cs.LG · 2026-09-01 · No. 102
Machine Learning, 2026-09-01.
71 new papers in cs.LG. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
71 entries-
01
Constant Individual Regret in General Games
Mingyang Liu, Gabriele Farina, Asuman Ozdaglar
cs.LG · cs.GT
Uncoupled no-regret dynamics provide a decentralized route to equilibrium, but prior guarantees for individual regret retain a polylogarithmic dependence on the horizon. We remove this dependence for every finite $N$-player normal-form game under full-information feedback. We introduce \emph{ECHO-OFTRL}: optimistic follow-the-regularized-leader (OFTRL) equipped with an EMA cascade for high-order optimism (ECHO), where EMA denotes exponential...
-
02
Sharp Approximation Rates for Neural Networks with Affine Latent Parameterizations
Shijun Zhang
cs.LG · stat.ML
Many parameter-efficient methods generate the parameters of a large neural network from a low-dimensional latent representation. Given an architecture $Φ$ with $P_Φ$ parameter slots, we write $\boldsymbolθ_f=\mathcal{G}(\boldsymbolξ_f)$, where $\mathcal{G}\colon\mathbb{R}^M\to\mathbb{R}^{P_Φ}$ is a parameter generator and $\boldsymbolξ_f\in\mathbb{R}^M$ is a latent representation of the target function $f$. The architecture $Φ$ and the...
-
03
On the Complexity of the Compatibility Problem for Succinctly Encoded Conditional Distributions
Guy Emerson
cs.LG · cs.CC · math.PR
The motivation for this paper is the investigation of the trade-offs implicit in probabilistic models used in machine learning. Models are often used to make predictions in the form of conditional probabilities. However, a pair of conditional distributions p(x|y) and p(y|x) may not be compatible with any joint distribution p(x,y). Given two such conditionals, determining if there exists a compatible joint is known as the compatibility...
-
04
Stress-Testing Efficient Responsible-AI Evaluation: When Compute Savings Change Benchmark Conclusions
Ahmed El Kady, Aravind Narayanan, Rehana Noorani, Yani Ioannou, Shaina Raza
cs.LG
Efficient evaluation changes the protocol used to support claims about model behavior, yet it is rarely tested whether those claims remain stable after the evaluation itself is made cheaper. We stress-test conclusion robustness in responsible-AI benchmarking by evaluating three dense and mixture-of-experts models on BBQ and BBQ-V under seven conditions spanning batching, quantization, benchmark reduction, and their combinations. Rather than...
-
05
Sycophantic Agreement Transfers with Neutral Data via Contrastive Preference Optimization
Camila Blank, Zhuofan Ying, Christopher Potts, Peter Hase, Jing Huang
cs.LG
Sycophantic agreement refers to a behavior in which language models excessively affirm the user, often at the cost of factual accuracy. Although sycophantic agreement is a well-known failure of model alignment, there is limited understanding of how it emerges from model training. In this work, we demonstrate that sycophantic agreement can emerge as an unintended consequence of widely used contrastive preference optimization objectives. Using...
-
06
A Model with No Head and Many Thoughts
Nikita Koriagin, Yaroslav Aksenov, George Bredis, Gleb Gerasimov, Nikita Balagansky, Daniil Gavrilov
cs.LG · cs.CL
Large language models decode by projecting hidden states through a large vocabulary head at every step. This operation is computationally costly and forces all reasoning to be expressed in discrete tokens. We introduce Soft Latent Thinking, a method that replaces the LM head during reasoning with a lightweight projector, enabling autoregressive rollout in embedding space where reasoning steps remain continuous rather than tokenized....
-
07
Universal Transformers for Circuit Computations: Perfect Length Generalization in Tiny Transformers
Takuya Ito, Ruchir Puri, Murray Campbell, Parikshit Ram
cs.LG
Learning generalizable algorithmic computations remains a challenge for neural networks, as reflected in persistent failures on compositional and length generalization benchmarks. We present a provably correct, transformer parameterization (with only 280 learnable parameters for Boolean algebra tasks) capable of learning and evaluating problems of any depth or length. We assume inputs are fully parenthesized, well-formed expressions. Our...
-
08
Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement
Yi Ding, Ruqi Zhang
cs.LG · cs.CL
On-policy distillation (OPD) offers dense token-level supervision as an alternative to the sparse outcome-level advantages of reinforcement learning with verifiable rewards (RLVR). However, the teacher scores student-generated trajectories that are inherently off-policy for it, so the reliability of its supervision, and hence the source of the student's improvement, remains unclear. We quantitatively analyze teacher supervision during OPD...
-
09
Rotational Equivariance in Machine Learning: A Comprehensive Tutorial
Peter Lippmann, Fred A. Hamprecht
cs.LG
Rotational symmetry is one of the most important structural principles in machine learning on 3D data. In applications ranging from physics and materials science to 3D computer vision, predictions should not depend on an arbitrary choice of coordinate frame. Rotational equivariance captures this requirement mathematically by enforcing that a rotation of the input induces a corresponding transformation of the model output. This tutorial...
