Machine Learning
Quantum-Inspired Fine-Tuning for Few-Shot AIGC Detection via Phase-Structured Reparameterization
Kaiyang Xing, Han Fang, Zhaoyun Chen et al. (+4 more)
Recent studies show that
quantum neural networks (QNNs) generalize well in few-shot regimes. To extend this advantage to large-scale tasks, we propose Q-LoRA, a
quantum-enhanced fine-tuning scheme that integrates lightweight QNNs into the low-rank adaptation (LoRA) adapter. Applied to AI-generated content (AIGC) detection, Q-LoRA consistently outperforms standard LoRA under few-shot settings. We analyze the source of this improvement and identify two possible structural inductive biases from QNNs: (i) phase-aware representations, which encode richer information across orthogonal amplitude-phase components, and (ii) norm-constrained transformations, which stabilize optimization via inherent orthogonality. However, Q-LoRA incurs non-trivial overhead due to
quantum simulation. Motivated by our analysis, we further introduce H-LoRA, a fully classical variant that applies the
Hilbert transform within the LoRA adapter to retain similar phase structure and constraints. Experiments on few-shot AIGC detection show that both Q-LoRA and H-LoRA outperform standard LoRA by over 5% accuracy, with H-LoRA achieving comparable accuracy at significantly lower cost in this task.
Read the full abstract ▾
All authors Kaiyang Xing, Han Fang, Zhaoyun Chen, Zhonghui Li, Yang Yang, Weiming Zhang, Guoping Guo
Machine Learning
Temporal Imbalance of Positive and Negative Supervision in Class-Incremental Learning
Jinge Ma and Fengqing Zhu
With the widespread adoption of deep learning in visual tasks, Class-Incremental Learning (CIL) has become an important paradigm for handling dynamically evolving data distributions. However, CIL faces the core challenge of catastrophic forgetting, often manifested as a prediction bias toward new classes. Existing methods mainly attribute this bias to intra-task class imbalance and focus on corrections at the classifier head. In this paper, we highlight an overlooked factor – temporal imbalance – as a key cause of this bias. Earlier classes receive stronger negative supervision toward the end of training, leading to asymmetric precision and recall. We establish a temporal supervision model, formally define temporal imbalance, and propose Temporal-Adjusted Loss (TAL), which uses a temporal decay kernel to construct a supervision strength vector and dynamically reweight the negative supervision in cross-
entropy loss. Theoretical analysis shows that TAL degenerates to standard cross-
entropy under balanced conditions and effectively mitigates prediction bias under imbalance. Extensive experiments demonstrate that TAL significantly reduces forgetting and improves performance on multiple CIL
benchmarks, underscoring the importance of temporal modeling for stable long-term learning.
Read the full abstract ▾
Machine Learning
Partial Causal Structure Learning for Valid Selective Conformal Inference under Interventions
Amir Asiaee, Kavey Aryan and James P. Long
Selective conformal prediction can yield substantially tighter uncertainty sets when we can identify calibration examples that are exchangeable with the test example. In interventional settings, such as perturbation experiments in genomics, exchangeability often holds only within subsets of interventions that leave a target variable "unaffected" (e.g., non-descendants of an intervened node in a causal graph). We study the practical regime where this invariance structure is unknown and must be estimated from data. Our main result quantifies how coverage degrades when the estimated safe calibration set accidentally includes interventions that affect the target, and gives a conservative correction when an upper bound on this error is available. Rather than learning a full causal graph, we learn only the intervention-target relationships needed to choose calibration interventions. We give
algorithms for this partial learning task and evaluate them on synthetic structural equation models and Replogle K562 CRISPR-interference data, where the experiments illustrate synthetic gains from selective calibration and finite-sample tradeoffs on real perturbation screens.
Read the full abstract ▾
Machine Learning
Frontier Models Can Take Actions at Low Probabilities
Alex Serrano, Wen Xing, David Lindner et al. (+1 more)
Pre-deployment evaluations inspect only a limited sample of model actions. A malicious model seeking to evade oversight could exploit this by randomizing when to "defect": misbehaving so rarely that no malicious actions are observed during evaluation, but often enough that they occur eventually in deployment. But this requires taking actions at very low rates, while maintaining calibration. Are frontier models even capable of that? We
prompt the GPT-5, Claude-4.5 and Qwen-3 families to take a target action at low probabilities (e.g. 0.01%), either given directly or requiring derivation, and evaluate their calibration (i.e. whether they perform the target action roughly 1 in 10,000 times when resampling). We find that frontier models are surprisingly good at this task. If there is a source of
entropy in-context (such as a UUID), they maintain high calibration at rates lower than 1 in 100,000 actions. Without external
entropy, some models can still reach rates lower than 1 in 10,000. When target rates are given, larger models achieve good calibration at lower rates. Yet, when models must derive the optimal target rate themselves, all models fail to achieve calibration without
entropy or hint to generate it. Successful low-rate strategies require explicit Chain-of-Thought (CoT)
reasoning, so malicious models attempting this approach could currently be caught by a CoT monitor. However, scaling trends suggest future evaluations may be unable to rely on models' lack of target rate calibration, especially if CoT is no longer legible.
