Fan Xia

ByteDance Seed, Jiaze Chen, Tiantian Fan et al. · bytedance

We introduce Seed1.5-Thinking, capable of reasoning through thinking before responding, resulting in improved performance on a wide range of benchmarks. Seed1.5-Thinking achieves 86.7 on AIME 2024, 55.0 on Codeforces and 77.3 on GPQA, demonstrating excellent reasoning abilities in STEM and coding. Beyond reasoning tasks, the method demonstrates notable generalization across diverse domains. For instance, it surpasses DeepSeek R1 by 8% in win rate on non-reasoning tasks, indicating its broader applicability. Compared to other state-of-the-art reasoning models, Seed1.5-Thinking is a Mixture-of-Experts (MoE) model with a relatively small size, featuring 20B activated and 200B total parameters. As part of our effort to assess generalized reasoning, we develop two internal benchmarks, BeyondAIME and Codeforces, both of which will be publicly released to support future research. Model trial link: https://www.volcengine.com/experience/ark.

Dichucheng Li, Yulun Wu, Qinyu Li et al.

The Guzheng is a kind of traditional Chinese instruments with diverse playing techniques. Instrument playing techniques (IPT) play an important role in musical performance. However, most of the existing works for IPT detection show low efficiency for variable-length audio and provide no assurance in the generalization as they rely on a single sound bank for training and testing. In this study, we propose an end-to-end Guzheng playing technique detection system using Fully Convolutional Networks that can be applied to variable-length audio. Because each Guzheng playing technique is applied to a note, a dedicated onset detector is trained to divide an audio into several notes and its predictions are fused with frame-wise IPT predictions. During fusion, we add the IPT predictions frame by frame inside each note and get the IPT with the highest probability within each note as the final output of that note. We create a new dataset named GZ_IsoTech from multiple sound banks and real-world recordings for Guzheng performance analysis. Our approach achieves 87.97% in frame-level accuracy and 80.76% in note-level F1-score, outperforming existing works by a large margin, which indicates the effectiveness of our proposed method in IPT detection.

Jean Feng, Adarsh Subbaswamy, Alexej Gossmann et al.

After a machine learning (ML)-based system is deployed, monitoring its performance is important to ensure the safety and effectiveness of the algorithm over time. When an ML algorithm interacts with its environment, the algorithm can affect the data-generating mechanism and be a major source of bias when evaluating its standalone performance, an issue known as performativity. Although prior work has shown how to validate models in the presence of performativity using causal inference techniques, there has been little work on how to monitor models in the presence of performativity. Unlike the setting of model validation, there is much less agreement on which performance metrics to monitor. Different monitoring criteria impact how interpretable the resulting test statistic is, what assumptions are needed for identifiability, and the speed of detection. When this choice is further coupled with the decision to use observational versus interventional data, ML deployment teams are faced with a multitude of monitoring options. The aim of this work is to highlight the relatively under-appreciated complexity of designing a monitoring strategy and how causal reasoning can provide a systematic framework for choosing between these options. As a motivating example, we consider an ML-based risk prediction algorithm for predicting unplanned readmissions. Bringing together tools from causal inference and statistical process control, we consider six monitoring procedures (three candidate monitoring criteria and two data sources) and investigate their operating characteristics in simulation studies. Results from this case study emphasize the seemingly simple (and obvious) fact that not all monitoring systems are created equal, which has real-world impacts on the design and documentation of ML monitoring systems.

Dichucheng Li, Yinghao Ma, Weixing Wei et al.

Instrument playing techniques (IPTs) constitute a pivotal component of musical expression. However, the development of automatic IPT detection methods suffers from limited labeled data and inherent class imbalance issues. In this paper, we propose to apply a self-supervised learning model pre-trained on large-scale unlabeled music data and finetune it on IPT detection tasks. This approach addresses data scarcity and class imbalance challenges. Recognizing the significance of pitch in capturing the nuances of IPTs and the importance of onset in locating IPT events, we investigate multi-task finetuning with pitch and onset detection as auxiliary tasks. Additionally, we apply a post-processing approach for event-level prediction, where an IPT activation initiates an event only if the onset output confirms an onset in that frame. Our method outperforms prior approaches in both frame-level and event-level metrics across multiple IPT benchmark datasets. Further experiments demonstrate the efficacy of multi-task finetuning on each IPT class.

Xinli Yue, Jianhui Sun, Liangchao Yao et al.