-
10
Normalized Low-Rank Adaptation
Jiale Kang, Ziyin Yue, Zheng Zhan, Yangyi Huang, Weiyang Liu
cs.LG
While low-rank adaptation (LoRA) is widely used for parameter-efficient model adaptation, how to regularize its training dynamics for stable and effective optimization remains underexplored. Because LoRA initializes the up-projection to zero, its early optimization dynamics are largely governed by the down-projection. Building on this observation, we introduce Normalized Low-Rank Adaptation (NoRA), a simple yet effective method that...
-
11
TSPFN: A Temporal Tabular Foundation Model for Physiological Time Series Classification
Jérémie Stym-Popper, Clément Rambour, Federica Granese, Nicolas Thome, Olivier Bernard
cs.LG · cs.CV
Designing models that generalize effectively in low- to medium-data regimes remains a primary challenge in medical machine learning, particularly for physiological time-series classification. While tabular foundation models such as TabPFN offer an attractive alternative to conventional fine-tuning through in-context learning, they are not designed to capture the temporal dependencies inherent to physiological signals. ~In this paper, we...
-
12
Language-Informed Flow Matching for Trend-Guided Structure-Based 3D Molecular Generation
Tianyu Gao, Zhikai Su, Jiashu Li, Wenjun Gao, Zichuan Ying, Zhe Zhao, Fei Zhang, Ye Wei
cs.LG
Structure-based drug design (SBDD) requires ligands that satisfy both 3D target affinity and 1D chemical validity. Existing controllable generation methods often rely on task-specific fine-tuning or externally imposed sampling-time guidance, adding cost and potentially conflicting with evolving 3D geometric constraints. We propose LiFT, a language-informed cross-modal framework built on Flow Matching for trend-guided 3D molecular generation...
-
13
Controlling Refusal Behavior of LLMs via Stiefel-Constrained Rotation Steering
Kirill Bunin, Dmitry Bylinkin, Vladimir Aletov, Daniil Medyakov, Vladimir Solodkin, Aleksandr Beznosikov
cs.LG · cs.CL
Activation steering has emerged as a lightweight approach for controlling model refusal at inference time. A growing line of research explores trainable rotations of activations to develop geometrically principled intervention mechanisms. However, existing techniques rely on auxiliary constructs, such as refusal vectors, to define these rotations. In our work, we develop a self-contained methodology for learning parameter-efficient rotational...
-
14
Sparse Competition during Training For the Emergence of Specialized Modules
Baptiste Rossigneux, Karim Haroun
cs.LG
Modularity in deep neural networks has been proposed as a means of improving both interpretability and training by promoting disentangled representations and reducing redundancy. In this work, we study the emergence of modular structure through competition dynamics between groups of neurons during training. We introduce a method that (i) maintains near-baseline accuracy, (ii) induces usage-based modularity by sparsely routing inputs to neuron...
-
15
A Human-in-the-Loop Autonomous Agent for Industry Time Series Forecasting
Xiaoyu Tao, Mingyue Cheng, Ze Guo, Bokai Pan, Qi Liu, Shijin Wang, Enhong Chen
cs.LG
Real-world time-series forecasting is rarely a one-shot model invocation: practitioners must formulate tasks, connect data and models, incorporate domain expertise, assess prediction plausibility, and communicate uncertainty. Specialized forecasting models provide strong numerical predictions but usually operate in fixed pipelines, while general-purpose large language model (LLM) agents often lack forecasting-specific checks, constraints, and...
-
16
A Universal Context-Reuse Layer for Cross-Model KV Sharing
Yi Li, Dongming Jiang, Yi Zhao, Bingzhe Li
cs.LG · cs.AI
Modern large language model (LLM) serving systems increasingly operate over repeated or shared context, yet each model typically performs its own prefill computation even when another model has already processed the same input. Existing KV-cache reuse mechanisms substantially reduce redundant computation within a single model, but generally assume that the producer and consumer of a cache are identical. We study \emph{cross-model KV sharing},...
-
17
Singular Curvature in ReLU Training:Differentiation and the Gradient-Flow Limit Need Not Commute
Xiaoyang Li, Runni Zhou
cs.LG
Gradient descent (GD) is explicit Euler for gradient flow, but a state-accurate continuous-time surrogate need not remain accurate after differentiation. At every fixed nonresonant step size, ordinary automatic differentiation exactly differentiates the executed hard-ReLU GD program. We prove that, over a fixed finite horizon, the GD states converge and these exact discrete derivatives approach an event-free regional propagator, whereas the...
-
18
One Policy Is Enough: Single-Agent Reinforcement Learning Outperforms Tree Search for Chemistry Tool Learning
Armin Dariani, Sifan Wu, Bang Liu, Entao Yang
cs.LG · cs.CL
Chemistry questions often demand exact computation and database lookups that a language model cannot supply from its parameters, so it must reach for external tools. Tool use here is a three-part problem: select the right tool from a large pool, fill it with correctly typed arguments, and chain calls so that each consumes the outputs of the last. CheMatAgent, a previously published system, addresses this with hierarchical evolutionary MCTS:...
