Operations research (OR) is widely deployed to solve critical decision-making problems with complex objectives and constraints, impacting manufacturing, logistics, finance, and healthcare outcomes. While Large Language Models (LLMs) have shown promising results in various domains, their practical application in industry-relevant operations research (OR) problems presents significant challenges and opportunities. Preliminary industrial applications of LLMs for operations research face two critical deployment challenges: 1) Self-correction focuses on code syntax rather than mathematical accuracy, causing costly errors; 2) Complex expert selection creates unpredictable workflows that reduce transparency and increase maintenance costs, making them impractical for time-sensitive business applications. To address these business limitations, we introduce ORMind, a cognitive-inspired framework that enhances optimization through counterfactual reasoning. Our approach emulates human cognition, implementing an end-to-end workflow that systematically transforms requirements into mathematical models and executable solver code. It is currently being tested internally in Lenovo's AI Assistant, with plans to enhance optimization capabilities for both business and consumer customers. Experiments demonstrate that ORMind outperforms existing methods, achieving a 9.5\% improvement on the NL4Opt dataset and a 14.6\% improvement on the ComplexOR dataset.

While soft context compression methods, which map input text to smaller latent representations, have shown promise, their real-world adoption is limited. Existing techniques typically compress the context as a single unit, which leads to quadratic compression complexity and an inability to reuse computations across queries with overlapping contexts. In this work, we introduce CompLLM, a soft compression technique designed for practical deployment. Instead of processing the context holistically, CompLLM divides it into segments and compresses each one independently. This simple design choice yields three critical properties: efficiency, as the compression step scales linearly with the context length; scalability, enabling models trained on short sequences (e.g., 1k tokens) to generalize to contexts of 100k tokens; and reusability, allowing compressed segments to be cached and reused across different queries. Our experiments show that with a 2x compression rate, at high context lengths CompLLM speeds up Time To First Token (TTFT) by up to 4x and reduces the KV cache size by 50%. Furthermore, CompLLM achieves performance comparable to that obtained with the uncompressed context, and even surpasses it on very long sequences, demonstrating its effectiveness and practical utility. LOFT is a long context benchmark (128k tokens) designed to stress-test the long context capabilities of frontiers LLMs as Gemini 1.5 Pro, GPT -4o, and Claude 3 Opus. With CompLLM we show that we can improve long context capabilities of much smaller open source LLMs. Figure 1: At high context lengths, CompLLM leads to considerable speedup and improved results, without requiring any modification or tuning of the LLM, by efficiently reducing the number of embeddings fed to the LLM. The plot shows the Time To First Token (TTFT) with CompLLM and without it (i.e. with a standard pipeline) as a function of context length. Among the many use cases of LLMs, one of the most popular is long context Q&A: given a textual context of arbitrary length, the LLM should answer questions about it. Applications include coding assistants reading large codebases (Team, 2024), web agents reasoning on HTML pages (Zeng et al., 2024), users querying an LLM about a set of documents (Liu et al., 2024a), or RAG systems 1 Due to the quadratic complexity of the transformer (V aswani et al., 2017), processing long contexts can be unfeasibly expensive: it is therefore important to reduce computational complexity, especially as contexts grows longer and longer.

What is autism and what are Trump's unproven claims about a Tylenol link? US President Donald Trump has claimed there is a link between the use of painkiller Tylenol by pregnant women and an increased risk of autism in some children. Going against current scientific advice and medical opinion, he said the drug, known as paracetamol in many countries, is no good and women should fight like hell to only take it in extreme cases, such as for high fevers. Medical bodies say the drug is safe and that it remains the best treatment for pain and fever during pregnancy. What is autism and how is it diagnosed?

Large language models (LLMs) offer a promising pre-screening tool, improving early disease detection and providing enhanced healthcare access for underprivileged communities. The early diagnosis of various diseases continues to be a significant challenge in healthcare, primarily due to the nonspecific nature of early symptoms, the shortage of expert medical practitioners, and the need for prolonged clinical evaluations, all of which can delay treatment and adversely affect patient outcomes. With impressive accuracy in prediction across a range of diseases, LLMs have the potential to revolutionize clinical pre-screening and decision-making for various medical conditions. In this work, we study the diagnostic capability of LLMs for Rheumatoid Arthritis (RA) with real world patients data. Patient data was collected alongside diagnoses from medical experts, and the performance of LLMs was evaluated in comparison to expert diagnoses for RA disease prediction. We notice an interesting pattern in disease diagnosis and find an unexpected \textit{misalignment between prediction and explanation}. We conduct a series of multi-round analyses using different LLM agents. The best-performing model accurately predicts rheumatoid arthritis (RA) diseases approximately 95\% of the time. However, when medical experts evaluated the reasoning generated by the model, they found that nearly 68\% of the reasoning was incorrect. This study highlights a clear misalignment between LLMs high prediction accuracy and its flawed reasoning, raising important questions about relying on LLM explanations in clinical settings. \textbf{LLMs provide incorrect reasoning to arrive at the correct answer for RA disease diagnosis.}

We gave an AI (ChatGpt) a challenge to write lyrics like Painkiller by Judas Priest and this is what it gave me. Let us know what you think in the comments section below. We are the Painkillers, we're here to rock and roll We'll break the chains that bind you, and free your soul We'll take you on a journey, to a place you've never been We are the Painkillers, and we're ready to win We'll never stop, until we've left our mark We'll light a fire, and set the world ablaze We'll make you feel alive, with every note we play We are the Painkillers, we're here to rock and roll We'll break the chains that bind you, and free your soul We'll take you on a journey, to a place you've never been We are the Painkillers, and we're ready to win We'll be your savior, your guiding light We'll be the ones to help you through We are the Painkillers, we're here to rock and roll We'll break the chains that bind you, and free your soul We'll take you on a journey, to a place you've never been We are the Painkillers, and we're ready to win So come on and join us, let's ride the lightning We'll take you to new heights, and keep your heart beating We are the Painkillers, and we'll never back down We'll keep the music alive, until the last sound.

