Min Li

Tianyi Xiong, Yi Ge, Ming Li et al.

Large multimodal models (LMMs) are increasingly adopted as judges in multimodal evaluation systems due to their strong instruction following and consistency with human preferences. However, their ability to follow diverse, fine-grained evaluation criteria remains underexplored. We develop Multi-Crit, a benchmark for evaluating multimodal judges on their capacity to follow pluralistic criteria and produce reliable criterion-level judgments. Covering both open-ended generation and verifiable reasoning tasks, Multi-Crit is built through a rigorous data curation pipeline that gathers challenging response pairs with multi-criterion human annotations. It further introduces three novel metrics for systematically assessing pluralistic adherence, criterion-switching flexibility, and the ability to recognize criterion-level preference conflicts. Comprehensive analysis of 25 LMMs reveals that 1) proprietary models still struggle to maintain consistent adherence to pluralistic criteria--especially in open-ended evaluation; 2) open-source models lag further behind in flexibly following diverse criteria; and 3) critic fine-tuning with holistic judgment signals enhances visual grounding but fails to generalize to pluralistic criterion-level judgment. Additional analyses on reasoning fine-tuning, test-time scaling, and boundary consistency between open-source and proprietary models further probe the limits of current multimodal judges. As a pioneering study, Multi-Crit lays the foundation for building reliable and steerable multimodal AI evaluation.

Boyong Wu, Chao Yan, Chen Hu et al.

This paper presents Step-Audio 2, an end-to-end multi-modal large language model designed for industry-strength audio understanding and speech conversation. By integrating a latent audio encoder and reasoning-centric reinforcement learning (RL), Step-Audio 2 achieves promising performance in automatic speech recognition (ASR) and audio understanding. To facilitate genuine end-to-end speech conversation, Step-Audio 2 incorporates the generation of discrete audio tokens into language modeling, significantly enhancing its responsiveness to paralinguistic information such as speaking styles and emotions. To effectively leverage the rich textual and acoustic knowledge in real-world data, Step-Audio 2 integrates retrieval-augmented generation (RAG) and is able to call external tools such as web search to mitigate hallucination and audio search to switch timbres. Trained on millions of hours of speech and audio data, Step-Audio 2 delivers intelligence and expressiveness across diverse conversational scenarios. Evaluation results demonstrate that Step-Audio 2 achieves state-of-the-art performance on various audio understanding and conversational benchmarks compared to other open-source and commercial solutions. Please visit https://github.com/stepfun-ai/Step-Audio2 for more information.

Jiabao Ji, Min Li, Priyanshu Kumar et al.

Large language models (LLMs) with integrated search tools show strong promise in open-domain question answering (QA), yet they often struggle to produce complete answer set to complex questions such as Which actor from the film Heat won at least one Academy Award?, which requires (1) distinguishing between multiple films sharing the same title and (2) reasoning across a large set of actors to gather and integrate evidence. Existing QA benchmarks rarely evaluate both challenges jointly. To address this, we introduce DeepAmbigQAGen, an automatic data generation pipeline that constructs QA tasks grounded in text corpora and linked knowledge graph, generating natural and verifiable questions that systematically embed name ambiguity and multi-step reasoning. Based on this, we build DeepAmbigQA, a dataset of 3,600 questions requiring multi-hop reasoning and half of them explicit name ambiguity resolving. Experiments reveal that, even state-of-the-art GPT-5 show incomplete answers, achieving only 0.13 exact match on ambiguous questions and 0.21 on non-ambiguous questions. These findings highlight the need for more robust QA systems aimed at information gathering and answer completeness.

Chenghua Gao, Min Li, Jianshuo Liu et al.

