traffic is substituted, and finds that 7 of 27 platform model cells in a six-platform shadow API audit are statistically inconsistent with their reference endpoints, with inconsistencies concentrated on premium Claude endpoints.

arXiv

Bellman-sufficient Information Complexity

Yunbei Xu

We develop Bellman-sufficient information complexity, a representation-level framework for the information-theoretic minimax analysis of sequential decision making. The theory covers interactive environments unfolding over long streams of experience and benchmarks all nonanticipating algorithms. A Bellman-sufficient state closes the controlled recursion, while an index $Y=χ(Ω)$ identifies the decision-relevant information. Upper bounds arise from a log-penalized Bellman program, and lower bounds from a Bellman-Fano comparison along a reference trajectory. When the two sides exhibit matching information growth at a common localization scale, they yield an information-risk sandwich. Within this framework, UCB, E2D, and AMS/EBO arise through calibration, one-step offsets, and robust belief optimization, respectively. As a major application, we give a negative resolution to a canonical, widely studied form of the GP-UCB minimax-optimality question. For every $0<α<1/4$, there exists a single bounded continuous kernel whose minimax regret is $Θ(T^{1-α})$ along an infinite sequence of horizons. On the same problem, a finite-marginal action-index AIR Bellman policy attains this order, whereas both an anytime maximal-information GP-UCB rule and the unit-ball specialization of the original RKHS GP-UCB exploration schedule incur linear regret. This separates realized information acquisition from the cost of uniform optimism and explains why localization can be essential within the Bellman recursion. A reproducible finite-scale experiment illustrates the predicted cloud-exploration mechanism for both headline GP-UCB calibrations.

arXiv

Causal Density Functions

Sridhar Mahadevan

We study the full density ratio between a specified intervention regime $P_a$ and an observational regime $P_0$, $ρ_a=dP_a/dP_0$, under the prerequisite $P_a\ll P_0$. We call the regime-indexed ratio a causal density function when $P_a$ is an identified or directly observed interventional law. The underlying Radon-Nikodym derivative and the identity $ \mathbb{E}_{a}[f(Z)] = \mathbb{E}_{0}\!\left[f(Z)ρ_a(Z)\right] $ are classical importance weighting, not new identification results. Our narrower question is whether retaining the entire pointwise ratio is useful as a reusable diagnostic across several downstream functionals. We evaluate a two-density plug-in baseline through held-out moment transport and overlap stress tests on synthetic and perturbation data. We also report a pairwise graph-scoring heuristic as a negative result: its F1 is \(0.10\) on a synthetic DAG, \(0.12\) on Sachs, and \(0.33\) on a multi-regime chain. These experiments do not establish an estimation advantage over direct density-ratio, inverse-probability, Riesz, or doubly robust methods; they instead delimit what the pointwise ratio target and the present plug-in estimator do and do not provide.

arXiv

Universal Decision Learners

Sridhar Mahadevan

Many theories of decision making -- planning, reinforcement learning, causal intervention, online learning, and game-theoretic equilibrium -- turn local information into globally coherent behavior. This paper proposes a common categorical formulation: a Universal Decision Learner (UDL) extends a partially specified decision functor from observed contexts to new contexts by a pair of universal constructions. Left Kan extensions express rollout, aggregation, and candidate generation; right Kan extensions express consistency, constraint satisfaction, and fixed-point semantics. The central claim is not that every decision problem has the same algorithm, but that many decision formalisms instantiate the same universal problem: extend local behavioral data canonically, then characterize the globally coherent extensions. We give the abstract UDL construction, prove its universal comparison property, define Kan-invariant behavioral equivalence and minimal abstractions, and show how Bellman equations, planning recursions, causal interventions, online regret, and equilibria arise as special cases. The supplementary material develops the reinforcement-learning specialization in more detail.

arXiv

Kan Extension Transformers: A Categorical Unification of Attention, Diffusion, and Predict-Detach Self-Conditioning

Sridhar Mahadevan

We propose Kan Extension Transformers (KETs) as a categorical design language for a diverse group of Transformer implementations. A layer can be viewed generally as a weighted structured extension operator: attention uses token neighborhoods, geometric mixing uses sparse incidences, and KET uses simplicial sources. This operator is an actual enriched left Kan extension only when the source values are functorial, the weights are representable hom-objects (or the specified profunctor action), and aggregation realizes the corresponding coend; otherwise ``Kan-style'' denotes an interpretation rather than an identity theorem. Predict-detach blocks gradients through a predictive carrier and avoids transporting teacher-forced hidden states, but detach alone does not make a noncausal update strictly autoregressive: every carrier consumed at target $t$ must also be measurable from the prefix available at $t$. We evaluate 12 implementations on Penn Treebank, WikiText-2, and WikiText-103 across strict-causal and self-conditioned regimes, using widths $d=64,256$ and depths $L=2,8,16$ across the reported studies. Quadratic KET is strongest among the compared strict-causal architectures on WikiText-2 and WikiText-103; the largest cross-regime gains arise from additional self-conditioning information, not neighborhood design alone.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.