Read the full abstract ▾
All authors Alex Serrano, Wen Xing, David Lindner, Erik Jenner
Machine Learning · Cross-listed from cs.CV
Adaptive Confidence Regularization for Multimodal Failure Detection
Moru Liu, Hao Dong, Olga Fink et al. (+1 more)
The deployment of
multimodal models in high-stakes domains, such as self-driving vehicles and medical diagnostics, demands not only strong predictive performance but also reliable mechanisms for detecting failures. In this work, we address the largely unexplored problem of failure detection in
multimodal contexts. We propose Adaptive Confidence Regularization (ACR), a novel framework specifically designed to detect
multimodal failures. Our approach is driven by a key observation: in most failure cases, the confidence of the
multimodal prediction is significantly lower than that of at least one unimodal branch, a phenomenon we term confidence degradation. To mitigate this, we introduce an Adaptive Confidence Loss that penalizes such degradations during training. In addition, we propose
Multimodal Feature Swapping, a novel outlier synthesis technique that generates challenging, failure-aware training examples. By training with these synthetic failures, ACR learns to more effectively recognize and reject uncertain predictions, thereby improving overall reliability. Extensive experiments across four
datasets, three modalities, and multiple evaluation settings demonstrate that ACR achieves consistent and robust gains. The source code will be available at https://github.com/mona4399/ACR.
Read the full abstract ▾
All authors Moru Liu, Hao Dong, Olga Fink, Mario Trapp
Machine Learning · Cross-listed from cs.AI
Conformal Policy Control
Drew Prinster, Clara Fannjiang, Ji Won Park et al. (+4 more)
An
agent must try new behaviors to explore and improve. In high-stakes environments, an
agent that violates safety constraints may cause harm and must be taken offline, curtailing any future interaction. Imitating old behavior is safe, but excessive conservatism discourages exploration. How much behavior change is too much? We show how to use any safe reference policy as a probabilistic regulator for any optimized but untested policy. Conformal calibration on data from the safe policy determines how aggressively the new policy can act, while provably enforcing the user's declared risk tolerance. Unlike conservative optimization methods, we do not assume the user has identified the correct model class nor tuned any hyperparameters. Unlike previous conformal methods, our theory provides finite-sample guarantees even for non-monotonic bounded loss functions, and it introduces a new policy control setting. Our experiments on applications ranging from natural
language question answering to biomolecular engineering show that safe exploration is not only possible from the first moment of deployment, but can also improve performance.
Read the full abstract ▾
All authors Drew Prinster, Clara Fannjiang, Ji Won Park, Kyunghyun Cho, Anqi Liu, Suchi Saria, Samuel Stanton
Machine Learning · Cross-listed from cs.CV
From Leaderboard to Deployment: Code Quality Challenges in AV Perception Repositories
Mateus Karvat, Bram Adams and Sidney Givigi
Autonomous vehicle (AV) perception models are typically evaluated solely on
benchmark performance metrics, with limited
attention to code quality, production readiness and long-term maintainability. This creates a significant gap between research excellence and real-world deployment in safety-critical systems subject to international safety standards. To address this gap, we present the first large-scale empirical study of software quality in AV perception repositories, systematically analyzing 178 unique models from the KITTI and NuScenes 3D Object Detection leaderboards. Using static analysis tools (Pylint, Bandit, and Radon), we evaluated code errors, security vulnerabilities, maintainability, and development practices. Our findings revealed that only 7.3% of the studied repositories meet basic production-readiness criteria, defined as having zero critical errors and no high-severity security vulnerabilities. Security issues are highly concentrated, with the top five issues responsible for almost 80% of occurrences, which prompted us to develop a set of actionable guidelines to prevent them. Additionally, the adoption of Continuous Integration/Continuous Deployment pipelines was correlated with better code maintainability. Our findings highlight that leaderboard performance does not reflect production readiness and that targeted interventions could substantially improve the quality and safety of AV perception code.
Read the full abstract ▾
Machine Learning
Symbol-Equivariant Recurrent Reasoning Models
Richard Freinschlag, Timo Bertram, Erich Kobler et al. (+2 more)
Reasoning problems such as Sudoku and ARC-AGI remain challenging for neural networks. The structured problem solving architecture family of Recurrent
Reasoning Models (RRMs), including Hierarchical
Reasoning Model (HRM) and Tiny Recursive Model (TRM), offer a compact alternative to large
language models, but currently handle symbol
symmetries only implicitly via costly data augmentation. We introduce Symbol-Equivariant Recurrent
Reasoning Models (SE-RRMs), which enforce permutation equivariance at the architectural level through symbol-equivariant layers, guaranteeing identical solutions under symbol or color permutations. SE-RRMs outperform prior RRMs on 9x9 Sudoku and generalize from just training on 9x9 to smaller 4x4 and larger 16x16 and 25x25 instances, to which existing RRMs cannot extrapolate. On ARC-AGI-1 and ARC-AGI-2, SE-RRMs achieve competitive performance with substantially less data augmentation and only 2 million parameters, demonstrating that explicitly encoding
symmetry improves the robustness and scalability of neural
reasoning. Code is available at https://github.com/ml-jku/SE-RRM.
