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
An optimal control approach for neural network architecture adaptation with a posteriori error estimation
C G Krishnanunni, Thomas Scott, Tan Bui-Thanh
Optimization Theory Efficient ML
  • Introduces a continuous-time optimal control framework for neural network architecture adaptation.
  • Derives rigorous a posteriori error estimates to guide layer insertion based on maximum estimated error.
  • Proposes a novel architecture representation with piecewise linear weights and biases.
  • Utilizes dual weighted residual methodology to compute error bounds and refine architecture.
Read more
Unlocking Temporal Generalization in Hamiltonian Video Dynamics Models
Eli Laird, Corey Clark
Generative Models Reinforcement Learning Robotics
  • Traditional world models are limited to fixed time steps, hindering temporal generalization.
  • Hamiltonian Generative Networks (HGN) can predict dynamics based on continuous-time energy functions but struggle in non-conservative settings.
  • The paper identifies failure modes in HGN rollouts when extrapolating beyond training step sizes.
  • Targeted fixes are proposed for each identified failure mode, enhancing stability in predictions.
Read more
ALER-TI: Aligned Latent Embedding Retrieval for Time Series Imputation
Xuan-Thong Truong, Trung-Kien Le, Tung Kieu, Thi-Thu Nguyen, Nhat-Hai Nguyen
Time Series
  • ALER-TI enhances time series imputation by integrating historical patterns through a retrieval-augmented framework.
  • Latent Embedding Alignment (LEA) allows for efficient retrieval while addressing representation mismatches between corrupted queries and clean candidates.
  • The framework is model-agnostic and can be integrated with various existing imputation models.
  • Extensive experiments show significant improvements in imputation performance across different datasets and missing rates.
Read more
The Key to Going Linear: Analysis-Driven Transformer Linearization
Anna Kuzina, Paul N. Whatmough, Babak Ehteshami Bejnordi
NLP Large Language Models Efficient ML
  • Isolated analysis of linearization methods in a frozen-backbone setting reveals key-dependent dynamics of softmax attention.
  • Delta-style updates outperform gated accumulation methods in approximating softmax attention.
  • Structural interventions like sink tokens and short convolutions effectively reduce performance gaps in linearized models.
  • The proposed linearization approach scales effectively across large models (up to 32B parameters) and outperforms prior baselines.
Read more
Federated Deep Learning for Privacy-Preserving Cardiovascular Disease Risk Prediction
Hyunho Mo, Djura Smits, Mahlet A. Birhanu, Maarten J.G. Leening, Daniel Bos, Pim van der Harst, Esther E. Bron
Federated Learning
  • Federated learning enables collaborative model development without sharing sensitive patient data.
  • The study integrates two heterogeneous cohorts to improve cardiovascular disease risk prediction.
  • Deep survival models trained via federated learning showed superior performance compared to local models.
  • C-statistic improvements indicate enhanced predictive accuracy for both cohorts.
Read more
Spectral Analysis of Dueling Q-Learning
Donghwan Lee
Reinforcement Learning Theory
  • Introduces a centered tabular decomposition of the Q-function for dueling Q-learning.
  • Establishes convergence guarantees for unregularized dueling Q-learning with constant step sizes.
  • Derives a finite-time error bound for the sampled stochastic version of dueling Q-learning.
  • Clarifies the roles of value and advantage updates in the learning process.
Read more
Distributed Sketching on Data Partitions for OLS Regression
Luyuan Yang, Brayden Garner, Shayan Shafaei, Chao Lan
Theory Efficient ML Optimization
  • Introduces a distributed sketching method for OLS regression that operates on data partitions.
  • Characterizes the exact excess loss of the averaged OLS estimator, showing it can be comparable to traditional methods.
  • Demonstrates that the performance of the proposed method is influenced by the divergence of subset covariances.
  • Highlights the computational efficiency gained by reducing the size of data subsets handled by each machine.
Read more
Vanilla SGD with Momentum Survives Heavy-Tailed Noise: Convergence Analysis without Gradient Clipping or Normalization
Ryusei Yamada, Naoki Sato, Hideaki Iiduka
Optimization Theory
  • First theoretical guarantee for vanilla SGD with momentum under heavy-tailed noise for various objective types.
  • Convergence rates established are slightly inferior to those of normalized SGD, highlighting limitations of vanilla methods.
  • Results do not require bounded gradients, offering a more general theoretical framework.
  • Experiments confirm the importance of the condition relating the Hรถlder continuity parameter and tail index for stable convergence.
