cs.LG · 2026-08-09 · No. 79
Machine Learning, 2026-08-09.
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
An Optimal Agnostic PAC Algorithm
Markus Engelund Mathiasen, Jian Qian, Nikita Zhivotovskiy
cs.LG · cs.AI · cs.DS · math.ST
Let $H\subseteq\{-1,+1\}^X$ be a class of finite VC dimension $d\ge1$. Writing $L$ for the binary risk and $L^*=\min_{h\in H}L(h)$, we construct a learner achieving the statistically optimal risk bound: from an i.i.d.\ sample of size $n$, for every $0<δ\le 1/2$, with probability at least $1-δ$, \[ L(\widehat h) \le L^*+ 7\cdot10^8\left( \sqrt{\frac{L^*(d+\log(1/δ))}{n}} +\frac{d+\log(1/δ)}{n} \right). \] This settles the sample complexity of...
-
02
CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks
Fanzhe Meng, Guoxin Chen, Jiale Zhao, Shuang Sun, Zhiyu Lin, Wayne Xin Zhao, Ruihua Song, Ji-Rong Wen, Kai Jia
cs.LG · cs.CL
Training terminal agents requires executable and verifiable tasks that are not merely solvable, but appropriately challenging for learning. Executable validation establishes feasibility, yet does not reveal how a task behaves relative to a given solver setting. In this paper, we present CalibForge, an autonomous terminal-task synthesis system that uses verified solver behavior to revise candidate tasks through adversarial solver calibration....
-
03
RRC: Unlocking Generative Reward Models in LLM Reinforcement Learning via Ranking-Based Reward Construction
Chenglong Wang, Ziming Zhu, Yifu Huo, Bei Li, Qiaozhi He, Yan Ding, Xiaoyang Hao, Yuxin Gao, Tianhua Zhou, Xiaojia...
cs.LG · cs.CL
Recent advances in reward modeling show a paradigm shift from discriminative reward models to generative reward models. However, despite their strong capabilities in response ranking, generative reward models have not realized their potential in reinforcement learning (RL). Our analysis reveals that this limitation arises from a mismatch between the comparative nature of generative reward modeling and the scalar scoring paradigm adopted by...
-
04
On-Policy Self-Distillation without Any Supervision
Yijiang Li, Bingyang Wang, Yijun Liang, Yunjie Tian, Di Fu, Nuno Vasconcelos
cs.LG
On-policy (Self-)Distillation (OPD / OPSD) has shown strong potential for post-training large language models (LLMs). However, existing methods still rely heavily on external supervision, including ground-truth signals, environmental feedback, or guidance from larger models, and therefore fall short of genuine "self"-distillation. In this study, we show that on-policy self-distillation can be achieved using only a model's own generations via...
-
05
BaKron: Efficient Quantization with Kronecker-Factored Hessians
Johann Birnick, Rayan Saab
cs.LG · cs.AI
We accelerate a family of algorithms for neural network quantization whose geometry is informed by any Kronecker-factored approximation of the Hessian. GPTQ-style adaptive rounding typically uses one-sided information derived from input activations. Two-sided Kronecker-factored Hessian approximations can additionally capture correlations across output coordinates, but applying GPTQ directly in the vectorized weight domain is computationally...
-
06
Surv-IPTB: An Attention-Based Model for Estimating Individual Probability of Treatment Benefit with Survival Data
Lev V. Utkin, Stanislav K. Kogan, Andrei V. Konstantinov
cs.LG · stat.ML
This work presents a novel attention-based framework for estimating the Individual Probability of Treatment Benefit (IPTB) in survival analysis contexts. The proposed model, called Surv-IPTB, directly quantifies the probability that a specific patient will experience extended survival time under treatment versus control. We reformulate IPTB estimation as a binary classification problem, leveraging pairwise patient comparisons across treatment...
