cs.LG papers | Gist.Science

Characterizing MARL for Energy Control: A Multi-KPI Benchmark on the CityLearn Environment

This paper establishes a comprehensive multi-KPI benchmark for Multi-Agent Reinforcement Learning in urban energy management using the CityLearn environment, demonstrating that Decentralized Training with Decentralized Execution (DTDE) consistently outperforms Centralized Training with Decentralized Execution (CTDE) in both average and worst-case performance while offering greater resilience and sustainability.

Aymen Khouja, Imen Jendoubi, Oumayma Mahjoub, Oussama Mahfoudhi, Ruan De Kock, Siddarth Singh, Claude Formanek2026-03-10🤖 cs.LG

RAmmStein: Regime Adaptation in Mean-reverting Markets with Stein Thresholds -- Optimal Impulse Control in Concentrated AMMs

This paper introduces RAmmStein, a deep reinforcement learning framework that optimizes liquidity provision in concentrated Automated Market Makers by solving an impulse control problem via a Hamilton-Jacobi-Bellman quasi-variational inequality, thereby significantly reducing rebalancing frequency and gas costs while maximizing net returns through regime-aware, mean-reversion-informed decision-making.

Pranay Anchuri2026-03-10🤖 cs.LG

Benchmarking GNN Models on Molecular Regression Tasks with CKA-Based Representation Analysis

This paper benchmarks four GNN architectures on molecular regression tasks, demonstrating that a hierarchical fusion framework combining GNNs with molecular fingerprints outperforms standalone models by over 7% in RMSE, while CKA analysis reveals that GNN and fingerprint embeddings occupy highly independent latent spaces despite high convergence among isotopic GNN architectures.

Rajan, Ishaan Gupta2026-03-10🤖 cs.LG

MrBERT: Modern Multilingual Encoders via Vocabulary, Domain, and Dimensional Adaptation

The paper introduces MrBERT, a family of efficient, open-source multilingual encoders built on the ModernBERT architecture that achieves state-of-the-art performance in specific languages and specialized domains while leveraging Matryoshka Representation Learning to reduce inference and storage costs.

Daniel Tamayo, Iñaki Lacunza, Paula Rivera-Hidalgo, Severino Da Dalt, Javier Aula-Blasco, Aitor Gonzalez-Agirre, Marta Villegas2026-03-10🤖 cs.LG

Autoregressive Visual Decoding from EEG Signals

The paper introduces AVDE, a lightweight and efficient autoregressive framework that leverages contrastive learning and multi-scale token prediction to decode EEG signals into coherent images, outperforming state-of-the-art methods with significantly fewer parameters while mimicking the hierarchical nature of human visual perception.

Sicheng Dai, Hongwang Xiao, Shan Yu, Qiwei Ye2026-03-10🤖 cs.LG

CeRA: Breaking the Linear Ceiling of Low-Rank Adaptation via Manifold Expansion

CeRA overcomes the linear performance ceiling of Low-Rank Adaptation (LoRA) in complex reasoning tasks by introducing a weight-level parallel adapter with SiLU gating and structural dropout to induce manifold expansion, thereby achieving superior spectral efficiency and preventing rank collapse.

Hung-Hsuan Chen2026-03-10🤖 cs.LG

Scaling Search Relevance: Augmenting App Store Ranking with LLM-Generated Judgments

This paper addresses the scarcity of expert textual relevance labels in large-scale app store search by leveraging a specialized, fine-tuned LLM to generate millions of high-quality labels, which, when used to augment the production ranker, significantly improves both offline metrics and real-world conversion rates, particularly for tail queries lacking reliable behavioral data.

Evangelia Christakopoulou, Vivekkumar Patel, Hemanth Velaga, Sandip Gaikwad, Sean Suchter, Venkat Sundaranatha2026-03-10🤖 cs.LG

End-to-end Differentiable Calibration and Reconstruction for Optical Particle Detectors

This paper introduces the first end-to-end differentiable optical particle detector simulator that unifies simulation, calibration, and reconstruction into a single gradient-based framework, demonstrating improved accuracy, speed, and flexibility for analyzing large-scale neutrino detectors compared to traditional methods.

Omar Alterkait, César Jesús-Valls, Ryo Matsumoto, Patrick de Perio, Kazuhiro Terao2026-03-10🤖 cs.LG

Attn-QAT: 4-Bit Attention With Quantization-Aware Training

This paper introduces Attn-QAT, the first systematic 4-bit quantization-aware training framework for attention mechanisms that ensures stable FP4 training and inference by matching low-precision recomputation in the backward pass and correcting implicit precision assumptions, thereby eliminating quality drops and delivering up to 1.5x speedup on FP4-capable GPUs without relying on outlier-mitigation heuristics.

Peiyuan Zhang, Matthew Noto, Wenxuan Tan, Chengquan Jiang, Will Lin, Wei Zhou, Hao Zhang2026-03-10🤖 cs.LG

The Partition Principle Revisited: Non-Equal Volume Designs Achieve Minimal Expected Star Discrepancy

This paper introduces a new class of non-equal volume partitions that achieve a lower expected star discrepancy and improved upper bounds compared to classical jittered sampling, thereby providing a theoretical foundation for their use in high-dimensional numerical integration.