Read more
Ensemble Diversity Optimization for Subjective Supervision
Xia Cui, Ziyi Huang, N. R. Abeynayake
NLP Optimization Theory
  • EDO framework optimizes ensemble weights and structure to handle annotator disagreement in subjective NLP tasks.
  • Introduces a signed diversity regularizer to control the balance between preserving and suppressing disagreement.
  • Implements a multi-objective optimization approach that integrates predictive utility, calibration, and diversity.
  • Demonstrates significant improvements in probabilistic calibration and alignment with annotator distributions across multiple benchmarks.
Read more
FourierQK: Spectral Preprocessing of Query-Key Projections Improves Transformer Attention
Athanasios Zeris
NLP Large Language Models
  • FFT-based spectral preprocessing of query-key projections significantly improves transformer attention.
  • Achieved a 79% reduction in validation loss over standard dot-product attention on the TinyShakespeare dataset.
  • Results are reproducible across multiple random seeds, confirming the reliability of the approach.
  • The improvements are attributed to global sequence mixing in the frequency domain, not positional artifacts.
Read more
path_boost: A Python Package for Interpretable Graph-Level Prediction using Path-Based Gradient Boosting
Claudio Meggio, Johan Pensar, Riccardo De Bin
Graph Learning Interpretability
  • PathBoost provides an interpretable alternative to graph neural networks for graph-level predictions.
  • The algorithm automatically discovers and utilizes predictive paths within graph structures.
  • path_boost supports both regression and binary classification tasks.
  • The package is compatible with scikit-learn, facilitating integration into existing workflows.
Read more
The Importance of Encoder Choice:A Tabular-Image Study
Ilia Koloiarov, Diego Coello de Portugal Mecke, Vijaya Krishna Yalavarthi, Tom Hanika, Lars Schmidt-Thieme
Multimodal
  • Multimodal rankings vary significantly across different tabular encoders.
  • Combining modalities can degrade performance below unimodal baselines in certain datasets.
  • Stronger unimodal encoders may provide a better estimate of the benefits of multimodal learning.
  • A simple bilinear fusion method can perform comparably to complex multimodal methods when using strong encoders.
Read more
Architecture Generalization with MetaNCA
Meet Barot, Daniel Berenberg, Sina Khajehabdollahi
Efficient ML Theory Graph Learning
  • Introduction of MetaNCA, a framework for self-organizing neural network weights using local rules.
  • Utilization of a Weight Transformer architecture for efficient weight updates based on local interactions.
  • Demonstration of architecture generalization capabilities to unseen neural network configurations.
  • Scalability to large networks with millions of parameters without backpropagation.
Read more
The Rank-One Corner: How Much Value Equivalence Does a Task Need from a World Model?
Donna Vakalis
Reinforcement Learning Theory
  • The concept of 'closure' is introduced, focusing on the specific predictive coordinates needed for task performance.
  • A scalar reward signal captures only a limited aspect of the task's structure, termed the 'rank-one corner.'
  • The dimensionality of the objective directly affects the model's ability to represent the closure, with higher dimensions allowing for richer representations.
  • The study provides empirical evidence that the objective's dimensionality governs the model's predictive capabilities.
Read more
Stop Guessing When to Stop Testing: Efficient Model Evaluation with Just Enough Data
Ofir Arviv, Kristjan Greenewald, Yotam Perlitz, Hadar Mulian, Michal Shmueli-Scheuer, Leshem Choshen
Efficient ML Theory
  • Proposes an adaptive evaluation framework to replace fixed-size benchmarks.
  • Utilizes sequential testing to balance efficiency and reliability in model evaluation.
  • Demonstrates significant computational cost savings (up to 80%) while maintaining statistical significance.
  • Allows users to define specific evaluation needs, enhancing transparency and decision-making.
Read more
What to Keep, What to Forget: A Rateโ€“Distortion View of Memory Compaction in LLMs and Agents
Ashwin Gerard Colaco, Nada Lahjouji
NLP Large Language Models Efficient ML
  • Memory compaction in LLMs can be framed as a rate-distortion problem, allowing for a unified approach across different methods.
  • The authors present a seven-axis taxonomy that classifies various memory compaction techniques uniformly.
  • Common failure modes in memory compaction include irreversible loss of information before query knowledge is available.
  • The proposed COMPACT-Bench benchmark aims to standardize the evaluation of memory compaction methods across different contexts.