Video Moment Retrieval (VMR) aims to retrieve relevant moments of an untrimmed video corresponding to the query. While cross-modal interaction approaches have shown progress in filtering out query-irrelevant information in videos, they assume the precise alignment between the query semantics and the corresponding video moments, potentially overlooking the misunderstanding of the natural language semantics. To address this challenge, we propose a novel model called \textit{QD-VMR}, a query debiasing model with enhanced contextual understanding. Firstly, we leverage a Global Partial Aligner module via video clip and query features alignment and video-query contrastive learning to enhance the cross-modal understanding capabilities of the model. Subsequently, we employ a Query Debiasing Module to obtain debiased query features efficiently, and a Visual Enhancement module to refine the video features related to the query. Finally, we adopt the DETR structure to predict the possible target video moments. Through extensive evaluations of three benchmark datasets, QD-VMR achieves state-of-the-art performance, proving its potential to improve the accuracy of VMR. Further analytical experiments demonstrate the effectiveness of our proposed module. Our code will be released to facilitate future research.

Zihan Su, Xuerui Qiu, Hongbin Xu et al.

The explosive growth of generative video models has amplified the demand for reliable copyright preservation of AI-generated content. Despite its popularity in image synthesis, invisible generative watermarking remains largely underexplored in video generation. To address this gap, we propose Safe-Sora, the first framework to embed graphical watermarks directly into the video generation process. Motivated by the observation that watermarking performance is closely tied to the visual similarity between the watermark and cover content, we introduce a hierarchical coarse-to-fine adaptive matching mechanism. Specifically, the watermark image is divided into patches, each assigned to the most visually similar video frame, and further localized to the optimal spatial region for seamless embedding. To enable spatiotemporal fusion of watermark patches across video frames, we develop a 3D wavelet transform-enhanced Mamba architecture with a novel spatiotemporal local scanning strategy, effectively modeling long-range dependencies during watermark embedding and retrieval. To the best of our knowledge, this is the first attempt to apply state space models to watermarking, opening new avenues for efficient and robust watermark protection. Extensive experiments demonstrate that Safe-Sora achieves state-of-the-art performance in terms of video quality, watermark fidelity, and robustness, which is largely attributed to our proposals. Code is publicly available at https://github.com/Sugewud/Safe-Sora

Yijun Liang, Ming Li, Chenrui Fan et al.

Color plays an important role in human perception and usually provides critical clues in visual reasoning. However, it is unclear whether and how vision-language models (VLMs) can perceive, understand, and leverage color as humans. This paper introduces ColorBench, an innovative benchmark meticulously crafted to assess the capabilities of VLMs in color understanding, including color perception, reasoning, and robustness. By curating a suite of diverse test scenarios, with grounding in real applications, ColorBench evaluates how these models perceive colors, infer meanings from color-based cues, and maintain consistent performance under varying color transformations. Through an extensive evaluation of 32 VLMs with varying language models and vision encoders, our paper reveals some undiscovered findings: (i) The scaling law (larger models are better) still holds on ColorBench, while the language model plays a more important role than the vision encoder. (ii) However, the performance gaps across models are relatively small, indicating that color understanding has been largely neglected by existing VLMs. (iii) CoT reasoning improves color understanding accuracies and robustness, though they are vision-centric tasks. (iv) Color clues are indeed leveraged by VLMs on ColorBench but they can also mislead models in some tasks. These findings highlight the critical limitations of current VLMs and underscore the need to enhance color comprehension. Our ColorBenchcan serve as a foundational tool for advancing the study of human-level color understanding of multimodal AI.

Mengkang Hu, Tianxing Chen, Yude Zou et al.

Recently, there has been growing interest in leveraging large language models (LLMs) to generate symbolic world models from textual descriptions. Although LLMs have been extensively explored in the context of world modeling, prior studies encountered several challenges, including evaluation randomness, dependence on indirect metrics, and a limited domain scope. To address these limitations, we introduce a novel benchmark, Text2World, based on planning domain definition language (PDDL), featuring hundreds of diverse domains and employing multi-criteria, execution-based metrics for a more robust evaluation. We benchmark current LLMs using Text2World and find that reasoning models trained with large-scale reinforcement learning outperform others. However, even the best-performing model still demonstrates limited capabilities in world modeling. Building on these insights, we examine several promising strategies to enhance the world modeling capabilities of LLMs, including test-time scaling, agent training, and more. We hope that Text2World can serve as a crucial resource, laying the groundwork for future research in leveraging LLMs as world models. The project page is available at https://text-to-world.github.io/.

