cs.LG · 2026-09-24 · No. 123
Machine Learning, 2026-09-24.
65 new papers in cs.LG. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
65 entries-
01
Even Sharper Bounds for Transductive Learning and Its Applications
Yingzhen Yang
cs.LG · cs.IT · math.ST
We introduce Sharper Transductive Local Complexity (STLC), a localized complexity method for transductive learning under uniform sampling without replacement. The construction starts from a Bernstein-type concentration inequality for the supremum of the test--train empirical process. Its proof uses the modified log-Sobolev inequality for the swap walk and a two-parameter entropy closure. A peeling argument with a surrogate localization...
-
02
Order-Invariant Answers, Order-Sensitive Representations in Mathematical Reasoning
Zhixu Silvia Tao
cs.LG · cs.AI · cs.CL · cs.SC
Reordering a set of mathematical rules without changing its meaning should preserve the correct answer, but must a model's internal representations stay invariant too? We investigate this question using synthetic multi-step function-composition problems, each presented under multiple rule orderings with the same correct answer. We measure accuracy and permutation signal-to-noise ratio (SNR), which quantifies how distinctly ordering patterns...
-
03
Minimal-Norm Univariate Two-Layer ReLU Classification: Exact Solutions and Global Optimality with Skip Connections
Karolina Drabik, Ben Lewis, Antoni Puch, Etienne Boursier, Piotr Hofman, Matthias Englert, Ranko Lazić
cs.LG
We study minimal-norm interpolation and $\ell_2$-regularized logistic-loss minimization for binary classification by univariate two-layer ReLU networks. We give complete geometric characterizations of the optimal classifiers in function space, resolving how the solutions depend on whether hidden-layer biases are included in the parameter norm. When biases are unpenalized, the minimal-norm interpolators are exactly the continuous...
-
04
Context-Continuous Preference Learning for Exoskeleton Personalization
Sunin Baek, Sungwoo Park, Daekyum Kim
cs.LG · cs.RO
Personalizing exoskeleton assistance across operating conditions is constrained by the time and physical effort required to collect user feedback. We examined whether a user's preference landscape varies smoothly across operating conditions and when this continuity supports learning from limited feedback. We propose Context-Continuous Preference Learning (CCPL), a Gaussian-process preference model that shares observations across nearby...
-
05
Learning Holographic Reduced Representations with Clifford Variational Autoencoders
Mohamed Malek Abid, P. Michael Furlong
cs.LG · cs.AI · cs.NE
Vector Symbolic Algebras project data structures into a hyperdimensional vector space through the application of their vector algebras to randomly generated atomic vector symbols and fractional power encodings of real-valued data. Embedding unstructured data remains an open question. We present \textit{Clifford-VAE}, a variational autoencoder that learns to project data onto a Clifford torus in arbitrary dimensions. Experiments using the...
-
06
Learning Collective Dynamics with Differentiable Gaussian Representations
Jianxiang Ma, Mingfu Zhang, Xiaocui Yang, Yichen Gao, Junzhao Huang, Yuesong Hou
cs.LG
Collective responses depend on individual differences, contact opportunities, and accumulated experience. Learning their dynamics from aggregate counts requires connecting a population's response distribution to both current observations and future behavior. We introduce Differentiable Gaussian Dynamics (DGD), which learns this connection through three components: a Gaussian mixture representing heterogeneous response propensities,...
-
07
Memory Attention
Jiale Kang
cs.LG
Language models typically construct attention values from contextual hidden states, even when some of their content may be reusable across contexts. We investigate whether token-indexed memory can replace the dedicated value projection when complemented by contextual information. We propose Memory Attention (MA), which forms values by combining layer-specific token memory with contextual keys. The memory supplies token-specific...
-
08
When and Where to Trust the Teacher: Unifying On-Policy Distillation and GRPO through Entropy-Calibrated Credit Assignment
Jie Zhang, Jingxiao Yang, Zhehao Huang, Yuhang Liu, Xiaolin Huang
cs.LG · cs.AI
Reinforcement learning with verifiable rewards (RLVR) supervises mathematical reasoning through final-answer correctness, but provides little guidance on individual tokens. On-policy distillation (OPD) supplies dense feedback on student-generated responses, yet teacher preference need not reflect correctness. Recent hybrids combine OPD and verifier-derived advantages or reweight task credit using teacher ratios. However, teacher guidance...
-
09
Resource-Adaptive Stochastic Gradient Descent for Online Linear Programming without Re-solving
Jiameng Lyu
cs.LG · math.OC
The growth of large language model (LLM) inference and search services increases the scale of online linear programming problems, motivating computationally efficient algorithms. We develop resource-adaptive stochastic gradient descent (RASGD) for stochastic online linear programming. The algorithm uses one request and current inventory to update resource prices, requiring O(m) operations for m resources and memory per arrival and no LP or...
