Model learns brevity by exposing to easy problems, improving efficiency without explicit length penalties.
problem Excessive verbosity in step-by-step reasoning models trained with RLVR.
method Retaining and up-weighting moderately easy problems as implicit length regularizers.
result Model generates solutions that are, on average, nearly twice as short without explicit length penalties.
Transformers solve parity problems efficiently with step-by-step reasoning.
problem Training transformers to solve complex, recursive problems like parity.
method Training a one-layer transformer to solve k-parity, incorporating intermediate parities into the loss function, and using teacher forcing or augmented data. result Transformers can learn parity in one gradient update with intermediate supervision or self-consistency checks.
Trading-R1 uses LLMs for financial trading, improving risk-adjusted returns.
problem Lack of interpretability and trust in AI for finance.
method Supervised fine-tuning and reinforcement learning with a curriculum.
result Improved risk-adjusted returns and lower drawdowns compared to other models.
Study learning from multiple thinkers providing step-by-step solutions to problems.
problem Learning from multiple, possibly different, thinkers providing step-by-step solutions to problems.
method Active learning algorithm that uses CoT data from multiple thinkers and end-result data.
result Learning can be hard from CoT supervision provided by two or a few different thinkers, but a generic algorithm can learn efficiently.
Transformers learn sparse Boolean functions through RL and SFT, revealing distinct learning behaviors.
problem Learning sparse Boolean functions with Transformers.
method Reinforcement Learning (RL) with process rewards and Supervised Fine-Tuning (SFT).
result RL learns the whole CoT chain simultaneously, while SFT learns step by step.
Method verifies if observed data fits Lévy-Driven Ornstein-Uhlenbeck process.
problem Verifying if observed data fits Lévy-Driven Ornstein-Uhlenbeck process.
method Estimating parameters and approximating the driving process to test CAR(1) Lévy-driven hypothesis.
result Demonstrates method's effectiveness through simulations and real data examples.
A simplified tutorial on diffusion models for beginners.
problem Educating technical audiences on diffusion models.
method Simplified mathematical explanations and heuristic derivations.
result Accessible algorithms for diffusion models.
A new method for disentangling action sequences improves model stability.
problem Challenges in unsupervised disentanglement learning due to incomplete theories and abstract notions.
method Introducing disentangling action sequences and a novel fractional variational autoencoder (FVAE) framework.
result FVAE improves the stability of disentanglement for action sequences.
LLapDiff models irregular multivariate time series without step-by-step integration.
problem Trade-off between discrete and continuous methods for long-horizon forecasting.
method Generative framework that models target as a low-dimensional latent trajectory, guided by modal parameterization and Laplace domain poles.
result Improves long-horizon forecasting over baselines and supports missing-value imputation.
TD-Flow improves long-term predictions in agent learning.
problem Cumulative errors in step-by-step inference of future states.
method Leverages flow-matching techniques and a novel Bellman equation to learn accurate geometric horizon models.
result Significantly reduces errors at long horizons compared to prior methods.
In the present paper, a fuzzy logic based method is combined with wavelet decomposition to develop a step-by-step dynamic hybrid model for the estimation of financial time series. Empirical tests on fuzzy regression, wavelet decomposition as well as the new hybrid model are conducted on the well known SP500 index fin…
The paper explores how LLMs with CoT improve performance on complex tasks.
problem Understanding the mechanisms behind LLMs' improved performance with CoT.
method Using circuit complexity theory, the paper examines LLMs' expressivity in solving mathematical and decision-making problems.
result LLMs with CoT can generate correct solutions step-by-step, even for complex tasks.
We construct an extension of the Kontsevich integral of knots to knotted trivalent graphs, which commutes with orientation switches, edge deletions, edge unzips, and connected sums. In 1997 Murakami and Ohtsuki [MO] first constructed such an extension, building on Drinfel'd's theory of associators. We construct a step …
Paper resolves the debate on process vs. outcome supervision in reinforcement learning.
problem Distinguishing between process and outcome supervision in reinforcement learning.
method Developed a technical tool (Change of Trajectory Measure Lemma) to show equivalence between outcome and process supervision under standard data coverage assumptions.
result Reinforcement learning through outcome supervision is statistically equivalent to process supervision, up to polynomial factors in horizon.
Federated learning enables private model training across devices.
problem Private and collaborative machine learning across multiple devices.
method Designing scalable, privacy-preserving FL systems using graph-based optimization.
result Personalized models for each device while maintaining data privacy.
