arXiv subjects

Stephen Li

Publications and source records attributed to Stephen Li.

4 recordsLinked to original sources

arXiv2026

Difficulty-Aware Semantic-ID Optimization for Generative Recommendation

Semantic-ID-based generative recommendation casts retrieval and ranking as autoregressive generation over hierarchical item identifiers. A common recipe is SFT followed by GRPO, yet vanilla GRPO is poorly matched to this tree-structured task. Under the frozen SFT checkpoint, the exact target is absent from the first 16 candidates of the 50-beam constrained ranking for many prompts, and in harder cases none of these candidates enters the target SID branch. This prompt-level diagnostic motivates a training concern: when on-policy GRPO groups are similarly target-missing, item-level rewards may produce weak or degenerate reward variation even if some candidates follow part of the target path. We propose Difficulty-Aware Semantic-ID Optimization (DASO), a tree-aware post-training method that addresses this failure mode as an online rollout-allocation problem. Instead of using fixed difficulty buckets or uniformly injecting ground-truth completions, DASO profiles each current rollout group by prefix-match depth, locates the bottleneck SID levels where candidates leave the target path, and reallocates a bounded portion of the group to prefix-guided completions while retaining raw rollouts for contrast. A SID-prefix reward provides graded credit, while an auxiliary SFT anchor mitigates regression on examples already solved by the SFT checkpoint. On the public benchmarks, DASO improves over MiniOneRec-style GRPO on 11 of 12 metrics and achieves the best result on 9 of 12 metrics; it also improves most level-wise recall metrics on the internal recommendation task.

cs.AI↗

arXiv2026

Ice Deposition Fronts In Porous Bodies From Transient Heating Events In a Protoplanetary Disk

Using a 1D mass and heat transport model, we numerically integrate heat flow and gas transport in a porous body exposed to a transient heating event while embedded in a protoplanetary disk. When small icy grains are heated, volatiles sublimate, enriching the disk with volatile gases. When a porous body enters this heated, volatile-rich environment, volatile gases diffuse throughout the cool, porous body and deposit ice where the partial pressure of a volatile exceeds its vapor pressure. We simulate sublimation and deposition fronts of water, carbon dioxide, and carbon monoxide. Our simulations show that an ice deposition front forms and moves deeper into the porous body as the body warms. The amount of nebular gas deposited in an initially dry body is usually extremely low; however, in an initially icy body, an ice deposition front contains locally sublimated volatiles. In this case, the front can increase the ice volume fraction (by a factor of 2) in a thin layer below the surface. We find that the propagation speed, propagation strength, and final depth of an ice deposition front primarily depend on pore size. We propose that nebular heating events can alter the subsurface morphology and physical properties of porous icy objects embedded in a protoplanetary disk.

astro-ph.EP↗

arXiv2024

Angular Momentum Drain: Despinning Embedded Planetesimals

Young and forming planetesimals experience impacts from particles present in a protostellar disk. Using crater scaling laws, we integrate ejecta distributions for oblique impacts. For impacts at 10 to 65 m/s, expected for impacts associated with a disk wind, we estimate the erosion rate and torque exerted on the planetesimal. We find that the mechanism for angular momentum drain proposed by Dobrovolskis and Burns (1984) for asteroids could operate in the low velocity regime of a disk wind. Though spin-down associated with impacts can facilitate planetesimal collapse, we find that the process is inefficient. We find that angular momentum drain via impacts operates in the gravitational focusing regime. The angular momentum transfer is most effective when the wind speed is high, the projectile density is high compared to the bulk planetesimal density, and the planetesimal is sufficiently weak that cratering is in the gravity regime. We find that angular momentum drain due to impacts within a pebble cloud may, in those specific conditions, facilitate collapse of single planetesimals.

astro-ph.EP↗

arXiv2018

VizML: A Machine Learning Approach to Visualization Recommendation

Data visualization should be accessible for all analysts with data, not just the few with technical expertise. Visualization recommender systems aim to lower the barrier to exploring basic visualizations by automatically generating results for analysts to search and select, rather than manually specify. Here, we demonstrate a novel machine learning-based approach to visualization recommendation that learns visualization design choices from a large corpus of datasets and associated visualizations. First, we identify five key design choices made by analysts while creating visualizations, such as selecting a visualization type and choosing to encode a column along the X- or Y-axis. We train models to predict these design choices using one million dataset-visualization pairs collected from a popular online visualization platform. Neural networks predict these design choices with high accuracy compared to baseline models. We report and interpret feature importances from one of these baseline models. To evaluate the generalizability and uncertainty of our approach, we benchmark with a crowdsourced test set, and show that the performance of our model is comparable to human performance when predicting consensus visualization type, and exceeds that of other ML-based systems.

cs.HC↗