Machine learning and reinforcement learning are increasingly popular and important fields in the modern age. There are problems that reinforcement learning agents can learn to solve more efficiently and consistently than any human when given enough time to practice. However, modern approaches like Q-learning run into issues when facing certain types of problems. Their approach to solving problems in combination with not using a model of the environment causes them to take longer than is necessary to learn to solve problems that are deterministic in nature. By working without model of the environment, information that is available and help the learning process is ignored. This paper introduces an adapted Q-learning agent called the recursive backwards Q-Learning (RBQL) agent. It solves these types of problems by building a model of its environment as it explores and recursively applying the Q-value update rule to find an optimal policy much quicker than a regular Q-learning agent. This agent is shown to work with the example of finding the fastest path through a maze. Its results are compared to the results of a regular Q-learning agent.

In RAG, the model's knowledge can be updated from documents provided in context. This leads to cases of conflict between the model's parametric knowledge and the contextual information, where the model may not always update its knowledge. Previous work studied knowledge conflicts by creating synthetic documents that contradict the model's correct parametric answers. We present a framework for studying knowledge conflicts in a realistic setup. We update incorrect parametric knowledge using real conflicting documents. This reflects how knowledge conflicts arise in practice. In this realistic scenario, we find that knowledge updates fail less often than previously reported. In cases where the models still fail to update their answers, we find a parametric bias: the incorrect parametric answer appearing in context makes the knowledge update likelier to fail. These results suggest that the factual parametric knowledge of LLMs can negatively influence their reading abilities and behaviors.

Misinformation about climate change poses a significant threat to societal well-being, prompting the urgent need for effective mitigation strategies. However, the rapid proliferation of online misinformation on social media platforms outpaces the ability of fact-checkers to debunk false claims. Automated detection of climate change misinformation offers a promising solution. In this study, we address this gap by developing a two-step hierarchical model, the Augmented CARDS model, specifically designed for detecting contrarian climate claims on Twitter. Furthermore, we apply the Augmented CARDS model to five million climate-themed tweets over a six-month period in 2022. We find that over half of contrarian climate claims on Twitter involve attacks on climate actors or conspiracy theories. Spikes in climate contrarianism coincide with one of four stimuli: political events, natural events, contrarian influencers, or convinced influencers. Implications for automated responses to climate misinformation are discussed.

Video Wire Inpainting (VWI) is a prominent application in video inpainting, aimed at flawlessly removing wires in films or TV series, offering significant time and labor savings compared to manual frame-by-frame removal. However, wire removal poses greater challenges due to the wires being longer and slimmer than objects typically targeted in general video inpainting tasks, and often intersecting with people and background objects irregularly, which adds complexity to the inpainting process. Recognizing the limitations posed by existing video wire datasets, which are characterized by their small size, poor quality, and limited variety of scenes, we introduce a new VWI dataset with a novel mask generation strategy, namely Wire Removal Video Dataset 2 (WRV2) and Pseudo Wire-Shaped (PWS) Masks. WRV2 dataset comprises over 4,000 videos with an average length of 80 frames, designed to facilitate the development and efficacy of inpainting models. Building upon this, our research proposes the Redundancy-Aware Transformer (Raformer) method that addresses the unique challenges of wire removal in video inpainting. Unlike conventional approaches that indiscriminately process all frame patches, Raformer employs a novel strategy to selectively bypass redundant parts, such as static background segments devoid of valuable information for inpainting. At the core of Raformer is the Redundancy-Aware Attention (RAA) module, which isolates and accentuates essential content through a coarse-grained, window-based attention mechanism. This is complemented by a Soft Feature Alignment (SFA) module, which refines these features and achieves end-to-end feature alignment. Extensive experiments on both the traditional video inpainting datasets and our proposed WRV2 dataset demonstrate that Raformer outperforms other state-of-the-art methods.

The use of retrieval-augmented generation (RAG) to retrieve relevant information from an external knowledge source enables large language models (LLMs) to answer questions over private and/or previously unseen document collections. However, RAG fails on global questions directed at an entire text corpus, such as "What are the main themes in the dataset?", since this is inherently a query-focused summarization (QFS) task, rather than an explicit retrieval task. Prior QFS methods, meanwhile, fail to scale to the quantities of text indexed by typical RAG systems. To combine the strengths of these contrasting methods, we propose a Graph RAG approach to question answering over private text corpora that scales with both the generality of user questions and the quantity of source text to be indexed. Our approach uses an LLM to build a graph-based text index in two stages: first to derive an entity knowledge graph from the source documents, then to pregenerate community summaries for all groups of closely-related entities. Given a question, each community summary is used to generate a partial response, before all partial responses are again summarized in a final response to the user. For a class of global sensemaking questions over datasets in the 1 million token range, we show that Graph RAG leads to substantial improvements over a na\"ive RAG baseline for both the comprehensiveness and diversity of generated answers. An open-source, Python-based implementation of both global and local Graph RAG approaches is forthcoming at https://aka.ms/graphrag.

