Recent works in Natural Language Inference (NLI) and related tasks, such as automated fact-checking, employ atomic fact decomposition to enhance interpretability and robustness. For this, existing methods rely on resource-intensive generative large language models (LLMs) to perform decomposition. We propose JEDI, an encoder-only architecture that jointly performs extractive atomic fact decomposition and interpretable inference without requiring generative models during inference. To facilitate training, we produce a large corpus of synthetic rationales covering multiple NLI benchmarks. Experimental results demonstrate that JEDI achieves competitive accuracy in distribution and significantly improves robustness out of distribution and in adversarial settings over models based solely on extractive rationale supervision. Our findings show that interpretability and robust generalization in NLI can be realized using encoder-only architectures and synthetic rationales. Code and data available at https://jedi.nicpopovic.com

We introduce JEDI, a test-time adaptation method that enhances subject separation and compositional alignment in diffusion models without requiring retraining or external supervision. JEDI operates by minimizing semantic entanglement in attention maps using a novel Jensen-Shannon divergence based objective. To improve efficiency, we leverage adversarial optimization, reducing the number of updating steps required. JEDI is model-agnostic and applicable to architectures such as Stable Diffusion 1.5 and 3.5, consistently improving prompt alignment and disentanglement in complex scenes. Additionally, JEDI provides a lightweight, CLIP-free disentanglement score derived from internal attention distributions, offering a principled benchmark for compositional alignment under test-time conditions. Code and results are available at https://ericbill21.github.io/JEDI/.

There's a new Star Wars show coming out, and it'll arrive sooner than expected. The show was originally scheduled to debut on December 3, but Disney moved it up just a few days beforehand. New episodes will drop at the same time each Tuesday for the remainder of the season. For the uninitiated, this is a live-action show set during the same time period as The Mandalorian and Ahsoka, or around ten years after the events of Return of the Jedi. We don't know too much about the plot, other than it involves some suburban kids finding a spaceship and going on an adventure.

The Fr\'echet Video Distance (FVD) is a widely adopted metric for evaluating video generation distribution quality. However, its effectiveness relies on critical assumptions. Our analysis reveals three significant limitations: (1) the non-Gaussianity of the Inflated 3D Convnet (I3D) feature space; (2) the insensitivity of I3D features to temporal distortions; (3) the impractical sample sizes required for reliable estimation. These findings undermine FVD's reliability and show that FVD falls short as a standalone metric for video generation evaluation. After extensive analysis of a wide range of metrics and backbone architectures, we propose JEDi, the JEPA Embedding Distance, based on features derived from a Joint Embedding Predictive Architecture, measured using Maximum Mean Discrepancy with polynomial kernel. Our experiments on multiple open-source datasets show clear evidence that it is a superior alternative to the widely used FVD metric, requiring only 16% of the samples to reach its steady value, while increasing alignment with human evaluation by 34%, on average.

About 10 minutes into the latest preview build of Star Wars Outlaws, Ubisoft's forthcoming open-world adventure, lead character Kay Vess enters Mirogana: a densely populated, worn-down city on the desolate moon of Toshara. Around us is a mix of sandstone hovels and metallic sci-fi buildings, crammed with flickering computer panels, neon signs and holographic adverts. Exotic aliens lurk in quiet corners, R2 droids glide past twittering to themselves. Nearby is a cantina, its shady clientele visible through the smoky doorway, and just to the side is a dimly lit gambling parlour. As you explore, robotic voices read out imperial propaganda over public address systems and stormtroopers patrol the streets, checking IDs. At least as far as this lifelong Star Wars fan is concerned, these moments perfectly capture the aesthetics and atmosphere of the original trilogy.

Evolution Strategies (ES) are effective gradient-free optimization methods that can be competitive with gradient-based approaches for policy search. ES only rely on the total episodic scores of solutions in their population, from which they estimate fitness gradients for their update with no access to true gradient information. However this makes them sensitive to deceptive fitness landscapes, and they tend to only explore one way to solve a problem. Quality-Diversity methods such as MAP-Elites introduced additional information with behavior descriptors (BD) to return a population of diverse solutions, which helps exploration but leads to a large part of the evaluation budget not being focused on finding the best performing solution. Here we show that behavior information can also be leveraged to find the best policy by identifying promising search areas which can then be efficiently explored with ES. We introduce the framework of Quality with Just Enough Diversity (JEDi) which learns the relationship between behavior and fitness to focus evaluations on solutions that matter. When trying to reach higher fitness values, JEDi outperforms both QD and ES methods on hard exploration tasks like mazes and on complex control problems with large policies.

More than anything, Star Wars: Episode 1 - The Phantom Menace is a fascinating cultural object. It's been 25 years since I saw the film in theaters, and over a decade since I last rewatched it (in a vain attempt to help my Trekkie wife catch up to the prequels). I've had enough time to process the initial disappointment and embarrassment of introducing my wife to Jar Jar Binks. So when Disney announced it was bringing the prequel trilogy back to theaters, I was practically giddy about revisiting them to see how George Lucas's final films compared to the onslaught of Star Wars media we've experienced over the past decade. Was The Phantom Menace as bad as I'd remembered?

It's been a terrible year for game developers, but an amazing year for games. There were some missteps along the way -- if you'd asked me to predict this list a year ago, I would've mentioned both Redfall and Starfield -- but overall it's been a packed year unusually low on disappointment. We've never tried to name a single title as "the Game of the Year." Instead, it's become a tradition to get the whole team together to talk about our individual favorites. So here are those games, presented in alphabetical order to avoid hurting any of our writers' feelings. Feel free to sound off about what your favorites are in the comments; there are no wrong answers. I rarely have time to finish games these days, but I devoured Alan Wake 2 in just a few weeks. For me and my limited gaming time, that felt miraculous. I'll admit, I'm a mark for Remedy Entertainment. I've been following its work since the first Max Payne arrived on PCs in 2001, right as I was gearing up to head to college and building my first desktop PC. Yah, I was one of the cool kids on campus..) Max Payne blew me away with its fluid slow-motion gunplay mechanics and immersive narrative. As a lifelong console gamer until then, it was a big step forward from something like Tomb Raider.

If you love the deals that come with Amazon Prime Day but don't love Amazon, or don't pay for a Prime membership, you can enjoy similar discounts at Target. The retailer's competing sale, this year called Target Circle Week, runs from July 9 to 15. Amazon's Prime Day falls on July 11 and 12. Nothing beats a free afternoon roaming the aisles of Target, picking up random things as you go along, but some of these discounts are worth the virtual shopping spree. Note: You need to register for Target Circle to see and save the deals. It's free to sign up. For almost all of the discounts, you will need to clip the coupon on the page to see the deal price at checkout.

The unlikeliest project to emerge from Electronic Arts's decade-long oversight of the Star Wars video game franchise, Squadrons is a spiritual successor to the much-loved X-Wing series of space combat simulators. Squadrons offers a decent facsimile of X-Wing's granular space battles, from its carefully crafted missions to its hallmark power-shunting mechanic, which lets you divert your ship's power to different systems for a tactical advantage. What earns Squadrons a place on this list, however, is its VR functionality. Plugging a VR headset into this game transforms it from a glossy throwback into an essential experience, bringing Star Wars' space dogfighting to life like nothing else. If you want to know just how massive a Star Destroyer is when you see it up close with your own eyes, this is the game to play.