The increasing popularity of short video platforms such as YouTube Shorts, TikTok, and Kwai has led to a surge in User-Generated Content (UGC), which presents significant challenges for the generalization performance of Video Quality Assessment (VQA) tasks. These challenges not only affect performance on test sets but also impact the ability to generalize across different datasets. While prior research has primarily focused on enhancing feature extractors, sampling methods, and network branches, it has largely overlooked the generalization capabilities of VQA tasks. In this work, we reevaluate the VQA task from a generalization standpoint. We begin by analyzing the weight loss landscape of VQA models, identifying a strong correlation between this landscape and the generalization gaps. We then investigate various techniques to regularize the weight loss landscape. Our results reveal that adversarial weight perturbations can effectively smooth this landscape, significantly improving the generalization performance, with cross-dataset generalization and fine-tuning performance enhanced by up to 1.8% and 3%, respectively. Through extensive experiments across various VQA methods and datasets, we validate the effectiveness of our approach. Furthermore, by leveraging our insights, we achieve state-of-the-art performance in Image Quality Assessment (IQA) tasks. Our code is available at https://github.com/XinliYue/VQA-Generalization.

Jinye Ran, Guanghua Zhang, Ximei Zhang et al.

Domain adaptation (DA) has been widely applied in the diabetic retinopathy (DR) grading of unannotated ultra-wide-field (UWF) fundus images, which can transfer annotated knowledge from labeled color fundus images. However, suffering from huge domain gaps and complex real-world scenarios, the DR grading performance of most mainstream DA is far from that of clinical diagnosis. To tackle this, we propose a novel source-free active domain adaptation (SFADA) in this paper. Specifically, we focus on DR grading problem itself and propose to generate features of color fundus images with continuously evolving relationships of DRs, actively select a few valuable UWF fundus images for labeling with local representation matching, and adapt model on UWF fundus images with DR lesion prototypes. Notably, the SFADA also takes data privacy and computational efficiency into consideration. Extensive experimental results demonstrate that our proposed SFADA achieves state-of-the-art DR grading performance, increasing accuracy by 20.9% and quadratic weighted kappa by 18.63% compared with baseline and reaching 85.36% and 92.38% respectively. These investigations show that the potential of our approach for real clinical practice is promising.

Dichucheng Li, Mingjin Che, Wenwu Meng et al.

Instrument playing technique (IPT) is a key element of musical presentation. However, most of the existing works for IPT detection only concern monophonic music signals, yet little has been done to detect IPTs in polyphonic instrumental solo pieces with overlapping IPTs or mixed IPTs. In this paper, we formulate it as a frame-level multi-label classification problem and apply it to Guzheng, a Chinese plucked string instrument. We create a new dataset, Guzheng\_Tech99, containing Guzheng recordings and onset, offset, pitch, IPT annotations of each note. Because different IPTs vary a lot in their lengths, we propose a new method to solve this problem using multi-scale network and self-attention. The multi-scale network extracts features from different scales, and the self-attention mechanism applied to the feature maps at the coarsest scale further enhances the long-range feature extraction. Our approach outperforms existing works by a large margin, indicating its effectiveness in IPT detection.

Seed, Baisheng Li, Banggu Wu et al.

We introduce Virtual Width Networks (VWN), a framework that delivers the benefits of wider representations without incurring the quadratic cost of increasing the hidden size. VWN decouples representational width from backbone width, expanding the embedding space while keeping backbone compute nearly constant. In our large-scale experiment, an 8-times expansion accelerates optimization by over 2 times for next-token and 3 times for next-2-token prediction. The advantage amplifies over training as both the loss gap grows and the convergence-speedup ratio increases, showing that VWN is not only token-efficient but also increasingly effective with scale. Moreover, we identify an approximately log-linear scaling relation between virtual width and loss reduction, offering an initial empirical basis and motivation for exploring virtual-width scaling as a new dimension of large-model efficiency.

Xinli Yue, JianHui Sun, Tao Shao et al.

Pairwise image quality assessment (IQA) in professional photography requires a model not only to identify the preferred image between two candidates, but also to provide convincing and image-grounded reasoning. In the NTIRE 2026 RAIM challenge, this requirement is further emphasized by jointly evaluating preference prediction and rationale generation. To address this task, we propose iDiff, an Interpretable Difference-aware framework for pairwise image quality assessment. Our method adopts a dual-branch design consisting of an Answer Model and a Thinking Model. The Answer Model performs robust preference prediction by explicitly decomposing each sample into left/right global and local views, followed by content-aware specialization for person and scene images and ensemble-based aggregation across backbones. The Thinking Model focuses on rationale generation and is progressively enhanced with expert-style templates, multi-source quality features, and answer-aware supervision conditioned on the Answer Model prediction. In this way, iDiff jointly models discriminative decision making and structured explanation, improving both robustness and interpretability. Extensive experiments demonstrate the effectiveness of the proposed framework on both accuracy and reasoning-quality metrics. Our method achieved first place in the NTIRE 2026 RAIM challenge, showing the effectiveness of integrating explicit difference modeling with structured multimodal reasoning for pairwise IQA.

