AI-generated summaries

Today's ML research,
without the noise.

Daily summaries of the latest machine learning papers from arXiv, processed every 8 hours.

48 Papers today
8h Update frequency
7 Days of history
Proxy Exploration and Reusable Guidance: A Modular LLM Post-Training Paradigm via Proxy-Guided Update Signals
Daocheng Fu, Rong Wu, Yu Yang, Xuemeng Yang, Jianbiao Mei, Licheng Wen, Pinlong Cai, Yong Liu, Botian Shi, Yu Qiao
Large Language Models Optimization Efficient ML
  • PUST decouples update-signal exploration from distribution alignment, enhancing efficiency.
  • A lightweight proxy model is used for exploration, reducing computational costs.
  • Relative improvement signals are extracted and transferred to guide primary model updates.
  • The framework supports asynchronous signal generation and cross-model transfer.
Read more
Reinforcement Learning with Verifiable Physics: Post-training LLMs with Continuous Rewards
Pengfei Cai, Utkarsh Utkarsh, Alan Edelman, Christopher Vincent Rackauckas, Rafael Gomez-Bombarelli
Reinforcement Learning Large Language Models Theory
  • Introduction of a hybrid verifier combining binary and continuous rewards for PDE solver generation.
  • Creation of a multi-PDE solver dataset and a reproducible post-training pipeline.
  • Demonstration of a single policy's ability to learn across diverse PDE families.
  • Smaller RLVP-trained models outperform larger static prompting baselines.
Read more
OmniPMNet: Bridging discrete and gridded PM10 forecasts via omni-query neural processes
Shuangshuang He, Shuo Wang
Graph Learning Time Series Multimodal
  • OmniPM-Net effectively combines discrete and gridded PM10 forecasts using a shared spatial representation.
  • The model outperforms both traditional chemical transport models and graph neural networks in accuracy and spatial resolution.
  • Significant improvements are observed in high-concentration PM10 scenarios and during severe dust events.
  • The approach provides a general framework for fusing heterogeneous atmospheric data sources.
Read more
The Singularity Space: A Generative Diffusion Framework for Signal Representation
Eli Bar-Yosef, Amir Averbuch, Eli Turkel
Generative Models Audio & Speech Theory
  • Introduces a generative framework that uses complex-plane singularities for signal representation.
  • Achieves interpretability by linking singularity configurations to physical parameters.
  • Demonstrates structural stability, reducing artifacts at discontinuities.
  • Shows significant improvements in reconstruction accuracy over traditional grid-based methods.
Read more
Differentiable Clone-Structured Causal Graphs for End-to-End Cognitive Map Learning from Image Sequences
Arash Nikzad, Sasan Sarbishegi, Ali Dasmeh, Muhammad Asif, Parsa Gharavi, Erik Husom, Sagar Sen, Andrew B. Lehr, Olivier Penacchio, Ana Clemente, Tristan M. StΓΆber
Computer Vision Graph Learning Generative Models
  • Introduction of gradCSCG, a differentiable version of the CSCG algorithm.
  • Development of an end-to-end trainable pipeline combining gradCSCG and VQ-VAE.
  • Implementation of loss-balancing mechanisms for stable joint training.
  • Successful recovery of topological maps from aliased image sequences.
Read more
Scale-Aware Attention for Scarce Neural Data: An RG-Flow Transformer on Sleep-EDF EEG
Dibakar Sigdel
Time Series Theory Interpretability
  • Introduction of the RG-Flow Transformer, which incorporates scale-aware attention mechanisms.
  • Benchmarking against a vanilla transformer shows no significant accuracy advantage in sleep staging tasks.
  • RG-Flow Transformer successfully recovers the spectral exponent Ξ², enhancing interpretability.
  • Study emphasizes the challenges of working with scarce neural data and the importance of inductive biases.
Read more
Data-Driven Telecom Marketing Optimization: A Machine Learning-Based Churn Prediction and Customer Segmentation Framework
Nada Ali, Lina Ahmed, Tahani Abdalla Attia Gasmalla
Optimization
  • Development of a comprehensive ML pipeline for churn prediction and customer segmentation.