Read the full abstract ▾
All authors Richard Freinschlag, Timo Bertram, Erich Kobler, Andreas Mayr, Günter Klambauer
Machine Learning · Cross-listed from cs.CV
Sketch2Colab: Sketch-Conditioned Multi-Human Animation via Controllable Flow Distillation
Divyanshu Daiya and Aniket Bera
We present Sketch2Colab, which turns storyboard-style 2D sketches into coherent, object-aware 3D multi-human motion with fine-grained control over
agents, joints, timing, and contacts.
Diffusion-based motion generators offer strong realism but often rely on costly guidance for multi-entity control and degrade under strong conditioning. Sketch2Colab instead learns a sketch-conditioned
diffusion prior and distills it into a rectified-flow student in latent space for fast, stable sampling. To make motion follow storyboards closely, we guide the student with differentiable objectives that enforce keyframes, paths, contacts, and physical consistency. Collaborative motion naturally involves discrete changes in interaction, such as converging, forming contact, cooperative transport, or disengaging, and a continuous flow alone struggles to sequence these shifts cleanly. We address this with a lightweight continuous-time Markov chain (CTMC) planner that tracks the active interaction regime and modulates the flow to produce clearer, synchronized coordination in human-object-human motion. Experiments on CORE4D and InterHuman show that Sketch2Colab outperforms baselines in constraint adherence and perceptual quality while sampling substantially faster than
diffusion-only alternatives.
Read the full abstract ▾
Machine Learning
Multi-Head Low-Rank Attention
Songtao Liu, Hongwu Peng, Zhiwei Zhang et al. (+2 more)
Long-context inference in large
language models is bottlenecked by Key–Value (KV) cache loading during the decoding stage, where the sequential nature of generation requires repeatedly transferring the KV cache from off-chip High-Bandwidth
Memory (HBM) to on-chip Static Random-Access
Memory (SRAM) at each step. While Multi-Head Latent
Attention (MLA) significantly reduces the total KV cache size, it suffers from a sharding bottleneck during distributed decoding via Tensor Parallelism (TP). Since its single latent head cannot be partitioned, each device is forced to redundantly load the complete KV cache for every
token, consuming excessive
memory traffic and diminishing TP benefits like weight sharding. In this work, we propose Multi-Head Low-Rank
Attention (MLRA), which enables partitionable latent states for efficient 4-way TP decoding. Extensive experiments show that MLRA achieves state-of-the-art perplexity and downstream task performance, while also delivering a 2.8$\times$ decoding speedup over MLA. Code is available at https://github.com/SongtaoLiu0823/MLRA. Pretrained weights, along with the training and evaluation data, are available at https://huggingface.co/Soughing/MLRA.
Read the full abstract ▾
All authors Songtao Liu, Hongwu Peng, Zhiwei Zhang, Zhengyu Chen, Yue Guo
Machine Learning
MAC: A Conversion Rate Prediction Benchmark Featuring Labels Under Multiple Attribution Mechanisms
Jinqi Wu, Sishuo Chen, Zhangming Chan et al. (+9 more)
Multi-attribution learning (MAL), which enhances model performance by learning from conversion labels yielded by multiple attribution mechanisms, has emerged as a promising learning paradigm for conversion rate (CVR) prediction. However, the conversion labels in public CVR
datasets are generated by a single attribution mechanism, hindering the development of MAL approaches. To address this data gap, we establish the Multi-Attribution
Benchmark (MAC), the first public CVR
dataset featuring labels from multiple attribution mechanisms. Besides, to promote reproducible research on MAL, we develop PyMAL, an open-source library covering a wide array of baseline methods. We conduct comprehensive experimental analyses on MAC and reveal three key insights: (1) MAL brings consistent performance gains across different attribution settings, especially for users featuring long conversion paths. (2) The performance growth scales up with objective complexity in most settings; however, when predicting first-click conversion targets, simply adding auxiliary objectives is counterproductive, underscoring the necessity of careful selection of auxiliary objectives. (3) Two architectural design principles are paramount: first, to fully learn the multi-attribution knowledge, and second, to fully leverage this knowledge to serve the main task. Motivated by these findings, we propose Mixture of Asymmetric Experts (MoAE), an effective MAL approach incorporating multi-attribution knowledge learning and main task-centric knowledge utilization. Experiments on MAC show that MoAE substantially surpasses the existing state-of-the-art MAL method. We believe that our
benchmark and insights will foster future research in the MAL field. Our MAC
benchmark and the PyMAL
algorithm library are publicly available at https://github.com/alimama-tech/PyMAL.