Xinli Yue, Jianhui Sun, Han Kong et al.

In recent years, AI generative models have made remarkable progress across various domains, including text generation, image generation, and video generation. However, assessing the quality of text-to-video generation is still in its infancy, and existing evaluation frameworks fall short when compared to those for natural videos. Current video quality assessment (VQA) methods primarily focus on evaluating the overall quality of natural videos and fail to adequately account for the substantial quality discrepancies between frames in generated videos. To address this issue, we propose a novel loss function that combines mean absolute error with cross-entropy loss to mitigate inter-frame quality inconsistencies. Additionally, we introduce the innovative S2CNet technique to retain critical content, while leveraging adversarial training to enhance the model's generalization capabilities. Experimental results demonstrate that our method outperforms existing VQA techniques on the AIGC Video dataset, surpassing the previous state-of-the-art by 3.1% in terms of PLCC.

Jianpeng Cheng, Xian Wu, Jiangfan Zhang et al.

Recent research has demonstrated that Universal Multimodal Embedding (UME) benefits significantly from Chain-of-Thought (CoT) reasoning. In this paradigm, a generative model produces explicit reasoning traces for a multimodal query, with the final representation extracted from an <eos> embedding token attending to both the query and the reasoning. Despite its effectiveness, the computational overhead of generating explicit CoT traces is often prohibitive. In this work, we propose replacing explicit CoT with latent think tokens, which are interpreted as latent variables that can produce explicit CoT traces as observed variables. By optimizing think tokens using CoT generation loss and subsequent embedding tokens using contrastive loss, we produce high-performance, reasoning-aware representations at a constant inference cost. Our study investigates two key architectural designs: 1) how think and embeddings tokens should be extracted from the same LLM backbone. 2) how the tokens should be trained as two dependent tasks. We introduce TTE-Flash-2B, a reasoning-aware multimodal representation model that outperforms its explicit-CoT counterpart on the MMEB-v2 benchmark, while producing latent think tokens that are interpretable both textually and visually. Furthermore, zero-shot evaluation across 15 video datasets reveals scaling behavior as the number of think tokens increases, and motivating a pilot study of adaptive think budget allocation based on task requirements.

Huifeng Li, Bin Wang, Fan Xia et al.

Predicting the next place to visit is a key in human mobility behavior modeling, which plays a significant role in various fields, such as epidemic control, urban planning, traffic management, and travel recommendation. To achieve this, one typical solution is designing modules based on RNN to capture their preferences to various locations. Although these RNN-based methods can effectively learn individual's hidden personalized preferences to her visited places, the interactions among users can only be weakly learned through the representations of locations. Targeting this, we propose an end-to-end framework named personalized and group preference guided network (PG$^2$Net), considering the users' preferences to various places at both individual and collective levels. Specifically, PG$^2$Net concatenates Bi-LSTM and attention mechanism to capture each user's long-term mobility tendency. To learn population's group preferences, we utilize spatial and temporal information of the visitations to construct a spatio-temporal dependency module. We adopt a graph embedding method to map users' trajectory into a hidden space, capturing their sequential relation. In addition, we devise an auxiliary loss to learn the vectorial representation of her next location. Experiment results on two Foursquare check-in datasets and one mobile phone dataset indicate the advantages of our model compared to the state-of-the-art baselines. Source codes are available at https://github.com/urbanmobility/PG2Net.

Yuxuan Song, Zheng Zhang, Cheng Luo et al.

We present Seed Diffusion Preview, a large-scale language model based on discrete-state diffusion, offering remarkably fast inference speed. Thanks to non-sequential, parallel generation, discrete diffusion models provide a notable speedup to mitigate the inherent latency of token-by-token decoding, as demonstrated recently (e.g., Mercury Coder, Gemini Diffusion). Seed Diffusion Preview achieves an inference speed of 2,146 token/s over H20 GPUs while maintaining competitive performance across a sweep of standard code evaluation benchmarks, significantly faster than contemporary Mercury and Gemini Diffusion, establishing new state of the art on the speed-quality Pareto frontier for code models.