-
10
hyperbolix: Hyperbolic Deep Learning in JAX
Timo Klein, Thomas Lang, Yllka Velaj, Sebastian Tschiatschek
cs.LG · cs.MS
We present hyperbolix, an open-source library for hyperbolic deep learning in JAX, built on Flax NNX. To our knowledge, it is the first comprehensive, general-purpose hyperbolic deep learning library in JAX. It includes six manifolds with a common interface: Euclidean space, the Poincaré ball, the hyperboloid, the $κ$-stereographic model, mixed-curvature product spaces, and the proper velocity space. We implement layer families that cover...
-
11
Log-Depth Recurrent Language Modeling
Yiqin Wang, Nuri Cingillioglu, Charles Pert
cs.LG · cs.CL
Language modeling using Transformers has become commonplace despite their fixed computational depth and quadratic runtime with respect to input tokens. Recurrent models on the other hand offer linear depth but no parallel execution. In this work, we extend balanced-tree recursive operators from sequence encoding to autoregressive prediction, enabling all prefix representations to be computed with logarithmic depth and linear runtime. Our...
-
12
Support-Compiled Feature Folding: More Evidence at Lower Memory Across Tabular Foundation Models
Tian Zhou, Beverly Jin, Xue Wang, Linxiao Yang, Wenwei Wang, Bingqing Peng, Mengni Ye, Jinjie Gu, Liang Sun
cs.LG
Tabular foundation models face a feature-side scaling dilemma: full-width pairwise mixing grows quadratically with the number of columns, whereas feature selection saves memory by discarding evidence. We introduce Support-Compiled Feature Folding (SCFF), a training-free inference framework that resolves this dilemma without changing the frozen backbone. SCFF routes support-ranked features through bounded leaves of the native feature encoder,...
-
13
Transferable Evidence Reconstruction for Longitudinal Glucose Representations
Tian Zhou, Bingqing Peng, Linxiao Yang, Wenwei Wang, Mengni Ye, Beverly Jin, Zuyi Zhu, Jinjie Gu, Liang Sun
cs.LG
Long physiological recordings contain many routine measurements, while predictive information is often concentrated in rare events, sustained burden, and recurring temporal patterns. Masked autoencoding recovers measurements; contrastive learning aligns views. We study self-supervision that explicitly prioritizes structured signal evidence. We introduce transferable evidence reconstruction (TER), which constructs evidence from unlabeled...
-
14
Geospatial embeddings detect old-growth forests but buffered spatial validation narrows their advantage over Sentinel features
Thomas Ratsakatika, Mihai Zotta, Srinivasan Keshav, Emily R. Lines
cs.LG · cs.CV · eess.IV
Old-growth forests develop over centuries under minimal anthropogenic disturbance, producing structurally complex and biodiverse stands. In Europe, protecting them requires mapping that is accurate for individual forest parcels yet deployable continent-wide. Geospatial foundation model (GFM) embeddings enable label-scarce land classification, but their value for old-growth detection remains unknown. Here, we map old-growth forests across...
-
15
Confidence Falls Short: Asymmetric Certainty Gains from Optimization Hinder Multimodal Classification
Longfei Huang, Xiangyu Wu, Yang Yang
cs.LG
Multimodal learning (MML) falls into the optimization dilemma due to the modality imbalance phenomenon, leading to suboptimal overall performance in practice. While many attempts primarily focus on balancing the optimization dynamics across modalities to address this issue, we identify a subtle yet critical flaw: optimization yields asymmetric gains in predictive certainty, with the strong modality more confident than the weak one, driving...
-
16
RL Starts before RL: On Policy Distillation for Better Reinforcement Learning
Shuai Dong, Yongfu Zhu, Yuqi Xu, Weichu Xie, Liuwenpu, Ziyue Wang, Kaiwen Tuo, Congcong Wang, Siyuan Wang, Wenqi...
cs.LG
Reinforcement learning (RL) improves reasoning, but its performance depends on the policy from which training begins. We study on-policy distillation (OPD) as a preparation stage for RL and ask whether its benefits extend beyond improvements in the distilled model's initial accuracy. Under shared RL settings, students initialized with OPD reach higher final performance than those trained with direct RL or supervised fine-tuning followed by...
