Chun Ye

Yueming Yin, Haifeng Hu, Zhen Yang et al.

Computational discovery of ideal lead compounds is a critical process for modern drug discovery. It comprises multiple stages: hit screening, molecular property prediction, and molecule optimization. Current efforts are disparate, involving the establishment of models for each stage, followed by multi-stage multi-model integration. However, this is non-ideal, as clumsy integration of incompatible models increases research overheads, and may even reduce success rates in drug discovery. Facilitating compatibilities requires establishing inherent model consistencies across lead discovery stages. Towards that effect, we propose an open deep graph learning (DGL) based pipeline: generative adversarial feature subspace enhancement (GAFSE), which first unifies the modeling of these stages into one learning framework. GAFSE also offers standardized modular design and streamlined interfaces for future expansions and community support. GAFSE combines adversarial/generative learning, graph attention network, graph reconstruction network, and optimizes the classification/regression loss, adversarial/generative loss, and reconstruction loss simultaneously. Convergence analysis theoretically guarantees model generalization performance. Exhaustive benchmarking demonstrates that the GAFSE pipeline achieves excellent performance across almost all lead discovery stages, while also providing valuable model interpretability. Hence, we believe this tool will enhance the efficiency and productivity of drug discovery researchers.

Xuan He, Dongfu Jiang, Ping Nie et al. · utoronto

Recent advances in text-to-video generation have produced increasingly realistic and diverse content, yet evaluating such videos remains a fundamental challenge due to their multi-faceted nature encompassing visual quality, semantic alignment, and physical consistency. Existing evaluators and reward models are limited to single opaque scores, lack interpretability, or provide only coarse analysis, making them insufficient for capturing the comprehensive nature of video quality assessment. We present VideoScore2, a multi-dimensional, interpretable, and human-aligned framework that explicitly evaluates visual quality, text-to-video alignment, and physical/common-sense consistency while producing detailed chain-of-thought rationales. Our model is trained on a large-scale dataset VideoFeedback2 containing 27,168 human-annotated videos with both scores and reasoning traces across three dimensions, using a two-stage pipeline of supervised fine-tuning followed by reinforcement learning with Group Relative Policy Optimization (GRPO) to enhance analytical robustness. Extensive experiments demonstrate that VideoScore2 achieves superior performance with 44.35 (+5.94) accuracy on our in-domain benchmark VideoScore-Bench-v2 and 50.37 (+4.32) average performance across four out-of-domain benchmarks (VideoGenReward-Bench, VideoPhy2, etc), while providing interpretable assessments that bridge the gap between evaluation and controllable generation through effective reward modeling for Best-of-N sampling. Project Page: https://tiger-ai-lab.github.io/VideoScore2/

Bharathan Balaji, Jordan Bell-Masterson, Enes Bilgin et al.

Reinforcement Learning (RL) has achieved state-of-the-art results in domains such as robotics and games. We build on this previous work by applying RL algorithms to a selection of canonical online stochastic optimization problems with a range of practical applications: Bin Packing, Newsvendor, and Vehicle Routing. While there is a nascent literature that applies RL to these problems, there are no commonly accepted benchmarks which can be used to compare proposed approaches rigorously in terms of performance, scale, or generalizability. This paper aims to fill that gap. For each problem we apply both standard approaches as well as newer RL algorithms and analyze results. In each case, the performance of the trained RL policy is competitive with or superior to the corresponding baselines, while not requiring much in the way of domain knowledge. This highlights the potential of RL in real-world dynamic resource allocation problems.