  • Utilization of advanced gradient boosting techniques for improved churn prediction accuracy.
  • Implementation of K-Means clustering for actionable customer segmentation.
  • Creation of a transparent ROI/CLV framework to assess marketing interventions.
Read more
From Global to Factor-Wise Expert Composition in Discrete Diffusion Models
Haozhe Huang, Yudong Xu, Abhijoy Mandal, AlΓ‘n Aspuru-Guzik
Generative Models Computer Vision Theory
  • Introduction of FactorDiff, a factor-wise composition framework for discrete diffusion models.
  • Dynamic routing of factors to relevant experts improves performance over traditional global scalar weighting methods.
  • Empirical validation on the ARC-AGI benchmark shows significant gains in logical consistency and spatial reasoning tasks.
  • The method highlights the importance of spatial and functional independence among experts in generative modeling.
Read more
Knowledge-Conditioned, Single-Pass LLM Synthesis of Executable Unity Game Scenes: A Compiler Error Census across 26 Goal Playable Concepts
Hugh Xuechen Liu, KΔ±vanΓ§ Tatar
Large Language Models
  • Introduces a Grounding/Hygiene taxonomy for categorizing compiler errors in LLM-generated Unity scripts.
  • Conducts a comprehensive error code census across 10,400 generated scripts, revealing patterns in model performance.
  • Demonstrates that larger models and different generation modes do not lead to successful compilations.
  • Links error profiles to gameplay design semantics, providing a framework for understanding model limitations in game design.
Read more
An Agentic AI Scientific Community for Automated Neural Operator Discovery
Luis Loo, Ulisses Braga-Neto
Theory Optimization Large Language Models
  • Introduces an agentic framework for neural operator discovery using a decentralized AI scientific community.
  • Demonstrates the importance of LLM agency in preserving architectural diversity during the discovery process.
  • Finds that no single neural operator architecture is universally superior, supporting a no-free-lunch theorem.
  • Evaluates the framework on multiple PDE problems, showcasing its effectiveness in discovering efficient neural architectures.
Read more
Graph-Constrained Policy Learning for Extreme Clinical Code Prediction
Amritpal Singh, Sebastian Torres, Khawar Shakeel, Syed Ahmad Chan Bukhari
NLP Graph Learning
  • Introduces a graph-constrained traversal policy for clinical code prediction.
  • Outperforms traditional flat multi-label classification methods.
  • Demonstrates that a single shared policy can match complex architectures.
  • Highlights the importance of increasing supervised training data.
Read more
Learning from Local Walks on Dynamic Graphs with Bandit Feedback
Sourav Chakraborty, Amit Kiran Rege, Claire Monteleoni, Lijun Chen
Graph Learning Theory Reinforcement Learning
  • Introduces a novel framework for stochastic multi-armed bandits on dynamic graphs with local movement constraints.
  • Establishes a structural condition (sliding-window mixing) that ensures stable exploration and navigation.
  • Analyzes local explore-then-commit algorithms that achieve sublinear expected regret.
  • Proposes a reward-aware strategy with formal guarantees on safety and performance.
Read more
Reliability Scaling Laws for Quantized Large Language Models
Sirine Ayadi, SΓ‘ndor DarΓ³czi, Stephan GΓΌnnemann, Bertrand Charpentier
NLP Large Language Models Efficient ML
  • Introduces a reliability evaluation framework for quantized LLMs focusing on uncertainty, calibration, and robustness.
  • Finds that reliability peaks at 4-bit quantization, suggesting an optimal trade-off between reliability and efficiency.
  • Demonstrates that quantization improves robustness to semantically-preserving input perturbations.
  • Conducts a comprehensive evaluation of six quantization techniques across models ranging from 1 billion to 70 billion parameters.
Read more
ERP Data Provisioning Financial Control Testing
Anitha Samudrala
Optimization
  • SEQ-FCT framework combines multiple data provisioning techniques to enhance financial control testing.