-
17
Probabilistic and Geometry Aware Neural Surrogate of Scrape Off Layer Plasma Simulations
Gabriele Gianuzzo, Stefan Dasbach, Fleur Hendriks, Sven Wiesen, Vlado Menkovski
cs.LG · physics.plasm-ph
Fast surrogates for tokamak boundary-plasma simulation are typically deterministic regressors mapping a global operating point to a flattened vector of cell values. Near the divertor detachment transition the steady state is not reliably single-valued. A point estimate must average over qualitatively different plasma states, and it arrives with no statement of confidence. Moreover, the flattened vector representation discards the geometric...
-
18
Fed-ReMasker: Federated Tabular Imputation under Feature-Level Missingness
Ioannis Papathanail, Rooholla Poursoleymani, Lubnaa Abdur Rahman, Stavroula Georgia Mougiakakou
cs.LG · cs.AI
Multi-center clinical studies and biomedical research collaborations increasingly seek to utilize data across centers to build models that generalize beyond any single center. This creates two distinct challenges: data protection regulations may restrict the sharing of raw patient data across institutions, while centers may collect only partially overlapping sets of features under different protocols. Federated learning enables collaborative...
-
19
LAYERSCOPE: A Layerwise Characterization of Video and Multimodal Learned Representations
Sandra Arcos-Holzinger, Debashish Chakraborty, Rohita Mocharla, Will Walden, Andrew Yates, Reno Kriz, Sarah M....
cs.LG · cs.AI · cs.CV
We propose LAYERSCOPE, a label-free, layerwise framework that aims to characterize a model's learned representations in video and multimodal settings. Evaluating downstream performance using representations from final or intermediate layers typically requires large amounts of labeled data, repeated task-specific evaluations, and substantial computation. To address these limitations, LAYERSCOPE uses local, global, distributional, and...
-
20
Curriculum Learning with GNN-based Reinforcement Learning for Job Shop Scheduling
Jayakrishnan K. Vasudevan, Jonathan Hoss, Noah Klarmann
cs.LG · cs.AI
The job shop scheduling problem is a challenging combinatorial optimization problem, and recent reinforcement learning approaches using graph neural networks have shown promise for learning scheduling policies directly from problem instances. However, training on large instances remains computationally expensive, and generalization across instance sizes remains challenging. This paper studies curriculum learning for graph neural network-based...
-
21
Exact Quantile Balancing and Load-Error Injection for Mixture-of-Experts
Pit Neitemeier, Jiaze Li, Alessio Serra, Philipp Scholl, Sohir Maskey
cs.LG · cs.CL
Mixture-of-Experts (MoE) training requires global load balance to prevent expert under-utilization and local balance for efficient expert-parallel execution. Existing distributed Quantile Balancing (QB) uses shard-dependent or approximate global quantiles, while token-independent expert biases cannot ensure microbatch-level balance. We introduce Exact Quantile Balancing (EQB), which computes exact global-batch BF16 quantiles with negligible...
-
22
PISCES: Physics-Informed Solar-wind Convolutional autoEncoder for Space-weather Anomaly Detection and Early Warning
Kevin Lee, Alison J. March
cs.LG · astro-ph.SR · cs.AI · physics.space-ph
Space weather early warning depends on detecting solar wind transients in in-situ measurements at the first Sun-Earth Lagrange point (L1), before they reach Earth. Fixed thresholds can miss combined magnetic and plasma structure, and many learning methods provide a single anomaly score. We present the Physics-Informed Solar-wind Convolutional autoEncoder for Space-weather (PISCES), a convolutional autoencoder trained without catalog labels on...
-
23
Shared Global KV with Layer-Specific Local History
Xinglang Xian
cs.LG
Decoder-only Transformer language models cache keys and values (KV) to reuse past computation during generation. Sharing KV across layers saves storage but reduces the diversity of representations available across depth. We study what local memory should retain alongside shared global KV, separating historical content from the input source used to form it. At 126M parameters and 2K context, an eight-seed study finds about 1.4% lower held-out...
-
24
Learning from Failures: Heterogeneous Graph Memory for Small Language Model Tool-Using Agents
Jiaxing Li, Lei Song, Rui Dong, Youyong Kong
cs.LG
Small and medium-sized language models offer cost-effective executors for tool-using agents, making them attractive for local and large-scale deployment. However, in long-horizon and stateful environments, they often make structural errors such as missing required observations, performing premature writes, repeating failed calls, and violating action preconditions. These errors can lead to incorrect state updates, policy violations, and...
-
25
PCQC: Privileged Counterfactual Question Credit for Multi-Turn Medical Dialogue
Chenxuan Li, Jiayi Wan, Xinrong Chen, Zhongyu Zhao, Xuecheng Shang, Peixing Wan
cs.LG
Large language models (LLMs) have made substantial progress on medical question-answering, yet effective medical dialogue also requires learning to ask questions that uncover relevant patient information. To train such dialogue policies, a common pipeline combines supervised fine-tuning with reinforcement learning (RL) based on final diagnostic correctness. However, this outcome-based supervision does not directly distinguish the...
