cs.LG · 2026-08-12 · No. 82
Machine Learning, 2026-08-12.
50 new papers in cs.LG. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
50 entries-
01
Beyond a Bag of Features: Set-Level Instability in Sparse Autoencoders
Nikolai Bolik, Lennart Stöpler, Artur Andrzejak
cs.LG · cs.CL
Shani et al. (2026) show that LLM representations broadly recover human category boundaries, while failing to reflect fine-grained typicality structure. Their analysis uses cosine similarity over dense model representations. We revisit their approach using overlap over active sparse autoencoder (SAE) latent sets as a more interpretable similarity measure. We first verify that this set-level measure is meaningful: SAE latent sets can recover...
-
02
Hierarchical Empirical-Bayes Naive Bayes: Minimax Smoothing and Calibration with AODE Extension
Nguyen Thai Anh, Truong Viet Vu, Tran Thien Thanh, Vo Nguyen Quoc Bao, Ngo Hoang Tu
cs.LG
The Naive Bayes (NB) classifier remains a standard choice for categorical data, yet its widely used smoothing rules, such as Laplace, Lidstone, Krichevsky-Trofimov, and the $m$-estimate, all prescribe a fixed smoothing strength that ignores feature cardinality, sample size, and class imbalance, inducing a non-vanishing bias on modern high-cardinality tabular data. We propose hierarchical empirical-Bayes Naive Bayes (HEB-NB), in which each...
-
03
DACRI: Decision-Aware Causal Intervention Ranking for Critical Supply Chains
Shiqi Huang, Jiani He, Dingyan Shang, Yihua Xu, Jize Li, Yan Lyu, Lashimi Muraleedharan Nair
cs.LG
Detecting or attributing a supply-chain disruption is not the same as selecting the intervention that maximizes recoverable net value. We present CriticalSCM-Bench v1, a controlled synthetic benchmark with causal ground truth, paired factual/counterfactual rollouts, and an explicit net-value objective. Relative to a full-information train-selected static benchmark, LambdaMART improves median normalized net value by 5.7--16.2\%, with paired...
-
04
A Recommendation System Approach for Interference-Robust Sensor Subset Selection
Kaan Buyukkalayci, Kyle Pak, Merve Karakas, Christina Fragouli
cs.LG
This paper develops a method for sensor-subset selection for tracking. Prior work showed that low-cost acoustic Received Signal Strength Indicator (RSSI) measurements can be used to recommend subsets of sensor nodes whose expensive sensing modalities, such as cameras, can achieve high tracking accuracy. While efficient, RSSI-based approaches are challenged by acoustic interference. We propose a recommendation-system-inspired framework that...
-
05
Two-stage Odd Residual Flows for Mean-Preserving Probabilistic Time Series Forecasting
Kiran Madhusudhanan, Christian Klötergens, Lars Schmidt-Thieme, Vijaya Krishna Yalavarthi
cs.LG · cs.AI
Probabilistic forecasting plays an essential role in risk-sensitive decision-making, particularly in long-horizon settings. However, existing approaches often face a fundamental trade-off between distributional flexibility and accurate mean prediction. Traditional parametric methods, such as Mean Variance Estimation (MVE), can suffer from degraded point accuracy when trained under joint Negative Log-Likelihood (NLL) objectives, while...
-
06
Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives
Songlin Du, Xiaoyong Lu, Zeyu Wu, Xiaobo Lu, Guobao Xiao, Bin Fan, Jiayi Ma, Takeshi Ikenaga
cs.LG · cs.CV
Cross-view feature matching aims to establish reliable correspondences across images with large viewpoint variations. Over the past decade, the field has evolved from task-specific models toward increasingly unified and generalizable correspondence models, with recent progress further driven by the emergence of vision foundation models (VFMs). Despite these advances, existing studies remain highly diverse in their problem formulations, model...
-
07
Batch Size or Negatives? A Selection Rule for Memory-Constrained Recommender Training
Artyom Sabitov, Daniil Volkov, Alexey Zaytsev
cs.LG
Large-scale neural recommender systems are typically trained with a softmax cross-entropy objective over the full item vocabulary. For a typical large number of possible items $K$, the final classification layer dominates memory, requiring $O(nK)$ logits and gradients to materialize for a batch of $n$ examples. Sampled softmax reduces this cost by restricting the objective to only $k \ll K$ candidate negative items, resulting in an $O(nk)$...