-
07
The Tamed Subgradient Unadjusted Langevin Algorithm beyond Convexity
Iosif Lytras, Nikolaos Makras, Sotirios Sabanis
cs.LG · math.OC · math.PR · stat.ML
We study the problem of sampling from target distributions whose potentials are simultaneously non-smooth, subject to superlinear gradient growth, and non-convex. We introduce the Subgradient Tamed Unadjusted Langevin Algorithm (SG-TULA), a discretisation of the Langevin diffusion that operates directly on subgradients, without relying on computationally demanding smoothing procedures. To handle the superlinear regime, taming techniques are...
-
08
Hypothesis Testing with Conditional Queries: Learnability and the Value of Interaction
Zonghuan Xu
cs.LG · math.ST
Model evaluations may fix all tests before observing any responses or select later tests using earlier responses. We study this choice in a conditional-query model on a finite outcome space $\mathcal{X}$ with $|\mathcal{X}|=N$. We first ask which pairs of distribution classes can be reliably distinguished. We then ask how many additional queries are required to match an adaptive tester when all queried events must be fixed in advance. We show...
-
09
RxnCLF: Contrastive Transformation-Aware Reaction Foundation Model for Improved Reactivity Prediction
Yiting Zheng, Cheng Fang, Anthony Donofrio, Haote Li
cs.LG
Reaction yield prediction remains challenging because labeled data are scarce and reaction space is both combinatorially large and sparsely populated, limiting the generalization of existing reaction representations. String-, fingerprint-, and graph-based reaction encodings only partially capture chemical transformations, making accurate prediction difficult for reactions with complex substrates. We propose reaction contrastive learning...
-
10
MetaboLLM: a metabolomics-specialized large language model for biochemical knowledge integration and predictive metabolite graph construction
Dohyun Ku, Min Gu Kwak, Francisco J. Pasquel, Jing Li
cs.LG
Metabolomics knowledge is distributed across heterogeneous resources and remains difficult to translate into predictive representations. We developed MetaboLLM, a metabolomics-specialized large language model adapted through continual pretraining, supervised fine-tuning, and structured retrieval, together with MetaboLLM-GIN, which converts generated biochemical descriptions into metabolite graphs for patient-level prediction using a graph...
-
11
A Six-Dimensional Taxonomy of Post-Training Adaptation Techniques with Applications in AI Governance
Fardin Afdideh, Fernando Seoane, Farhad Abtahi
cs.LG
Post-training adaptation has become central to modern machine learning practice and includes techniques such as retraining, fine-tuning, parameter-efficient adaptation, alignment, retrieval augmentation, model editing, unlearning, calibration, and Multimodal Instruction Tuning. However, the literature remains fragmented across technique families, model classes, and deployment contexts, making it difficult to compare methods or describe how a...
-
12
Timestep-Conditioned Transformers for Global Weather Forecasting
Sam Levang, Fran Bartolic, Ty Dickinson, Chase Dwelle, Paulius Rauba, Viktor Cikojevic
cs.LG · cs.OS
Existing machine-learning weather forecasting models rely on predetermined and fixed autoregressive timesteps. The choice of model timestep involves a fundamental trade-off: shorter timesteps (e.g. 1 to 6 hours) finely resolve atmospheric dynamics within the diurnal cycle but increase error accumulation for a given forecast horizon, while longer timesteps (e.g. 24 hours) reduce error accumulation but limit the usability of short-range...
-
13
Continual Learning in Transition
Zhiyan Hou, Dan Zhang, Tao Feng, Liyuan Wang, Wei Li, Xiangzhao Hao, Hongyan An, Junfeng Fang, Haokai Ma, Zhaohui...
cs.LG · cs.AI
Classical continual learning (CL) has primarily focused on enabling models to update and retain knowledge through parameter-centric mechanisms, e.g., training strategies, architectural designs, and weight adaptation. However, emerging paradigms are reshaping the scope of CL beyond this traditional model adaptation view. For instance, on-policy learning broadens the space of update mechanisms; test-time training extends CL from the training...
-
14
SAGA: Score-Weighted Adaptive Generation Alignment for Low-Resource Nordic Language Models
Hoda Fakharzadehjahromy, Emil Wiman, Andreas Bueff, Hafsteinn Einarsson, Fredrik Heintz
cs.LG
Preference optimisation has proven effective for improving large language models but typically relies on costly human preference annotations. Extending these methods to morphologically rich, low-resource languages remains challenging because such annotations are scarce. We present SAGA (Score-weighted Adaptive Generation Alignment), a parser-guided preference optimisation framework that replaces human labels with dependency-parser...