  • Utilizes a synthetic dataset to evaluate the effectiveness of the proposed methods.
  • Achieves high performance metrics in reconciliation and fraud detection while minimizing data leakage risk.
  • Highlights the necessity of integrated governance in data provisioning for ERP systems.
Read more
Mathematics of Data Science
Afonso S. Bandeira, Amit Singer, Thomas Strohmer
Theory Optimization Graph Learning
  • Emphasizes the foundational role of mathematics in data science.
  • Covers a wide range of topics including high-dimensional geometry, linear regression, and deep learning.
  • Includes exercises to facilitate understanding and application of concepts.
  • Aims to serve as a comprehensive resource for both researchers and practitioners in data science.
Read more
The Spectrum Is Not Enough: When Context Helps Time-Series Forecasting
Mert Onur Cakiroglu, Mehmet Dalkilic, Hasan Kurban
Time Series
  • Distinction between series-level predictability and configuration-level context value.
  • Introduction of the 'coverage deficit' as a diagnostic tool for assessing context value.
  • Demonstration that spectral indices do not capture the benefits of context due to phase randomization.
  • Experimental validation showing that context can significantly alter forecasting outcomes.
Read more
Machine Learning-based Correlation of Charpy Impact Properties Between Sub-sized and Standard-sized Specimens for Nuclear Structural Materials
Yugandhar Kasala Sreenivasulu, Isshu Lee, John W. Merickel, Fei Xu, Yalei Tang, Joshua E. Rittenhouse, Aleksandar Vakanski, Rongjie Song
  • Introduces a machine learning framework for correlating Charpy impact properties between different specimen sizes.
  • Achieves improved correlation performance with RΒ² values of 0.942 for USE and 0.892 for DBTT.
  • Validates the framework using a comprehensive dataset of 389 matched tests on SA533B steel.
  • The approach is applicable without needing full-sized Charpy data during inference.
Read more
Exploratory Analysis of Deep Learning Models for Forecasting Meteorological Parameters in the Agricultural Sector
Piotr Sikora, Sotirios Kontogiannis
Time Series
  • Hybrid deep learning models (1D-CNN-GRU and 1D-CNN-LSTM) outperform traditional GRU and LSTM models in forecasting accuracy.
  • The study utilizes a comprehensive dataset of 134,376 hourly meteorological observations from Ioannina, Greece.
  • Convolutional feature extraction significantly enhances the performance of short-term forecasting tasks.
  • The best-performing models achieved a WQS improvement of 1.22–1.63% for 24-hour forecasts and 0.44–0.45% for 168-hour forecasts compared to baseline models.
Read more
Semidirect Fourier Delta Attention: Phase-Controlled Delta Memory with Constructive Chunk-WY Kernels
Tiantian Zhang
Theory Efficient ML NLP
  • Introduction of SFDA, enhancing KDA with phase-controlled dynamics.
  • Establishment of a constructive chunk-WY theorem for efficient updates.
  • Demonstration of compact realizations for various memory structures.
  • Proof that every deterministic finite automaton can be realized by the proposed system.
Read more
LLMs as a Jury: Cross-Model Consensus Can Outperform Process Reward Models for LLM Reasoning
Ning Liu
Large Language Models Theory Efficient ML
  • Cross-model consensus outperforms traditional self-consistency and trained reward models in selecting correct answers.
  • The LLM-jury mechanism relies on error decorrelation, allowing correct answers to accumulate agreement while wrong answers scatter.
  • A closed-form predictive law quantifies consensus accuracy and establishes a ceiling for the method's effectiveness.
  • The LLM-jury serves as a free selector that matches or exceeds the performance of trained verifiers across various benchmarks.
Read more
PhysMRV: Physical Memory Retrieval and Verification for Physics Plausibility Reasoning
Wenyuan Wang, Lianyu Hu, Hao Wang, Yang Liu
Multimodal
  • PhysMRV provides a training-free framework for physical plausibility reasoning in VLMs.