Read the full abstract ▾
All authors Jinqi Wu, Sishuo Chen, Zhangming Chan, Yong Bai, Lei Zhang, Sheng Chen, Chenghuan Hou, Xiang-Rong Sheng, Han Zhu, Jian Xu, Bo Zheng, Chaoyou Fu
Machine Learning · Cross-listed from cs.CV
Leveraging Model Soups to Classify Intangible Cultural Heritage Images from the Mekong Delta
Quoc-Khang Tran, Minh-Thien Nguyen and Nguyen-Khang Pham
The classification of Intangible Cultural Heritage (ICH) images in the Mekong Delta poses unique challenges due to limited annotated data, high visual similarity among classes, and domain heterogeneity. In such low-resource settings, conventional deep learning models often suffer from high variance or overfit to spurious correlations, leading to poor generalization. To address these limitations, we propose a robust framework that integrates the hybrid CoAtNet architecture with model soups, a lightweight weight-space ensembling technique that averages checkpoints from a single training trajectory without increasing inference cost. CoAtNet captures both local and global patterns through stage-wise fusion of convolution and self-
attention. We apply two ensembling strategies - greedy and uniform soup - to selectively combine diverse checkpoints into a final model. Beyond performance improvements, we analyze the ensembling effect through the lens of bias-variance decomposition. Our findings show that model soups reduces variance by stabilizing predictions across diverse model snapshots, while introducing minimal additional bias. Furthermore, using cross-
entropy-based distance metrics and Multidimensional Scaling (MDS), we show that model soups selects geometrically diverse checkpoints, unlike Soft Voting, which blends redundant models centered in output space. Evaluated on the ICH-17
dataset (7,406 images across 17 classes), our approach achieves state-of-the-art results with 72.36% top-1 accuracy and 69.28% macro F1-score, outperforming strong baselines including ResNet-50, DenseNet-121, and ViT. These results underscore that diversity-aware checkpoint averaging provides a principled and efficient way to reduce variance and enhance generalization in culturally rich, data-scarce classification tasks.
Read the full abstract ▾
Machine Learning
Reservoir Subspace Injection for Online ICA under Top-n Whitening
Wenjun Xiao, Yuda Bi and Vince D Calhoun
Reservoir expansion can improve online independent component analysis (ICA) under nonlinear mixing, yet top-$n$ whitening may discard injected features. We formalize this bottleneck as reservoir subspace injection (RSI): injected features help only if they enter the retained eigenspace without displacing passthrough directions. RSI diagnostics (IER, SSO, $\rho_x$) identify a failure mode in our top-$n$ setting: stronger injection increases IER but crowds out passthrough energy ($\rho_x: 1.00\!\rightarrow\!0.77$), degrading SI-SDR by up to $2.2$\,dB. A guarded RSI controller preserves passthrough retention and recovers mean performance to within $0.1$\,dB of baseline $1/N$ scaling. With passthrough preserved, RE-OICA improves over vanilla online ICA by $+1.7$\,dB under nonlinear mixing and achieves positive SI-SDR$_{\mathrm{sc}}$ on the tested super-Gaussian
benchmark ($+0.6$\,dB).
Read the full abstract ▾
Machine Learning
De-paradox Tree: Breaking Down Simpson's Paradox via A Kernel-Based Partition Algorithm
Xian Teng and Yu-Ru Lin
Real-world observational
datasets and machine learning have revolutionized data-driven decision-making, yet many models rely on empirical associations that may be misleading due to confounding and subgroup heterogeneity. Simpson's paradox exemplifies this challenge, where aggregated and subgroup-level associations contradict each other, leading to misleading conclusions. Existing methods provide limited support for detecting and interpreting such paradoxical associations, especially for practitioners without deep causal expertise. We introduce De-paradox Tree, an interpretable
algorithm designed to uncover hidden subgroup patterns behind paradoxical associations under assumed causal structures involving confounders and effect heterogeneity. It employs novel split criteria and balancing-based procedures to adjust for confounders and homogenize heterogeneous effects through recursive partitioning. Compared to state-of-the-art methods, De-paradox Tree builds simpler, more interpretable trees, selects relevant
covariates, and identifies nested opposite effects while ensuring robust estimation of causal effects when causally admissible variables are provided. Our approach addresses the limitations of traditional causal inference and machine learning methods by introducing an interpretable framework that supports non-expert practitioners while explicitly acknowledging causal assumptions and scope limitations, enabling more reliable and informed decision-making in complex observational data environments.
Read the full abstract ▾
Machine Learning
SageBwd: A Trainable Low-bit Attention
Jintao Zhang, Marco Chen, Haoxu Wang et al. (+5 more)
Low-bit
attention, such as SageAttention, has emerged as an effective approach for accelerating model inference, but its applicability to training remains poorly understood. In prior work, we introduced SageBwd, a trainable INT8
attention that quantizes six of seven
attention matrix multiplications while preserving fine-tuning performance. However, SageBwd exhibited a persistent performance gap to full-precision
attention (FPA) during pre-training. In this work, we investigate why this gap occurs and demonstrate that SageBwd matches full-precision
attention during pretraining. Through experiments and theoretical analysis, we reach a few important insights and conclusions: (i) QK-norm is necessary for stable training at large
tokens per step, (ii) quantization errors primarily arise from the backward-pass score gradient dS, (iii) reducing
tokens per step enables SageBwd to match FPA performance in pre-training, and (iv) K-smoothing remains essential for training stability, while Q-smoothing provides limited benefit during pre-training.