-
15
Threshold-Based Early Stopping of Accumulations in Neural Networks with Binary Activation
Quentin Luquet de Saint-Germain, Massil Ait Abdeslam, Jean Pierre David
cs.LG · cs.NE
Binary neural networks are very attractive for constrained deployment, enabling small footprint and low-power inference. For binary activations, the dot products become sign-controlled additions or subtractions, but the number of operations is unchanged. Indeed, every neuron or output channel still accumulates all of its input, even though only the sign will be retained, which is often wasteful. As the accumulation progresses, the running...
-
16
SkillTFM: Gated Skill Evolution for Training-Free Adaptation of Tabular Foundation Models
Yi He, Zhengkang Guan, Anpeng Wu, Peng Cui, Fei Wu, Kun Kuang
cs.LG
Tabular data are ubiquitous in real-world applications and are crucial for data-driven prediction and decision-making across science, industry, finance, healthcare, and public services. Tabular foundation models (TFMs) have emerged as a promising paradigm for general-purpose tabular learning, offering reusable predictors across diverse datasets and substantially reducing the need for task-specific training, tuning, and model development....
-
17
LLM Inference Under Bursty Workload Distribution: Modifying the WAIT Algorithm
Anjali Gangadhar Katageria, Shobha Rani, Raghu Nandan Sengupta
cs.LG
Large Language Models (LLMs) such as ChatGPT and Claude are widely used for information retrieval and problem-solving. Recent work has focused on improving scheduling algorithms to boost throughput while maintaining low latency. However, these approaches often assume Poisson request arrivals with constant rates - an assumption that fails to reflect the inherently bursty and dynamic nature of real-world traffic. We propose a lightweight...
-
18
Is Self-Pretraining really useful to improve diagnosis in medical Time Series?
Omar Coser, Antonio Orvieto, Paolo Soda, Loredana Zollo
cs.LG · cs.AI
Inspired by recent evidence that transformer architectures benefit from Self-PreTraining (SPT) on long-context benchmarks, we investigate whether similar gains extend to multimodal, multivariate, and even simple univariate medical time series. Our objective is to assess the impact of SPT on the performance and scalability of transformer-based models across diverse medical applications, particularly under limited data conditions. We evaluate...
-
19
Kastor: An efficient fine-tuning strategy for generative emulation of PDE simulations
Guillaume Couairon, Alexis Jacq, Yu-Han Wu, Renu Singh, Yana Hasson, Quentin Berthet, Romuald Elie
cs.LG · math.NA
Machine learning offers a promising avenue to accelerate physical simulations by replacing computationally expensive traditional Partial Differential Equation (PDE) solvers with fast, differentiable surrogate models. However, standard auto-regressive ML emulators often suffer from error accumulation over long horizons and struggle to capture the stochasticity of complex physical systems. In this paper, we propose Kastor, a comprehensive...
-
20
Does Latent Context Help? A Controlled Evaluation of Inverse Reinforcement Learning in Arctic Shipping
Vaishnav Vaidheeswaran, Dilith Jayakody, Biruk Ambaw, Jaswanth Kumar, Md Mahbub Alam, Gabriel Spadon
cs.LG · cs.AI · cs.MA
Artificial Intelligence (AI)-assisted navigation can help Arctic shipping adapt to rapidly changing sea-ice conditions, but reliable deployment requires reward models that are interpretable and robust to changing environments. Inverse reinforcement learning (IRL) provides a framework for recovering such rewards from vessel trajectories, while recent meta-IRL methods introduce latent context variables to capture behavioral heterogeneity....
-
21
Dynamic Graph Prompting via Topology-Routed Mixed-Curvature Experts
Quanxin Wang, Xuanting Xie, Bingheng Li, Xingtong Yu, Shuo Wang, Ruiyi Fang, Zhao Kang
cs.LG
Dynamic graph prompting freezes a pre-trained temporal backbone and adapts it to label-scarce downstream tasks using lightweight prompts. However, existing methods operate within a single, fixed embedding space. In this work, we reveal that temporal shifts in local clustering and degree heterogeneity actively reorganize the edge curvature spectrum---indicating that the optimal representation geometry dynamically evolves with local topology...
