Aligning large language models with human feedback at inference time has received increasing attention due to its flexibility. Existing methods rely on generating multiple responses from the base policy for search using a reward model, which can be considered as searching in a discrete response space. However, these methods struggle to explore informative candidates when the base policy is weak or the candidate set is small, resulting in limited effectiveness. In this paper, to address this problem, we propose Simple Energy Adaptation (SEA), a simple yet effective algorithm for inference-time alignment.

Regularization is one of the most fundamental topics in optimization, statistics and machine learning. To get sparsity in estimating a parameter u Rd, an ℓq penalty term, u q, is usually added to the objective function. What is the probabilistic distribution corresponding to such ℓq penalty? What is the correct stochastic process corresponding to u q when we model functions u Lq? This is important for statistically modeling high-dimensional objects such as images, with penalty to preserve certain properties, e.g.

Jack Dorsey leaves the Élysée Palace in Paris, France, on 7 June 2019. Jack Dorsey leaves the Élysée Palace in Paris, France, on 7 June 2019. What was really behind Jack Dorsey laying off nearly half of Block's staff? Jack Dorsey cited AI as the driving force behind cutting 40% of his company's employees, but other factors such as a weak crypto market, overstaffing and a declining stock price may also have motivated the move. Last week, the financial technology company Block announced that it would lay off 4,000 of its 10,000 workers.

Regularization is one of the most fundamental topics in optimization, statistics and machine learning.

As the housing market stalls, Zillow's CEO sees AI as "an ingredient rather than a threat" that can both help the company protect its turf and reinvent how people search for homes. This will not be a banner year for the real estate app Zillow. "We describe the home market as bouncing along the bottom," CEO Jeremy Wacksman said in our conversation this week. Last year was dismal for the real estate market, and he expects things to improve only marginally in 2026. "The way to think about it is that there were 4.1 million existing homes sold last year--a normal market is 5.5 to 6 million," Wacksman says.

Stock market prediction is a long-standing challenge in finance, as accurate forecasts support informed investment decisions. Traditional models rely mainly on historical prices, but recent work shows that financial news can provide useful external signals. This paper investigates a multimodal approach that integrates companies' news articles with their historical stock data to improve prediction performance. We compare a Graph Neural Network (GNN) model with a baseline LSTM model. Historical data for each company is encoded using an LSTM, while news titles are embedded with a language model. These embeddings form nodes in a heterogeneous graph, and GraphSAGE is used to capture interactions between articles, companies, and industries. We evaluate two targets: a binary direction-of-change label and a significance-based label. Experiments on the US equities and Bloomberg datasets show that the GNN outperforms the LSTM baseline, achieving 53% accuracy on the first target and a 4% precision gain on the second. Results also indicate that companies with more associated news yield higher prediction accuracy. Moreover, headlines contain stronger predictive signals than full articles, suggesting that concise news summaries play an important role in short-term market reactions.

The aim of this paper is the analysis and selection of stock trading systems that combine different models with data of different nature, such as financial and microeconomic information. Specifically, based on previous work by the authors and applying advanced techniques of Machine Learning and Deep Learning, our objective is to formulate trading algorithms for the stock market with empirically tested statistical advantages, thus improving results published in the literature. Our approach integrates Long Short-Term Memory (LSTM) networks with algorithms based on decision trees, such as Random Forest and Gradient Boosting. While the former analyze price patterns of financial assets, the latter are fed with economic data of companies. Numerical simulations of algorithmic trading with data from international companies and 10-weekday predictions confirm that an approach based on both fundamental and technical variables can outperform the usual approaches, which do not combine those two types of variables. In doing so, Random Forest turned out to be the best performer among the decision trees. We also discuss how the prediction performance of such a hybrid approach can be boosted by selecting the technical variables.