Read the full abstract ▾
All authors Jintao Zhang, Marco Chen, Haoxu Wang, Kai Jiang, Ion Stoica, Joseph E. Gonzalez, Jianfei Chen, Jun Zhu
Machine Learning · Cross-listed from stat.ML
Instrumental and Proximal Causal Inference with Gaussian Processes
Yuqi Zhang, Krikamol Muandet, Dino Sejdinovic et al. (+2 more)
Instrumental variable (IV) and proximal causal learning (Proxy) methods are central frameworks for causal inference in the presence of unobserved confounding. Despite substantial methodological advances, existing approaches rarely provide reliable epistemic uncertainty (EU) quantification. We address this gap through a Deconditional Gaussian Process (DGP) framework for uncertainty-aware causal learning. Our formulation recovers popular kernel
estimators as the posterior mean, ensuring predictive precision, while the posterior variance yields principled and well-calibrated EU. Moreover, the probabilistic structure enables systematic model selection via marginal log-likelihood optimization. Empirical results demonstrate strong predictive performance alongside informative EU quantification, evaluated via empirical coverage frequencies and decision-aware accuracy rejection curves. Together, our approach provides a unified, practical solution for causal inference under unobserved confounding with reliable uncertainty.
Read the full abstract ▾
All authors Yuqi Zhang, Krikamol Muandet, Dino Sejdinovic, Edwin Fong, Siu Lun Chau
Machine Learning
Near-Optimal Regret for KL-Regularized Multi-Armed Bandits
Kaixuan Ji, Qingyue Zhao, Heyang Zhao et al. (+2 more)
Recent studies have shown that reinforcement learning with KL-regularized objectives can enjoy faster rates of convergence or logarithmic regret, in contrast to the classical $\sqrt{T}$-type regret in the unregularized setting. However, the statistical efficiency of online learning with respect to KL-regularized objectives remains far from completely characterized, even when specialized to multi-armed bandits (MABs). We address this problem for MABs via a sharp analysis of KL-UCB using a novel peeling argument, which yields a $\tilde{O}(\eta K\log^2T)$ upper bound: the first high-probability regret bound with linear dependence on $K$. Here, $T$ is the time horizon, $K$ is the number of arms, $\eta^{-1}$ is the regularization intensity, and $\tilde{O}$ hides all logarithmic factors except those involving $\log T$. The near-tightness of our analysis is certified by the first non-constant lower bound $\Omega(\eta K \log T)$, which follows from subtle hard-instance constructions and a tailored decomposition of the Bayes prior. Moreover, in the low-regularization regime (i.e., large $\eta$), we show that the KL-regularized regret for MABs is $\eta$-independent and scales as $\tilde{\Theta}(\sqrt{KT})$. Overall, our results provide a thorough understanding of KL-regularized MABs across all regimes of $\eta$ and yield nearly optimal bounds in terms of $K$, $\eta$, and $T$.
Read the full abstract ▾
All authors Kaixuan Ji, Qingyue Zhao, Heyang Zhao, Qiwei Di, Quanquan Gu
Machine Learning
Machine Learning (ML) library in Linux kernel
Viacheslav Dubeyko
Linux kernel is a huge code base with enormous number of subsystems and possible configuration options that results in unmanageable complexity of elaborating an efficient configuration. Machine Learning (ML) is approach/area of learning from data, finding patterns, and making predictions without implementing
algorithms by developers that can introduce a self-evolving capability in Linux kernel. However, introduction of ML approaches in Linux kernel is not easy way because there is no direct use of floating-point operations (FPU) in kernel space and, potentially, ML models can be a reason of significant performance degradation in Linux kernel. Paper suggests the ML infrastructure architecture in Linux kernel that can solve the declared problem and introduce of employing ML models in kernel space. Suggested approach of kernel ML library has been implemented as Proof Of Concept (PoC) project with the goal to demonstrate feasibility of the suggestion and to design the interface of interaction the kernel-space ML model proxy and the ML model user-space thread.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
When Bigger is Worse: A Practitioner's Guide to Model Selection Under Data Scarcity
Kwame Mbobda-Kuate and Gabriel Kasmi
Scaling laws assume larger models trained on more data consistently outperform smaller ones – an assumption that drives model selection in computer
vision but remains untested in resource-constrained Earth observation (EO). We conduct a systematic efficiency analysis across three scaling dimensions: model size,
dataset size, and input resolution, on rooftop photovoltaic (PV) detection in Madagascar, yielding 180 training runs across 60 configurations. Optimizing for model efficiency (mAP$_{50}$ per unit of model size), we find a consistent efficiency inversion: YOLO11N achieves the highest efficiency ($22\times$ higher than YOLO11X) with no accuracy penalty: it reaches the second highest absolute mAP$_{50}$ (0.459), outperforming all models except YOLO11S by a margin smaller than run-to-run variance, directly contradicting the scaling prior. Resolution is the dominant resource allocation lever: moving from 416 px to 1280 px at 10 % of the data matches the efficiency gain of collecting the full
dataset at low resolution. These findings are robust to the deployment objective: small high-resolution configurations are Pareto-dominant across all 60 experimental setups in the joint accuracy-throughput space, leaving no tradeoff to resolve. In data-scarce EO, the scaling prior does not just fail: it inverts.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
Pencil Puzzle Bench: A Benchmark for Multi-Step Verifiable Reasoning
Justin Waugh
We introduce Pencil Puzzle Bench, a framework for evaluating large