Matthew Neeley, Guantong Qi, Guanchu Wang et al.

Rare diseases are challenging to diagnose due to limited patient data and genetic diversity. Despite advances in variant prioritization, many cases remain undiagnosed. While large language models (LLMs) have performed well in medical exams, their effectiveness in diagnosing rare genetic diseases has not been assessed. To identify causal genes, we benchmarked various LLMs for gene prioritization. Using multi-agent and Human Phenotype Ontology (HPO) classification, we categorized patients based on phenotypes and solvability levels. As gene set size increased, LLM performance deteriorated, so we used a divide-and-conquer strategy to break the task into smaller subsets. At baseline, GPT-4 outperformed other LLMs, achieving near 30% accuracy in ranking causal genes correctly. The multi-agent and HPO approaches helped distinguish confidently solved cases from challenging ones, highlighting the importance of known gene-phenotype associations and phenotype specificity. We found that cases with specific phenotypes or clear associations were more accurately solved. However, we observed biases toward well-studied genes and input order sensitivity, which hindered gene prioritization. Our divide-and-conquer strategy improved accuracy by overcoming these biases. By utilizing HPO classification, novel multi-agent techniques, and our LLM strategy, we improved causal gene identification accuracy compared to our baseline evaluation. This approach streamlines rare disease diagnosis, facilitates reanalysis of unsolved cases, and accelerates gene discovery, supporting the development of targeted diagnostics and therapies.

Jean Feng, Harvineet Singh, Fan Xia et al.

Machine learning (ML) algorithms can often differ in performance across domains. Understanding $\textit{why}$ their performance differs is crucial for determining what types of interventions (e.g., algorithmic or operational) are most effective at closing the performance gaps. Existing methods focus on $\textit{aggregate decompositions}$ of the total performance gap into the impact of a shift in the distribution of features $p(X)$ versus the impact of a shift in the conditional distribution of the outcome $p(Y|X)$; however, such coarse explanations offer only a few options for how one can close the performance gap. $\textit{Detailed variable-level decompositions}$ that quantify the importance of each variable to each term in the aggregate decomposition can provide a much deeper understanding and suggest much more targeted interventions. However, existing methods assume knowledge of the full causal graph or make strong parametric assumptions. We introduce a nonparametric hierarchical framework that provides both aggregate and detailed decompositions for explaining why the performance of an ML algorithm differs across domains, without requiring causal knowledge. We derive debiased, computationally-efficient estimators, and statistical inference procedures for asymptotically valid confidence intervals.

Xinli Yue, JianHui Sun, Junda Lu et al.

With the rapid advancement of text-to-image (T2I) generation models, assessing the semantic alignment between generated images and text descriptions has become a significant research challenge. Current methods, including those based on Visual Question Answering (VQA), still struggle with fine-grained assessments and precise quantification of image-text alignment. This paper presents an improved evaluation method named Instruction-augmented Multimodal Alignment for Image-Text and Element Matching (iMatch), which evaluates image-text semantic alignment by fine-tuning multimodal large language models. We introduce four innovative augmentation strategies: First, the QAlign strategy creates a precise probabilistic mapping to convert discrete scores from multimodal large language models into continuous matching scores. Second, a validation set augmentation strategy uses pseudo-labels from model predictions to expand training data, boosting the model's generalization performance. Third, an element augmentation strategy integrates element category labels to refine the model's understanding of image-text matching. Fourth, an image augmentation strategy employs techniques like random lighting to increase the model's robustness. Additionally, we propose prompt type augmentation and score perturbation strategies to further enhance the accuracy of element assessments. Our experimental results show that the iMatch method significantly surpasses existing methods, confirming its effectiveness and practical value. Furthermore, our iMatch won first place in the CVPR NTIRE 2025 Text to Image Generation Model Quality Assessment - Track 1 Image-Text Alignment.

Bohong Wu, Mengzhao Chen, Xiang Luo et al.

Large Language Models (LLMs) are powerful but often too slow and costly for real-world use during inference. Looped transformers save on parameters by reusing the same weights for multiple computational steps, or "loops." However, this approach has a major flaw: the loops run one after another, causing inference latency and memory requirements to increase with each added loop. This makes them impractical for fast applications. To solve this problem, we introduce the Parallel Loop Transformer (PLT). PLT is a new architecture that delivers the performance benefits of a deep, looped model but with the low latency of a standard, non-looped model. PLT works using two key techniques. First, Cross-Loop Parallelism (CLP) breaks the sequential dependency by computing different loops for different tokens at the same time, all within a single pass. Second, to prevent memory costs from growing, we use an Efficient Representation Enhancement strategy. This method shares the memory (KV cache) from the first loop with all other loops. It then uses a Gated Sliding-Window Attention (G-SWA) to combine this shared global information with local information, maintaining high accuracy. Our experiments show that PLT achieves the high accuracy of a traditional looped model but with almost no extra latency or memory cost compared to a standard transformer.