Xiaoda Xu2026-03-10🤖 cs.LG

How Well Do Multimodal Models Reason on ECG Signals?

This paper introduces a reproducible, scalable framework for evaluating multimodal models on ECG signals by decomposing reasoning into "Perception" (verified via code generation) and "Deduction" (verified via retrieval against clinical criteria) to address the limitations of existing manual or superficial evaluation methods.

Maxwell A. Xu, Harish Haresamudram, Catherine W. Liu, Patrick Langer, Jathurshan Pradeepkumar, Wanting Mao, Sunita J. Ferns, Aradhana Verma, Jimeng Sun, Paul Schmiedmayer, Xin Liu, Daniel McDuff, Emily B. Fox, James M. Rehg2026-03-10🤖 cs.LG

Opponent State Inference Under Partial Observability: An HMM-POMDP Framework for 2026 Formula 1 Energy Strategy

This paper proposes a tractable two-layer framework combining a Hidden Markov Model for inferring rival energy states and a Deep Q-Network for decision-making to optimize 2026 Formula 1 energy strategies under partial observability, specifically addressing the "counter-harvest trap" where opponents deliberately mask their deployment signals.

Kalliopi Kleisarchaki2026-03-10🤖 cs.LG

TCG CREST System Description for the DISPLACE-M Challenge

The TCG CREST system achieved a sixth-place ranking in the DISPLACE-M challenge's speaker diarization track by demonstrating that a hybrid end-to-end Diarizen framework with WavLM embeddings and optimized agglomerative hierarchical clustering significantly outperformed a SpeechBrain baseline, reducing the diarization error rate to 9.21% on the evaluation set.

Nikhil Raghav, Md Sahidullah2026-03-10🤖 cs.LG

A Detection-Gated Pipeline for Robust Glottal Area Waveform Extraction and Clinical Pathology Assessment

This paper presents a computationally efficient, detection-gated deep learning pipeline that achieves state-of-the-art robustness and cross-dataset generalization in glottal segmentation from high-speed videoendoscopy, enabling reliable extraction of clinical biomarkers for distinguishing healthy from pathological vocal function.

Harikrishnan Unnikrishnan2026-03-10🤖 cs.LG

Leveraging Model Soups to Classify Intangible Cultural Heritage Images from the Mekong Delta

This paper proposes a robust framework combining the hybrid CoAtNet architecture with model soups ensembling to effectively classify Intangible Cultural Heritage images from the Mekong Delta, achieving state-of-the-art performance on the ICH-17 dataset by reducing variance and enhancing generalization in data-scarce, high-similarity settings.

Quoc-Khang Tran, Minh-Thien Nguyen, Nguyen-Khang Pham2026-03-10🤖 cs.LG

Personalized Multi-Agent Average Reward TD-Learning via Joint Linear Approximation

This paper proposes and analyzes a personalized multi-agent average reward TD-learning algorithm that leverages joint linear approximation to learn shared subspaces and local heads, demonstrating convergence with linear speedup despite the challenges of environmental heterogeneity and Markovian sampling.

Leo Muxing Wang, Pengkun Yang, Lili Su2026-03-10🤖 cs.LG

Embedding interpretable $\ell_1$ -regression into neural networks for uncovering temporal structure in cell imaging

This paper proposes a hybrid neural network architecture that embeds an interpretable, $\ell_1$ -regularized vector autoregressive model within a convolutional autoencoder to effectively extract and visualize sparse temporal dynamics from two-photon calcium imaging data while preserving non-sparse spatial information.

Fabian Kabus, Maren Hackenberg, Julia Hindel, Thibault Cholvin, Antje Kilias, Thomas Brox, Abhinav Valada, Marlene Bartos, Harald Binder2026-03-10🤖 cs.LG

Interpretable Motion-Attentive Maps: Spatio-Temporally Localizing Concepts in Video Diffusion Transformers

This paper introduces GramCol and a motion-feature selection algorithm to generate Interpretable Motion-Attentive Maps (IMAPs) that effectively localize both motion and non-motion concepts in Video Diffusion Transformers without requiring gradient calculations or parameter updates.

Youngjun Jun, Seil Kang, Woojung Han, Seong Jae Hwang2026-03-10🤖 cs.LG

CGL: Advancing Continual GUI Learning via Reinforcement Fine-Tuning

This paper introduces CGL, a continual GUI learning framework that mitigates catastrophic forgetting by dynamically balancing Supervised Fine-Tuning and Reinforcement Learning through an entropy-guided proportion adjustment mechanism and a specialized gradient surgery strategy, validated by a new AndroidControl-CL benchmark.

Zhenquan Yao, Zitong Huang, Yihan Zeng, Jianhua Han, Hang Xu, Chun-Mei Feng, Jianwei Ma, Wangmeng Zuo2026-03-10🤖 cs.LG

Why Adam Can Beat SGD: Second-Moment Normalization Yields Sharper Tails

This paper provides the first theoretical proof that Adam's second-moment normalization yields significantly sharper high-probability convergence guarantees ( $\delta^{-1/2}$ dependence) compared to SGD ( $\delta^{-1}$ dependence) under the classical bounded variance model, thereby explaining its empirical superiority.

Ruinan Jin, Yingbin Liang, Shaofeng Zou2026-03-10🤖 cs.LG

← Previous Next →

cs.LG