Read more
NEST: Tackling Dataset-Level Distribution Shifts via Regime-Oriented Mixture-of-Experts
Lanhao Li, Bingshu Xie, Lijun Sun, Xin Xue, Haoyi Zhou, Jianxin Li
Time Series
  • NEST models dataset-level distribution shifts by dynamically recomposing inter-variable dependencies.
  • The framework utilizes unsupervised moment-entropy metrics for principled regime discovery.
  • A regime-oriented router mechanism enhances expert orchestration and improves prediction accuracy.
  • NEST achieves state-of-the-art performance across diverse benchmarks.
Read more
Trustworthy Machine Learning through the Lens of Combinatorial Optimization: Survey and Research Perspectives
Thibaut Vidal, Julien Ferry
Optimization Theory Interpretability
  • Trustworthy ML requires more than just predictive accuracy; it necessitates transparency, interpretability, robustness, fairness, and privacy.
  • The Rashomon effect suggests that multiple models can achieve similar performance, allowing for the selection of models based on additional trustworthiness criteria.
  • Combinatorial optimization offers a robust framework for addressing various trustworthiness challenges in ML, including model training and post-training tasks.
  • CO techniques can provide global optimality and formal certificates, enhancing the reliability of ML systems.
Read more
Entropy-Guided Tensor Compression for Multimodal Federated Learning on Edge Devices
Quoc Bao Phan, Tuy Tan Nguyen
Federated Learning Multimodal Efficient ML
  • MESH-FL introduces an entropy-guided approach for update compression in multimodal federated learning.
  • The framework adapts compression ranks based on the spectral entropy of updates, enhancing communication efficiency.
  • MESH-FL shows significant improvements in accuracy and data transmission efficiency over traditional methods.
  • The proposed method is validated on a heterogeneous edge device setup, showcasing its practical applicability.
Read more
Frequency-Domain Multi-Modality Transportation Modeling
Jiewen Deng, Hangchen Liu, Junchen Li, Boyuan Zhang, Renhe Jiang
Time Series Multimodal
  • Introduces a frequency-domain approach for multi-modality transportation modeling.
  • Utilizes a Modality-Wise Frequency Filter (MFF) for spectral refinement.
  • Incorporates a Frequency-Guided Synergy Integrator (FSI) for selective information aggregation.
  • Demonstrates significant performance improvements over existing forecasting methods.
Read more
Robust Human-AI Complementarity under Uncertainty
Yewon Byun, Bryan Wilder
Theory Large Language Models NLP
  • Human decision makers struggle to utilize AI predictions due to uncertainty about AI quality.
  • The correlation of prediction errors between humans and AI is critical for achieving complementarity.
  • Negative correlation of errors allows for robust decision-making strategies that improve utility.
  • Empirical findings show that human and AI prediction errors are often positively correlated.
Read more
Information Allocation Dynamics in Neural Network Optimization
Zhang Gongyue, Liu Donghan, Ren Weihong, Sheng Yixuan, Wang Zhiyong, Liu Honghai
Optimization Theory
  • Introduces the concept of information allocation dynamics to explain optimizer implicit bias.
  • Defines a continuous preconditioning exponent p that regulates the update dynamics of weight and bias parameters.
  • Demonstrates that different values of p can significantly affect training trajectories and generalization.
  • Highlights the importance of understanding optimizer biases in the context of training signal allocation.
Read more
NFTR: From Provable Mode-Averaging to Geodesic Subgoal Selection in Offline Goal-Conditioned RL
Erdemt Bao, Xing Lei, Jun Chen
Reinforcement Learning Robotics Theory
  • NFTR addresses optimistic bias and mode collapse in HIQL by using Normalizing Flows for subgoal selection.
  • The triangle-slack score effectively downweights unreliable subgoals based on geometric considerations.
  • NFTR maintains population-level monotonic improvement and provides a three-term suboptimality decomposition.
  • Empirical results show substantial performance improvements over HIQL across multiple task types.
Read more
Fingerprint, Not Blueprint: How Positional Schemes Set the Default Spectral Algebra of Attention
Li Hengyu
NLP Large Language Models Theory
  • Introduces a matched-null spectral framework for analyzing the QK operator in attention heads.
  • Demonstrates that positional encoding schemes significantly influence the spectral properties and head functions of attention mechanisms.
  • Finds that the strongest previous-token heads are spectrally rotational under RoPE, while other schemes are not.
  • Establishes that the symmetric part of the operator M is more load-bearing than the antisymmetric part.
Read more
Does Demand Response Increase Vulnerability to Cyber Attacks by Adversarial Data Modifications?