In this paper, we establish a robustification of an on-line algorithm for modelling asset prices within a hidden Markov model (HMM). In this HMM framework, parameters of the model are guided by a Markov chain in discrete time, parameters of the asset returns are therefore able to switch between different regimes. The p…
Deep learning predicts currency volatility accurately.
problem Predicting future volatility in Forex trading.
method Constructed a deep-learning network using multiscale LSTM with multi-currency pairs.
result Multiscale LSTM model outperforms conventional models.
This study tackles XVA model risk and computational effort in derivatives pricing.
problem XVA model risk and computational effort in derivatives pricing, especially for counterparty and funding risk.
method Realistic and complete XVA modelling framework based on multi-curve time-dependent volatility G2++ stochastic dynamics, calibrated on real market data, and multi-step Monte Carlo simulation.
result Identification and quantification of model risk sources and computational effort in XVA figures.
In this paper, we study the PSV construction, which provides a step by step method for obtaining tame translation surfaces with a suitable Veech group. In addition, we modify slightly this construction, and for each finitely generated subgroup G<GL+(2,R) without contracting elements, we produce a ta…
In this paper, we introduce a system called GamePad that can be used to explore the application of machine learning methods to theorem proving in the Coq proof assistant. Interactive theorem provers such as Coq enable users to construct machine-checkable proofs in a step-by-step manner. Hence, they provide an opportuni…
A symplectic fibration is a fibre bundle in the symplectic category. We find the relation between deformation quantization of the base and the fibre, and the total space. We use the weak coupling form of Guillemin, Lerman, Sternberg and find the characteristic class of deformation of symplectic fibration. We also prove…
New embedding method in function spaces improves expressiveness.
problem Enhancing expressiveness in knowledge graph embeddings.
method Employing polynomial functions and neural networks with varying layer complexities.
result Improved expressiveness and more degrees of freedom in entity representation.
This paper is a step-by-step tutorial for fitting a mixture distribution to data. It merely assumes the reader has the background of calculus and linear algebra. Other required background is briefly reviewed before explaining the main algorithm. In explaining the main algorithm, first, fitting a mixture of two distribu…
Investment strategy depends on many factors for venture capital funds.
problem Finding the optimal portfolio size for venture capital funds.
method Analyzes various factors affecting fund returns and optimal portfolio size, starting with basic assumptions and increasing complexity.
result Investment strategy depends on many factors, not a one-size-fits-all formula.
To act and plan in complex environments, we posit that agents should have a mental simulator of the world with three characteristics: (a) it should build an abstract state representing the condition of the world; (b) it should form a belief which represents uncertainty on the world; (c) it should go beyond simple step-…
Given any diagram of a link, we define on the cube of Kauffman's states a "2-complex" whose homology is an invariant of the associated framed links, and such that the graded Euler characteristic reproduces the unnormalized Kauffman bracket. This includes a categorification of brackets skein relation. Then we incorporat…
Starting with an ideal triangulation of the interior of a compact 3-manifold M with boundary, no component of which is a 2-sphere, we provide a construction, called an inflation of the ideal triangulation, to obtain a strongly related triangulations of M itself. Besides a step-by-step algorithm for such a construction,…
A step by step procedure to derive analytically the exact dynamical evolution equations of the probability density functions (PDF) of well known kinetic wealth exchange economic models is shown. This technique gives a dynamical insight into the evolution of the PDF, e.g., allowing the calculation of its relaxation time…
A new model uses Lorentz-Finsler geometry to predict wave propagation.
problem Modeling wave propagation in anisotropic and rheonomic media.
method Identifying wave trajectories as lightlike pregeodesics of a specific Lorentz-Finsler metric, solving ODE systems.
result Wave trajectories can be easily computed in real time.
This tutorial provides a gentle introduction to the particle Metropolis-Hastings (PMH) algorithm for parameter inference in nonlinear state-space models together with a software implementation in the statistical programming language R. We employ a step-by-step approach to develop an implementation of the PMH algorithm …
We discuss a recurrent geometrical method, due to Élie Cartan and von Weber ([1],[11]) enabling us to determine, step by step, the maximal integral manifolds of a not necessarily integrable nor regular Pfaffian system. The dimensions of such integral manifolds can, of course, vary from point to point but more so can va…
Study global geometry of dynamical systems with entire vector fields.
problem Understanding the global structure of equilibria and their basins.
method Step-by-step analysis of basins of centers, nodes, and foci; introduction of global elliptic sectors.
result Characterization of heteroclinic regions connecting equilibria.