-
22
Hybrid-Adaptive Thread Tuning to Mitigate Simulation Execution Bottlenecks in High-Performance Reinforcement Learning Inference
Jiming Su, Hantao Hua, Lujia Yin, Yiping Yao, Feng Zhu
cs.LG · cs.MA · cs.PF
In simulation-in-the-loop decision-making systems, reinforcement learning (RL) inference is often constrained by simulator-side execution overhead, where workloads are highly dynamic and sensitive to runtime thread configurations. Existing multithreaded strategies struggle to match thread resources before or during execution, causing resource contention, scheduling overhead, and reduced throughput. Through empirical analysis, we identify the...
-
23
BioKD: Selective Physiology-to-Video Knowledge Distillation via Reliability Gate for Emotion Recognition
Bojing Hou, Ruohao Li, Yitong Zhu, Hongjun Liu, Luwen Yu, Yuyang Wang
cs.LG
To address the limitations of video-based emotion recognition under ambiguous or socially masked behavioral cues, as well as the poor deployability of physiological signals, this paper proposes a reliability-aware physiology-to-video knowledge distillation framework, termed BioKD. The proposed framework leverages physiological signals as privileged information during training to guide a video-based student model in learning deep affective...
-
24
ProDVI: Programmatic Dynamics Priors for Value Network Initialization
Xinwei Liu, Junyuan Liang, Jianting Zhang, Wuhui Chen
cs.LG · cs.AI
Deep Reinforcement Learning (RL) is notoriously sample inefficient. One contributing factor is that RL agents are typically initialized from scratch, forcing them to acquire task-relevant knowledge through online interaction. Existing approaches obtain informative initializations through pre-collected datasets, high-fidelity simulators, or meta-learning over related tasks, but these prerequisites may be difficult to access or even...
-
25
Do Tabular Foundation Models Agree with Themselves?
Christian Klötergens, Vijaya Krishna Yalavarthi, Lars Schmidt-Thieme, Tom Hanika
cs.LG
Tabular Foundation Models (TFMs) are currently the best approach to tabular prediction problems. They are constructed as transformers that approximate the Bayesian posterior predictive distribution based on a pre-training prior. These univariate predictors can be converted into multivariate ones autoregressively by sampling one target and adding it to the features. However, the faithfulness of the resulting joint has not been investigated....
-
26
A Unified Risk View of Uncertainty: Posterior Risk for Disentanglement and Evaluation Beyond Proxies
Frieder Wizgall, Georg Tirpitz, Moritz Seiler, Kerstin Ritter, Bálint Mucsányi
cs.LG
Reliable uncertainty estimates are critical in safety-sensitive applications, where understanding the sources of predictive uncertainty is essential. This often requires disentangling epistemic uncertainty from aleatoric uncertainty, yet these uncertainty types are not defined consistently across the literature, making it difficult to assess whether a method produces accurate uncertainty estimates. Evaluation is further complicated by the...
-
27
Observation-Grounded Self-Predictive Reinforcement Learning for Visual Continuous Control
Xinwei Liu, Junyuan Liang, Jianting Zhang, Wuhui Chen
cs.LG · cs.RO
Sample-efficient policy learning from pixels is a long-standing challenge in reinforcement learning (RL). Recent dynamics-based representation learning methods have significantly improved the sample efficiency of model-free visual RL by learning dynamics-aware representations through auxiliary prediction performed either in latent space (self-prediction) or observation space (observation prediction). However, state-of-the-art methods from...
-
28
THBKG: A Temporal Biomedical Knowledge Graph for Decision-Aligned Clinical Advancement Prediction
Pui Chung Siu, Claudia Cabrera, Mani Mudaliar, Arkaitz Zubiaga
cs.LG · q-bio.QM
Inadequate target--disease linkage accounts for 40--50\% of Phase~II efficacy failures, so anticipating which programmes will advance would let sponsors back the hypotheses most likely to reach patients. What a programme can be judged on is the evidence that supported its linkage \emph{when it entered the clinic}. No existing biomedical knowledge graph allows that evidence profile to be assembled as of a past date. We present the Temporal...