-
19
Reproducible macroscopic dynamics in a closed-loop human-AI learning system
Minlin Wu, Xu Fang, Yicheng Zhang, Chenyu Zhou, Zhiyi Liu
cs.LG · nlin.AO
Closed-loop human-AI systems generate high-dimensional behavioural trajectories whose collective dynamics remain obscure. Using 297,915 learners' adaptive-tutoring histories, we define semantic order variables before model fitting and test them in user-disjoint cohorts. The state exhibits reproducible basin-like flow and operationally defined, state-heterogeneous metastable-like kinetics. A construction-matched null distinguishes...
-
20
Nonparametric Contextual Pricing and Inventory Learning under Censored Demand
Zean Han, Jing Liang, Ruihan Lin, Zezhen Ding, Jiheng Zhang
cs.LG
In online retailing, when a product sells out, a retailer often sees only the units sold, not how many customers would have bought it had inventory been available. However, the inventory level determines how much demand is revealed, and this information can influence subsequent decisions and future profits. We study an online selling problem in which, in each round, the seller observes a market context and then makes pricing and stocking...
-
21
Towards Stream Learning on Embedded Systems: Benchmarking the Memory Consumption of Stream Learning Methods
Sebastian Buschjäger, Nuwan Gunasekara, Heitor Murilo Gomes
cs.LG · cs.AI · cs.PF
Stream learning is commonly evaluated through predictive performance and adaptation to concept drift. However, sustained operation of a stream learner also requires predictable and bounded resource usage even on long streams. This requirement becomes even more critical when learning moves from servers to near-sensor embedded systems where memory and processing are scarce resources. In state-of-the-art stream learning, however, we perceive a...
-
22
Selection-Aware Stress Testing for Interactive Agents
Yang Xu, Chenang Li, Jiefu Zhang, Haixiang Sun, Zhou Li, Vaneet Aggarwal
cs.LG · stat.AP · stat.ML
Agent evaluations often use one benchmark to choose a workflow and then search for task types where its advantage weakens, so both conclusions are selected from the same data. We introduce Selection-Aware Semantic Stress Testing (\SASST{}), which learns a task reweighting from pre-execution features on discovery tasks and evaluates the same paired comparison on separate confirmation tasks. The protocol checks support and stability, uses joint...
-
23
S3C-LLM: Skill-Code Guided Agentic Language Models for Spectrum-to-Structure Elucidation
Xuanle Zhao, Xinyuan Cai, Xiang Cheng, Bo Xu
cs.LG · cs.CL
Spectroscopic structure elucidation is central to molecular analysis, but recent Large Language Model (LLM)-based methods mostly formulate it as direct spectrum-to-SMILES generation. Although this paradigm can leverage paired spectral data, it does not explicitly model the analytical workflow used by spectroscopists, such as diagnostic peak interpretation, fragment reasoning, formula constraints, and chemical consistency checking. In this...
-
24
Fine-Tuning Low-Bit Models with Gradient in Quantized Code Space
Shiguang Wu, Zhouchen Lin, Quanming Yao
cs.LG
Fine-tuning Low-bit models aims to adapt a quantized model while keeping the final deployed checkpoint in the same low-bit form. This setting is practically important as it reduces memory and inference cost for storage and deployment. Under this constraint, adaptation becomes an optimization problem over quantization codes and scales. Existing continuous low-bit training is efficient, but it can be distorted by straight through estimation...
-
25
Deploying DeepSeek 175B Locally on a Single Consumer-Grade RTX 4060 Laptop with 32GB RAM for 200k-Scale Protein-Ligand Virtual Screening
Rui Xiao, Yili Xu
cs.LG
Recent advances in large language models (LLMs) have demonstrated exceptional performance in protein-ligand interaction prediction, but state-of-the-art pipelines for large-scale virtual screening almost exclusively rely on high-end GPU clusters with hundreds of gigabytes of memory, creating prohibitive hardware barriers for small academic teams. In this work, we present a fully local low-resource framework that deploys the...
-
26
What Emerges and What Breaks in Self-Play Driving
Laur Sisask, Ardi Tampuu, Tambet Matiisen
cs.LG
Training autonomous driving policies through pure self-play has recently shown promising results. Following Gigaflow and Puffer- Drive, we train driving policies in a similar self-play fashion, but extend the models from MLPs to Transformers and train on the high-definition map of a real city, where we ultimately aim to deploy them. On the CARLA and Waymax benchmarks, our policies fall short of Gigaflow, and we trace the gap to specific...
-
27
Geometric Attractor Monitoring: A Robust and Frugal Framework for Multi-modal Industrial Robotic Cycles
Martin Bonsergent-Brachet, Jesse Read, Dany Abboud
cs.LG
Monitoring the health of heterogeneous industrial robot fleets is severely challenged by the multi-modal nature of their operational cycles and a persistent scarcity of run-to-failure data. Standard data-driven approaches, particularly deep learning architectures relying on sequential reconstruction, often struggle in this specific setting; they tend to over-smooth complex dynamics, masking early signs of degradation. To address these...