-
26
Relative Discharge Stage (RDS) Classification: A Practical Indicator of Battery Discharge Progress
Khoa Tran, Tri Le, Hung-Cuong Trinh, Hung Tran-Nam
cs.LG
Accurate remaining discharge time (RDT) prediction is challenging in real-world battery applications because future load profiles are unknown and highly dynamic. To address the uncertainty of continuous RDT regression, this paper introduces Relative Discharge Stage (RDS), a battery-management indicator that represents the remaining discharge condition using five interpretable classes: Normal, Good, Moderate, Low, and Recharge Required. Unlike...
-
27
Riemannian Structure and Optimization for a Class of Low-Parametric Orthogonal Matrices
Ali Aliev, Maxim Rakhuba
cs.LG · cs.AI · math.DG · math.NA
In this paper, we are concerned with matrices formed by block-diagonal factors interleaved with fixed permutations -- a flexible family of structured matrices. This class has recently drawn interest in deep learning architectures for its balanced expressivity-efficiency trade-off, yet efficient computational strategies for working with it remain to be found. We approach this problem through Riemannian geometry and examine under what...
-
28
Limiting-Kernel Q($λ$): Bridging Short and Long Horizons
Tolga Ok, Arman Sharifi Kolarijani, Peyman Mohajerin Esfahani, Mohamad Amin Sharifi Kolarijani
cs.LG · math.OC
In value-based reinforcement learning, improving the accuracy of policy evaluation has been shown to improve downstream policy optimization performance. The widely adopted family of approximations relying on $n$-step truncation yields computationally efficient value estimators but is inherently limited to a short evaluation horizon. In contrast, methods that exploit the global structure of the transition dynamics can accelerate policy...
-
29
MENO: Memory-Efficient Neural Operator
Shengyang Xu, Weijun Zhang, Jun Hu, Pengzhan Jin
cs.LG
We propose the Memory-Efficient Neural Operator (MENO) as a high-performance PDE neural solver based on the Manifold Function Encoder (MFE). MENO features three primary advantages: (1) MENO has a significantly smaller memory footprint and much faster training speed than other popular architectures, with the memory footprint being independent of the data resolution, and therefore holds the potential for scaling up to large-scale models. (2)...
-
30
NS-ATTENTION: Newton-Schulz Transformations of Attention Outputs in Vision Transformers
Xiaohe Jiang, Guoqiang Zhang, Tianjin Huang, Ronghui Mu
cs.LG
Newton-Schulz (NS) iteration has recently been used in the Muon optimizer to transform update matrices during the training of large language models. Motivated by its spectral effect, we investigate applying NS directly to Transformer attention representations. We introduce Newton-Schulz Attention (NS-Attn.), a parameter-free transformation applied to the output of each attention head. Each head output is arranged as a feature-by-token matrix...
-
31
What Do Tabular Foundation Models Compute In Context? In-Situ Representation Refinement through Attention-Gated Updates
Tian Zhou, Beverly Jin, Linxiao Yang, Xue Wang, Wenwei Wang, Bingqing Peng, Mengni Ye, Jinjie Gu, Liang Sun
cs.LG
What reusable computation should a tabular foundation model learn when every table defines a new supervised task? We develop in-situ representation refinement: support labels guide updates to the episode's representations, and these updates transfer to unlabeled queries without changing model parameters. A regularized leave-one-out objective yields a support correction and its query extension. The leading term separates attention-based...
-
32
Robust Adversarial Reinforcement Learning with Risk Sensitivity and Critic Consistency Regularization
Jiaxi Wu, Tiantian Zhang, Yuxing Wang, Yongzhe Chang, Xueqian Wang
cs.LG
Reinforcement learning (RL) achieves strong performance in sequential decision-making but remains brittle under dynamic uncertainty and distributional shifts. Robust Adversarial Reinforcement Learning (RARL) improves robustness via worst-case perturbations, but existing approaches frequently suffer from unstable optimization and degraded value estimation. In particular, overly aggressive adversaries can drive the agent toward uninformative...
-
33
Private Decentralized Optimization with Noise Reduction and Bias Correction
Yizhao Fan, Wenjian Luo, Jiaojiao Zhang
cs.LG
Private decentralized learning is affected by sampling noise, privacy noise, and decentralized bias under heterogeneous data. We propose Private Recursive Decentralized Optimization (PRDO). PRDO uses recursive estimation with same-batch gradient differences to reduce estimation errors caused by sampling and privacy noise, while its Exact Diffusion component corrects decentralized bias arising from data heterogeneity. Our analysis establishes...