-
08
Uncertainty-Aware Deep Learning for Genomics Applications: Insights from an Empirical Study
Sepideh Saran, Mahsa Ghanbari, Uwe Ohler
cs.LG
Deep learning models have emerged as the standard computational tool for a wide range of applications in genomics. Yet, uncertainty quantification (UQ) -- and more specifically, the reliability of different uncertainty estimates in this domain -- has received little systematic attention. This work presents an empirical analysis of UQ in deep learning models, focusing on genomics applications. In a series of experiments, we contrast Deep...
-
09
Efficient Hypergradient Descent for Inverse Reinforcement Learning
Nikita Sevriukov, Anna Barabanova, Uliana Gagarina, Karina Ivanova, Sofiia Kasaeva, Ilya Levin, Marina Sheshukova
cs.LG · stat.ML
Inverse reinforcement learning (IRL) aims to recover a reward function under which the resulting policy reproduces the behavior observed in expert demonstrations. A natural approach is to formulate IRL as a bilevel optimization problem, in which the inner level corresponds to policy optimization under the learned reward and the outer level measures the discrepancy between the induced policy and expert data. However, this formulation is...
-
10
ReRound: Reconstructive Rounding to Resolve Midpoint Ambiguity in Calibration-Free LLM Quantization
He-Yen Hsieh, H. T. Kung
cs.LG · cs.CL
ReRound (Reconstructive Rounding) is a post-training quantization method that addresses the midpoint ambiguity inherent in standard round-to-nearest (RTN) schemes when quantizing weights near the centers of quantization intervals. Starting from a pretrained LLM, ReRound trains a conditional diffusion model to produce continuous reconstructions of low-bit weights for the LLM. These reconstructed weights act as a guidance signal to disambiguate...
-
11
Mapping and Measuring the Behavioral Evolution of Large Language Models
Dong Qiao, Chris Ding, Jicong Fan
cs.LG · cs.CL
Benchmark leaderboards summarize how well a language model performs, but not how its behavior relates to that of other models or changes across generations. We characterize the output behavior of 32 models from six families using their responses to a shared bank of 10{,}000 prompts. After embedding each response, we construct three complementary sentence-level dissimilarities: an aligned mean per-prompt distance, which is a pseudometric on...
-
12
Derivative Computation in PINNs: Automatic Differentiation, Finite Differences and Beyond
Maciej J. Mikulski, Tadeusz Uhl
cs.LG · math.NA · physics.comp-ph
We systematically investigate finite-difference (FD) derivative computation in Physics-Informed Neural Networks (PINNs) as an alternative to automatic differentiation (AD). On three benchmark PDEs we show that, with a properly calibrated step size, FD matches AD in accuracy on every problem while running faster across the full tested batch-size range and using substantially less GPU memory, and that a stochastic variant we propose outperforms...
-
13
DEFT: Data-Efficient Frequency-domain Top-k Sampling via Inverse Discrete Fourier Transform for Spatiotemporal Dynamical Systems Modeling
Hengbo Xiao, Jiale Liu, Jiahao Song, Guannan He
cs.LG
Modeling spatiotemporal dynamical systems governed by partial differential equations (PDEs) poses two major challenges: it either requires expensive physics-based simulators that entail iterative numerical solving at high computational cost, or it depends on abundant training data, yet purely data-driven models often generalize poorly to downstream dynamic operating conditions. We propose DEFT, a frequency-domain data sampling method that...
-
14
GARLIC: Graph Attention-based Relational Learning of Multivariate Time Series in Intensive Care
Ruirui Wang, Yanke Li, Manuel Günther, Diego Paez-Granados
cs.LG
Healthcare data, such as Intensive Care Unit (ICU) records, comprise heterogeneous multivariate time series sampled at irregular intervals with pervasive missingness. However, clinical applications demand predictive models that are both accurate and interpretable. We present our Graph Attention-based Relational Learning for Intensive Care (GARLIC) model, a novel neural network architecture that imputes missing data through a learnable...