Clemens Kortmann, Eike Cramer
Optimization Theory
  • Adversarial attacks can undermine the financial benefits of demand response in industrial settings.
  • Limited and undetectable perturbations can allow demand response to maintain most of its financial advantage.
  • The orientation of adversarial perturbations plays a crucial role in their impact on decision-making.
  • The study emphasizes the need for incorporating model sensitivities into adversarial attack analyses.
Read more
Reinforcing the Generation Order of Multimodal Masked Diffusion Models
Yidong Ouyang, Zhe Wang, Sourav Bhabesh, Dmitriy Bespalov
Multimodal Generative Models Optimization
  • Existing confidence-based strategies for generation order do not improve image generation quality and multimodal reasoning.
  • A learnable control block is proposed to optimize generation order using Group Relative Policy Optimization (GRPO).
  • The proposed method shows significant improvements in text-to-image alignment and multimodal understanding benchmarks.
  • The approach captures fine-grained spatial relationships in generated images effectively.
Read more
Steering Neural Network Training through Interpretable Constraints Based on Partial Dependence
Yann Claes, Pierre Geurts, Vรขn Anh Huynh-Thu
Interpretability Time Series Theory
  • Introduces a novel method for steering neural network training using partial dependence.
  • Focuses on explanation-guided learning to align model outputs with domain knowledge.
  • Demonstrates improved performance and data efficiency in regression tasks compared to unconstrained models.
  • Ensures that model interpretations are faithful to prior knowledge provided by users.
Read more
Structural Adversarial Attacks on Relational Deep Learning under Integrity Constraints
Alan Gany, Bogdan Cautis, Silviu Maniu
Graph Learning Optimization Theory
  • The paper focuses on structural adversarial attacks on Relational Deep Learning systems.
  • A white-box attacker can manipulate the database while preserving integrity constraints.
  • Seven heuristic strategies for generating adversarial attacks are evaluated.
  • Gradient-based attacks show superior performance in regression tasks compared to random baselines.
Read more
Provably Optimal Learning Algorithms for Assistance Games
Nivasini Ananthakrishnan, Mark Bedaywi, Michael I. Jordan, Stuart Russell, Nika Haghtalab
Reinforcement Learning Theory Optimization
  • Introduces the concept of assistance regret in the context of assistance games.
  • Presents decentralized algorithms for informed and uninformed agents with provable efficiency.
  • Achieves a (1 - 1/e)-approximate assistance regret rate of หœO(T^(3/4)).
  • Demonstrates that improving upon the (1 - 1/e) approximation is computationally intractable.
Read more
Robust Federated Learning Under Real-World Client Churn
Dhruv Garg, Neha Lakhani, Debopam Sanyal, Myungjin Lee, Alexey Tumanov, Ada Gavrilovska
Federated Learning
  • FeLiX optimizes Federated Learning for real-time applications by addressing client churn and dynamic data distributions.
  • Introduces novel mechanisms for client selection and aggregation that enhance model freshness and accuracy.
  • Achieves up to 2.37ร— reduction in time-to-target accuracy and 1.30ร— savings in communication bandwidth over existing methods.
Read more
An exact information theory of generalization phase transitions in Bayesian diffusion models
Henry Hunt, Mason Kamb, Surya Ganguli
Generative Models Theory
  • Introduces BIRD models that analytically address generalization in diffusion models.
  • Identifies an information-theoretic phase boundary between memorization and generalization.
  • Demonstrates that BIRD models can approximate trained diffusion models early in training.
  • Confirms theoretical predictions through experiments across various datasets.
Read more
Deep Learning for Joint Narrowband Interference Cancellation and Soft Demodulation in OFDM Systems
Emmanouil Kavvousanos, Francky Catthoor, Vassilis Paliouras
Theory Efficient ML
  • Introduces a deep learning framework for joint NBI cancellation and soft demodulation in OFDM systems.
  • NBI-CNet reduces computational complexity by up to 60% compared to state-of-the-art methods.
  • LLR-CNet effectively maps non-Gaussian residuals to calibrated soft metrics, improving demodulation reliability.
  • The framework eliminates error floors and achieves significant performance gains under severe interference conditions.
Read more
A knowledge-augmented dataset of high-risk driving scenarios with LLM annotations for autonomous driving
Heye Huang, Jingguang Li, Zhiyuan Zhou, Paul Liang, Mingyu Wu, Kitae Jang, Jianqiang Wang
NLP Large Language Models Robotics
  • K-Risk dataset includes 31,398 high-risk driving events with LLM annotations.
