Yiqing Yang

Yiqing Yang, Xinlong Zhao, Zhao Liu et al.

Watch-time prediction is a central regression task in short-video recommender systems, where labels are highly long-tailed and residual errors vary systematically across observed watch-time regions. In practice, a model may appear globally calibrated while still overestimating short views and underestimating long views, because opposite errors cancel out in aggregate. Existing methods mainly improve the first-stage watch-time predictor, but often leave such residual distributional bias insufficiently corrected. We propose DADF, a distribution-aware debiasing framework for watch-time regression. Instead of replacing a deployed predictor, DADF performs second-stage multiplicative residual correction on top of it. DADF combines three complementary designs: a dynamic distribution-aware transformation for stabilizing long-tailed correction targets, a debias-factor-aware module for modeling heterogeneous residual patterns using inference-time observable factors, especially video duration, and a multi-label-aware module that exploits auxiliary prediction signals from engagement heads. We evaluate DADF on public short-video benchmarks and a large-scale industrial ranking system. DADF consistently improves both pointwise accuracy and ranking quality across datasets and backbones. In the industrial setting, it achieves a 1.88 percentage-point WUAUC gain over the production baseline, reduces MAE by 12.57%, and yields a statistically significant 0.347% lift in average time spent per device in online A/B testing. These results demonstrate that DADF effectively mitigates local calibration bias and provides a practical plug-in solution for debiasing long-tailed continuous targets. The source code is available at https://github.com/liuzhao09/DADF.

Jiawei Ren, Yan Zhuang, Xiaokang Ye et al.

While LLM/VLM-powered AI agents have advanced rapidly in math, coding, and computer use, their applications in complex physical and social environments remain challenging. Building agents that can survive and thrive in the real world (for example, by autonomously earning income or running a business) requires massive-scale interaction, reasoning, training, and evaluation across diverse embodied scenarios. However, existing world simulators for such development fall short: they often rely on limited hand-crafted environments, simulate simplified game-like physics and social rules, and lack native support for LLM/VLM agents. We introduce SimWorld, a new simulator built on Unreal Engine 5, designed for developing and evaluating LLM/VLM agents in rich, real-world-like settings. SimWorld offers three core capabilities: (1) realistic, open-ended world simulation, including accurate physical and social dynamics and language-driven procedural environment generation; (2) a rich interface for LLM/VLM agents, with multimodal world inputs and open-vocabulary actions at varying levels of abstraction; and (3) diverse and extensible physical and social reasoning scenarios that are easily customizable by users. We demonstrate SimWorld by deploying frontier LLM agents (e.g., GPT-4o, Gemini-2.5-Flash, Claude-3.5, and DeepSeek-Prover-V2) on long-horizon multi-agent delivery tasks involving strategic cooperation and competition. The results reveal distinct reasoning patterns and limitations across models. We open-source SimWorld and hope it becomes a foundational platform for advancing real-world agent intelligence across disciplines: https://simworld.org.

Yiqing Yang, Kin-Man Lam

Key frame selection in video understanding presents significant challenges. Traditional top-K selection methods, which score frames independently, often fail to optimize the selection as a whole. This independent scoring frequently results in selecting frames that are temporally clustered and visually redundant. Additionally, training lightweight selectors using pseudo labels generated offline by Multimodal Large Language Models (MLLMs) prevents the supervisory signal from dynamically adapting to task objectives. To address these limitations, we propose an end-to-end trainable, task-adaptive framework for frame selection. A Chain-of-Thought approach guides a Small Language Model (SLM) to generate task-specific implicit query vectors, which are combined with multimodal features to enable dynamic frame scoring. We further define a continuous set-level objective function that incorporates relevance, coverage, and redundancy, enabling differentiable optimization via Gumbel-Softmax to select optimal frame combinations at the set level. Finally, student-teacher mutual learning is employed, where the student selector (SLM) and teacher reasoner (MLLM) are trained to align their frame importance distributions via KL divergence. Combined with cross-entropy loss, this enables end-to-end optimization, eliminating reliance on static pseudo labels. Experiments across various benchmarks, including Video-MME, LongVideoBench, MLVU, and NExT-QA, demonstrate that our method significantly outperforms existing approaches.

Zhao Liu, Yichen Zhu, Yiqing Yang et al.

Generative recommendation (GR) is an emerging paradigm that represents each item via a tokenizer as an n-digit semantic ID (SID) and predicts the next item by autoregressively generating its SID conditioned on the user's history. However, two structural properties of SIDs make ARMs ill-suited. First, intra-item consistency: the n digits jointly specify one item, yet the left-to-right causality trains each digit only under its prefix and blocks bidirectional cross-digit evidence, collapsing supervision to a single causal path. Second, inter-digit heterogeneity: digits differ in semantic granularity and predictability, while the uniform next-token objective assigns equal weight to all digits, overtraining easy digits and undertraining hard digits. To address these two issues, we propose DiffGRM, a diffusion-based GR model that replaces the autoregressive decoder with a masked discrete diffusion model (MDM), thereby enabling bidirectional context and any-order parallel generation of SID digits for recommendation. Specifically, we tailor DiffGRM in three aspects: (1) tokenization with Parallel Semantic Encoding (PSE) to decouple digits and balance per-digit information; (2) training with On-policy Coherent Noising (OCN) that prioritizes uncertain digits via coherent masking to concentrate supervision on high-value signals; and (3) inference with Confidence-guided Parallel Denoising (CPD) that fills higher-confidence digits first and generates diverse Top-K candidates. Experiments show consistent gains over strong generative and discriminative recommendation baselines on multiple datasets, improving NDCG@10 by 6.9%-15.5%. Code is available at https://github.com/liuzhao09/DiffGRM.

Yue Zhao, Zhongtian Qiu, Yiqing Yang et al.

The emergence of smartwatches poses new challenges to information security. Although there are mature touch-based authentication methods for smartphones, the effectiveness of using these methods on smartwatches is still unclear. We conducted a user study (n=16) to evaluate how authentication methods (PIN and Pattern), UIs (Square and Circular), and display sizes (38mm and 42mm) affect authentication accuracy, speed, and security. Circular UIs are tailored to smartwatches with fewer UI elements. Results show that 1) PIN is more accurate and secure than Pattern; 2) Pattern is much faster than PIN; 3) Square UIs are more secure but less accurate than Circular UIs; 4) display size does not affect accuracy or speed, but security; 5) Square PIN is the most secure method of all. The study also reveals a security concern that participants' favorite method is not the best in any of the measures. We finally discuss implications for future touch-based smartwatch authentication design.