-
15
Physics-informed Diffusion Generative Model for Time-Series Data Synthesis in Dynamic Systems
Haiteng Wang, Yunfei Zhu, Tao Wang, Yikang Li, Jiabao Dong, Xiaoge Zhang, Lei Ren
cs.LG
Industrial time-series signals, such as turbine temperature and rotational speed in aero-engines, are essential for monitoring the health and operational status of complex dynamical systems. However, collecting such data is often limited by harsh environments (e.g., high temperature and high pressure) and the high cost of experimental testing. To address this challenge, we introduce PhysDGM, a stepwise physics-embedded diffusion generative...
-
16
ReOrder-OPD:Reliability-Aware Prompt Ordering for On-Policy Distillation
Ximo Zhu, Ruiqi Liu, Rong Wang, Ping Wu, Xiang Zheng, Wenzhuo Xu, Xubin Yao, Zhiyuan Yan, Bo Li, Jun Gao, Xiaolei Lv
cs.LG
On-policy distillation (OPD) applies token-level teacher supervision to student-generated trajectories, but this supervision is not always reliable. Existing methods use local confidence or teacher-student agreement to weight, filter, or truncate the sampled trajectory. These signals do not directly determine whether the teacher can continue a student prefix to a correct answer, and trajectory-level interventions can conflate one rollout's...
-
17
Partially Observable Learning for Multi-Platform Dispatch Optimization
Fengming Yao, Man Luo
cs.LG
Instant delivery platforms have become a critical component of urban logistics, increasingly relying on crowdsourced couriers to fulfill highly dynamic orders. In real-world systems, couriers are not exclusive to a single platform and may concurrently serve multiple platforms, while each platform can only observe its own orders and couriers' interactions due to privacy and operational constraints. This results in a multi-platform dispatch...
-
18
Benchmarking Time Series Generation Methods for Privacy-Preserving Forecasting
Luis Amorim, Vitor Cerqueira, Moises Santos, Paulo J. Azevedo, Carlos Soares
cs.LG
Time series forecasting in privacy-sensitive domains often requires training models on released data rather than original observations. Synthetic time series generation has been developed primarily for data augmentation, where generated series supplement the original training set. How well these methods perform when fully replacing the original data - and how much privacy risk the released series carry - remains underexplored. We address this...
-
19
Optimistic Rates for Multiclass PAC Learning
Xiaoyu Li, Andi Han, Jiaojiao Jiang, Junbin Gao
cs.LG · stat.ML
Worst-case multiclass bounds do not become smaller when the best classifier is already nearly correct: what is missing is an optimistic rate, a guarantee whose fluctuation scales with the oracle risk itself. For a class of Natarajan dimension $d_N$ and Daniely-Shalev-Shwartz dimension $d_{DS}$, the optimal excess risk is known at the two endpoints ($d_{DS}/n$ realizable, $\sqrt{d_N/n}+d_{DS}/n$ agnostic [HMZ24, CEH+26, Pab26]) and open in...
-
20
Can Bayesian Optimization Efficiently Find a Strong Single Expert in Neural Thickets?
Nigel Bastian Cendra, Abdelhamid Ezzerg, Fernando Julio Cendra, Jeremias Knoblauch, Jakob Zeitler
cs.LG
Gradient-free post-training has emerged as a compelling alternative to gradient-based optimization for large language models (LLMs), but existing approaches remain costly. We ask whether structured search can identify a strong single expert under a modest evaluation budget. Motivated by evidence that useful weight updates lie in low-dimensional subspaces, we apply Bayesian optimization within a random linear embedding of weight space. Our...
-
21
FiGuRO: Intrinsic Dimension Estimation for Multi-Modal Data
Viktoria Schuster, Sana Tonekaboni, Caroline Uhler
cs.LG
Determining the complexity, or Intrinsic Dimension (ID), of data is fundamental to efficient and interpretable representation learning. This is particularly challenging in multi-modal settings when trying to learn disentangled representations for shared and private information. Existing techniques leave a critical gap: they are often static, uni-modal, or in the case of contrastive methods, adapt only to the shared ID implicitly. We introduce...
