Generative Recommendation (GR) models treat a user's interaction history as a sequence to be autoregressively predicted. When both items and actions (e.g., watch time, purchase, comment) are modeled, the layout-the ordering and visibility of item/action tokens-critically determines what information the model can use and how it generalizes. We present a unified study of token layouts for GR grounded in first principles: (P1) maximize item/action signal in both input/output space, (P2) preserve the conditioning relationship "action given item" and (P3) no information leakage. While interleaved layout (where item and action occupy separate tokens) naturally satisfies these principles, it also bloats sequence length with larger training/inference cost. On the non-interleaved front, we design a novel and effective approach, Lagged Action Conditioning (LAC), which appears strange on the surface but aligns well with the design principles to yield strong accuracy. Comprehensive experiments on public datasets and large-scale production logs evaluate different layout options and empirically verifies the design principles. Our proposed non-interleaved method, LAC, achieves competitive or superior quality at substantially lower FLOPs than interleaving. Our findings offer actionable guidance for assembling GR systems that are both accurate and efficient.

Generative recommenders, typically transformer-based autoregressive models, predict the next item or action from a user's interaction history. Their effectiveness depends on how the model represents where an interaction event occurs in the sequence (discrete index) and when it occurred in wall-clock time. Prevailing approaches inject time via learned embeddings or relative attention biases. In this paper, we argue that RoPE-based approaches, if designed properly, can be a stronger alternative for jointly modeling temporal and sequential information in user behavior sequences. While vanilla RoPE in LLMs considers only token order, generative recommendation requires incorporating both event time and token index. To address this, we propose Time-and-Order RoPE (TO-RoPE), a family of rotary position embedding designs that treat index and time as angle sources shaping the query-key geometry directly. We present three instantiations: early fusion, split-by-dim, and split-by-head. Extensive experiments on both publicly available datasets and a proprietary industrial dataset show that TO-RoPE variants consistently improve accuracy over existing methods for encoding time and index. These results position rotary embeddings as a simple, principled, and deployment-friendly foundation for generative recommendation.

This paper introduces a method for simplifying textured surface triangle meshes in the wild while maintaining high visual quality. While previous methods achieve excellent results on manifold meshes by using the quadric error metric, they struggle to produce high-quality outputs for meshes in the wild, which typically contain non-manifold elements and multiple connected components. In this work, we propose a method for simplifying these wild textured triangle meshes. We formulate mesh simplification as a problem of decimating simplicial 2-complexes to handle multiple non-manifold mesh components collectively. Building on the success of quadric error simplification, we iteratively collapse 1-simplices (vertex pairs). Our approach employs a modified quadric error that converges to the original quadric error metric for watertight manifold meshes, while significantly improving the results on wild meshes. For textures, instead of following existing strategies to preserve UVs, we adopt a novel perspective which focuses on computing mesh correspondences throughout the decimation, independent of the UV layout. This combination yields a textured mesh simplification system that is capable of handling arbitrary triangle meshes, achieving to high-quality results on wild inputs without sacrificing the excellent performance on clean inputs. Our method guarantees to avoid common problems in textured mesh simplification, including the prevalent problem of texture bleeding. We extensively evaluate our method on multiple datasets, showing improvements over prior techniques through qualitative, quantitative, and user study evaluations.

While collaborative filtering delivers predictive accuracy and efficiency, and Large Language Models (LLMs) enable expressive and generalizable reasoning, modern recommendation systems must bring these strengths together. Growing user expectations, such as natural-language queries and transparent explanations, further highlight the need for a unified approach. However, doing so is nontrivial. Collaborative signals are often token-efficient but semantically opaque, while LLMs are semantically rich but struggle to model implicit user preferences when trained only on textual inputs. This paper introduces Item-ID + Oral-language Mixture-of-Experts Language Model (IDIOMoE), which treats item interaction histories as a native dialect within the language space, enabling collaborative signals to be understood in the same way as natural language. By splitting the Feed Forward Network of each block of a pretrained LLM into a separate text expert and an item expert with token-type gating, our method avoids destructive interference between text and catalog modalities. IDIOMoE demonstrates strong recommendation performance across both public and proprietary datasets, while preserving the text understanding of the pretrained model.

Diffusion Transformers (DiT) have emerged as powerful generative models for various tasks, including image, video, and speech synthesis. However, their inference process remains computationally expensive due to the repeated evaluation of resource-intensive attention and feed-forward modules. To address this, we introduce SmoothCache, a model-agnostic inference acceleration technique for DiT architectures. SmoothCache leverages the observed high similarity between layer outputs across adjacent diffusion timesteps. By analyzing layer-wise representation errors from a small calibration set, SmoothCache adaptively caches and reuses key features during inference. Our experiments demonstrate that SmoothCache achieves 8% to 71% speed up while maintaining or even improving generation quality across diverse modalities. We showcase its effectiveness on DiT-XL for image generation, Open-Sora for text-to-video, and Stable Audio Open for text-to-audio, highlighting its potential to enable real-time applications and broaden the accessibility of powerful DiT models.

We present GEOPARD, a transformer-based architecture for predicting articulation from a single static snapshot of a 3D shape. The key idea of our method is a pretraining strategy that allows our transformer to learn plausible candidate articulations for 3D shapes based on a geometric-driven search without manual articulation annotation. The search automatically discovers physically valid part motions that do not cause detachments or collisions with other shape parts. Our experiments indicate that this geometric pretraining strategy, along with carefully designed choices in our transformer architecture, yields state-of-the-art results in articulation inference in the PartNet-Mobility dataset.

We introduce Kinematic Kitbashing, an automatic framework that synthesizes functionality-aware articulated objects by reusing parts from existing models. Given a kinematic graph with a small collection of articulated parts, our optimizer jointly solves for the spatial placement of every part so that (i) attachments remain geometrically sound over the entire range of motion and (ii) the assembled object satisfies user-specified functional goals such as collision-free actuation, reachability, or trajectory following. At its core is a kinematics-aware attachment energy that aligns vector distance function features sampled across multiple articulation snapshots. We embed this attachment term within an annealed Riemannian Langevin dynamics sampler that treats functionality objectives as additional energies, enabling robust global exploration while accommodating non-differentiable functionality objectives and constraints. Our framework produces a wide spectrum of assembled articulated shapes, from trash-can wheels grafted onto car bodies to multi-segment lamps, gear-driven paddlers, and reconfigurable furniture, and delivers strong quantitative improvements over state-of-the-art baselines across geometric, kinematic, and functional metrics. By tightly coupling articulation-aware geometry matching with functionality-driven optimization, Kinematic Kitbashing bridges part-based shape modeling and functional assembly design, empowering rapid creation of interactive articulated assets.