-
28
Reciprocity Separates Gradient Flow from Rotation in Conservative Physical Learning
Ruiwu Niu, Xiaowen Bi, Michaël Antonie van Wyk
cs.LG · nlin.AO
Physical learning lets a trainable material or network use its own physical response to carry error signals, reducing the need for a separately programmed backward computation. We ask what determines whether such a system follows conventional gradient descent or evolves along a genuinely different learning trajectory. Our canonical model is a directed layered transport network in which every node redistributes a fixed amount of flow, so...
-
29
TrainSDC: Characterizing and Mitigating Silent Data Corruption in Large Language Model Training
Zhipeng Xia, Haotian Xu, Siyu Yun, Liqi Lin, Hu Liu, Yu Li, Cheng Zhuo
cs.LG
LLM training is increasingly vulnerable to silent data corruption (SDC), yet existing protection methods largely treat Transformer computations uniformly because their vulnerability remains poorly understood. We present the first systematic characterization of SDC vulnerability across major computation interfaces in both the forward and backward passes of Transformer training. Our analysis reveals two distinct error propagation mechanisms:...
-
30
T3S: Improving Multi-Task Reinforcement Learning with Task-Specific Feature Selector and Scheduler
Yuanqiang Yu, Tianpei Yang, Yongliang Lv, Yan Zheng, Jianye Hao
cs.LG
Multi-task reinforcement learning (MTRL) is a technique to train multiple tasks simultaneously, where previous works usually train a single model to solve different tasks by sharing parameters across various tasks. However, these methods are faced with inter-task interference since what parameters should be shared across tasks is not addressed, dramatically reducing learning efficiency. To solve these problems, we propose a novel MTRL...
-
31
PRACTICE: From Experience to Expertise in Self-Evolving Embodied Agents
Ziyi Bai, Siqi Li, Tinglei Huang, Börje F. Karlsson
cs.LG
Recent studies have shown that multimodal large language models (MLLMs) can serve as embodied agents, translating language instructions and visual observations into executable plans. However, building agents that can continually improve through interaction and rapidly adapt to their environments remains challenging. Summing up experience from past interaction trajectories provides a promising solution, but existing experience-based methods...
-
32
Do VLMs Share Safety Neurons Across Modalities?
Jiaxuan Li, Jiahao Zhang, Duc Minh Vo, Huy H. Nguyen, Pride Kavumba, Koki Wataoka
cs.LG
Vision-language models (VLMs) can comply with harmful requests delivered through images, even when their LLM backbones would refuse the same content in text. While prior work characterizes these jailbreaks empirically or at the representation level, how visual inputs perturb safety pathways at the neuron level remains uncharted. We close this gap with a causal, neuron-level analysis of safety mechanisms in 10 VLMs. We propose a two-stage...
-
33
TDDM-Melatt: A Decoupled Memory and Diffusion Framework for Generalizable Encrypted Traffic Classification
Ze Chen, Qiming Yu, Zijia Song, Guozheng Yang, Wei Yan
cs.LG
The widespread adoption of encrypted traffic poses severe challenges to current security situational awareness systems based on network traffic monitoring. In existing dataset-driven training and testing studies, limitations such as shortcut learning induced by spurious feature correlations and sample imbalance caused by the long-tail distribution of real-world traffic result in weak generalization of traffic identification performance to...
-
34
Functional Degeneracy in Neural Networks: Measurement and Pruning
Maria Matveev, Pascal Esser, Ayush Bharadwaj, Lucius Bushnaq, Gitta Kutyniok
cs.LG
A central question in modern machine learning is how much a trained model can be compressed without changing its behavior, to reduce the memory, compute and energy required to deploy it. To study this, we quantify functional degeneracy through the behavioral recovery rank, defined as the number of leading behavioral-Hessian eigendirections required to recover a trained model's performance. Using the behavioral recovery rank as a geometric...
-
35
E-Commerce Bench: Evaluating LLM Agents on Long-Horizon Autonomous Business Operation
Wei Fan, Xinjie Shen, Xudong Guo, Jianhong Tu, Yang Su, Yinger Zhang, Lianghao Deng, Fengyu Wang, Baohua Dong,...
cs.LG · cs.CL
Long-horizon agentic tasks go beyond chaining short tasks over more interaction turns. Their evolving dynamic environments and long-range dependencies require Large Language Models (LLMs) to continually explore, learn from experience, and adapt their policies over thousands of steps. We introduce E-Commerce Bench, the first open-source benchmark that integrates multi-round counterpart negotiation and dynamic events into a year-long business...
-
36
BAITBENCH: Measuring Agent Reward Hacking with Optional Shortcuts Planted in ML Tasks
Pradyumna Shyama Prasad, Meiri Anto, Leon Eshuijs, Julian Moncarz, Kaustubh Kislay, Juan J. Vazquez
cs.LG · cs.AI
LLM agents are increasingly used to run autonomous ML experiments, iterating on target metrics with little human oversight. Prior work has documented reward hacking in these environments, bringing into question the validity of produced research and the broader safety case for AI R&D. Existing benchmarks do not measure exploits that live in the data or the modeling task itself. We introduce BAITBENCH, a suite of three synthetic tabular ML...