-
22
Diffract: Spectral View of LLM Domain Adaptation
Nikita Borodin, Maria Krylova, Artem Zabolotnyi, Dmitry Aspisov, Egor Shikov, Nikita Tyuplyaev, Oleg Travkin, Roman...
cs.LG
We study continual pre-training (CPT) as a mechanism for adapting general-purpose large language models to specialized domains: mathematics, instruction, code, and natural text. Using singular value decomposition of weight matrices, we find that CPT leaves singular value spectra largely invariant, with adaptation driven mainly by changes in singular vectors. An analysis of attention-head projection matrices reveals strong, domain-dependent...
-
23
TACTICL: Task-Aware Compression of Tabular ICL Models
Mykhailo Koshil, Matthias Feurer, Katharina Eggensperger
cs.LG · cs.AI
The strong performance of foundation models for tabular tasks comes at substantial inference costs. Distilling models into task-specific architectures reduces model size and computational demands but also sacrifices in-context adaptability. Here we introduce TACTICL, an automated task-aware compression framework for tabular in-context learning models that jointly prunes transformer layers and replaces them with lightweight adapters trained on...
-
24
MoE Proxy Models for Low-Cost Failure Reproduction and Diagnosis in LLM RL Post-Training
Yikai Wang, Chuansai Zhou, Yuhang Zhou, Weiqiang Wu, Cong Wu, Yue Deng, Ben Feng, Mingming Zhu, Beirong Zhou, Zhibin...
cs.LG
Reinforcement learning (RL) post-training of large language models (LLMs) is computationally intensive and involves complex system pipelines with substantial debugging overhead. In practice, factors such as framework adaptation, numerical precision, and operator implementation can cause failures, including gradient overflow and loss divergence. Reproducing such failures directly on large models requires considerable time and computational...
-
25
Path Integral Value Matching for Linear Quadratic Stochastic Optimal Control
Bangyan Liao, Chenglei Yu, Yuchen Yang, Chuanrui Wang, Zhisheng Song, Peidong Liu, Tailin Wu
cs.LG · math.OC · stat.ML
Linear Quadratic Stochastic Optimal Control (LQ-SOC) establishes a fundamental framework for steering noisy dynamical systems and has recently gained renewed interest in the machine learning community. However, current state-of-the-art policy-based methods suffer from prohibitive computational costs and instability due to their heavy reliance on full-trajectory simulation. To overcome these limitations, we propose a paradigm shift toward a...
-
26
Long-Time Trajectory Approximation via SA-NODEs: Model Predictive and Floquet Strategies
Ziqian Li, Nikolaos M. Matzakos
cs.LG · math.NA
We study the approximation of dynamical systems by semi-autonomous neural ordinary differential equations (SA-NODEs) over long time horizons. For a single network trained on the whole horizon, the available error bound deteriorates double exponentially in the horizon length. We develop two training strategies that avoid this barrier, each built on a reset of the state. The model predictive strategy partitions the horizon adaptively and...
-
27
SQuaT: Self-Supervised Knowledge Distillation via Student-Aware Quantized Teacher Features
HyeonJun Lee, Hyeonsik Jo, Jinwoo Chung, Jangho Kim
cs.LG
Quantization-Aware Training (QAT) enables the deployment of quantized models with minimal accuracy degradation. However, in practical scenarios, training labels are often unavailable due to privacy, copyright, or cost constraints. Knowledge Distillation (KD) is a common approach to address this challenge, but we observe that prior work combining QAT with KD suffers from a fundamental limitation: during distillation, the range mismatch between...
-
28
Your LLM, Your Style: Behavioral Mode Axes for LLM Behavioral Control
Haoze Liu, Run Liu, Haiying Xu, Jiahui Han, Siyuan Fang, Siyu Yan, Huiqi Deng, Guanchu Wang, Na Zou
cs.LG · cs.AI · cs.CL · cs.HC
Large language models (LLMs) increasingly act in interactive settings where their behavioral styles affect user experience, safety, and downstream decision making. Existing LLM personality studies largely rely on self-report questionnaires administered in first-person settings, making the resulting profiles sensitive to surface elicitation choices and poorly grounded in concrete model behavior. In this work, we introduce a situated...