-
34
FLEET: From Logits Entropy to Enhanced Trajectories in Text Generation
Oleksii Streltsov, Oleksandra Vitko
cs.LG · cs.AI · cs.CL
Solutions based on large language models (LLMs) often rely on temperature sampling to improve accuracy and stability by aggregating multiple samples from the completion distribution. However, this memoryless approach is inherently suboptimal: because it lacks awareness of prior generations and their evaluations, it produces an increasing proportion of semantically duplicate answers as more samples are drawn, leading to diminishing returns. To...
-
35
Learning Local Heterogeneity and Cross-Region Context for Large-Scale Traffic Forecasting
Qi Feng, Zidong Wang, Bo Li, Xiaoguang Gao, Jiayu Zhang, Chenfeng Wang, Kaifang Wan
cs.LG · cs.AI
Traffic flow forecasting is essential to intelligent transportation systems. Large-scale traffic forecasting requires jointly modeling local spatial dependencies and cross-region context.Spatial dependencies between geographically neighboring nodes are heterogeneous due to differences in road identity and travel direction, while acquiring global information through allpairs node interactions incurs substantial computational costs. Therefore,...
-
36
Pheno-GS: Phenoscape-scale Geodesic Sinkhorn
Alistair Wilkinson, Christopher J. Tape, Smita Krishnaswamy
cs.LG · q-bio.QM
High-throughput single-cell data is now collected across large patient cohorts. Understanding patient-level heterogeneity from cellular-level data motivates phenoscaping: embedding each single-cell distribution as a "datapoint," with distances given by optimal transport (OT). Computing geometry-aware OT at this scale, between all pairs of patient datasets, remains an open challenge, since existing methods either rely on Euclidean ground...
-
37
Efficient Linear Bandits via Cluster-Aware Sketching
Hantao Yang, Hong Xie, Defu Lian
cs.LG
We study the problem of computational efficiency for linear bandits in high-dimensional settings with a finite arm set. In linear bandits, the increase in the dimension $d$ of the feature vectors leads to growing computational costs of $O(d^2)$ at each round of update. Traditional sketching-based methods such as SOFUL reduce computation via fixed-size matrix sketching, yet run the risk of incurring vacuous linear regret when the spectral tail...
-
38
Hidden not Deleted: How Networks Suppress Entangled Features
Akash Samanta, Manish Pratap Singh, Debasis Chaudhuri
cs.LG · cs.AI
Concept erasure methods that operate via linear projection assume that features occupy separable subspaces. We show this assumption fails under dense superposition: when two features are forced into an antipodal pair sharing a single subspace, state-of-the-art linear erasure destroys both, not just the target. Networks trained with gradient descent instead solve this problem non-linearly, but not uniformly: they converge to one of two...
-
39
The Capability Manifold and ML Scaling Laws
Syed Ali Raza Zaidi, Maryam Hafeez
cs.LG · cs.AI
Existing machine learning (ML) scaling laws relate predictive loss to compute, model parameters, and data. However, as models are increasingly deployed through agentic harnesses, loss alone is insufficient to characterize downstream performance: models with similar loss can exhibit different capabilities in reasoning, retrieval, planning, and adaptation. Yet, no unified framework connects such capabilities to the coupled resources available...
-
40
Does Step Law Transfer to Small-Scale Language Models? An Empirical Recalibration Below 59M Parameters
Egor Romanyukov, Timofey Novikov, Timur Shokarov, Elizaveta Zorkina, Anastasia Palienko, Stepan Dergachev
cs.LG · cs.CL
Step Law gives power-law formulas for the optimal peak learning rate eta* and batch size B* when pre-training language models. It was calibrated on models between 59M and 1B parameters; the small-model regime N < 59M was never tested empirically by its authors. This regime matters for single-GPU training, interpretability research, educational experiments, and settings where larger models are infeasible on memory or cost grounds. We test...
-
41
VCMM: Variance-Calibrated Momentum for Multimodal Learning
Zhongjing Gu, Chenyang Huang, Yufa Feng, Chong He, Qinxu Ding, Yiming Cui
cs.LG
Multimodal joint training often suffers from modality imbalance, where a dominant modality suppresses the optimization of others. Existing methods mainly balance modality learning by modulating gradient magnitudes or directions, modifying optimization objectives, or adjusting training strategies, with most interventions focusing on the current update. However, when combined with widely used momentum-based optimizers, the update also...
