Machine Learning

81 papers

Every entry carries a structured overview and the reproduction evidence collected so far. A paper is listed here when it carries the category as its primary field or as a secondary classification. Both are shown on the paper page.

Latest in Machine Learning

Showing 61–80 of 81

Apr 20, 2026Formal Sciences260421.0060

Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts

Jacob Morrison, Sanjay Adhikesaven, Akshita Bhagia, Matei Zaharia +2 more

BAR (Branch-Adapt-Route) trains separate domain experts independently and combines them via Mixture-of-Experts, enabling modular updates to language models without retraining everything or degrading existing capabilities. This approach matches monolithic retraining performance while scaling linearly instead of quadratically when adding new domains.

Apr 20, 2026Formal Sciences260421.0061

NI Sampling: Accelerating Discrete Diffusion Sampling by Token Order Optimization

Enshu Liu, Xuefei Ning, Yu Wang, Zinan Lin

This paper introduces Neural Indicator Sampling (NI Sampling), a method that optimizes the token sampling order in discrete diffusion language models to achieve up to 14.3× speedup over standard sampling while maintaining accuracy. The approach uses a trained neural indicator to intelligently select which tokens to sample at each step, dramatically reducing the number of required sampling iterations.

CodeRun failed7 attempts

Apr 20, 2026Formal Sciences260421.0062

Asset Harvester: Extracting 3D Assets from Autonomous Driving Logs for Simulation

Tianshi Cao, Jiawei Ren, Yuxuan Zhang, Jaewoo Seo +11 more

Asset Harvester converts sparse, real-world object observations from autonomous vehicle driving logs into complete 3D assets suitable for simulation. The system combines large-scale data curation, geometry-aware preprocessing, and a novel sparse-view-conditioned model (SparseViewDiT) to generate simulation-ready 3D objects from limited viewing angles.

Apr 20, 2026Formal Sciences260421.0063

Semantic Step Prediction: Multi-Step Latent Forecasting in LLM Reasoning Trajectories via Step Sampling

Yidi Yuan

This paper shows that applying Semantic Tube Prediction (STP) at reasoning step boundaries instead of random token positions dramatically improves multi-step latent prediction in LLMs (168x vs 4x improvement), revealing that sampling position is critical for geometric regularization of reasoning trajectories.

Apr 20, 2026Formal Sciences260421.0064

Using large language models for embodied planning introduces systematic safety risks

Tao Zhang, Kaixian Qu, Zhibin Li, Jiajun Wu +3 more

This paper introduces DESPITE, a benchmark of over 12,000 tasks to evaluate safety in LLM-based robotic planning, revealing that even models with near-perfect planning ability produce dangerous plans 28% of the time. The study shows planning ability scales with model size while safety awareness remains relatively flat, creating a critical gap for deploying LLMs in robotics.

Apr 20, 2026Formal Sciences260421.0065

Learning Invariant Modality Representation for Robust Multimodal Learning from a Causal Inference Perspective

Sijie Mai, Shiqin Han

This paper proposes CmIR, a causal inference framework that separates multimodal data into stable causal features and spurious environment-specific features to improve robustness in affective computing. The method achieves state-of-the-art performance, especially on out-of-distribution and noisy data.

Apr 20, 2026Formal Sciences260421.0067

AutoPPA: Automated Circuit PPA Optimization via Contrastive Code-based Rule Library Learning

Chongxiao Li, Pengwei Jin, Di Huang, Guangrun Sun +13 more

AutoPPA is an automated framework for optimizing circuit performance, power, and area (PPA) that learns optimization rules by contrasting code pairs rather than relying on manual rules. It outperforms existing methods including manual optimization and state-of-the-art automated approaches.

Apr 20, 2026Formal Sciences260421.0068

ProtoCLIP: Prototype-Aligned Latent Refinement for Robust Zero-Shot Chest X-Ray Classification

Florian Kittler, Sheethal Bhat, Andreas Maier

ProtoCLIP refines CLIP-style vision-language models for chest X-ray classification by using curated training data and prototype-aligned distillation to reduce co-occurrence bias and improve zero-shot performance. The method achieves 2-10 percentage point AUC improvements over baseline CLIP on unseen chest X-ray datasets without large-scale retraining.

Apr 20, 2026Formal Sciences260421.0069

Scalable Physics-Informed Neural Differential Equations and Data-Driven Algorithms for HVAC Systems

Hanfeng Zhai, Hongtao Qiao, Hassan Mansour, Christopher Laughman

This paper develops a hybrid simulation framework for large HVAC systems that combines physics-informed neural networks with traditional differential-algebraic equation solvers, achieving multi-fold speedups over high-fidelity simulations while maintaining low errors. The approach scales to systems with 32+ compressor-condenser pairs by learning component-level dynamics and enforcing system-level physical constraints.

Apr 20, 2026Formal Sciences260421.0071

Knowing When to Quit: A Principled Framework for Dynamic Abstention in LLM Reasoning

Hen Davidov, Nachshon Cohen, Oren Kalinsky, Yaron Fairstein +3 more

This paper develops a principled reinforcement learning framework for deciding when language models should stop generating text mid-response to avoid wasting compute on incorrect outputs. The approach uses value function estimation to determine optimal stopping points, improving accuracy-compute tradeoffs compared to existing methods.