-
37
Tracing distinguishability through transformer processing with stochastic LayerNorm
Kieran Murphy
cs.LG
Representational similarity is foundational to analyses of deep networks, yet distances between point-valued representations are not intrinsically tied to downstream function: nearby states may produce different behaviors, while distant states may behave similarly. We instead give representations volume, turning similarity into statistical distinguishability. Overlapping stochastic representations necessarily induce overlapping downstream...
-
38
Kolmogorov--Arnold against bounded translations
Sviatoslav V. Dzhenzher
cs.LG · math.FA
Historically originating from Hilbert's 13th problem, the Kolmogorov-Arnold representation theorem (KART) has recently experienced a major revitalisation through its applications to neural networks, specifically Kolmogorov-Arnold Networks (KANs). While the exact representation is well established, its stability under continuous adversarial perturbations of the hidden layer remains a critical open question. In this paper, we investigate the...
-
39
Learning Dynamics of Logits Debiasing for Long-Tailed Semi-Supervised Learning
Yue Cheng, Jiajun Zhang, Xiaohui Gao, Weiwei Xing, Zhanxing Zhu
cs.LG · cs.AI
Long-tailed distributions are prevalent in real-world semi-supervised learning (SSL), where pseudo-labels tend to favor majority classes, leading to degraded generalization. While many long-tailed semi-supervised learning (LTSSL) methods have been proposed, the mechanisms by which they implicitly debias logits remain poorly understood. In this work, we revisit LTSSL through the lens of learning dynamics and provide a theoretical...
-
40
Liquid Gated Attention
Yiheng Jiang, Yuanbo Xu, Yongjian Yang
cs.LG
Real-world time series often exhibit irregular sampling and extended temporal horizons, requiring models to capture continuous-time dynamics across arbitrary intervals without prohibitive scaling costs. Discrete-time methods collapse variable time intervals into static positional steps; solver-dependent continuous-time models preserve temporal structure but rely on sequential integration, precluding parallelization; and solver-free...
-
41
Learning Materials Properties from Scarce Labels and Unlabeled Crystals
Wentao Li, Yizhe Chen, Jiangjie Qiu, Yijun Li, Leyi Zhao, Xiaonan Wang
cs.LG · cs.AI
Learning materials properties from scarce labels and unlabeled crystals is a central challenge for data-driven materials discovery. We present SemiMat, a controlled benchmark for semi-supervised materials property regression, and MatRank, a reliability-weighted objective for continuous pseudo-label uncertainty. SemiMat fixes labeled and unlabeled crystal inputs, graph-backbone interfaces, validation-only checkpoint selection, held-out test...
-
42
CoMPASS: Collaborative Molecular Property Prediction via Adaptive Small-Large Model Synergy
Wentao Li, Jiangjie Qiu, Yijun Li, Leyi Zhao, Xiaonan Wang
cs.LG · cs.AI
Accurate molecular property prediction requires both statistical reliability and chemical reasoning. Graph neural networks can be calibrated directly on labeled assays but remain limited by the coverage of their training data. Large language models (LLMs) can compare molecular evidence and articulate chemical rationales, yet are unreliable as standalone quantitative predictors. The central challenge is therefore to determine when an LLM...
-
43
Season-Aware Hybrid Convolutional-Transformer for Antarctic Sea Ice Concentration Forecasting
Danyang Li, John Taylor, Thang Bui, Quanling Deng
cs.LG
Antarctic sea ice concentration (SIC) forecasting is an important yet challenging task due to the coexistence of complex spatial structure, long-range temporal dependencies, and strong seasonal variability. Conventional convolution-based models are effective at capturing local spatial patterns, but often have limited ability to model long-term temporal evolution. To address these challenges, we build on a hybrid Convolutional-Transformer...
-
44
Three Steps at a Time: Learning Representations from Action Sequences in Contrastive RL
Michal Korniak, Kamil Dybek, Benjamin Eysenbach, Marco Bagatella, Michał Bortkiewicz
cs.LG
While self-supervised approaches to reinforcement learning have achieved strong results by learning representations of states and actions, a key open question is the time scale over which actions should be modeled. Departing from the standard formulation relying on single-step actions, we extend contrastive reinforcement learning (CRL), a prototypical self-supervised method, to operate over action chunks, and find that this results in large,...
-
45
MolLedger: An Additive Graph Neural Network with Chemically Grounded ADME Attributions
Christina X. Ji
cs.LG
Optimizing absorption, distribution, metabolism, and excretion (ADME) is an important part of small molecule drug discovery. Many machine learning models have been built to predict ADME properties to facilitate this optimization process, but explaining model predictions is challenging. We propose a new graph neural network architecture with built-in meaningful per-atom attributions. Our model MolLedger outputs predictions that are the sum of...