  • It organizes physical knowledge into a Hierarchical Memory Bank with three complementary levels.
  • The framework improves physical reasoning without requiring model fine-tuning or parameter updates.
  • Experimental results show consistent performance improvements across multiple benchmarks.
Read more
Adversarial Attacks on Online Handwriting using Salience-based Temporal Editing
Yataro Tamura, Brian Kenji Iwana, Jiseok Lee
Time Series
  • Introduces a new adversarial attack framework for online handwriting recognition based on temporal editing.
  • Demonstrates the inadequacy of spatial perturbations for time series data like handwriting.
  • Achieves better transferability in black-box settings compared to traditional image-based attacks.
  • Preserves the visual structure and kinematic smoothness of handwriting during adversarial attacks.
Read more
SCOPE-RL: Optimizing Reasoning Paths Before and After Success
Xiaojian Liu, Han Xu, Jianqiang Xia, Zhixuan Li, Ke Xu, Yiwei Dai, Xinran Chen, Changwo Wu, Yuchen Li
Reinforcement Learning Large Language Models Optimization
  • SCOPE-RL introduces a two-stage framework to enhance reasoning path optimization in RLVR.
  • Adaptive Scaffolded RL (ASR) provides rewards for sub-question chains before achieving the final answer.
  • Quality-Aware Process RL (QPR) refines reasoning quality after success using correctness-gated rewards.
  • The Step-Quality Evaluation Protocol offers a comprehensive assessment of reasoning processes beyond final-answer accuracy.
Read more
Extractable Memorization From First Principles
A. Feder Cooper, Marika Swanberg, Jamie Hayes, Lea Duesterwald, Christopher De Sa, Daniel E. Ho, Mark A. Lemley, Percy Liang
NLP Large Language Models Theory
  • Valid extraction claims require high probability generation of training sequences compared to non-training sequences.
  • Matched comparisons are essential to distinguish memorization from predictability.
  • The paper introduces two formal methods for conducting matched comparisons: a conformal test and a census.
  • Experiments reveal that previous setups often overstate memorization claims due to validity issues.
Read more
From Preimage Search To Source-Grounded Feature Inversion
Kaixiang Shu
Interpretability
  • Introduces source-grounded feature inversion for improved interpretability of neural networks.
  • Conditions feature inversion on the local network geometry at the input that generated the feature.
  • Utilizes closed-form matrix Wiener maps to correct adjoint signals during backpropagation.
  • Demonstrates effectiveness across diverse architectures without requiring query-specific optimization.
Read more
Sample Efficient Generative Optimization for Molecular Design
Sarina Kopf, Cristina Nevado, Philippe Schwaller
Optimization Generative Models Efficient ML
  • Introduction of SEGO framework for molecular optimization.
  • Combines Bayesian optimization and generative modeling for efficient search.
  • Achieves state-of-the-art performance with significantly reduced oracle evaluations.
  • Demonstrates effectiveness in both practical molecular optimization and multiparameter docking tasks.
Read more
Condition-Stratified Robustness Analysis of Post-Hoc Calibration Methods for Probabilistic Classifiers
Gurdeep Singh Virdee
Theory
  • Post-hoc calibration methods need to be evaluated across distinct conditions, not just aggregate performance.
  • Temperature scaling (TEMP) consistently outperformed isotonic regression (ISO) in terms of calibration slope and stability across conditions.
  • The analysis revealed that the relative advantages of TEMP and ISO are condition-dependent and metric-specific.
  • Holm-adjusted multiplicity control was applied to ensure robust statistical comparisons.
Read more
Signal-Guided Optimization for Machine Unlearning
Xujia Li, Dan Li, Jian Lou, Wenjie Feng
Optimization Efficient ML Theory
  • GSUO introduces task-specific guidance signals for improved machine unlearning.
  • The framework addresses issues of over-unlearning and under-unlearning by tailoring optimization based on sample characteristics.
  • GSUO outperforms 14 existing methods in terms of unlearning effectiveness and generalization.
  • The method achieves significant speedups, with up to 31Γ— faster performance.