Patrick Vossler, Fan Xia, Yifan Mai et al. · stanford

Automated evaluation of free-form outputs from large language models (LLMs) is challenging because many distinct answers can be equally valid. A common practice is to use LLMs themselves as judges, but the theoretical properties of this approach are not yet well understood. We show that a geometric framework that represents both judges and candidates as points on a probability simplex can provide helpful insight on what is or is not identifiable using LLM judges. Our theoretical analysis uncovers a "phase transition" in ranking identifiability: for binary scoring systems, true rankings are identifiable even with weak judges under mild assumptions, while rankings become non-identifiable for three or more scoring levels even with infinite data, absent additional prior knowledge. This non-identifiability highlights how uncertainty in rankings stems from not only aleatoric uncertainty (i.e., inherent stochasticity in the data) but also epistemic uncertainty regarding which assumptions hold, an aspect that has received limited attention until now. To integrate both types of uncertainty, we use Bayesian inference to encode assumptions as priors and conduct sensitivity analysis of ranking estimates and credible intervals. Empirical evaluations across multiple benchmarks demonstrate that Bayesian inference yields more accurate rankings and substantially improves coverage rates. These results underscore the importance of taking a more holistic approach to uncertainty quantification when using LLMs as judges.

Harvineet Singh, Fan Xia, Mi-Ok Kim et al.

In fairness audits, a standard objective is to detect whether a given algorithm performs substantially differently between subgroups. Properly powering the statistical analysis of such audits is crucial for obtaining informative fairness assessments, as it ensures a high probability of detecting unfairness when it exists. However, limited guidance is available on the amount of data necessary for a fairness audit, lacking directly applicable results concerning commonly used fairness metrics. Additionally, the consideration of unequal subgroup sample sizes is also missing. In this tutorial, we address these issues by providing guidance on how to determine the required subgroup sample sizes to maximize the statistical power of hypothesis tests for detecting unfairness. Our findings are applicable to audits of binary classification models and multiple fairness metrics derived as summaries of the confusion matrix. Furthermore, we discuss other aspects of audit study designs that can increase the reliability of audit results.

Zhaoran Zhao, Xinli Yue, Jianhui Sun et al.

Image Quality Assessment (IQA) has progressed from scalar quality prediction to more interpretable, human-aligned evaluation paradigms. In this work, we address the emerging challenge of detailed and explainable IQA by proposing iDETEX-a unified multimodal large language model (MLLM) capable of simultaneously performing three key tasks: quality grounding, perception, and description. To facilitate efficient and generalizable training across these heterogeneous subtasks, we design a suite of task-specific offline augmentation modules and a data mixing strategy. These are further complemented by online enhancement strategies to fully exploit multi-sourced supervision. We validate our approach on the large-scale ViDA-UGC benchmark, where iDETEX achieves state-of-the-art performance across all subtasks. Our model ranks first in the ICCV MIPI 2025 Detailed Image Quality Assessment Challenge, demonstrating its effectiveness and robustness in delivering accurate and interpretable quality assessments.

Harvineet Singh, Fan Xia, Alexej Gossmann et al.

Machine learning (ML) models frequently experience performance degradation when deployed in new contexts. Such degradation is rarely uniform: some subgroups may suffer large performance decay while others may not. Understanding where and how large differences in performance arise is critical for designing targeted corrective actions that mitigate decay for the most affected subgroups while minimizing any unintended effects. Current approaches do not provide such detailed insight, as they either (i) explain how average performance shifts arise or (ii) identify adversely affected subgroups without insight into how this occurred. To this end, we introduce a Subgroup-scanning Hierarchical Inference Framework for performance drifT (SHIFT). SHIFT first asks "Is there any subgroup with unacceptably large performance decay due to covariate/outcome shifts?" (Where?) and, if so, dives deeper to ask "Can we explain this using more detailed variable(subset)-specific shifts?" (How?). In real-world experiments, we find that SHIFT identifies interpretable subgroups affected by performance decay, and suggests targeted actions that effectively mitigate the decay.