-
46
PLC-DPO: Posterior Label Correction in Noisy and Ambiguous Preference Optimization
Boryeong Cho, Sumyeong Ahn, Se-Young Yun
cs.LG · cs.CL
Direct Preference Optimization (DPO) simplifies alignment through pairwise comparisons but assumes all observed preferences are reliable. Real data often violates this assumption, leading to reversed, weak, or ambiguous labels that cause harmful policy updates. To address this, we propose Posterior Label Correction DPO (PLC-DPO) to robustly optimize preferences by routing each pair's training signal as a clean, flip, or tie case. The key idea...
-
47
State of Health Estimation using Convolutional and Bidirectional LSTM Neural Networks tuned by Bayesian Optimization
Panagiotis Eleftheriadis, Foivos Georgios Kyrgios, Sonia Leva
cs.LG
In this research, a novel framework is proposed for the SOH estimation, which employs a hybrid deep learning architecture of a concatenation of a Convolution Neural Network (CNN) and a Bidirectional Long Short-Term Memory (BiLSTM) Neural Network (NN) with the integration of Bayesian Optimization-based hyperparameter tuning for the network. Three different deep learning architectures are being evaluated: standalone recurrent models, CNN-RNN...
-
48
The Safety Relay in Roleplay Jailbreaks: A Component-Resolved Causal Analysis of Harm Recognition and Refusal
Md Mokarram Chowdhury, Ernie Chang, Yang Li
cs.LG
Large language models are trained to follow instructions while refusing harmful requests. Jailbreaks exploit this balance to elicit content a model would ordinarily reject. Roleplay jailbreaks are especially concerning: the harmful request can remain visible inside a roleplay wrapper made of a persona, scenario, and task, yet the model may comply. We use mechanistic interpretability to determine how this context reverses refusal and which...
-
49
Collapsibility of Performance Metrics in Clinical Predictive AI
João Matos, Ben Van Calster, Richard D. Riley, Paula Dhiman, Gary S. Collins
cs.LG · cs.AI
Background: Population level assessments of predictive artificial intelligence (AI) can conceal performance disparities across subgroups. Fairness evaluations commonly rely on performance analyses across subgroups. However, some performance metrics are non-collapsible, meaning that the overall population performance value does not equal the weighted average of subgroup specific values. Objective: To examine the collapsibility properties of...
-
50
Q-Strata: Hierarchical Bit Allocation for Mixed-Precision Quantization of Mixture-of-Experts LLMs
Deokjae Lee, Sihun Chu, Hyun Oh Song
cs.LG · cs.AI
Mixed-precision quantization (MPQ) assigns a different bitwidth to each linear layer of a large language model (LLM) to minimize the quantization-induced quality loss under a fixed budget, but Mixture-of-Experts (MoE) models contain these layers in every expert of every MoE block, so the allocation space grows far larger than in a dense model. Existing methods either allocate within each block under a uniform per-block budget, or allocate...
-
51
PAC: Progress-Augmented Advantage Curriculum for Multi-Task Reinforcement Learning of LLMs
Yuanqiang Yu, Yanzhao Zheng, Zhentao Zhang, Tianze Xu, Chao Ma, Jihuai Zhu, Jiashun Liu, Xinle Deng, Baohua Dong,...
cs.LG
Reinforcement learning (RL) is used to improve the reasoning abilities of LLMs, while training data span heterogeneous tasks. However, most RL post-training pipelines rely on fixed or manually designed task mixtures, even though task usefulness changes as training progresses. Online curriculum methods often define learnability by update magnitude, ignoring whether the update translates into reward gains, which can misallocate rollout budget...
-
52
Trajectory-Initialized Neural Double Q-Routing for Large-Scale Overhead Hoist Transport Systems
Cheng Gu, Qiusheng Zhao, Anbang Liu, Shaochong Lin, Max Z. J. Shen
cs.LG · cs.AI · math.OC
Large-scale industrial robot fleets share constrained physical infrastructure, making vehicle travel times dependent on safety separation, intersection access, downstream blocking, and station contention. We study this problem in overhead hoist transport (OHT) systems, a representative ceiling-mounted material-handling system used in semiconductor fabs. Static shortest-path routing cannot account for these time-varying traffic costs, whereas...
-
53
Tensor Methods for Language Models: From Token Representation to Training, Adaptation, Inference, Compression, and Interpretability
Matvei Tarasov, Salman Ahmadi-Asl, Andre L. F. de Almeida, Andrzej Cichocki
cs.LG · cs.AI
Large language models (LLMs) are built from structured high-dimensional objects such as token representations, weights, adaptation updates, caches, and activations, whose multilinear structure is underexploited by the conventional matrix-centric view. Tensor decompositions and tensor networks provide a principled algebraic language for this structure, yet the literature often treats them as isolated compression mechanisms. This survey...
-
54
When the Martingale Never Stops Firing: Anytime-Valid Gating on Real Forecast Streams
Weijia Han, Lisha Qu
cs.LG · stat.ME · stat.ML
Machine learning systems are increasingly corrected while they run, and the decision of when to intervene is increasingly delegated to statistical monitors. Anytime-valid inference promises evidence that can be acted on at any moment, exactly the guarantee this setting needs, and it is moving from theory into deployed monitoring. Conformal test martingales are the change-detection instrument, and Ville's inequality caps their false-alarm...
