Generative recommendation (GR) has become a powerful paradigm in recommendation systems that implicitly links modality and semantics to item representation, in contrast to previous methods that relied on non-semantic item identifiers in autoregressive models. However, previous research has predominantly treated modalities in isolation, typically assuming item content is unimodal (usually text). We argue that this is a significant limitation given the rich, multimodal nature of real-world data and the potential sensitivity of GR models to modality choices and usage. Our work aims to explore the critical problem of Multimodal Generative Recommendation (MGR), highlighting the importance of modality choices in GR nframeworks. We reveal that GR models are particularly sensitive to different modalities and examine the challenges in achieving effective GR when multiple modalities are available. By evaluating design strategies for effectively leveraging multiple modalities, we identify key challenges and introduce MGR-LF++, an enhanced late fusion framework that employs contrastive modality alignment and special tokens to denote different modalities, achieving a performance improvement of over 20% compared to single-modality alternatives.

Existing 2D-to-3D human pose estimation (HPE) methods struggle with the occlusion issue by enriching information like temporal and visual cues in the lifting stage. In this paper, we argue that these methods ignore the limitation of the sparse skeleton 2D input representation, which fundamentally restricts the 2D-to-3D lifting and worsens the occlusion issue. T o address these, we propose a novel two-stage generative densification method, named Hierarchical Pose AutoRegressive Transformer (HiP ART), to generate hierarchical 2D dense poses from the original sparse 2D pose. Specifically, we first develop a multi-scale skeleton tokenization module to quantize the highly dense 2D pose into hierarchical tokens and propose a Skeleton-aware Alignment to strengthen token connections. W e then develop a Hierarchical AutoRegressive Modeling scheme for hierarchical 2D pose generation. With generated hierarchical poses as inputs for 2D-to-3D lifting, the proposed method shows strong robustness in occluded scenarios and achieves state-of-the-art performance on the single-frame-based 3D HPE. Moreover, it outperforms numerous multi-frame methods while reducing parameter and computational complexity and can also complement them to further enhance performance and robustness.

This paper introduces JiraiBench, the first bilingual benchmark for evaluating large language models' effectiveness in detecting self-destructive content across Chinese and Japanese social media communities. Focusing on the transnational "Jirai" (landmine) online subculture that encompasses multiple forms of self-destructive behaviors including drug overdose, eating disorders, and self-harm, we present a comprehensive evaluation framework incorporating both linguistic and cultural dimensions. Our dataset comprises 10,419 Chinese posts and 5,000 Japanese posts with multidimensional annotation along three behavioral categories, achieving substantial inter-annotator agreement. Experimental evaluations across four state-of-the-art models reveal significant performance variations based on instructional language, with Japanese prompts unexpectedly outperforming Chinese prompts when processing Chinese content. This emergent cross-cultural transfer suggests that cultural proximity can sometimes outweigh linguistic similarity in detection tasks. Cross-lingual transfer experiments with fine-tuned models further demonstrate the potential for knowledge transfer between these language systems without explicit target language training. These findings highlight the need for culturally-informed approaches to multilingual content moderation and provide empirical evidence for the importance of cultural context in developing more effective detection systems for vulnerable online communities.

SAVE 100: As of March 29, the iRobot Roomba Q011 is on sale for 149.99 at Amazon. This is a 40% saving on the list price. We'll always be shouting about robot vacuums here at Mashable, especially now, when you can find great deals in Amazon's Big Spring Sale. If you've been shopping around for something for a while, the name Roomba won't be new to you. And as of March 29, we've found you an incredible deal at Amazon on the iRobot Roomba Q011, now down to just 149.99. This model has a three-level cleaning system that delivers customizable suction for carpets and hard floors.

SAVE 320: As of March 29, the Shark Robot Vacuum and Mop is on sale for 379.99 at Amazon. This deal saves you 46% on the list price. Anything that reduces your chore list is a plus in our book. So, with Amazon's Big Spring Sale currently underway, we've been tracking all the best vacuum sales for you to enjoy, and this latest on the Shark Robot Vacuum and Mop deserves your attention. As of March 29, you can take home this impressive model for 320 less than usual, now 379.99.

One notable trend at CES earlier this year was the quirky robot vacuum. It seemed every third booth had a new model that could climb stairs, pick up socks, serve drinks and, oh yeah, suck up dirt from your floor. Now that Amazon's Spring Sale is here, we're seeing lots of discounts -- not on those wacky prototypes, but on robo vacs that make keeping your floors clean easier and automated. Engadget has two guides to these handy home gadgets, based on years of testing and reviewing products from brands like iRobot, Shark, Dyson, Eufy and more. Here are the best deals on robot vacuums and cordless stick vacs we could find for the Big Spring Sale. This "essential" Roomba is relatively no-frills, but it has the added benefit of being a mopping robot in addition to a vacuum.

This year's Amazon Spring Sale is in full swing, and as promised, a ton of household, fashion and outdoor gear has dropped to record-low prices. Tech isn't a huge focus for this sale, but there are a decent number of devices on sale right now for some of the best prices we've seen all year. The selection may not be as good as that of Amazon Prime Day in July, but it still provides a good opportunity to save on things like headphones, robot vacuums, air purifiers and more. We've collected the best Amazon Spring Sale deals on tech gear here so you don't have to go searching for them. The Spring Sale runs through March 31, so check back here for all of the latest deals as they drop.

A Russian drone attack has killed at least four people and wounded 21 in the eastern Ukrainian city of Dnipro, damaging high-rise buildings and triggering fires in a hotel and homes, the regional governor said, as Moscow claims to have made gains on the ground elsewhere. Late Friday, Russia sent "more than two dozen drones" to Dnipro, the governor of the surrounding Dnipropetrovsk region, Sergiy Lysak, wrote on his official Telegram account on Saturday. "The massive attack caused large-scale destruction and fires. A hotel and restaurant complex, 11 private houses, garages, and a service station were on fire," he said, adding that high-rises and cars were also damaged. Pictures and videos posted online showed flames and large plumes of smoke wafting skyward.

Don't let fraudsters create a false sense of urgency. If you receive a communication claiming to be from a financial institution, call that institution directly using the official number from its website.

The reviews train rolls on at Engadget. We've had another busy couple of weeks, and more new devices are arriving for testing every day. For now, catch up on our in-depth analysis of the new base-model iPad, Nothing Phone 3a duo, some incredible sounding headphones and more. It's not a particularly exciting update, and it lacks Apple Intelligence entirely, but Apple's latest entry-level tablet still meets most iPad users where they live with little drama. Apple has been busy updating several devices over the past few weeks, including the "regular" iPad.