Read more
Optimizing ARDL Models for Retail Sales Forecasting and Fair Pricing
Sujay Uday Rittikar
Time Series Optimization
  • Integrates fairness constraints into retail sales forecasting models.
  • Uses ARDL models to analyze the impact of pricing on sales elasticity.
  • Demonstrates that Simulated Annealing can achieve fairer pricing compared to unconstrained optimization.
  • Establishes a transparent framework for pricing that aligns with consumer welfare.
Read more
AdaPCLA: Adaptive Prior-Calibrated Logit Adjustment for Long-Tailed Longitudinal EHR Generation
Shuai Cui, Chen Wenxuan, Wenjie Du, Jian Lou, Dan Li, Wenjie Feng
Generative Models Time Series Theory
  • Introduction of AdaPCLA framework for generating longitudinal EHR data.
  • Focus on improving the representation of rare clinical events in synthetic data.
  • Theoretical analysis of logit updates and prior-internalization dynamics.
  • Significant performance improvements over existing generative models.
Read more
LLM-PDESR: Robust PDE Discovery via Subdomain Weighted Residuals and LLM-Guided Symbolic Hypothesis Generation
Jinyang Du, Hao Ma, Xiaohu Shi, Bo Yang, Yanchun Liang, Heow Pueh Lee, Chunguo Wu
Large Language Models Optimization Interpretability
  • LLM-PDESR integrates LLMs with continuous numerical optimization for automated PDE discovery.
  • The framework utilizes C4 continuous quintic splines and SWR evaluations to reduce noise impact on derivative calculations.
  • A rigorous benchmark of 23 canonical PDEs and five novel equations validates the framework's discovery capabilities.
  • LLM-PDESR successfully extracts interpretable models from noisy climate data, demonstrating real-world applicability.
Read more
Mechanical Analysis of Parachute Suspension Line Deployment with Binding Tapes Using PINN
Xiang Zhao, Ronghui Quan, Yaqi Xiao, Junlin Chen
Theory Optimization
  • Development of a PINN algorithm for predicting tension in parachute suspension lines.
  • Outperformance of the PINN method compared to traditional numerical integration techniques.
  • Investigation of the effect of binding tape parameters on dynamic tension.
  • Validation of the model against real flight test data, demonstrating its effectiveness.
Read more
HyperSafe: Inference-Time Safety Recovery for Fine-Tuned Language Models
Aznaur Aliev, Carlos Hinojosa, Abdelrahman Eldesokey, Bang An, Bernard Ghanem, Yibo Yang
NLP Large Language Models
  • HyperSafe provides a model-specific, non-invasive approach to safety recovery in fine-tuned LLMs.
  • The framework generates a Safe Side Network (SSN) using layer-wise activation fingerprints, ensuring tailored safety assessments.
  • HyperSafe achieves harmful response rate reductions from 19-31% to below 1% without degrading task performance.
  • The method requires no gradient updates or safety data at deployment time, making it efficient and practical.
Read more
When Does Reward Teach State? A Hidden-Automaton Instrument and the Group-Language Boundary
Jim Allchin
Reinforcement Learning Theory Optimization
  • Introduces a white-box instrument for measuring latent state learning in RL agents.
  • Establishes that reward success and latent-state learning are distinct and measurable.
  • Identifies three axes influencing the coupling of reward and state learning: optimizer strength, task structure, and observation informativeness.
  • Demonstrates the existence of perception and planning gaps in agent learning.
Read more
Inside the Unfair Judge: A Mechanistic Interpretability Account of LLM-as-Judge Bias
Zixiang Xu, Sixian Li, Huaxing Liu, Xiang Wang, Shuai Li, Zirui Song, Xiuying Chen
NLP Large Language Models Interpretability
  • Bias in LLMs as judges can be understood through their internal representation rather than just input-output interactions.
  • The geometry of activation manifolds reveals how biases manifest and can be manipulated.
  • Causal control over hidden states allows for effective steering of scoring outcomes.
  • A linear projection onto bias features can predict judge performance on unseen data.