  • Integrates data from 20 human-driven and autonomous vehicle trajectory datasets.
  • Provides multi-dimensional risk annotations and causal risk analyses for better decision-making.
  • Addresses the underrepresentation of extreme long-tail scenarios in existing datasets.
Read more
Prior-matched evaluation of operational Earth-observation classifiers: a three-number reporting method demonstrated on Sentinel-1 internal-wave detection
Joao Pinelo, Joao Goncalves, Arun Shukla, Adriana Santos-Ferreira
Computer Vision Theory Efficient ML
  • Traditional balanced-test metrics can misrepresent classifier performance in operational settings with skewed data.
  • A three-number reporting method provides a more accurate evaluation of classifier effectiveness.
  • The proposed methodology improves the classifier's precision while maintaining a fixed recall threshold.
  • The study establishes the Internal Waves Service as a pioneering operational classifier for internal solitary waves detection.
Read more
Dual Attention Heads for Personalized Federated Learning in ECG Classification
Kien Le, Joseph Lindley, Quoc Bao Phan, Tuy Tan Nguyen
Federated Learning Time Series
  • Introduction of FedDualAtt, a dual-attention transformer for ECG classification in federated learning.
  • Global and local attention heads allow for both cross-site generalization and local adaptation.
  • Empirical results show superior performance of FedDualAtt over existing federated learning methods.
  • Analysis of head ratios indicates varying benefits of architectural personalization for different clients.
Read more
A Quiet Failure in Calibrated Virtual Screening: Marginal Conformal Prediction Under-Covers the Minority Class, and a Class-Conditional Fix Recovers It
Muhammadjon Tursunbadalov, Mustafojon Tursunbadalov
Theory Graph Learning
  • Marginal conformal prediction can under-cover minority classes in imbalanced datasets, despite meeting overall coverage targets.
  • The failure is consistent across different model architectures and is linked to the calibration of minority class predictions.
  • Class-conditional conformal prediction effectively addresses the minority coverage issue, restoring reliability.
  • Standard aggregate metrics can obscure significant failures in minority class predictions.
Read more
Constrained Decoding for Diffusion Language Models via Efficient Inference over Finite Automata
Meihua Dang, Stefano Ermon
NLP Large Language Models Generative Models
  • Introduces a novel algorithm for constrained decoding in diffusion language models using finite automata.
  • Guarantees constraint satisfaction by construction, applicable to various decoding strategies.
  • Implements depth-reduction techniques to enhance inference efficiency.
  • Empirical results show substantial accuracy improvements in multiple tasks with low overhead.
Read more
Avoiding unsafe sets when training with Langevin Dynamics
Adam M. Oberman
Theory Optimization
  • The paper provides bounds on the probability of a training trajectory entering a failure region during training.
  • Equilibrium mass ฯ€(AH) is shown to be exponentially small in the dimension d.
  • Transient swelling of trajectory mass can occur, necessitating a burn-in time for safety.
  • A local relaxation rate is introduced to address swelling in geometrically isolated failure regions.
Read more
RhyMix: A Lightweight Adaptive Multi-Rhythm Network for Long-Term Time Series Forecasting
Sumit Satishrao Shevtekar, Chandresh Kumar Maurya
Time Series
  • RhyMix integrates explicit multi-period cyclic priors into a dual-path forecasting architecture.
  • The model utilizes Multi-Scale Temporal Convolution with Channel Attention for enhanced temporal representation learning.
  • Adaptive gating mechanisms allow for dynamic fusion of multiple forecasting heads tailored to specific input samples.
  • RhyMix is lightweight, with approximately 40K parameters and low inference latency, making it suitable for edge devices.
Read more
FMMVCC: Fuzzy Mamba-based Multi-View Contrastive Clustering for Univariate Time Series
Donato Cerciello, Leonardo Schiavo, Angel Panizo-LLedot, Javier Huertas Tato, David Camacho
Time Series
  • Introduces FMMVCC, a deep clustering framework for univariate time series data.
  • Utilizes Mamba-based encoders for efficient long-range temporal dependency modeling.
  • Implements multi-view self-supervised learning through temporal masking and augmentations.
  • Incorporates a fuzzy clustering objective for improved cluster separability.
Read more
Who Analyses the Analyser? Self-Validating LLM Hazard Analysis with Constitutional Meta-STPA
Samuel Tetteh, Udip Shrestha, Joshua R. Waite, Cody Fleming
Large Language Models Theory Interpretability
  • Introduces Constitutional Meta-STPA to analyze LLM-assisted safety tools.