-
42
DCRL: Decoupling and Coupling Reinforcement Learning via Policy-Reward Manifold Alignment
Henan Sun, Zehua Li, Haitao Hu, Qifan Zhang, Jianfeng Zhang, Nuo Chen, Jia Li
cs.LG · cs.AI
Reinforcement learning (RL) has emerged as a key paradigm for improving the reasoning capabilities of large language models (LLMs). However, existing reward systems, such as rule-based and reward-model-based, often exhibit issues such as unstable optimization and reward hacking. In this work, we revisit the general reasoning of LLMs from a geometric perspective, conceptualizing it as a coupled manifold composed of three interdependent...
-
43
TNLearn: An Open Source Python Package for Task-based Neurons
Meng Wang, Tieyun Li, Juntong Fan, Hanyu Pei, Jing-Xiao Liao, Yaodong Yang, Jianwei Ma, Fenglei Fan
cs.LG · cs.AI
The brain does not rely on a single type of neuron to perform all kinds of tasks; instead, it designs different neurons for different tasks. The concept of task-based neurons represents a paradigm shift compared to task-based architectures. It argues that solving a specific problem requires customized neurons, as task-based neurons capture useful prior knowledge from task-related data. To facilitate the use of task-based neurons in scientific...
-
44
PhyMo: A Physical-Field Modality for Multimodal AI4Physics
Henan Sun, Haitao Hu, Jin Liu, Jianfeng Zhang, Lujia Pan, Nuo Chen, Jia Li
cs.LG · cs.AI
Multimodal learning is emerging as a powerful paradigm for AI for Physics (AI4Physics), where predicting physical systems requires the joint interpretation of heterogeneous observations, measurements, and domain knowledge. However, existing approaches typically represent physical quantities and governing equations as generic numerical or textual tokens, overlooking the physical constraints that determine their spatiotemporal interactions. To...
-
45
EBRL: Asynchronous Embodied RL by Multi-Grained Resource Management
Liang Mi, Weijun Wang, Bowen Gao, Tianze Yu, Zixu Hao, Han Xiao, Xin Ding, Mingzhe Huang, Xin He, Lu Shi, Hao Wu,...
cs.LG · cs.DC
Embodied reinforcement learning (RL) improves model capabilities with a pipeline of environment simulation, action generation, and model updates. These stages show heterogeneous CPU and GPU demands, making efficient resource utilization difficult. Recent systems overlap rollout (simulation and generation) with training for efficiency, but exclusive GPU allocation and synchronized barrier in rollout still leave substantial hardware resource...
-
46
ProCredit: From Outcome Rewards to Progress Credit in Agentic Reinforcement Learning
Ming Ma, Yi Zhu, Yiran Zhong, Feida Zhu, Chonghan Liu, Pengkun Jiao, Qichao Wang, Yanhao Jia, Tianming Yang, Steven Hoi
cs.LG · cs.CL
Long-horizon agentic tasks require an agent to modify an environment through a sequence of tool calls, with success determined by the final state. The standard recipe assigns a single outcome reward at the end and compares trajectories sampled for the same task. As a result, a group with no successful trajectory yields no training signal, failed attempts cannot be told apart by how close they came to completion, and turns that advance the...
-
47
Learning Where to Look: A Shared Relative-Alignment Module for Time-Series Forecasting and PPG-to-Vital-Sign Reconstruction
Ragamayi Puli, Shunya Nagashima
cs.LG
PPG-to-vital-sign reconstruction turns a wrist-worn photoplethysmogram into clinical waveforms such as the ECG. Long-horizon multivariate time-series forecasting underpins planning in energy, weather, and traffic. Both generate a target sequence from a condition sequence, and current models hard-code where each target position reads it, as a same-position copy or seasonal recurrence, so neither transfers between tasks. We propose ROOSTER, one...
-
48
Quantum Reinforcement Learning for Cost and Delay Tradeoffs in Quantum Cloud Orchestration
An N. H. Phan, Dang Van Huynh, Muhammad Usman, Hoa T. Nguyen
cs.LG · cs.AI · cs.DC · cs.ET · quant-ph
Quantum cloud computing, delivered through the quantum-as-a-service (QaaS) model, provides access to quantum computing resources. However, applying uniform time-based pricing across fundamentally heterogeneous quantum resources significantly complicates task orchestration, particularly when addressing the tradeoff between execution costs and system performance. While heuristic methods rely on predefined scheduling rules, classical deep...
-
49
Stable Neural Decoding Across Sessions via Task-Conditioned Latent Alignment for Brain-Machine Interfaces
Canyang Zhao, Bolin Peng, J. Patrick Mayo, Ce Ju, Bing Liu
cs.LG · eess.SP
Achieving stable long-term neural decoding in invasive brain-machine interfaces (BMIs) remains challenging due to variations in recorded neural populations across sessions. Current latent alignment approaches may overlook task-dependent structure during cross-session adaptation. We propose Task-Conditioned Latent Alignment (TCLA), a framework that stabilizes neural decoding by learning a shared latent space. TCLA learns a low-dimensional...