Ming Li, Jike Zhong, Tianle Chen et al.

Recent studies on large language models (LLMs) and large multimodal models (LMMs) have demonstrated promising skills in various domains including science and mathematics. However, their capability in more challenging and real-world related scenarios like engineering has not been systematically studied. To bridge this gap, we propose EEE-Bench, a multimodal benchmark aimed at assessing LMMs' capabilities in solving practical engineering tasks, using electrical and electronics engineering (EEE) as the testbed. Our benchmark consists of 2860 carefully curated problems spanning 10 essential subdomains such as analog circuits, control systems, etc. Compared to benchmarks in other domains, engineering problems are intrinsically 1) more visually complex and versatile and 2) less deterministic in solutions. Successful solutions to these problems often demand more-than-usual rigorous integration of visual and textual information as models need to understand intricate images like abstract circuits and system diagrams while taking professional instructions, making them excellent candidates for LMM evaluations. Alongside EEE-Bench, we provide extensive quantitative evaluations and fine-grained analysis of 17 widely-used open and closed-sourced LLMs and LMMs. Our results demonstrate notable deficiencies of current foundation models in EEE, with an average performance ranging from 19.48% to 46.78%. Finally, we reveal and explore a critical shortcoming in LMMs which we term laziness: the tendency to take shortcuts by relying on the text while overlooking the visual context when reasoning for technical image problems. In summary, we believe EEE-Bench not only reveals some noteworthy limitations of LMMs but also provides a valuable resource for advancing research on their application in practical engineering tasks, driving future improvements in their capability to handle complex, real-world scenarios.

Fufangchen Zhao, Ming Li, Linrui Xu et al.

Video-based multimodal large language models (VMLLMs) have demonstrated remarkable potential in cross-modal video understanding. However, their abilities in fine-grained face comprehension remain largely underexplored. Given its pivotal role in human-centric intelligence, developing VMLLMs for facial understanding holds a fundamental problem. To address this gap, we propose FaVChat, the first VMLLM specifically designed for fine-grained facial video understanding. To facilitate its training, we construct a large-scale facial video dataset comprising over 60k videos, with the majority annotated with 83 fine-grained facial attributes. These attributes are incorporated to enrich GPT-4o-generated captions, yielding 60k high-quality video-summary pairs and an additional 170k fine-grained question-answering (QA) pairs. To effectively capture rich facial clues, we propose a hybrid model architecture composed of a general visual encoder, a dedicated facial encoder, and a mixture-of-experts-enhanced adapter for adaptive fusion of multi-source visual features. To mitigate information loss during feature transformation, we extract multi-granularity representations from the facial encoder and integrate them into the subsequent LLM. This design enhances the model's ability to comprehend and respond to questions involving diverse levels of visual details. We employ a progressive training paradigm, transitioning from video summarization to a high-quality subset of video QA, gradually increasing task complexity to enhance the model's fine-grained visual perception. We conduct extensive zero-shot evaluation on a couple of public benchmarks, demonstrating that FaVChat consistently surpasses existing VMLLMs across multiple tasks.

Ming Li

Large Language Models demonstrate strong capabilities in single-turn instruction following but suffer from Lost-in-Conversation (LiC), a degradation in performance as information is revealed progressively in multi-turn settings. Motivated by the current progress on Reinforcement Learning with Verifiable Rewards (RLVR), we propose Curriculum Reinforcement Learning with Verifiable Accuracy and Abstention Rewards (RLAAR), a framework that encourages models not only to generate correct answers, but also to judge the solvability of questions in the multi-turn conversation setting. Our approach employs a competence-gated curriculum that incrementally increases dialogue difficulty (in terms of instruction shards), stabilizing training while promoting reliability. Using multi-turn, on-policy rollouts and a mixed-reward system, RLAAR teaches models to balance problem-solving with informed abstention, reducing premature answering behaviors that cause LiC. Evaluated on LiC benchmarks, RLAAR significantly mitigates LiC performance decay (62.6% to 75.1%) and improves calibrated abstention rates (33.5% to 73.4%). Together, these results provide a practical recipe for building multi-turn reliable and trustworthy LLMs.