Apr 20, 2026Formal Sciences260421.0072

Bridge-Centered Metapath Classification Using R-GCN-VGAE for Disaster-Resilient Maintenance Decisions

Takato Yasuno

This paper develops a graph neural network approach to classify bridges based on their disaster-resilience roles by analyzing metapaths connecting highways, bridges, and critical buildings. The method helps prioritize bridge maintenance budgets by identifying which bridges are essential for supply chains, medical access, or residential protection during disasters.

Apr 20, 2026Formal Sciences260421.0073

Randomly Initialized Networks Can Learn from Peer-to-Peer Consensus

Esteban Rodríguez-Betancourt, Edgar Casasola-Murillo

This paper shows that randomly initialized neural networks can learn useful representations through simple peer-to-peer consensus (self-distillation) alone, without projectors, predictors, or pretext tasks. The findings suggest that self-distillation itself is a key mechanism driving learning in self-supervised methods, independent of other architectural components.

Apr 20, 2026Formal Sciences260421.0074

Learning from Less: Measuring the Effectiveness of RLVR in Low Data and Compute Regimes

Justin Bauer, Thomas Walshe, Derek Pham, Harit Vishwakarma +3 more

This paper investigates how well small language models can learn reasoning tasks through reinforcement learning when training data and compute are limited. The study finds that mixing easy and hard problems during training provides up to 5x better sample efficiency than training on easy problems alone.

Apr 20, 2026Formal Sciences260421.0075

Forecasting Ionospheric Irregularities on GNSS Lines of Sight Using Dynamic Graphs with Ephemeris Conditioning

Mert Can Turkmen, Eng Leong Tan, Yee Hui Lee

This paper introduces IonoDGNN, a dynamic graph neural network that forecasts ionospheric irregularities by modeling satellite pierce points as graph nodes with time-varying connectivity, conditioned on predictable future satellite positions. The approach outperforms persistence baselines by 35-52% and enables forecasting on lines of sight that don't yet exist in the observation period.

Apr 20, 2026Formal Sciences260421.0076

Parkinson's Disease Detection via Self-Supervised Dual-Channel Cross-Attention on Bilateral Wrist-Worn IMU Signals

Meheru Zannat

This paper presents a self-supervised deep learning method using bilateral wrist-worn IMU sensors to detect Parkinson's disease, achieving over 93% accuracy for distinguishing PD from healthy controls and demonstrating effective transfer learning with only 20% labeled data. The model is lightweight enough to run in real-time on a Raspberry Pi, making it practical for clinical deployment.

Apr 20, 2026Formal Sciences260421.0077

Tight Auditing of Differential Privacy in MST and AIM

Georgi Ganev, Meenatchi Sundaram Muthu Selva Annamalai, Bogdan Kulynych

This paper introduces a GDP-based auditing framework that provides the first tight privacy audits for state-of-the-art differentially private synthetic data generators MST and AIM. The audits show a small gap between theoretical guarantees and empirical measurements in strong-privacy regimes.

CodeRun failed2 attempts

Apr 20, 2026Formal Sciences260421.0078

Balanced Co-Clustering of Users and Items for Embedding Table Compression in Recommender Systems

Runhao Jiang, Renchi Yang, Donghao Wu

BACO is a framework that compresses embedding tables in recommender systems by clustering similar users and items to share embeddings, achieving over 75% parameter reduction with minimal accuracy loss. It outperforms existing methods by being up to 346X faster while maintaining recommendation quality.

Apr 20, 2026Formal Sciences260421.0081

Scale-free adaptive planning for deterministic dynamics & discounted rewards

Peter L. Bartlett, Victor Gabillon, Jennifer Healey, Michal Valko

Platypoos is a planning algorithm for deterministic environments with stochastic rewards that automatically adapts to unknown reward scales and smoothness without requiring prior knowledge of discount factors or reward bounds. It achieves optimal sample complexity with matching upper and lower bounds.

Apr 20, 2026Formal Sciences260421.0083

CAARL: In-Context Learning for Interpretable Co-Evolving Time Series Forecasting

Etienne Tajeuna, Patrick Asante Owusu, Armelle Brun, Shengrui Wang

CAARL uses large language models to forecast co-evolving time series by converting temporal dependencies into narrative form, enabling interpretable chain-of-thought reasoning for predictions. The approach decomposes series into autoregressive segments and builds dependency graphs that LLMs can process as text, achieving competitive accuracy with enhanced transparency.

Apr 20, 2026Formal Sciences260421.0084

Dissipative Latent Residual Physics-Informed Neural Networks for Modeling and Identification of Electromechanical Systems

Youyuan Long, Gokhan Solak, Arash Ajoudani

DiLaR-PINN is a physics-informed neural network that learns unmodeled dissipative effects in electromechanical systems by constraining residual terms to be energy-dissipating rather than energy-injecting. The method combines first-principles models with data-driven components that operate on latent states and guarantee physically consistent energy behavior.