You're viewing the US edition You can switch to the UK, AU or IE homepage at any time using this menu. Madonna's family make intervention: After forgetful and embarrassing VMAs comeback, insiders reveal clash between'control freak' star and her team Nobody wants to say this about Cindy Crawford after her son Presley Gerber's death... but maybe someone should: MAUREEN CALLAHAN Trump'grand conspiracy' case in crisis as lawyers defy Todd Blanche and QUIT in mass exodus Death of the Pastor's Wife preacher John Paul Miller faced jaw-dropping humiliation during date night with new bride at his favorite restaurant... then an exceptionally petty TripAdvisor review appeared I've seen what cocaine is doing to middle-aged men. Most of my patients think an occasional line is harmless but this is what it does to your heart, brain and sex life... and why the impact is so much worse later in life'Presley never felt good enough. It bothered him enormously': Modeling agency owner tells ROB SHUTER the nasty industry rumor that haunted Gerber as a teenager Candace Owens in crisis: As family begs her to'disappear' and prays she isn't KILLED, insiders reveal whispers of a foreign reconnaissance mission... and her links to secret military location Extraordinary twist in killer dad Chris Watts' prison love life after jail makeout sessions with new wife were exposed... and his major mommy issues are laid bare Teresa Giudice says daughter Milania had'fentanyl in her system' as she breaks silence following airport incident Woman, 54, gives birth to baby girl using 22-year-old frozen embryo after son's tragic death My perfect affair: For six glorious years, I've followed these five rules for not getting caught. My partner and his wife still have no idea... Explosive Tom Brady marriage revelations that have'hit a nerve' with Gisele Bundchen and left her'worried': As she puts on brave face, insiders reveal her'biggest concern' Frail Texas man, 81, flooded with $700k in donations after kindly'neighbor' spotted him working to pay wife's medical bills... but now he's lost ALL the cash after disturbing truth was exposed Truth behind Kevin Costner's rotation of blondes: Christine Baumgartner split left him so'burned', there was only one way to revive his spirit... now, insiders spill on his daring next steps Biden's Afghan vetting disaster exposed as bombshell audit finds 40% of files riddled with errors and terror red flags missed LADY SYBILLA HART: Forget Florence, Amelia, Poppy, Oscar and Theodore.

You're viewing the US edition You can switch to the UK, AU or IE homepage at any time using this menu. Transgender New York Times executive who was shot dead'by his in-laws' abused BOTH his young children and left them with head injuries, wife claims Female death row inmate set to be executed TOMORROW reveals'kinship' with Lindsay Clancy Madonna's family make intervention: After forgetful and embarrassing VMAs comeback, insiders reveal clash between'control freak' star and her team Nobody wants to say this about Cindy Crawford after her son Presley Gerber's death... but maybe someone should: MAUREEN CALLAHAN Christopher Reeve's son Will, 34, reveals rare testicular cancer diagnosis Taylor Swift's unreleased suicide note song: Tracks the world was never meant to hear... including one her co-writer said is'the most chilling he's ever heard' Trump's Canadian whiskey ban hits Americans TODAY as trade war escalates - but president faces brutal warning from US experts The forgotten ...

Follow this section to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW? Smart Alerts: Get notified about major news as it happens. Follow this tag to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW?

These luxurious outdoor products don't go on sale often, so stock up now and get ready for summer weddings, road trips, or anything else that requires you to change out of sweats. More information Adding us as a Preferred Source in Google by using this link indicates that you would like to see more of our content in Google News results. You don't have to be outdoorsy to look outdoorsy. We may earn revenue from the products available on this page and participate in affiliate programs. Huckberry kicked off its Memorial Day Weekend Sale with up to 20 percent off a deep cross-section of its catalog, and the long weekend itself is the deadline.

Lead optimization in drug discovery requires efficiently navigating vast chemical space through iterative cycles to enhance molecular properties while preserving structural similarity to the original lead compound. Despite recent advances, traditional optimization methods struggle with sample efficiency-achieving good optimization performance with limited oracle evaluations. Large Language Models (LLMs) provide a promising approach through their in-context learning and instruction following capabilities, which align naturally with these iterative processes. However, existing LLM-based methods fail to leverage this strength, treating each optimization step independently. To address this, we present POLO (Preference-guided multi-turn Optimization for Lead Optimization), which enables LLMs to learn from complete optimization trajectories rather than isolated steps. At its core, POLO introduces Preference-Guided Policy Optimization (PGPO), a novel reinforcement learning algorithm that extracts learning signals at two complementary levels: trajectory-level optimization reinforces successful strategies, while turn-level preference learning provides dense comparative feedback by ranking intermediate molecules within each trajectory. Through this dual-level learning from intermediate evaluation, POLO achieves superior sample efficiency by fully exploiting each costly oracle call. Extensive experiments demonstrate that POLO achieves 84% average success rate on single-property tasks (2.3x better than baselines) and 50% on multi-property tasks using only 500 oracle evaluations, significantly advancing the state-of-the-art in sample-efficient molecular optimization.