-
55
Measuring Memory and Generalization as Separable Geometric Channels: The Topo^2 Framework
Zhanbo Zhang, Ming Liu, Qing Wang
cs.LG · cs.AI
Deep networks trained on noisy labels simultaneously generalize on clean data and memorize flipped labels. These are usually conflated as pressures on one capacity. We present Topo^2, a measurement framework that makes them causally separable, measurable, and law-governed. Persistent-homology H1 structure of the representation space separates into a within-class manifold channel (a function of the training stopping point) and a cross-class...
-
56
ToxLens: A Reproducible Graph-Learning Framework for Leakage-Aware, Uncertainty-Calibrated Molecular Toxicity Prediction
Magnus H. Strømme, Alex G. C. de Sá, David B. Ascher
cs.LG
Molecular toxicity prediction is increasingly used to prioritise compounds before experimental testing, but conventional benchmark performance can overstate practical utility when structurally related molecules occur across training and test folds. We introduce ToxLens, a reproducible multi-task graph-learning framework for 11 toxicity endpoints spanning Ames mutagenicity, acute oral toxicity, hERG inhibition, and Tox21 nuclear-receptor and...
-
57
Learning Where Outcomes Change:Credit-Addressable Reasoning for Multimodal Geometry
Jiani Guo, Junjie Wang, Jie Wu, Pengxiang Zhao, Dongdong Zhang, Shaohan Huang, Yujiu Yang, Furu Wei
cs.LG · cs.CL
Multimodal geometry reasoning requires VLMs to extract precise visual relations and preserve them through multi-step deduction. Existing free-form traces obscure the decisions that determine the answer, and trajectory-level reinforcement learning distributes a single terminal signal across the entire response. We introduce credit-addressable reasoning, in which the semantic units exposed during inference also define where learning compares...
-
58
Self-Supervised Pretext Tasks for Infant Cry Analysis: A Controlled Comparison and a Cautionary Result on Donateacry
Luigi Simeone
cs.LG
We compare six self-supervised pretext tasks for infant cry analysis under a fixed budget, meaning the same compact encoder of 1.17M parameters, the same 115 hours of license-verified public pretraining audio, and the same evaluation protocol for every candidate. On cry detection the reconstructive objectives dominate, and a linear probe over a masked-spectrogram encoder reaches 0.988 AUC with subject-wise splits even though the encoder never...
-
59
PRIME: Mitigating Subgroup Optimization Competition in Shared CTR Top Networks with Plug-in Residual Input-Conditioned Mixture of Expert
Heng Yao, Siyun Hou, Tianying Liu, Yulou Shu, Yong He, Chuan Yuan, Kaibin Qiu, Guowei Chen, Jiayu Zhao, Chao Yu, Ke Ding
cs.LG · cs.IR
Click-through rate (CTR) models vary in feature-interaction design, yet their top networks usually remain a single multilayer perceptron shared by all examples. Heterogeneous user, item, and context subgroups therefore update the same parameters; weakly aligned learning signals make the aggregate gradient a compromise among competing directions. We study the competition on Avazu with 4 models and 4 semantic fields. Across all architectures,...
-
60
Confounding Masquerading as Improvement: A Systematic Evaluation of Offline Reinforcement Learning for Stroke Antithrombotic Treatment in a 129,000-Patient Registry
Kihun Rhee
cs.LG · stat.ML
Recent offline reinforcement learning (RL) studies report policies that outperform physician decisions on clinical outcomes. We conduct a systematic, partially crossed evaluation of five offline RL algorithm families and 14 reward designs in 44,894 post-2018 acute ischemic stroke patients from a nationwide registry (N = 129,033). Standard Fitted Q-Evaluation (FQE) yields an apparent policy-improvement estimate of +0.0069; adding an Early...
-
61
No Equivariant Architecture Covers All Equivariant Attention
Tīkun Ông
cs.LG · math.AG · math.RT
We give a complete characterization of equivariant multi-head self-attention (MHSA): if an MHSA layer is equivariant to a symmetry group $G$, then $G$ can only act by permuting head-clusters, with QK and OV matrices satisfying an equivariance constraint tied to the group action. As a consequence, we prove that any fixed MHSA architecture that achieves exact equivariance by polynomially parameterizing unconstrained MHSA parameters inevitably...
-
62
Locally-Guided Actor-Critic: Training a Goal-conditioned Actor with a Subgoal-aware Critic
Olivier Serris, Stéphane Doncieux, Olivier Sigaud
cs.LG
Goal-conditioned reinforcement learning struggles with long horizons when rewards are sparse. While a planner can provide subgoals to guide a low-level policy, its use at test time may introduce practical subgoal management difficulties. An alternative paradigm utilizes a high-level planner to assist learning, while the policy remains conditioned only on the final goal, enabling planner-free deployment. Among these methods, Reinforcement...