-
29
How Far Do Simple Transformations Translate Across Text Embedding Models?
Sid Ali Hamideche, Louis Adrien Dufrene, Quentin Lampin, Guillaume Larue
cs.LG
We investigate whether simple transformations can translate representations across heterogeneous text embedding models. Understanding how independently trained models organize semantic information is an enabler for AI-to-AI latent communication without decoding into human-readable text. Focusing on lightweight translators such as linear mappings, we test the literature hypothesis of latent universality in a realistic text setting beyond...
-
30
BioM-JEPA: joint-embedding prediction of graph-connected gene blocks in single cells
Yuhao Wang, Zelin Zang, Yuxuan Liu, Zhen Lei, Stan Z. Li
cs.LG
Single-cell transcriptomes are sparse observations of coordinated biological programmes, yet most self-supervised models learn by reconstructing individual genes. Here we present BioM-JEPA, a joint-embedding predictive architecture that instead predicts aggregate representations of graph-connected gene blocks defined by protein-association and corpus-derived coexpression evidence. A student network infers each target-block representation from...
-
31
CohortHijack: Robustness of Single Cell Annotation to Companion Cell Removal
Arash Vashagh, Yasmin Vashagh
cs.LG
Many single-cell annotation tools refine an initial cell label using nearby cells or cluster-level voting. We study whether this refinement can be manipulated without changing the target cell. We introduce CohortHijack, a robustness audit that removes selected non-target cells from the query cohort while preserving the target expression profile, base prediction, and trained model. We evaluate random and structured removal methods, together...
-
32
Alternating Levenberg-Marquardt Training of Physics-Informed Neural Networks with Fourier-Enhanced Features
Yulun Wu, Matthieu Barreau, Miguel Aguiar, Karl H. Johansson
cs.LG · math.NA
Physics-informed neural networks (PINNs) often fail to accurately resolve partial differential equations (PDEs) with high-frequency or multi-scale solutions, as well as strongly nonlinear problems. Two factors underlie this difficulty: spectral bias, the tendency of neural networks to underfit high-frequency features; and representation-coefficient coupling, the entanglement of representation learning and coefficient fitting within a single...
-
33
Beyond Feature Importance: A Comparative Analysis of Pattern Detection Methods in Cluster Interpretation
Benjamin Connor, Anna Jurek-Loughrey, Lu Bai, Muhammad Fahim
cs.LG · cs.AI
Interpreting clustering outcomes remains a fundamental challenge in data analysis, particularly in domains such as healthcare where meaningful patterns must be extracted from high-dimensional data. While numerous explainability techniques exist, they are primarily designed to assess feature importance or provide local instance-level explanations rather than to identify structured patterns present within clusters. This work presents a...
-
34
Evidential Rule Learning for Interpretable Classification with Abstention
Javier Fumanal-Idocin, Javier Andreu-Perez
cs.LG · cs.AI
Interpretable classification often requires more than accurate predictions for real-life deployment: models should be transparent about the evidence behind their decisions and abstain when they cannot decide reliably. We introduce Fast Evidential Rule Learning (FERL), a method that learns interpretable, accurate fuzzy rule models whose outputs are evidential. Unlike post-hoc calibration, FERL's belief, plausibility, and abstention...
-
35
Learning to Rank Tensor Network Contraction Plans for GPU-Accelerated Quantum Circuit Simulation
Alfred M. Pastor, Maribel Castillo, Jose M. Badia
cs.LG · cs.DC · cs.PF · quant-ph
Classical simulation remains essential for developing and validating quantum algorithms, but its cost grows rapidly with circuit size. Tensor-network contraction can reduce this cost by exploiting circuit structure, although its efficiency depends strongly on the chosen contraction plan. On GPUs, plans with similar theoretical complexity may perform very differently because execution also depends on parallelism, reduction structure, memory...