Read more
From Geometric Recovery to Causal Validation: A Reproducible Audit of Sparse Autoencoder Features, from Superposition Geometry to Causal Inertness
Mohamed Abdessalem Bal
Interpretability
  • Demonstrates the conflation of decoder-geometry alignment and encoder-activation behavior in SAE evaluations.
  • Introduces a causal validation method revealing that many features deemed recovered are causally inert.
  • Develops the sae-causal-audit tool for structured feature auditing across various models.
  • Proposes a two-axis taxonomy of causal inertness, distinguishing between structural and competitive inertness.
Read more
SMETA-ZSL: Semantic Meta-Alignment for Zero-Shot Threat Classification
Ivan Alejandro Montoya Sanchez, Anantaa Kotal, Aritran Piplai
NLP Large Language Models Multimodal
  • SMETA-ZSL utilizes semantic knowledge from CTI reports for zero-shot threat classification.
  • The framework addresses challenges like semantic ambiguity and class imbalance in cybersecurity.
  • It combines contrastive fine-tuning, episodic meta-learning, and adaptive routing for improved performance.
  • SMETA-ZSL shows significant performance improvements over existing zero-shot learning methods.
Read more
What Does Goodness Measure? A Likelihood-Ratio Account of Forward-Forward Learning
Paolo Giannitrapani
Theory
  • The goodness measure is shown to be a sufficient statistic for a likelihood-ratio test, providing a theoretical foundation for FF learning.
  • Generalizations to anisotropic and heavy-tailed distributions yield new insights into the behavior of the goodness measure.
  • Proper normalization between layers is critical for maintaining effective learning dynamics in FF networks.
  • Empirical results validate the theoretical predictions, although no significant performance improvements were observed.
Read more
EvoClawBench: Can Agents Learn Reusable Skills from Their Own Runs?
Zhiyuan Peng, Xin Yin, Chenhao Ying, Zhe Cui, Zixiang Ding, Zhenhua Liu, Jiang Wu, Yuan Luo
Large Language Models Reinforcement Learning Robotics
  • EvoClawBench is a novel benchmark focusing on agents' ability to learn reusable skills from their own runs.
  • The evaluation includes three distinct strategies: BASELINE, PRESKILL, and POSTSKILL, to measure skill effectiveness.
  • Results indicate that the effectiveness of self-authored skills is highly dependent on the runtime environment.
  • The study highlights the non-monotonic nature of skill performance improvements, challenging assumptions about automatic benefits from skill authoring.
Read more
DAG-FM: A Foundation Model for Causal Discovery under Heterogeneous Causal Mechanisms
Yikang Chen, Zhengkang Guan, Haoyuan Qian, Peng Cui, Yi Yang, Kun Kuang
Graph Learning Theory Efficient ML
  • DAG-FM introduces a two-stage auto-regressive process for causal discovery, enhancing model performance.
  • The Mixture-of-Leaf-Experts (MoLE) mechanism allows for dynamic adaptation to various causal mechanisms.
  • The model guarantees the identification of a unique DAG from observational data, addressing limitations of traditional methods.
  • DAG-FM demonstrates superior performance on synthetic and real-world datasets compared to existing approaches.
Read more
Beyond Coordinate Gauge: An Audited Protocol for Detecting Donor-Specific Functional Fingerprints after Neural Collapse
Truong Xuan Khanh, Phan Thanh Duc
Theory
  • Independently trained neural networks lack a common neuron-index reference frame, complicating cross-trajectory comparisons.
  • Neural Collapse creates a shared low-dimensional geometry, but does not eliminate functional differences between networks.
  • The study successfully demonstrates the detectability of donor-specific functional fingerprints using a controlled empirical approach.
  • An orthogonal Procrustes alignment and affine correction were employed to accurately map donor classifier heads into recipient coordinates.
Read more
From Many to Meaningful: Feature-Guided Zero-Shot Chronic Kidney Disease Screening Using Large Language Models
Muhammad Ashad Kabir, Sirajam Munira
Large Language Models NLP
  • Introduces a feature-guided zero-shot framework for CKD screening using LLMs.
