A Multimodal Foundation Model to Enhance Generalizability and Data Efficiency for Pan-cancer Prognosis Prediction

Multimodal data provides heterogeneous information for a holistic understanding of the tumor microenvironment. However, existing AI models often struggle to harness the rich information within multimodal data and extract poorly generalizable representations. Here we present MICE (Multimodal data Integration via Collaborative Experts), a multimodal foundation model that effectively integrates pathology images, clinical reports, and genomics data for precise pan-cancer prognosis prediction. Instead of conventional multi-expert modules, MICE employs multiple functionally diverse experts to comprehensively capture both cross-cancer and cancer-specific insights. Leveraging data from 11,799 patients across 30 cancer types, we enhanced MICE's generalizability by coupling contrastive and supervised learning. MICE outperformed both unimodal and state-of-the-art multi-expert-based multimodal models, demonstrating substantial improvements in C-index ranging from 3.8% to 11.2% on internal cohorts and 5.8% to 8.8% on independent cohorts, respectively. Moreover, it exhibited remarkable data efficiency across diverse clinical scenarios. With its enhanced generalizability and data efficiency, MICE establishes an effective and scalable foundation for pan-cancer prognosis prediction, holding strong potential to personalize tailored therapies and improve treatment outcomes.

Learning by Imagining: Debiased Feature Augmentation for Compositional Zero-Shot Learning

Compositional Zero-Shot Learning (CZSL) aims to recognize unseen attribute-object compositions by learning prior knowledge of seen primitives, \textit{i.e.}, attributes and objects. Learning generalizable compositional representations in CZSL remains challenging due to the entangled nature of attributes and objects as well as the prevalence of long-tailed distributions in real-world data. Inspired by neuroscientific findings that imagination and perception share similar neural processes, we propose a novel approach called Debiased Feature Augmentation (DeFA) to address these challenges. The proposed DeFA integrates a disentangle-and-reconstruct framework for feature augmentation with a debiasing strategy. DeFA explicitly leverages the prior knowledge of seen attributes and objects by synthesizing high-fidelity composition features to support compositional generalization. Extensive experiments on three widely used datasets demonstrate that DeFA achieves state-of-the-art performance in both \textit{closed-world} and \textit{open-world} settings.

Image Tokenizer Needs Post-Training

Recent image generative models typically capture the image distribution in a pre-constructed latent space, relying on a frozen image tokenizer. However, there exists a significant discrepancy between the reconstruction and generation distribution, where current tokenizers only prioritize the reconstruction task that happens before generative training without considering the generation errors during sampling. In this paper, we comprehensively analyze the reason for this discrepancy in a discrete latent space, and, from which, we propose a novel tokenizer training scheme including both main-training and post-training, focusing on improving latent space construction and decoding respectively. During the main training, a latent perturbation strategy is proposed to simulate sampling noises, \ie, the unexpected tokens generated in generative inference. Specifically, we propose a plug-and-play tokenizer training scheme, which significantly enhances the robustness of tokenizer, thus boosting the generation quality and convergence speed, and a novel tokenizer evaluation metric, \ie, pFID, which successfully correlates the tokenizer performance to generation quality. During post-training, we further optimize the tokenizer decoder regarding a well-trained generative model to mitigate the distribution difference between generated and reconstructed tokens. With a $\sim$400M generator, a discrete tokenizer trained with our proposed main training achieves a notable 1.60 gFID and further obtains 1.36 gFID with the additional post-training. Further experiments are conducted to broadly validate the effectiveness of our post-training strategy on off-the-shelf discrete and continuous tokenizers, coupled with autoregressive and diffusion-based generators.

Merge-of-Thought Distillation

Efficient reasoning distillation for long chain-of-thought (CoT) models is increasingly constrained by the assumption of a single oracle teacher, despite practical availability of multiple candidate teachers and growing CoT corpora. We revisit teacher selection and observe that different students have different "best teachers," and even for the same student the best teacher can vary across datasets. Therefore, to unify multiple teachers' reasoning abilities into student with overcoming conflicts among various teachers' supervision, we propose Merge-of-Thought Distillation (MoT), a lightweight framework that alternates between teacher-specific supervised fine-tuning branches and weight-space merging of the resulting student variants. On competition math benchmarks, using only about 200 high-quality CoT samples, applying MoT to a Qwen3-14B student surpasses strong models including DEEPSEEK-R1, QWEN3-30B-A3B, QWEN3-32B, and OPENAI-O1, demonstrating substantial gains. Besides, MoT consistently outperforms the best single-teacher distillation and the naive multi-teacher union, raises the performance ceiling while mitigating overfitting, and shows robustness to distribution-shifted and peer-level teachers. Moreover, MoT reduces catastrophic forgetting, improves general reasoning beyond mathematics and even cultivates a better teacher, indicating that consensus-filtered reasoning features transfer broadly. These results position MoT as a simple, scalable route to efficiently distilling long CoT capabilities from diverse teachers into compact students.