language model
reasoning through pencil puzzles, a family of constraint-satisfaction problems closely related to NP-complete problems, with deterministic, step-level verification. From a database of 62,231 puzzles across 94 varieties with verified unique solutions, we select a
benchmark of 300 puzzles spanning 20 varieties and evaluate 51 models from 11 providers in two modes: direct ask (single-shot) and agentic (multi-turn with iterative verification). A key differentiator of our
benchmark is that every intermediate board state can be checked against variety-specific constraints, localizing errors to the exact rule violated, providing the infrastructure for dense, per-move reward signals for process supervision and reinforcement learning. Our evaluation reveals two distinct axes of capability: (1)
reasoning effort scaling, where GPT-5.2 improves 81x from no
reasoning to maximum effort; and (2) agentic iteration, where Claude Opus 4.6 rises from 0.3% to 30.0% through iterative checking, while GPT-5.2@xhigh improves from 20.2% to 56.0%. Agentic attempts span a median of 29 turns over 17 minutes, with the longest exceeding 1,221 turns and 14.3 hours - a demanding test of long-context utilization, not just
reasoning.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.RO
Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons
Anthony Liang, Yigit Korkmaz, Jiahui Zhang et al. (+14 more)
General-purpose
robot reward models are typically trained to predict absolute task progress from expert demonstrations, providing only local, frame-level supervision. While effective for expert demonstrations, this paradigm scales poorly to large-scale robotics
datasets where failed and suboptimal trajectories are abundant and assigning dense progress labels is ambiguous. We introduce Robometer, a scalable reward modeling framework that combines intra-trajectory progress supervision with inter-trajectory preference supervision. Robometer is trained with a dual objective: a frame-level progress loss that anchors reward magnitude on expert data, and a trajectory-comparison preference loss that imposes global ordering constraints across trajectories of the same task, enabling effective learning from both real and augmented failed trajectories. To support this formulation at scale, we curate RBM-1M, a reward-learning
dataset comprising over one million trajectories spanning diverse
robot embodiments and tasks, including substantial suboptimal and failure data. Across
benchmarks and real-world evaluations, Robometer learns more generalizable reward functions than prior methods and improves
robot learning performance across a diverse set of downstream applications. Code, model weights, and
videos at https://robometer.github.io/.
Read the full abstract ▾
All authors Anthony Liang, Yigit Korkmaz, Jiahui Zhang, Minyoung Hwang, Abrar Anwar, Sidhant Kaushik, Aditya Shah, Alex S. Huang, Luke Zettlemoyer, Dieter Fox, Yu Xiang, Anqi Li, Andreea Bobu, Abhishek Gupta, Stephen Tu, Erdem Biyik, Jesse Zhang
Machine Learning
Recursive Models for Long-Horizon Reasoning
Chenxiao Yang, Nathan Srebro and Zhiyuan Li
Modern
language models reason within bounded context, an inherent constraint that poses a fundamental barrier to long-horizon
reasoning. We identify recursion as a core principle for overcoming this barrier, and propose recursive models as a minimal realization, where the model can recursively invoke itself to solve subtasks in isolated contexts. We prove that any computable problem admits a recursive decomposition of
reasoning in which each subtask requires only exponentially smaller active context than standard autoregressive models; this strictly surpasses any context management approach confined to a single sequence, such as summarization. We further generalize our framework to modern agentic systems with arbitrary context processing and control flows, and prove that recursive models can achieve optimal power within this broader class. Experimentally, we test two settings: fine-tuning a pretrained base model for recursive SAT solving, and training a small model from scratch on Go traces generated by exact game-tree search. Both show improved long-horizon accuracy with small active contexts.
Read the full abstract ▾
Machine Learning · Cross-listed from eess.SP
Orchestrating Multimodal DNN Workloads in Wireless Neural Processing
Sai Xu, Kai-Kit Wong, Yanan Du et al. (+1 more)
In edge inference, wireless resource allocation and accelerator-level deep neural network (DNN) scheduling have yet to be co-optimized in an end-to-end manner. The lack of coordination between wireless transmission and accelerator-level DNN execution prevents efficient overlap, leading to higher end-to-end inference latency. To address this issue, this paper investigates
multimodal DNN workload orchestration in wireless neural processing (WNP), a paradigm that integrates wireless transmission and multi-core accelerator execution into a unified end-to-end pipeline. First, we develop a unified communication-computation model for
multimodal DNN execution and formulate the corresponding optimization problem. Second, we propose O-WiN, a framework that orchestrates DNN workloads in WNP through two tightly coupled stages: simulation-based optimization and runtime execution. Third, we develop two
algorithms, RTFS and PACS. RTFS schedules communication and computation sequentially, whereas PACS interleaves them to enable pipeline parallelism by overlapping wireless data transfer with accelerator-level DNN execution. Simulation results demonstrate that PACS significantly outperforms RTFS under high modality heterogeneity by better masking wireless latency through communication-computation overlap, thereby highlighting the effectiveness of communication-computation pipelining in accelerating
multimodal DNN execution in WNP.