  • Evaluates the performance of four LLMs without dataset-specific training.
  • Demonstrates that a compact set of clinically relevant features can enhance screening accuracy.
  • Validates the approach across three heterogeneous datasets from different countries.
Read more
Verifier-Based Reinforcement Fine-Tuning of Reasoning Models for Thermal Energy Storage Control
Takumi Shioda, Kohei Terashima, Tatsuo Nagai
Reinforcement Learning Large Language Models Optimization
  • Introduces a novel reinforcement learning approach with verifiable rewards for optimizing thermal energy storage scheduling.
  • Achieves significant emission reductions in a controlled environment, demonstrating the effectiveness of the proposed method.
  • Highlights the importance of reasoning capabilities in large language models for energy management tasks.
  • Demonstrates robustness and generalization of planning patterns across different conditions and tasks.
Read more
Constraint-Aware Aggregation for Federated Reinforcement Learning in Microgrid Energy Coordination
Usman Haider, Karl Mason
Reinforcement Learning Federated Learning Optimization
  • Proposes a constraint-aware aggregation framework for FedRL that enhances safety in energy coordination.
  • Introduces DairyGridEnv as a benchmark for evaluating federated reinforcement learning in microgrids.
  • Demonstrates that penalty-based aggregation consistently outperforms traditional FedAvg in terms of reward and safety.
  • Shows that lightweight aggregation strategies can significantly improve empirical safety without modifying local training.
Read more
Are we Merging the Right Models? Impact of Expert Training Duration on Model Merging for LLMs
Nikita Kozodoi, Zainab Afolabi, Jack Butler
Large Language Models Theory Efficient ML
  • The optimal training duration for merging models is dependent on the merging method used.
  • Simple averaging degrades with overfitting, while sparsification-based methods benefit from overfitted experts.
  • Bias-variance decomposition analysis provides insights into the performance of different merging strategies.
  • The study emphasizes the need to jointly consider training duration and merging method for optimal model performance.
Read more
Vilya-1: An all-atom foundation model for macrocycle structure prediction and design
Pascal Sturmfels, Milad Salem, Naozumi Hiranuma, Stephen Rettie, Xiaoliang Pan, Benjamin D. Sellers, Adam P. Moyer, Patrick J. Salveson, Ivan Anishchanka
Generative Models Optimization
  • Vilya-1 significantly improves the geometric accuracy of macrocycle structure predictions compared to existing methods.
  • The model operates on a uniform all-atom representation, allowing it to generalize across diverse chemical classes.
  • Vilya-1 supports generative applications for designing novel macrocycles tailored to specific properties.
  • The model demonstrates superior performance in conformational sampling, particularly for non-canonical and non-peptidic macrocycles.
Read more
How to Tame Grokking: Representation Geometry as a Control Signal
Maksim A Kazanskii
Theory Optimization
  • Grokking is characterized by delayed generalization in neural networks, where initial memorization is followed by improved test performance after prolonged training.
  • GeomDR is introduced as a method to directly control the effective dimensionality of hidden representations, impacting grokking dynamics.
  • Empirical results show that geometric interventions can accelerate grokking by up to 52 times, depending on the intervention schedule and target dimensionality.
  • Changes in effective dimensionality consistently precede the transition from memorization to generalization, indicating its role as a controllable variable.
Read more
Learning-based Probabilistic Load Forecasting with Post-hoc and In-model Uncertainty
Sarah Al-Shareeda, Gulcihan Ozdemir, Heung Seok Jeon
Time Series
  • Developed a unified framework for one-day-ahead probabilistic load forecasting under feature-asymmetric conditions.
  • Compared modular post-hoc and integrated in-model uncertainty placement methods using three deep learning architectures.
  • Found that the Temporal Fusion Transformer outperformed other models in terms of accuracy and interval calibration.
  • Demonstrated that reconstruction-induced uncertainty significantly impacts forecast quality.
Read more