The audio, etched onto a plastic disc in 1949, predates the era when researchers could even recognize whale calls. Breakthroughs, discoveries, and DIY tips sent six days a week. In 1970, a single record would change history.

In a game of scientific telephone, if you find the food, you find the whales--and sound the alarm. North Atlantic right whales sometimes gather at Jeffrey's Ledge, a 62-mile-long underwater ridge about 25 miles off the coast of Portsmouth, New Hampshire. Breakthroughs, discoveries, and DIY tips sent six days a week. It was a cold and windy week last January, when a group of Maine lobstermen couldn't haul in their traps from Jeffrey's Ledge. The reason why surprised everyone.

Estimating Heterogeneous Treatment Effects (HTE) in industrial applications such as AdTech and healthcare presents a dual challenge: extreme class imbalance and heavy-tailed outcome distributions. While the X-Learner framework effectively addresses imbalance through cross-imputation, we demonstrate that it is fundamentally vulnerable to "Outlier Smearing" when reliant on Mean Squared Error (MSE) minimization. In this failure mode, the bias from a few extreme observations ("whales") in the minority group is propagated to the entire majority group during the imputation step, corrupting the estimated treatment effect structure. To resolve this, we propose the Robust X-Learner (RX-Learner). This framework integrates a redescending γ-divergence objective -- structurally equivalent to the Welsch loss under Gaussian assumptions -- into the gradient boosting machinery. We further stabilize the non-convex optimization using a Proxy Hessian strategy grounded in Majorization-Minimization (MM) principles. Empirical evaluation on a semi-synthetic Criteo Uplift dataset demonstrates that the RX-Learner reduces the Precision in Estimation of Heterogeneous Effect (PEHE) metric by 98.6% compared to the standard X-Learner, effectively decoupling the stable "Core" population from the volatile "Periphery".

To survive, this isolated population of only 2,000 whales needs to be smart about mates. Breakthroughs, discoveries, and DIY tips sent six days a week. Among marine mammals, beluga whales () are particularly difficult to study in their icy habitat. To better understand and protect this endangered species, scientists must piece together bits of their lives from fragments, including one of the most important behaviors of any species--mating. One small population of beluga whales living in southwest Alaska's Bristol Bay appears to have a surprising strategy.

At least 18 new baby North Atlantic right whales have been spotted swimming with their mothers. Breakthroughs, discoveries, and DIY tips sent every weekday. While most of us were feasting on holiday foods over the past few weeks, the New England Aquarium was busy counting North Atlantic right whale () mom-calf pairs off the coast of Florida, South Carolina, and Georgia. "Congrats to all of these North Atlantic right whale moms!" reads a social media post by the aquarium highlighting six recent sightings, including Juno--an over 40-year-old mother with her ninth documented calf spotted on December 27. On January 8, the count jumped up to 18 calves, according to the Clearwater Marine Aquarium .

That time Oregon blew up a whale with dynamite. And why we should never do it again. Breakthroughs, discoveries, and DIY tips sent every weekday. When a whale dies in the ocean, an ecosystem grows around its sunken carcass. It's an epic burial at sea, something researchers call a whale fall .

We introduce a system for real-time sperm whale rendezvous at sea using an autonomous uncrewed aerial vehicle. Our system employs model-based reinforcement learning that combines in situ sensor data with an empirical whale dive model to guide navigation decisions. Key challenges include (i) real-time acoustic tracking in the presence of multiple whales, (ii) distributed communication and decision-making for robot deployments, and (iii) on-board signal processing and long-range detection from fish-trackers. We evaluate our system by conducting rendezvous with sperm whales at sea in Dominica, performing hardware experiments on land, and running simulations using whale trajectories interpolated from marine biologists' surface observations.

For years, the discourse around poker AI has been dominated by the concept of solvers and the pursuit of unexploitable, machine-perfect play. This paper challenges that orthodoxy. It presents Patrick, an AI built on the contrary philosophy: that the path to victory lies not in being unexploitable, but in being maximally exploitative. Patrick's architecture is a purpose-built engine for understanding and attacking the flawed, psychological, and often irrational nature of human opponents. Through detailed analysis of its design, its novel prediction-anchored learning method, and its profitable performance in a 64,267-hand trial, this paper makes the case that the solved myth is a distraction from the real, far more interesting challenge: creating AI that can master the art of human imperfection.

Perch 2.0 is a supervised bioacoustics foundation model pretrained on 14,597 species, including birds, mammals, amphibians, and insects, and has state-of-the-art performance on multiple benchmarks. Given that Perch 2.0 includes almost no marine mammal audio or classes in the training data, we evaluate Perch 2.0 performance on marine mammal and underwater audio tasks through few-shot transfer learning. We perform linear probing with the embeddings generated from this foundation model and compare performance to other pretrained bioacoustics models. In particular, we compare Perch 2.0 with previous multispecies whale, Perch 1.0, SurfPerch, AVES-bio, BirdAVES, and Birdnet V2.3 models, which have open-source tools for transfer-learning and agile modeling. We show that the embeddings from the Perch 2.0 model have consistently high performance for few-shot transfer learning, generally outperforming alternative embedding models on the majority of tasks, and thus is recommended when developing new linear classifiers for marine mammal classification with few labeled examples.

Sperm whales communicate in short sequences of clicks known as codas. We present WhAM (Whale Acoustics Model), the first transformer-based model capable of generating synthetic sperm whale codas from any audio prompt. WhAM is built by finetuning VampNet, a masked acoustic token model pretrained on musical audio, using 10k coda recordings collected over the past two decades. Through iterative masked token prediction, WhAM generates high-fidelity synthetic codas that preserve key acoustic features of the source recordings. We evaluate WhAM's synthetic codas using Fréchet Audio Distance and through perceptual studies with expert marine biologists. On downstream classification tasks including rhythm, social unit, and vowel classification, WhAM's learned representations achieve strong performance, despite being trained for generation rather than classification. Our code is available at https://github.com/Project-CETI/wham