-
29
ProTAGAD: A Foundation Model for TAG Anomaly Detection with Decoupled Topological and Textual Prototypes
Ziyan Wang, Liwen Wu, Cheng Xie, Song Gao, Zhenli He, Xin Jin
cs.LG · cs.AI
Text-Attributed Graphs (TAGs), endowed with abundant textual content along with topological structures, have emerged as a versatile backbone for real-world anomaly detection spanning large language model security, social network moderation, and cyber threat identification. Unlike conventional Graph Anomaly Detection (GAD), which relies primarily on structural irregularities, TAG anomaly detection must jointly leverage both topological...
-
30
Optimize Cheap, Deploy Strong: Cost-Aware Cross-Tier Transfer for Evolutionary Optimization
Tal Oved, Roi Pony, Oshri Naparstek, Udi barzelay
cs.LG · cs.AI · cs.CL · cs.NE
Evolutionary optimization of LLM prompts and agentic programs (e.g., GEPA) is dominated by fitness evaluation: scoring each candidate runs an answering LLM over a validation set, so the evaluator's price tier dictates total search cost. We restructure that search by decoupling the three roles an LLM plays, running the high-volume answering role on the cheapest tier, reserving a strong model for the rare reflection/variation operator, then...
-
31
IADD-TR: Intervention-Aware Dynamics Decoupling with Targeted Regularization for Model-Based Reinforcement Learning
Zefeng Liang, Jie Qiao, Ruichu Cai, Weilin Chen, Zhifeng Hao
cs.LG
Model-based reinforcement learning (MBRL), which learns environment dynamics to generate synthetic experience, is a promising approach to sample-efficient decision making. Numerous methods have been developed to improve dynamics prediction and policy optimization for MBRL through uncertainty estimation, model regularization, and conservative value learning. However, these methods typically treat the transition model and critic as monolithic...
-
32
ProbGuard: Calibrated Safety Risk Estimation from LLM Output Distributions
Xinzhe Huang, Biwu Yao, Kedong Xiu, Mengnan Zhao, Di Wang, Puning Zhao, Tianhang Zheng
cs.LG
Recent research on Large Language Model (LLM) safety has widely adopted guardrails to identify unsafe LLM outputs. Existing guardrails typically formulate safety assessment as a deterministic classification task, mapping a discrete token sequence to a discrete safety label. However, this paradigm has two limitations: First, safety assessment is inherently an uncertain problem, particularly during the early generation state. Second, relying...
-
33
Pair-Centric Graph Rewiring for Over-Squashing via Optimal Transport-Guided Communication Alignment
Yan Wang, Chuan-Xian Ren
cs.LG
Message-passing neural networks (MPNNs) often struggle when task-relevant information is distributed across distant regions of a graph, since local propagation must compress remote signals through limited structural interfaces. Graph rewiring provides a structural response to over-squashing. Most existing methods rely on edge-level bottleneck scores or graph-level connectivity surrogates. With a limited rewiring budget, the key question is...
-
34
Compute-Optimal Is Not Cluster-Optimal: Systems-Aware Scaling for Sparse Mixture-of-Experts
Soumajyoti Sarkar, Yuxin Tang, Sheng Zha
cs.LG · cs.AI
In large-scale pretraining, the algorithm, architecture, and systems decisions are conventionally made in disconnected stages. A scaling law stage selects an architecture and training recipe, optimizing loss under compute constraints, and a separate systems stage then optimizes the implementation for hardware efficiency. In this work, we develop MOSAIC, which formulates model architecture and systems co-design as an optimization problem....
-
35
$β$-VAEs as Effective Theories: Tolerance-Dependent Dimension
Johannes Hirn
cs.LG
In a $β$-VAE, increasing the regularization strength acts as a spectral cutoff by collapsing low-utility latent coordinates. In the linear Gaussian VAE, the collapse order matches the ranking of reconstruction utilities exactly, because both are set by the PCA spectrum. We ask which parts of this picture survive in fully connected nonlinear VAEs trained on WorldClim. We find that nonlinear interactions shift and broaden collapse onsets, so...