Read the full abstract ▾
All authors Sai Xu, Kai-Kit Wong, Yanan Du, Hyundong Shin
Machine Learning
Stochastic Multi-Armed Bandits with Limited Control Variates
Arun Verma, Manjesh Kumar Hanawal and Arun Rajkumar
Motivated by wireless networks where interference or channel state estimates provide partial insight into throughput, we study a variant of the classical
stochastic multi-armed bandit problem in which the learner has limited access to auxiliary information. Recent work has shown that such auxiliary information, when available as control variates, can be used to get tighter confidence bounds, leading to lower regret. However, existing works assume that control variates are available in every round, which may not be realistic in several real-life scenarios. To address this, we propose UCB-LCV, an upper confidence bound (UCB) based
algorithm that effectively combines the
estimators obtained from rewards and control variates. When there is no control variate, UCB-LCV leads to a novel
algorithm that we call UCB-NORMAL, outperforming its existing
algorithms for the standard MAB setting with normally distributed rewards. Finally, we discuss variants of the proposed UCB-LCV that apply to general distributions and experimentally demonstrate that UCB-LCV outperforms existing bandit
algorithms.
Read the full abstract ▾
Machine Learning
On the Rate of Convergence of GD in Non-linear Neural Networks: An Adversarial Robustness Perspective
Guy Smorodinsky, Sveta Gimpleson and Itay Safran
We study the convergence dynamics of Gradient Descent (GD) in a minimal binary classification setting, consisting of a two-
neuron ReLU network and two training instances. We prove that even under these strong simplifying assumptions, while GD successfully converges to an optimal robustness margin, effectively maximizing the distance between the decision boundary and the training points, this convergence occurs at a prohibitively slow rate, scaling strictly as $\Theta(1/\ln(t))$. To the best of our knowledge, this establishes the first explicit lower bound on the convergence rate of the robustness margin in a non-linear model. Through empirical simulations, we further demonstrate that this inherent failure mode is pervasive, exhibiting the exact same tight convergence rate across multiple natural network initializations. Our theoretical guarantees are derived via a rigorous analysis of the GD trajectories across the distinct activation patterns of the model. Specifically, we develop tight control over the system's dynamics to bound the trajectory of the decision boundary, overcoming the primary technical challenge introduced by the non-linear nature of the architecture.
Read the full abstract ▾
Machine Learning
Adam Converges Without Any Modification On Update Rules
Yushun Zhang, Bingran Li, Congliang Chen et al. (+2 more)
Adam is the default
algorithm for training neural networks, including large
language models (LLMs). However, \citet{reddi2019convergence} provided an example that Adam diverges, raising concerns for its deployment in AI model training. We identify a key mismatch between the divergence example and practice: \citet{reddi2019convergence} pick the problem after picking the hyperparameters of Adam, i.e., $(\beta_1,\beta_2)$; while practical applications often fix the problem first and then tune $(\beta_1,\beta_2)$. In this work, we prove that Adam converges with proper problem-dependent hyperparameters. First, we prove that Adam converges when $\beta_2$ is large and $\beta_1 < \sqrt{\beta_2}$. Second, when $\beta_2$ is small, we point out a region of $(\beta_1,\beta_2)$ combinations where Adam can diverge to infinity. Our results indicate a phase transition for Adam from divergence to convergence when changing the $(\beta_1, \beta_2)$ combination. To our knowledge, this is the first phase transition in $(\beta_1,\beta_2)$ 2D-plane reported in the literature, providing rigorous theoretical guarantees for Adam optimizer. We further point out that the critical boundary $(\beta_1^*, \beta_2^*)$ is problem-dependent, and particularly, dependent on batch size. This provides suggestions on how to tune $\beta_1$ and $\beta_2$: when Adam does not work well, we suggest tuning up $\beta_2$ inversely with batch size to surpass the threshold $\beta_2^*$, and then trying $\beta_1< \sqrt{\beta_2}$. Our suggestions are supported by reports from several empirical studies, which observe improved LLM training performance when applying them.
Read the full abstract ▾
All authors Yushun Zhang, Bingran Li, Congliang Chen, Zhi-Quan Luo, Ruoyu Sun
Machine Learning
Learning from Synthetic Data Improves Multi-hop Reasoning
Anmol Kabra, Yilun Yin, Albert Gong et al. (+6 more)
Reinforcement Learning (RL) has been shown to significantly boost
reasoning capabilities of large
language models (LLMs) in math, coding, and multi-hop
reasoning tasks. However, RL fine-tuning requires abundant high-quality verifiable data, often sourced from human annotations, generated from frontier LLMs, or scored by LLM-based verifiers. All three have considerable limitations: human-annotated
datasets are small and expensive to curate, LLM-generated data is
hallucination-prone and costly, and LLM-based verifiers are inaccurate and slow. In this work, we investigate a cheaper alternative: RL fine-tuning on rule-generated synthetic data for multi-hop
reasoning tasks. We discover that LLMs fine-tuned on synthetic data perform significantly better on popular real-world question-answering
benchmarks, despite the synthetic data containing only fictional knowledge. On stratifying performance by question difficulty, we find that synthetic data teaches LLMs to compose knowledge – a fundamental and generalizable
reasoning skill. Our work highlights rule-generated synthetic
reasoning data as a free and scalable resource to improve LLM
reasoning capabilities.