-
63
TopGQ: Fast GNN Post-Training Quantization Leveraging Topology Information
Dain Kwon, Kanghyun Choi, Hyeyoon Lee, Sunjong Park, Seoyong Lee, Sukjin Kim, Jinho Lee
cs.LG · cs.AI
Existing GNN quantization methods suffer from considerable quantization overhead, which severely limits their practical usage in real-world scenarios. To this end, we present TopGQ, an accurate post-training GNN quantization framework, alleviating redundant quantization overhead. We propose dual-axis scale absorption, which enables activation quantization along both the outer and inner dimensions by merging one into the adjacency matrix. On...
-
64
Foundation Models Meet Agriculture: Challenges Beyond Pretraining
Vishal Nedungadi, Xingguo Xiong, Marc Rußwurm, Ioannis N. Athanasiadis
cs.LG
Global food security and sustainable climate action increasingly rely on robust, scalable agricultural monitoring. Earth observation foundation models have emerged as powerful, label-efficient tools across general remote sensing domains, yet early attempts to deploy them for agricultural applications have yielded surprisingly poor results. We hypothesize that this performance gap stems from the extreme heterogeneity of agricultural landscapes...
-
65
Uncertainty of Vision Medical Foundation Models
Haoxu Huang, Narges Razavian
cs.LG
Accurate uncertainty estimation is essential for machine learning systems de- ployed in high-stakes domains such as medicine. Traditional approaches primarily rely on probability outputs from trained models (point predictions), which provide no formal guarantees on prediction coverage and often require additional calibra- tion techniques to improve reliability. In contrast, conformal prediction (region prediction) offers a principled...
-
66
DASC: Decay-Aware State Compression for Hybrid Linear-Attention Serving
Yanqi Yu, Pingwei Sun, Jianchao Tan, Tao Zhang, Yuchen Xie, Xunliang Cai, Yao Liu
cs.LG · cs.AI
Hybrid linear-attention architectures have recently scaled to large open-weight models, offering quality competitive with full attention while substantially reducing key/value (KV) cache growth. However, their in-place recurrent-state updates complicate cache management: prefix reuse requires state checkpoints alongside full-attention KV, while storing state checkpoints in full increases memory pressure, leading to more evictions and repeated...
-
67
RSLM: Training-Free Vector Quantization for Approximate Nearest Neighbor Search
Rastislav Lenhardt, Teodora Dobos, Thomas Vecchiato, Jiri Isa, Igor Ginzburg
cs.LG · cs.IR
By introducing RSLM (Rotated Scaled Lloyd-Max), a family of training-free vector quantization codecs compressing embeddings to 1--4 bits per dimension, we reduce memory cost and memory bandwidth of a typical large-scale Approximate Nearest Neighbor (ANN) search system, while reducing its complexity and keeping or improving recall across multiple benchmark datasets. State-of-the-art systems filter candidates using coarse partitions,...
-
68
Convergence rates for the RMSprop optimizer with full control of the hyperparameters
Steffen Dereich, Arnulf Jentzen
cs.LG · math.OC · math.PR
Popular adaptive stochastic gradient descent (SGD) methods to train artificial intelligence (AI) systems include the RMSprop, the Adam, and the AdamW optimizers, where the adaptivity parts in Adam and AdamW basically just coincide with RMSprop. Such adaptive methods involve several hyperparameters including the regularization parameter $ε$ (which ensures that one does not divide by 0 and is often chosen to be very close to zero such as...
-
69
Beat-Synchronous Tokenization for ECG Transformers
Ahmed Sameh, Nolan Wilson, Max Enderlein, Yogatheesan Varatharajah
cs.LG · eess.SP
Transformer-based electrocardiogram (ECG) models commonly tokenize waveforms into fixed temporal patches. Though convenient, fixed patching can split heartbeat structures across token boundaries. We study beat-synchronous tokenization as a physiologically grounded alternative, comparing fixed patches with three beat-aligned strategies: resampled beats, adaptive pooled beats, and resampled beats augmented with R--R interval information....
-
70
Mode Connectivity Beyond Classifiers: Evidence from Generative and Contrastive Models
Chengzheyi Yao, Yongzhao Zhang, Yongding Tian
cs.LG
The loss landscape of Deep Neural Networks (DNNs) exhibits highly complex and non-convex properties. Recent studies have revealed the phenomenon of mode connectivity, demonstrating that independently trained network modes can be connected via a continuous low-loss path. However, existing mode connectivity research is predominantly confined to classifier-based models, leaving it an open question whether similar geometric properties exist in...
-
71
Beyond Churn: Predicting Financial Fragmentation in Retail Banking with Temporal Machine Learning
Ananyaa Chopra, Brandon Xu, Brendan Yuen, Lauren Zung, Sarabroop Aulakh
cs.LG
Retail banking attrition is usually represented as a terminal binary event, even though client relationships often weaken earlier through partial movements of deposits, investments, and recurring activity to external financial institutions. This paper defines that preceding state as financial fragmentation and presents an end-to-end temporal machine-learning system for predicting it before complete disengagement. Using anonymized multi-source...
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.