-
36
BREAD: Baseline-Referenced Explanations for Anomaly Diagnosis
Jiaqi Qiu, Rob Goedhart, Jannis Kurtz, Inez M. Zwetsloot
cs.LG
Artificial Intelligence (AI)-based prospective anomaly detection methods are increasingly deployed in high-dimensional and nonlinear settings. Among these approaches, AI-based statistical process monitoring (SPM) is widely used, providing a structured framework for prospective monitoring. Once an anomaly is detected, a diagnosis method is needed to identify the features driving the flagged observation away from normal behaviour. Traditional...
-
37
MARCO: Click-Intent Decomposition for Calibrated Ads Conversion Prediction
Shiwen Shen, Xiru Huang, Liang Luo, Jianbo Sun, He Lyu, Zihang Fu, Ivonne Xu, Zhizhuo Li, Zhengyu Zhang, Pei-Ju...
cs.LG
Not all clicks are equal. Industrial ads ranking decouples conversion probability into click-through rate (CTR) and post-click conversion rate (CVR), yet treats every click as the same event. In reality, users provide a free, self-generated signal of intent through their physical UI interactions. Different click types on the same ad exhibit a 4-fold difference in actual conversion rates. By conflating these signals, the standard CVR model...
-
38
Retrieval-Corrected Conformal Prediction for Time Series
Sangjin Jin, Kangmin Kim, Junhyeong Lee, Yongjae Lee
cs.LG · cs.AI
Conformal prediction (CP) provides distribution-free prediction intervals for fixed forecasters, but its standard calibration procedure is often inefficient for time series data, where forecast errors are temporally dependent and change across time and operating conditions. Recent time series CP methods improve local calibration using recent, weighted, or localized residuals. Yet local calibration can remain indirect, since broad residual...
-
39
Robust Multi-Agent Bandits with Heavy-Tailed Rewards and Information Asymmetry
Daphne Feng, Ricardo Parada, Lily Jiang, Sophia Yi, William Chang
cs.LG · cs.AI
The multi-armed bandit problem is a central framework in sequential decision-making, extensively studied under sub-Gaussian reward assumptions. However, real-world applications often involve heavy-tailed reward distributions and decentralized, information-asymmetric interactions. We study multi-agent multi-armed bandits with heavy-tailed rewards under three information-asymmetry regimes: unobserved actions with common rewards, observed...
-
40
Coordinating the Unknown Lipschitz Constant in Multiplayer Bandits
Ricardo Parada, Chenzhang Zhao, William Chang
cs.LG · cs.AI
Motivated by decentralized applications, we study cooperative multi-agent bandits in continuous (Lipschitz) action spaces when the Lipschitz constant is unknown. We consider three information structures: (A)~unobserved actions with common rewards, (B)~observed actions with independent rewards, and (C)~unobserved actions with independent rewards. In each case we design and analyze an algorithm that estimates the Lipschitz constant, chooses a...
-
41
Exploration-Driven Personalized Federated Reinforcement Learning via Intrinsic Motivation
Md Rafid Islam, Rafsan Jany, Zahid Hasan, Ratun Rahman
cs.LG · cs.AI
Personalized Federated Reinforcement Learning (PFRL) takes a decentralized approach to storing and accessing information based on past experiences while keeping each client's data private during the learning of each client's policy. Many current methods for PFRL rely heavily on exploiting existing reinforcement learning reward signals to derive an optimal policy for each client, thereby neglecting exploration in non-stationary or...
-
42
Critic-Free Pretraining for Efficient Online Reinforcement Learning Fine-Tuning
Daoyi Li, Yixian Zhang, Chao Yu, Wenbo Ding, Yu Wang
cs.LG · cs.AI
Offline-to-online (O2O) reinforcement learning aims to leverage policies pretrained on static datasets while improving them through online interaction. However, directly reusing an offline-trained critic can hinder online fine-tuning: as the policy and data distribution change rapidly, value estimates inherited from offline training may become misaligned with the online environment, leading to inaccurate policy improvement and inefficient...