Short- and long-term outcomes of an algorithm often differ, with damaging downstream effects. A known example is a click-bait algorithm, which may increase short-term clicks but damage long-term user engagement. A possible solution to estimate the long-term outcome is to run an online experiment or A/B test for the potential algorithms, but it takes months or even longer to observe the long-term outcomes of interest, making the algorithm selection process unacceptably slow. This work thus studies the problem of feasibly yet accurately estimating the long-term outcome of an algorithm using only historical and short-term experiment data. Existing approaches to this problem either need a restrictive assumption about the short-term outcomes called surrogacy or cannot effectively use short-term outcomes, which is inefficient. Therefore, we propose a new framework called Long-term Off-Policy Evaluation (LOPE), which is based on reward function decomposition. LOPE works under a more relaxed assumption than surrogacy and effectively leverages short-term rewards to substantially reduce the variance. Synthetic experiments show that LOPE outperforms existing approaches particularly when surrogacy is severely violated and the long-term reward is noisy. In addition, real-world experiments on large-scale A/B test data collected on a music streaming platform show that LOPE can estimate the long-term outcome of actual algorithms more accurately than existing feasible methods.

Captchas are becoming more difficult to solve and there's a reason why - bots are outsmarting you. The'I'm not a robot' prompt originally made the users copy a series of letters and numbers or identify all the buses in a series of images that were often difficult to get wrong. But new versions that ask users to select the objects that are the same shape or click on the non-aquatic animal. Captchas are puzzles that are used to safeguard websites from nefarious bots, and used to pose a simple'copy the text' question but have now evolved to ask people to solve brain-teasing questions. Captcha puzzles (pictured) can include anything from matching a puzzle piece to the opened slot to copying a series of numbers and letters.

Fox News Flash top entertainment and celebrity headlines are here. Sorry to break to everyone, but Henry Cavill and Margot Robbie aren't starring in a new James Bond film. In fact, it's pretty easy to fake things to a degree that the untrained eye can't even tell the difference. While there are certainly advantages to artificial intelligence, the fact it can be used as a tool to manipulate and spread misinformation is certainly concerning. That also now applies to movies. MARGOT ROBBIE SAYS ACTING CAREER ALMOST ENDED AFTER'THE WOLF OF WALL STREET' The popular YouTube page KH Studio is known for creating fake/concept trailers for upcoming movies, and it uses AI technology to get the job done.

Tiffany Henyard, the embattled mayor of Dolton, Illinois, faced such an outcry of anger from town residents that many had to be kept outside the building. Much like Dolton, Illinois self-declared "Super Mayor" Tiffany Henyard, Philadelphia Sheriff Rochelle Bilal has been slammed with allegations of wild offenses ranging from spending department money on promotional items like trading cards with her likeness to having bogus news stories about her being generated by AI. While Bilal testified before the City Council last year that her department is underfunded to the point it "jeopardizes the lives and safety of our sworn and civilian personnel," her department's spending habits indicate that money may have been used in questionable ways, according to a new report from The Philadelphia Inquirer. The Philadelphia Sheriff's Office allegedly spent 9,250 on a new mascot, an African-American Wild Western-style female sheriff named Deputy Sheriff Justice, who debuted at the Thanksgiving Day parade, made by a company that makes some of the world's most recognizable mascot costumes, like that of the Geico gecko. Philadelphia Sheriff Rochelle Bilal speaks at a news conference, Philadelphia, Thursday, Sept. 21, 2023.

After an anti-Israel protest escalated at New York University on Monday – requiring city police presence – the university released a statement explaining while it supports students' rights to protest, safety remains its priority. HATE RAGES – Elite university reverses on NYPD presence as antisemitic mob takes over campus and more top headlines. POISON IVY – Columbia University shifts to hybrid learning as escalating anti-Israel protests cause safety concerns. NO COFFEE, NO PEACE – Angry Alec Baldwin smacks anti-Israel agitator's phone after hounding actor. TRUMP TRIAL – Judge to hear gag order arguments after former president's all-caps rant on social media.