Multimodal Contrastive Pretraining of CBCT and IOS for Enhanced Tooth Segmentation

Digital dentistry represents a transformative shift in modern dental practice. The foundational step in this transformation is the accurate digital representation of the patient's dentition, which is obtained from segmented Cone-Beam Computed Tomography (CBCT) and Intraoral Scans (IOS). Despite the growing interest in digital dental technologies, existing segmentation methodologies frequently lack rigorous validation and demonstrate limited performance and clinical applicability. To the best of our knowledge, this is the first work to introduce a multimodal pretraining framework for tooth segmentation. We present ToothMCL, a Tooth Multimodal Contrastive Learning for pretraining that integrates volumetric (CBCT) and surface-based (IOS) modalities. By capturing modality-invariant representations through multimodal contrastive learning, our approach effectively models fine-grained anatomical features, enabling precise multi-class segmentation and accurate identification of F\'ed\'eration Dentaire Internationale (FDI) tooth numbering. Along with the framework, we curated CBCT-IOS3.8K, the largest paired CBCT and IOS dataset to date, comprising 3,867 patients. We then evaluated ToothMCL on a comprehensive collection of independent datasets, representing the largest and most diverse evaluation to date. Our method achieves state-of-the-art performance in both internal and external testing, with an increase of 12\% for CBCT segmentation and 8\% for IOS segmentation in the Dice Similarity Coefficient (DSC). Furthermore, ToothMCL consistently surpasses existing approaches in tooth groups and demonstrates robust generalizability across varying imaging conditions and clinical scenarios.

Hybrid Matrix Factorization Based Graph Contrastive Learning for Recommendation System

In recent years, methods that combine contrastive learning with graph neural networks have emerged to address the challenges of recommendation systems, demonstrating powerful performance and playing a significant role in this domain. Contrastive learning primarily tackles the issue of data sparsity by employing data augmentation strategies, effectively alleviating this problem and showing promising results. Although existing research has achieved favorable outcomes, most current graph contrastive learning methods are based on two types of data augmentation strategies: the first involves perturbing the graph structure, such as by randomly adding or removing edges; and the second applies clustering techniques. We believe that the interactive information obtained through these two strategies does not fully capture the user-item interactions. In this paper, we propose a novel method called HMFGCL (Hybrid Matrix Factorization Based Graph Contrastive Learning), which integrates two distinct matrix factorization techniques-low-rank matrix factorization (MF) and singular value decomposition (SVD)-to complementarily acquire global collaborative information, thereby constructing enhanced views. Experimental results on multiple public datasets demonstrate that our model outperforms existing baselines, particularly on small-scale datasets.

TalkToAgent: A Human-centric Explanation of Reinforcement Learning Agents with Large Language Models

Explainable Reinforcement Learning (XRL) has emerged as a promising approach in improving the transparency of Reinforcement Learning (RL) agents. However, there remains a gap between complex RL policies and domain experts, due to the limited comprehensibility of XRL results and isolated coverage of current XRL approaches that leave users uncertain about which tools to employ. To address these challenges, we introduce TalkToAgent, a multi-agent Large Language Models (LLM) framework that delivers interactive, natural language explanations for RL policies. The architecture with five specialized LLM agents (Coordinator, Explainer, Coder, Evaluator, and Debugger) enables TalkToAgent to automatically map user queries to relevant XRL tools and clarify an agent's actions in terms of either key state variables, expected outcomes, or counterfactual explanations. Moreover, our approach extends previous counterfactual explanations by deriving alternative scenarios from qualitative behavioral descriptions, or even new rule-based policies. We validated TalkToAgent on quadruple-tank process control problem, a well-known nonlinear control benchmark. Results demonstrated that TalkToAgent successfully mapped user queries into XRL tasks with high accuracy, and coder-debugger interactions minimized failures in counterfactual generation. Furthermore, qualitative evaluation confirmed that TalkToAgent effectively interpreted agent's actions and contextualized their meaning within the problem domain.

Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training

Reinforcement learning with verifiable rewards (RLVR) has emerged to be a predominant paradigm for mathematical reasoning tasks, offering stable improvements in reasoning ability. However, Outcome Reward Models (ORMs) in RLVR are too coarse-grained to distinguish flawed reasoning within correct answers or valid reasoning within incorrect answers. This lack of granularity introduces noisy and misleading gradients significantly and hinders further progress in reasoning process quality. While Process Reward Models (PRMs) offer fine-grained guidance for intermediate steps, they frequently suffer from inaccuracies and are susceptible to reward hacking. To resolve this dilemma, we introduce PRocess cOnsistency Filter (PROF), an effective data process curation method that harmonizes noisy, fine-grained process rewards with accurate, coarse-grained outcome rewards. Rather than naively blending PRM and ORM in the objective function (arXiv:archive/2506.18896), PROF leverages their complementary strengths through consistency-driven sample selection. Our approach retains correct responses with higher averaged process values and incorrect responses with lower averaged process values, while maintaining positive/negative training sample balance. Extensive experiments demonstrate that our method not only consistently improves the final accuracy over $4\%$ compared to the blending approaches, but also strengthens the quality of intermediate reasoning steps. Codes and training recipes are available at https://github.com/Chenluye99/PROF.

Towards a Real-World Aligned Benchmark for Unlearning in Recommender Systems

Modern recommender systems heavily leverage user interaction data to deliver personalized experiences. However, relying on personal data presents challenges in adhering to privacy regulations, such as the GDPR's "right to be forgotten". Machine unlearning (MU) aims to address these challenges by enabling the efficient removal of specific training data from models post-training, without compromising model utility or leaving residual information. However, current benchmarks for unlearning in recommender systems -- most notably CURE4Rec -- fail to reflect real-world operational demands. They focus narrowly on collaborative filtering, overlook tasks like session-based and next-basket recommendation, simulate unrealistically large unlearning requests, and ignore critical efficiency constraints. In this paper, we propose a set of design desiderata and research questions to guide the development of a more realistic benchmark for unlearning in recommender systems, with the goal of gathering feedback from the research community. Our benchmark proposal spans multiple recommendation tasks, includes domain-specific unlearning scenarios, and several unlearning algorithms -- including ones adapted from a recent NeurIPS unlearning competition. Furthermore, we argue for an unlearning setup that reflects the sequential, time-sensitive nature of real-world deletion requests. We also present a preliminary experiment in a next-basket recommendation setting based on our proposed desiderata and find that unlearning also works for sequential recommendation models, exposed to many small unlearning requests. In this case, we observe that a modification of a custom-designed unlearning algorithm for recommender systems outperforms general unlearning algorithms significantly, and that unlearning can be executed with a latency of only several seconds.

Tinker: Diffusion's Gift to 3D--Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization

We introduce Tinker, a versatile framework for high-fidelity 3D editing that operates in both one-shot and few-shot regimes without any per-scene finetuning. Unlike prior techniques that demand extensive per-scene optimization to ensure multi-view consistency or to produce dozens of consistent edited input views, Tinker delivers robust, multi-view consistent edits from as few as one or two images. This capability stems from repurposing pretrained diffusion models, which unlocks their latent 3D awareness. To drive research in this space, we curate the first large-scale multi-view editing dataset and data pipeline, spanning diverse scenes and styles. Building on this dataset, we develop our framework capable of generating multi-view consistent edited views without per-scene training, which consists of two novel components: (1) Referring multi-view editor: Enables precise, reference-driven edits that remain coherent across all viewpoints. (2) Any-view-to-video synthesizer: Leverages spatial-temporal priors from video diffusion to perform high-quality scene completion and novel-view generation even from sparse inputs. Through extensive experiments, Tinker significantly reduces the barrier to generalizable 3D content creation, achieving state-of-the-art performance on editing, novel-view synthesis, and rendering enhancement tasks. We believe that Tinker represents a key step towards truly scalable, zero-shot 3D editing. Project webpage: https://aim-uofa.github.io/Tinker