Read the full abstract ▾
All authors Anmol Kabra, Yilun Yin, Albert Gong, Kamilė Stankevičiūtė, Dongyoung Go, Johann Lee, Katie Z. Luo, Carla P. Gomes, Kilian Q. Weinberger
Machine Learning · Cross-listed from cs.CV
A Detection-Gated Pipeline for Robust Glottal Area Waveform Extraction and Clinical Pathology Assessment
Harikrishnan Unnikrishnan and Rita Patel
We present a fully automated, two-stage modular glottal area
segmentation framework for high-speed videoendoscopy (HSV) designed for accuracy, generalizability, and real-time playback. Our detection-gated pipeline combines a YOLOv8n glottis localizer with a U-Net segmenter; the localizer defines a tight crop to ensure a consistent field of view and gates the output to reduce spurious
segmentations during glottal closure. The models were trained on the GIRAFE (N=600) and BAGLS (N=55,750)
datasets. Cross-
dataset portability was evaluated by benchmarking GIRAFE-trained models on the BAGLS test set without fine-tuning. In these evaluations, the pipeline achieved a Dice Similarity Coefficient (DSC) of 0.745 (87% of the in-domain ceiling). On in-distribution test sets, the system achieved DSCs of 0.81 (GIRAFE) and 0.856 (BAGLS), outperforming or competing with state-of-the-art methods. An exploratory clinical study of 40 subjects demonstrated that the glottal area Coefficient of Variation (CV distinguished healthy from pathological function (p=0.006). The system processes ~35 frames per second on commodity hardware, enabling interactive clinical review. This design supports uniform extraction of laryngeal kinematic measures across varying acquisition settings. Code, weights, and software are available at https://github.com/hari-krishnan/openglottal.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.DB
GenDB: The Next Generation of Query Processing – Synthesized, Not Engineered
Jiale Lao and Immanuel Trummer
Traditional query processing relies on engines that are carefully optimized and engineered by many experts. However, new techniques and user requirements evolve rapidly, and existing systems often cannot keep pace. At the same time, these systems are difficult to extend due to their internal complexity, and developing new systems requires substantial engineering effort and cost. In this paper, we argue that recent advances in Large
Language Models (LLMs) are starting to shape the next generation of query processing systems. We propose using LLMs to synthesize execution code for each incoming query, instead of continuously building, extending, and maintaining complex query processing engines. As a proof of concept, we present GenDB, an LLM-powered agentic system that generates instance-optimized and customized query execution code tailored to specific data, workloads, and hardware resources. We implemented an early prototype of GenDB that uses Claude Code
Agent as the underlying component in the multi-
agent system, and we evaluate it on OLAP workloads. We use queries from the well-known TPC-H
benchmark and also construct a new
benchmark designed to reduce potential data leakage from LLM training data. We compare GenDB with state-of-the-art query engines, including DuckDB, Umbra, MonetDB, ClickHouse, and PostgreSQL. GenDB achieves significantly better performance than these systems. Finally, we discuss the current limitations of GenDB and outline future extensions and related research challenges.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
From Pixels to Patches: Pooling Strategies for Earth Embeddings
Isaac Corley, Caleb Robinson, Inbal Becker-Reshef et al. (+1 more)
Geospatial foundation models increasingly expose pixel-level
embedding products that can be downloaded and reused without access to the underlying encoder. In this setting, downstream tasks with patch- or region-level labels require a post-hoc aggregation step that maps dense pixel
embeddings to a single representation. The default choice, mean pooling, discards within-patch variability and can underperform under spatial distribution shift. To study this setting, we introduce EuroSAT-Embed: 81,000
embedding GeoTIFFs derived from three foundation models: AlphaEarth, OlmoEarth, and Tessera. Using these fixed
embedding products, we
benchmark 11 training-free pooling methods and 2 train-set-fitted baselines under both random and geographically disjoint test splits. Richer pooling schemes reduce the geographic generalization gap by over 50% relative to mean pooling and improve accuracy by up to 6% on spatial splits. We recommend a three-tier strategy: (1) mean as a baseline, (2) stats pooling (min/max/mean/std) as the default at 4x the
embedding dimension, and (3) covariance pooling for peak accuracy. Across all three
embedding products, simple distributional statistics improve spatial-split performance over mean pooling.
Read the full abstract ▾
All authors Isaac Corley, Caleb Robinson, Inbal Becker-Reshef, Juan M. Lavista Ferres