  • Derives a governance constitution with 21 Tool Principles and 8 Meta-Safety Principles.
  • Demonstrates significant improvement in safety scores using the derived principles.
  • Highlights the importance of self-analysis for LLMs in safety-critical applications.
Read more
PGD-NO: A Neural Operator with Precomputed Geometry Decomposition for 3D Million-scale Physics Simulations
Weiheng Zhong, Jing Bi, Victor Oancea, Hadi Meidani
Efficient ML Interpretability Theory
  • PGD-NO utilizes a precomputed geometry decomposition approach to reduce memory consumption.
  • The model allows for linear scalability, handling meshes with over 10 million nodes.
  • It demonstrates competitive accuracy in predictive tasks across diverse industrial benchmarks.
  • The architecture provides intrinsic interpretability through attention mechanisms.
Read more
Imputation Meets Clustering: Exploiting Latent Subgroup Structure for Missing Data Recovery
Chuyao Zhang, E Li, Taochen Chen, Yiqun Zhang, Yuzhu Ji, Shuping Zhao, Peng Liu, Yiu-ming Cheung
Generative Models Optimization
  • CAGI integrates clustering and imputation into a co-optimization framework to enhance data recovery.
  • The 'Partition-Guide-Restore' strategy allows for dynamic cluster assignments that inform the imputation process.
  • The method addresses the circular dependency between subgroup identification and data completion.
  • CAGI outperforms traditional imputation methods by preserving subgroup distributions.
Read more
Converge to Surprise: Evolutionary Self-supervised Image Clustering
Canlin Zhang, Xiuwen Liu
Computer Vision Optimization Theory
  • Introduction of a surprise score to measure non-randomness in image representations.
  • Development of the 'converge-to-surprise' optimization scheme combining evolution strategies and gradient descent.
  • Achievement of state-of-the-art results in non-parametric self-supervised image clustering.
  • Demonstration of the framework's ability to discover meaningful features without predefined targets.
Read more
Super Weights in LLMs and the Failure of Selective Training
Shreyas Subramanian, Adewale Akinfaderin, Akarsha Sehwag
Large Language Models Efficient ML Theory
  • Super Weights do not universally lead to improved performance when trained in isolation.
  • Training Super Weights results in accuracy drops to random-guessing levels, while random parameter training improves performance.
  • LoRA achieves significant accuracy with minimal parameter updates, highlighting the importance of structured training.
  • The study validates Super Weight consistency across diverse models and demonstrates the failure of selective training approaches.
Read more
When Does Continual Learning Require Learning
Anne Harrington, Nayan Saxena, Michael Murphy, Anastasia Borovykh, Zeyu Yun, Sridhar Kamath, Ara Eindra Kyi, Trevor Darrell, Jitendra Malik, Yutong Bai
Large Language Models NLP Reinforcement Learning
  • Continual learning is framed as increasing competence in response to environmental changes.
  • The authors categorize changes along two axes: space (new domains) and time (data drift).
  • Different continual learning methods exhibit unique strengths and weaknesses, highlighting the need for tailored approaches.
  • Prompt-based methods excel in backward accuracy but degrade on future tasks, while distillation methods struggle with rapid updates.
Read more
Max Out GRPO Signal: Adaptive Trace Prefix Control for Hard Reasoning Problems
Vladislav Beliaev
Reinforcement Learning Large Language Models Optimization
  • Introduces AdaPrefix-GRPO, a method that adapts prefix length dynamically during training to optimize gradient signal.
  • Demonstrates that maintaining a success rate of approximately 50% maximizes the learning signal in GRPO.
  • Implements the method with minimal modifications to existing GRPO frameworks, focusing on data preparation.
  • Achieves substantial improvements in accuracy on hard reasoning problems while reducing trace lengths.
Read more
When Do Geometric Algebra Layers Beat Scalarization? A Controlled Study on SO(3)-Equivariant Vector Laws
Fabien Polly
Robotics Theory Efficient ML
  • Geometric algebra layers do not outperform scalarization for single-stage laws, which can be computed with one equivariant interaction.
  • For compositional laws involving nested group operations, geometric algebra networks significantly outperform scalarization in low-data regimes.
  • No tested model, including equivariant architectures, successfully extrapolates invariant magnitudes under radial out-of-distribution conditions.
  • The study emphasizes the importance of distinguishing between the effects of equivariance and specific parameterization in model performance.
Read more