The 4-dimensional abstract Kummer variety K^4 with 16 nodes leads to the K3 surface by resolving the 16 singularities. Here we present a simplicial realization of this minimal resolution. Starting with a minimal 16-vertex triangulation of K^4 we resolve its 16 isolated singularities - step by step - by simplicial blowu…
Python package for functional data analysis.
problem Handling and analysis of functional data.
method Comprehensive tools for representation, preprocessing, and exploratory analysis of functional data.
result Scikit-fda package provides a comprehensive set of tools for functional data analysis.
jinns is a JAX library for physics-informed neural networks.
problem Physics-informed neural networks for forward and inverse problems.
method Physics-informed neural networks using JAX ecosystem.
result Efficient prototyping and extensions for real problems.
Study fairness in vaccine allocation in social networks.
problem Fairness implications of vaccine allocation strategies in social networks.
method Defined precision disease control problem, used ML Fairness Gym to simulate and analyze.
result Different treatment strategies distribute disease burden differently across subgroups.
Analyzes factors affecting flow VI performance.
problem Consistent performance of flow VI across studies.
method Step-by-step analysis of capacity, objectives, batchsize, estimators, and step-sizes.
result Specific recommendations and a flow VI recipe.
New method solves tensor equations including parity odd and even terms in 4D.
problem Solving linear tensor equations with parity odd and even terms in 4D.
method Extending previous results, solving a 30-parameter linear tensor equation step by step.
result Explicit solution for tensor field components in terms of known components.
The paper detects and identifies bias in data using a counterfactual approach.
problem Detecting and identifying bias in data, especially in medical image classification.
method A global explanation framework using the counterfactual approach to identify bias causing artifacts.
result Black frames significantly influence Convolutional Neural Network's prediction, changing benign to malignant.
LaTRO optimizes latent reasoning in LLMs without external reward.
problem Training LLMs to perform complex reasoning tasks.
method Formulates reasoning as latent distribution sampling and optimizes via variational approaches.
result LLMs improve reasoning and evaluation quality through self-improvement.
The Prescriptive Canvas improves business outcomes by directly prescribing actions based on predictions.
problem Sub-optimal performance in business projects due to a two-step approach of prediction and decision-making.
method The Prescriptive Canvas methodology for framing and communicating actions directly based on predictions.
result Improves framing and communication across stakeholders for successful business impact.
In this paper, we deal with the problem of curves clustering. We propose a nonparametric method which partitions the curves into clusters and discretizes the dimensions of the curve points into intervals. The cross-product of these partitions forms a data-grid which is obtained using a Bayesian model selection approach…
Auto-CEI improves LLM reasoning by balancing assertiveness and conservativeness.
problem Hallucinations and laziness in LLM reasoning tasks.
method Expert Iteration explores reasoning trajectories, guiding incorrect paths back on track and promoting appropriate 'I don't know' responses.
result Auto-CEI achieves superior alignment in logical reasoning, mathematics, and planning tasks.
A framework isolates VQA reasoning from perception for better model evaluation.
problem Improper separation of visual perception and reasoning in VQA models.
method Introducing a framework and a top-down calibration technique to decouple reasoning from perception.
result Improved evaluation of VQA models by separating reasoning from perception.
A new method for math reasoning that allows for iterative correction.
problem Standard reasoning models commit to each token and cannot recover from early errors.
method Generative framework with latent thought vectors for iterative self-correction.
result 30 rethinking iterations surpass baselines with 15 times more parameters.
In this paper we study the main geometric properties of the Carnot-Carathéodory (abbreviated CC) distance $\dc$ in the setting of k-step sub-Riemannian Carnot groups from many different points of view. An extensive study of the so-called normal CC-geodesics is given. We state and prove some related variational formul…
Inferring new facts from existing knowledge graphs (KG) with explainable reasoning processes is a significant problem and has received much attention recently. However, few studies have focused on relation types unseen in the original KG, given only one or a few instances for training. To bridge this gap, we propose Co…
Transformers learn multi-step reasoning through gradient descent.
problem Understanding how transformers solve symbolic multi-step reasoning tasks.
method Theoretical analysis of gradient descent dynamics and multi-phase training.
result Trained one-layer transformers can solve both backward and forward reasoning tasks with generalization guarantees.