-
43
A Joint-Distribution Route to Fair Representations with Continuous Sensitive Attributes
Yijin Ni, Xiaoming Huo
cs.LG · stat.AP
Fair representation learning with a continuous sensitive attribute $S$ requires a representation $Z$ that is statistically independent of $S$. Existing criteria, including generalized demographic parity, the expectation of integral probability metrics (EIPM), and mutual information, enforce this independence by averaging a per-value discrepancy between the conditional law $P_{Z \mid S=s}$ and the marginal $P_Z$ over the law of $S$. This...
-
44
Detecting an Effect Is Not Learning to Act on It: A Reward-SNR Floor for LLM Acquisition Agents
Ying Yuan
cs.LG · cs.CL · cs.IR
Many pipelines can pay a per-example cost to acquire an auxiliary, model-derived observation -- an LLM's structured reasoning, a slow oracle, an expensive measurement -- and then must decide when the acquired signal is worth using. Our thesis is a distinction that is easy to miss: detecting that such a signal helps on average is not the same as learning to act on it per instance, and a reward-SNR floor governs when the second is even...
-
45
Do Time-Series Forecasters Use the Right History: Recoverability, Recovery, and Functional Use of Temporal Delays
Qipeng Qian, Yuntao Qian
cs.LG
Forecast accuracy does not tell us which past inputs produced a prediction. We separate three questions for time-series models with known delay structure: can the true delay be recovered from the observed data, does the model report it, and does the forecast actually use the same history? We first derive input-conditioned recoverability measures that separate intrinsic ambiguity from model error. We then prove that a delay report can become...
-
46
Actionable Hallucination Detection: Translating Latent Uncertainty into Agentic Critique
Sanidhya Vijayvargiya, Rahul Lokesh
cs.LG · cs.AI
Large Language Models (LLMs) deployed as AI agents frequently exhibit user specification-grounding failures, executing hallucinated, undesired actions to force a resolution rather than expressing uncertainty. Existing detection methods fail to provide actionable, real-time correction as they either do not localize the hallucinations, or incur prohibitive inference latency. We introduce the Latent Critic, a lightweight low-rank adapter (LoRA)...
-
47
TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling
Yanyu Ren, Xizheng Wang, Xiao Liu, Bowen Lv, Hanchen Zhang, Shudan Zhang, Hanyu Lai, Shuai Wang, Li Chen, Dan Li, Jie Tang
cs.LG · cs.DC
Reinforcement learning (RL) for large language models is moving toward multi-turn agentic workloads, where rollout tasks repeatedly pause for external environments, resume with growing contexts, and finish at highly variable times. In this setting, RL training goodput, measured by training throughput, matters more than raw GPU occupancy: GPU waiting and repeated prefill recomputation are pure overhead. We present TideRL, a readiness-aware...
-
48
Do Judges Behave Like Algorithms?
Riya Manchanda, Eric Chen, Chloe Zhu, Cynthia Rudin, Brandon Garrett, Songman Kang
cs.LG
What if judges already behave like algorithms? As artificial intelligence and algorithms are deployed in many settings, including the judicial system, many have debated whether judges should be allowed to rely on them. Instead, we ask whether judges follow predictable, algorithmic-like rules already. If judges already follow consistent, formula-like rules based on discrete and static factors such as criminal history, age, and charge type,...
-
49
ELVAE: Evidential Learning-Based Variational Autoencoder for Uncertainty-Aware Generation
Ge Wang
cs.LG · cs.AI
Variational autoencoders generate samples from probabilistic latent representations but do not distinguish uncertainty about the latent location from variability around it. We formulate ELVAE, an evidential learning-based VAE in which each latent coordinate is governed by an input-dependent normal-inverse-gamma posterior. This hierarchy yields an explicit latent-location uncertainty that can be used during generation, not merely reported...
-
50
Share First, Route What Remains: A Unified Framework for Token-Adaptive MoE Computation
Gongli Zhang, Zhulin Liu, C. L. Philip Chen
cs.LG · cs.CL · cs.CV
Mixture-of-experts (MoE) models have recently moved beyond routing a fixed number of complete experts. Shared-expert designs preserve reusable knowledge, fine-grained methods vary computation within experts, and dynamic routers adapt the number of active experts. Yet these decisions are usually made independently, overlooking a basic dependency: extracting reusable computation changes both what remains and how much expert capacity the...
This edition is part of The Daily Abstract — cs.LG archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.