-
50
Counterfactual Constraint-Conditioned On-Policy Distillation for Multi-Constraint Instruction Following
Yanzhao Zheng, Yuanqiang Yu, Tianze Xu, Chao Ma, Zhentao Zhang, Jihuai Zhu, Baohua Dong, Hangcheng Zhu, Ruohui Huang
cs.LG · stat.ML
Multi-constraint instruction following requires a model to respond to a query under many simultaneously active constraints. Even strong instruction-tuned models still routinely violate some of them. Existing approaches either augment supervision with sequence- or token-level RL rewards from external verifiers or learned graders, or use on-policy distillation (OPD) against a single full-context teacher whose probability mass becomes diluted as...
-
51
When Labels Are Scarce: An Oscillatory State Space Model for Vibration Diagnosis
Mainak Mallick, Seung-Kyum Choi
cs.LG · eess.SP
Machine fault diagnosis from vibration requires learning from scarce labelled fault recordings while meeting the computational constraints of edge devices for local inference. We introduce DualRes, a compact oscillatory state-space model that combines two complementary spectral views of vibration, capturing rapid changes and fine frequency structure. Time-aligned views are processed by selective oscillatory memory, which learns how long to...
-
52
Active Learning for Biodiversity Monitoring: From Label Efficiency to Reliable Ecological Inference
Ben McEwen, Shiqi Zhang, Dan Stowell
cs.LG
Limited expert annotation capacity is a pervasive constraint in biodiversity monitoring. Passive acoustic recorders and camera traps generate data faster than experts can analyse them. Machine learning (ML) models can process these data at scale, but their reliability depends on the quality, quantity, and coverage of labelled samples, so expert time remains a constraint. Active learning (AL) eases this bottleneck by selecting, under a fixed...
-
53
Forecast Workflow Bench: Evaluating Language-Model Decisions with Budgeted Forecast Tools
Shunya Nagashima
cs.LG · cs.AI
Time-series foundation models (TSFMs) provide forecasts for operational decisions, but accuracy alone does not determine their value. Evaluating agents that use these models requires measuring decision quality and forecast cost. FWBench evaluates this capability on 1,251 electricity and cycle-hire cases using fixed forecast tools and simulated capacity contracts. Agents select models, histories and horizons, then submit capacities to minimize...
-
54
Anomaly-Free Self-Optimization via AUC Bounds
Kevin Wilkinghoff, Zheng-Hua Tan
cs.LG · eess.AS
Anomalies are rare, and anomalous data are often unavailable during development, making it difficult to determine which anomaly detection models and configurations will generalize to unseen anomalies. Recent approaches address this challenge by generating pseudo-anomalies and using bounds on the achievable area under the ROC curve (AUC) to select the optimal configuration from a finite set of candidates. Instead, we use the AUC bound as a...
-
55
Quantization-Robust Unlearning through the Lens of Retain-Forget Loss Landscapes Interaction
Jialu Wang, Jianing Deng, Shuqing Luo, Yuanzhe Li, Dongwei Wang, Jingtong Hu, Huanrui Yang, Song Wang, Tianlong Chen
cs.LG · cs.AI
Unlearning ensures LLM compliance by removing the influence of private or copyrighted training data. However, since LLM models typically undergo post-training compression, like quantization, in practical deployment, it has been observed that the unlearning effect can be substantially weakened, with the forgetting behavior degrading more severely than that of model utility. This paper proposes a quantization-robust unlearning framework that...
-
56
Discrete Diffusion Models via Evolving Variational Autoregressive Networks
Kewen Pan, Ying Tang
cs.LG · cond-mat.dis-nn · stat.ML
Conventional score-based diffusion models learn scores without representing normalized densities, whereas tractable normalized models support both sampling and direct likelihood evaluation. A recent tensor-network approach provides such a representation but is largely restricted to low-dimensional lattices. Here we introduce a discrete diffusion model that parameterizes normalized probability distributions using variational autoregressive...
-
57
Live Assistant: Learning Whether, When, and Whom to Assist in Real-World Live Social Streams
Shujian Gao, Jiamei Yan, Yuchen Yang, Penghao Zhou, Qinglei Wang, Tiehan Fan, Yuan Wang, Zuxuan Wu, Yu-gang Jiang
cs.LG
Livestreams are long-lasting interactive environments where audiovisual content, viewer activity, host behavior, and platform signals evolve together, creating assistance needs that emerge from the stream itself. We introduce \liveassistant, a framework for mixed-initiative, role-conditioned assistance that formulates livestream interaction as four coupled decisions: \textbf{whether to act, when to act, whom to address, and what to...