While cone snails are stunning animals with beautifully adorned shells, they're also some of the deadliest creatures to roam the oceans. Now, scientists from the University of Glasgow have revealed plans to harness their venom to develop new painkillers that are more effective and less addictive than current options. Dr Andrew Jamieson, who is leading the project, said: 'The cone snail might seem like an unlikely prospect for breakthroughs in drug discovery, but the conotoxins it produces have a lot of intriguing properties which have already shown promise in medicine.' While cone snails are stunning animals with beautifully adorned shells, they're also some of the deadliest creatures to roam the oceans Cone snails are marine gastropods characterized by a conical shell and beautiful color patterns. Cone snails possess a harpoonlike tooth capable of injecting a potent neurotoxin that can be dangerous to humans.

Social media such as Instagram and Twitter have become important platforms for marketing and selling illicit drugs. Detection of online illicit drug trafficking has become critical to combat the online trade of illicit drugs. However, the legal status often varies spatially and temporally; even for the same drug, federal and state legislation can have different regulations about its legality. Meanwhile, more drug trafficking events are disguised as a novel form of advertising commenting leading to information heterogeneity. Accordingly, accurate detection of illicit drug trafficking events (IDTEs) from social media has become even more challenging. In this work, we conduct the first systematic study on fine-grained detection of IDTEs on Instagram. We propose to take a deep multimodal multilabel learning (DMML) approach to detect IDTEs and demonstrate its effectiveness on a newly constructed dataset called multimodal IDTE(MM-IDTE). Specifically, our model takes text and image data as the input and combines multimodal information to predict multiple labels of illicit drugs. Inspired by the success of BERT, we have developed a self-supervised multimodal bidirectional transformer by jointly fine-tuning pretrained text and image encoders. We have constructed a large-scale dataset MM-IDTE with manually annotated multiple drug labels to support fine-grained detection of illicit drugs. Extensive experimental results on the MM-IDTE dataset show that the proposed DMML methodology can accurately detect IDTEs even in the presence of special characters and style changes attempting to evade detection.

Kaia Health, a self-styled digital therapeutics" startup, has pulled in $10 million in Series A funding for an app-based approach to chronic pain management. The idea is to offer an alternative to painkillers, using mobile technology to deliver what the founder describes as multimodal, "mind body therapy" for musculoskeletal (MSK) disorders -- comprised of guided physical exercises, psychological techniques and on tap medical education. "Once you fall into this category of you're a chronic pain patient, and not just you have acute pain for two or three days, then this is the best therapy to do," says co-founder and CEO Konstantin Mehl. "But at the moment because this therapy is so expensive only 2% of the patients who should get access to it actually get access to it and the other 98% of patients are treated with treatments against acute pain, like painkillers and surgery… This is why there's this crazy cost explosion when you look at the costs in the healthcare systems." The 2015-founded startup has developed a personal trainer app that uses computer vision technology so it can act as a fully autonomous exercise coach. The app works by visually monitoring the user as they perform exercises (via their smartphone's camera), enabling it to keep track of repetitions and also provide vocal feedback -- to correct posture and motion. The idea is to offer a more accessible and less expensive alternative to the one-on-one in person physiotherapy which a person suffering chronic pain from a MSK disorder might otherwise use to manage their pain -- such as by visiting a dedicated pain center for weeks of guided treatment. However as Mehl notes that can be prohibitively expensive and also entail long wait times to get seen. Kaia's first focus has been on back pain which Mehl knows plenty about -- having suffered himself for two years. His struggles to find effective and affordable pain management were the inspiration for setting up the company, he tells us. The goal he's shooting for with Kaia is to democratize access to proven multimodal therapies and reduce reliance on pharmaceuticals -- pointing to rising use of opioid-based painkillers, including in the U.S., where reliance on the drug has been driven by over-prescription leading to an epidemic of addiction and rising numbers of overdose deaths. "Most treatments against chronic back pain are just crazy expensive and crazy ineffective.

Millions of women over the last two decades have undergone vaginal mesh surgery, but it has recently become clear just how many have experienced severe complications. In our main interview this week, we hear from Sohier Elneil, one of the few surgeons in the UK qualified to remove mesh. Here, Kath Sansom shares her story of what it's like to undergo the treatment and the impact it had on her life. She had a mesh sling implanted in March 2015 to treat mild stress urinary incontinence. It was removed seven months later.

AI is learning parkour, Amazon's huge sale is upon us and we see how technology is replacing painkillers. What happens when AI teaches itself parkour? Come for the reinforcement learning, stay for the GIFs. Amazon Prime Day is upon us, have you bought your Echo? It's hard to say what counts as a'real' holiday these days, but discounts are discounts.