-
36
Predicting Task Difficulty Without Rollouts
Stefan Krsteski, Charlotte Meyer
cs.LG · cs.CL
Task difficulty dictates an agent's likelihood of success, and estimating it without rollouts means forecasting this directly from a task description before executing costly simulations in stateful environments. Reliable estimates would therefore allow environment designers to calibrate evaluation benchmarks and construct progressive training curricula. This becomes increasingly important as agents move into long-horizon domains, where...
-
37
GROM: Gradient-Free Rapid One-Shot Machine Unlearning
Paweł Batorski, Przemysław Spurek, Paul Swoboda
cs.LG · cs.AI · cs.CL
Machine unlearning has become a critical capability for safely removing specific, sensitive knowledge from large language models (LLMs). Current state-of-the-art approaches primarily rely on iterative, training-time unlearning via fine-tuning. However, even when utilizing parameter-efficient dimensionality reduction techniques like LoRA, gradient-based optimization remains computationally expensive and lacks explicit analytical formulations....
-
38
Neuro-Symbolic Closed-Loop Control of Laser Powder Bed Fusion with an In-Loop Ontology
Gisuk Hong, Jaebong Cho, Hyunbo Cho
cs.LG
A geometry-conditioned, neuro-symbolic closed-loop architecture is proposed for laser powder bed fusion, in which a standards-aligned ontology operates inside the control loop and couples symbolic reasoning with statistical learning to set the targets of a constraint-aware predictive controller. The ontology links the process objectives and constraints to the signals a controller can observe, and a description-logic reasoner converts them...
-
39
Accelerating nanodrug development in continuous flow systems using informed prediction models based on low-cost surrogate nanoparticles
Kai Dahms, Eilien Heinrich, Jochen Schmid, Michael Bortz, Iryna Savych, Regina Bleul
cs.LG · cs.CE
The development of nanotherapeutics often involves extensive empirical optimization due to the sensitivity of nanoparticle properties, such as size and polydispersity index (PDI), to minor changes in process parameters. Factors like formulation concentration, flow rates, and mixing ratios can significantly influence clinical efficacy and therapeutic outcomes. The absence of predictive mathematical frameworks has made iterative experimental...
-
40
Equipment-centric workpiece localization in near real-time using deep learning-based vision and event-driven finite state machines
Dohyeon Kong, Jaebong Cho, Hyunbo Cho
cs.LG
Continuous workpiece localization is essential for traceability and process coordination in hot forging, but direct tracking is unreliable because of extreme temperatures, surface degradation, and irregular routing. This study presents an equipment-centric framework that infers workpiece locations from handling equipment observed by multiple static 2D cameras. The framework estimates floorplan-space 3D equipment coordinates and recognizes...
-
41
Multivariate Time Series Forecasting needs Cross Variable Loss
Kuiye Ding, Yifan Hu, Hanchen Wang, Hao Xue
cs.LG · cs.AI
Multivariate time series forecasting presents unique challenges because future variables often co-evolve under shared system dynamics. While existing studies mainly focus on cross-variable dependencies in historical observations, dependencies among future values are much less explored. Specifically, modern forecasting models largely follow the Direct Forecasting (DF) paradigm, generating multi-step forecasts with point-wise objectives that do...
-
42
CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits
Mehrshad Saadatinia, Parsa Razmara, Ardalan Aryashad, Ali Abbasi, Seyedarmin Azizi
cs.LG
Controlling the behavior of large language models (LLMs) remains a critical challenge for AI alignment. Existing steering methods, such as Contrastive Activation Addition (CAA), typically rely on fixed single-layer interventions derived from aggregate activation differences. These methods impose a single intervention across semantically diverse inputs and often fail to sustain consistent behavioral changes across layers, limiting the...
-
43
Spectral Aliasing Pretext: A novel task for Self-Supervised fault diagnosis in rotating machinery
Victor Gialis, Maxime Metz, David Esteve, Abdenour Soualhi
cs.LG · cs.AI
Deep learning is a new way for machinery fault diagnosis but requires extensive labeled data, a scarce resource in industrial settings. We propose Spectral Aliasing Pretext (SAP), a self-supervised learning method that pretrains models on unlabeled vibration data by exploiting spectral aliasing. We deliberately undersample signals to create folded spectrum, then train a Transformer to reconstruct the original unfolded spectrum. This pretext...