-
58
KITE: KV-Invariant Transformer Expansion for Efficient Agentic LLM Scaling
Zhiheng Hu, Yixun Wei, Jian Zhou, Yizhuang Zhou, Ji Li, Xing Chen, Yang Li, Bojun Wang, Yibo Zhu, Xiangyu Zhang, Daxin Jiang
cs.LG · cs.AI
Scaling a language model is not only a question of final quality: the architectural choice determines how much computation is spent during training, prompt processing, and autoregressive decoding to achieve certain model quality. An ideal model architecture should lower all above computation costs to facilitate scaling to a larger model, while ensure the larger model indeed outperforms smaller baselines. We introduce KV-Invariant Transformer...
-
59
NGN: Learning Neural Network Size as a Differentiable Count
Lixing Li
cs.LG
Neural network size is usually chosen before training, separating architecture selection from weight optimization. We introduce the Neurogenesis Network (NGN), a differentiable parameterization for learning how many ordered structural components a model should use. For each ordered component group, one learnable boundary selects an active prefix while the model parameters are trained. The boundary can grow from a compact initialization and...
-
60
SR-Fraud: An Outcome-Supervised Reflective LLM Agent Framework for Non-Stationary Payment Fraud Detection
Xuwei Tan, Yao Ma, Xueru Zhang
cs.LG · cs.CR
Real-time payment fraud detection is a non-stationary streaming prediction problem: adversaries adapt before supervised labels mature, and localized burst attacks can cause losses before retraining. Production systems typically rely on tabular classifiers and rules, which can struggle to capture these emerging sequential patterns before periodic retraining occurs. We present SR-Fraud, an outcome-supervised reflective LLM framework that...
-
61
Graph Learning with Spectral Connectivity Priors for Scarce Data
Mingxiao Liu, Bahar Oveisgharan, Bingyan Zou, Gene Cheung, H. Vicky Zhao, Feifei Gao
cs.LG · eess.SP
Learning a sparse graph from scarce data is practically important but challenging. Motivated by the desirable combination of local sparsity and strong global connectivity exhibited by expander-like graphs, we propose spectral connectivity-regularized graph learning (SCoGL), a framework that incorporates a family of Laplacian spectral priors to explicitly promote global connectivity. Specifically, SCoGL augments a...
-
62
What Converges in the Platonic Representation Hypothesis? Structure over Geometry
Junwon You, Mihyun Jang, Sangwoo Mo, Jae-Hun Jung
cs.LG · cs.CV · math.AT
The Platonic Representation Hypothesis suggests that increasingly capable models converge toward shared representations. Recent work narrows this claim to shared local neighborhood relationships, finding that capacity-dependent trends in several global similarity measures largely disappear after calibration. We challenge this interpretation by showing that prior local-global comparisons confound structural scale (local versus global) with...
-
63
Repurposing Pre-trained LLMs as High Fidelity Continuous Text Autoencoders
Arkanath Pathak, Unnat Jain, Alexander C. Berg
cs.LG
Next-token prediction has enabled highly fluent autoregressive language models, but it represents global structure only indirectly through sequential factorization. In contrast, high-fidelity autoencoders have become a standard primitive in image generation, enabling generative models to operate over continuous latent spaces; text lacks a comparably faithful continuous representation. We propose LLMAE, a method for repurposing a pretrained...
-
64
Full-Covariance Smoothing of Bayesian Neural Networks for Online Adaptation
Oren Wright, Haoming Jing, Qiaoan Shen, Koichiro Niinuma, Yorie Nakahira, José M. F. Moura
cs.LG · eess.SY
A neural network's layers can be treated as time steps of a state-space model, turning Bayesian training into a smoothing problem: a forward pass propagates Gaussian moments through the network, and a backward Rauch--Tung--Striebel pass updates the weight posteriors in closed form. Such methods learn from each observation in a single pass, in an uncertainty-aware manner, and without gradient-based iterations or replay, which makes them well...
-
65
Discover, Falsify, Revise: Auditing Input-Use Claims from Source Code to Predictive Contribution in Agent-Discovered Cell Models
Mengran Li, Bo Li, Chengyang Zhang, Yang Yan, Jinfeng Xu, Zhenchao Tang
cs.LG · q-bio.QM
AI virtual cells aim to predict cellular responses to specified interventions, yet held-out predictive performance alone does not establish use of the supplied perturbation information. This prediction-claim gap matters in agentic model discovery, where language-model agents generate and revise predictors using score-based feedback. We introduce CELLAUDIT, which audits input-use claims by asking whether an input can enter the cited...
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.