Machine learning models are increasingly shared and outsourced, raising requirements of verifying training effort (Proof-of-Learning, PoL) to ensure claimed performance and establishing ownership (Proof-of-Ownership, PoO) for transactions. When models are trained by untrusted parties, PoL and PoO must be enforced together to enable protection, attribution, and compensation. However, existing studies typically address them separately, which not only weakens protection against forgery and privacy breaches but also leads to high verification overhead. We propose PoLO, a unified framework that simultaneously achieves PoL and PoO using chained watermarks. PoLO splits the training process into fine-grained training shards and embeds a dedicated watermark in each shard. Each watermark is generated using the hash of the preceding shard, certifying the training process of the preceding shard. The chained structure makes it computationally difficult to forge any individual part of the whole training process. The complete set of watermarks serves as the PoL, while the final watermark provides the PoO. PoLO offers more efficient and privacy-preserving verification compared to the vanilla PoL solutions that rely on gradient-based trajectory tracing and inadvertently expose training data during verification, while maintaining the same level of ownership assurance of watermark-based PoO schemes. Our evaluation shows that PoLO achieves 99% watermark detection accuracy for ownership verification, while preserving data privacy and cutting verification costs to just 1.5-10% of traditional methods. Forging PoLO demands 1.1-4x more resources than honest proof generation, with the original proof retaining over 90% detection accuracy even after attacks.

Establishing an automatic evaluation metric that closely aligns with human judgments is essential for effectively developing image captioning models. Recent data-driven metrics have demonstrated a stronger correlation with human judgments than classic metrics such as CIDEr; however they lack sufficient capabilities to handle hallucinations and generalize across diverse images and texts partially because they compute scalar similarities merely using embeddings learned from tasks unrelated to image captioning evaluation. In this study, we propose Polos, a supervised automatic evaluation metric for image captioning models. Polos computes scores from multimodal inputs, using a parallel feature extraction mechanism that leverages embeddings trained through large-scale contrastive learning. To train Polos, we introduce Multimodal Metric Learning from Human Feedback (M$^2$LHF), a framework for developing metrics based on human feedback. We constructed the Polaris dataset, which comprises 131K human judgments from 550 evaluators, which is approximately ten times larger than standard datasets. Our approach achieved state-of-the-art performance on Composite, Flickr8K-Expert, Flickr8K-CF, PASCAL-50S, FOIL, and the Polaris dataset, thereby demonstrating its effectiveness and robustness.

For Artificial Intelligence to have a greater impact in biology and medicine, it is crucial that recommendations are both accurate and transparent. In other domains, a neurosymbolic approach of multi-hop reasoning on knowledge graphs has been shown to produce transparent explanations. However, there is a lack of research applying it to complex biomedical datasets and problems. In this paper, the approach is explored for drug discovery to draw solid conclusions on its applicability. For the first time, we systematically apply it to multiple biomedical datasets and recommendation tasks with fair benchmark comparisons. The approach is found to outperform the best baselines by 21.7% on average whilst producing novel, biologically relevant explanations.

We propose a "plan online and learn offline" framework for the setting where an agent, with an internal model, needs to continually act and learn in the world. Our work builds on the synergistic relationship between local model-based control, global value function learning, and exploration. We study how local trajectory optimization can cope with approximation errors in the value function, and can stabilize and accelerate value function learning. Conversely, we also study how approximate value functions can help reduce the planning horizon and allow for better policies beyond local solutions. Finally, we also demonstrate how trajectory optimization can be used to perform temporally coordinated exploration in conjunction with estimating uncertainty in value function approximation. This exploration is critical for fast and stable learning of the value function. Combining these components enable solutions to complex control tasks, like humanoid locomotion and dexterous in-hand manipulation, in the equivalent of a few minutes of experience in the real world.

We present POLO --- a C++ library for large-scale parallel optimization research that emphasizes ease-of-use, flexibility and efficiency in algorithm design. It uses multiple inheritance and template programming to decompose algorithms into essential policies and facilitate code reuse. With its clear separation between algorithm and execution policies, it provides researchers with a simple and powerful platform for prototyping ideas, evaluating them on different parallel computing architectures and hardware platforms, and generating compact and efficient production code. A C-API is included for customization and data loading in high-level languages. POLO enables users to move seamlessly from serial to multi-threaded shared-memory and multi-node distributed-memory executors. We demonstrate how POLO allows users to implement state-of-the-art asynchronous parallel optimization algorithms in just a few lines of code and report experiment results from shared and distributed-memory computing architectures. We provide both POLO and POLO.jl, a wrapper around POLO written in the Julia language, at https://github.com/pologrp under the permissive MIT license.