-
44
SEAM: Global consistency beyond local accuracy in scientific machine learning
Gnankan Landry Regis N'guessan, Bum Jun Kim
cs.LG · cs.CE
Scientific machine learning commonly validates models at the level of a subdomain, a benchmark split, or an explanation for one prediction. Yet such local checks cannot establish whether the resulting explanations can be assembled into one globally admissible explanation. We introduce Scientific Explanation-Admissibility Machines (SEAM), a generator-agnostic framework that makes this local-to-global consistency question computable across...
-
45
Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading
Rasul Khanbayov, Hasan Kurban
cs.LG
Label-free reliability for vision-language models rests on invariance: perturb the input and a faithful reader's answer should not change. This has a known blind spot, a systematic misreading survives the perturbation and gets certified wrong, which we show is computable, not just real: an error is invisible to an edit exactly when the two commute, so the errors a suite cannot reach form its joint centralizer, a set that shrinks as edits are...
-
46
When Does Consensus Mean Correctness? Measuring the Agreement-Accuracy Coupling with Semantics-Preserving Re-Rendering
Rasul Khanbayov, Hasan Kurban
cs.LG
A model's agreement across perturbed inputs is used both as a label-free reliability signal and as a self-training target, on the premise that agreement tracks correctness. That coupling is rarely measured directly: natural-image perturbations preserve meaning only by assumption, and no exact answer key localizes errors. Scientific figures remove both obstacles, a figure is drawn from data by a program, so redrawing it yields images that are...
-
47
Potential Matching Optimal Transport: Continuous Normalizing Flows for Exact $p$-Wasserstein Dynamics
Lishuo Zhang, Ruizhi Huang, Yang Yu, Lei Li
cs.LG · math.NA
We introduce Potential Matching Optimal Transport (PMOT), a potential-flow framework for general $p$-cost optimal transport with $c_p(x,y)=\|x-y\|^p$. PMOT parameterizes the CNF velocity field with a scalar potential in the generalized Benamou--Brenier form for the chosen exponent $p$. It trains the potential gradient with a self-induced matching loss along straight bridges determined by the model's own endpoints, while allowing flexible...
-
48
Reasoning Errors Have a Region and a Direction in the Residual-Stream Trajectory of LLMs
Hamed Damirchi, Ignacio Meza De la Jara, Damith Ranasinghe, Yuhang Liu, Javen Shi
cs.LG · cs.CL
As language models are increasingly used for tasks that require verifiable reasoning, reliably distinguishing sound reasoning from flawed reasoning has become an important practical problem. Recent trajectory-based methods seek this signal in layerwise residual-stream displacements, which capture how representations change while attenuating some stable, token-specific information. However, displacement omits the state from which an update...
-
49
GAUGE: Granularity-Adaptive Counterfactual Gating of Evidence for Incomplete Multimodal Classification
Yunping Shi, En Yu, Kairui Guo, Jie Lu
cs.LG · cs.AI
Multimodal classification typically assumes all modalities are available, yet real-world inputs are often incomplete. Imputation and dynamic fusion can mitigate such incompleteness, but existing methods operate at a coarse modality level and thus cannot retain reliable components while suppressing misleading ones within the same recovered modality, compromising prediction reliability. To address this issue, we propose GAUGE, a lightweight...
-
50
LC-GRPO: Bridging Train-Inference Gap for Flow-Based GRPO with Langevin Correction
Yingqing Guo, Hui Yuan, Zijian He, Mengdi Wang, Zheng Ding
cs.LG · cs.AI · cs.CV
Flow-based generative models are typically sampled by solving a deterministic ordinary differential equation (ODE), whereas online reinforcement learning requires stochastic rollouts for policy exploration and optimization. Existing GRPO methods for flow models therefore replace the inference-time ODE with a stochastic differential equation (SDE) during training. Although the ODE and SDE share the same marginal distributions in continuous...
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.