Qixiang Yin

Zeyu Chen, Guanghao Zhou, Qixiang Yin et al.

In this work, we present Valley3, an omni multimodal large language model (MLLM) developed for diverse global e-commerce tasks, with unified understanding and reasoning capabilities across text, images, video, and audio. A key feature of Valley3 is its native multilingual audio capability for e-commerce, developed by extending vision-language models to better support crucial audio-visual tasks, particularly in short-video scenarios. To achieve this, we carefully design a four-stage omni e-commerce continued pre-training pipeline, through which Valley3 progressively acquires audio understanding, cross-modal instruction-following, e-commerce domain knowledge, and long-context reasoning capabilities, ultimately evolving into an omni model for diverse e-commerce scenarios. Then, we further improve Valley3 through post-training to encourage long-chain reasoning with controllable reasoning modes, enabling one non-thinking mode and three distinct levels of thinking, thereby balancing inference efficiency in simple scenarios with deep reasoning for complex applications. Moreover, we equip Valley3 with agentic search capabilities to proactively invoke search tools and acquire task-relevant information for e-commerce deep research tasks. To comprehensively assess the capabilities of Valley3, we construct an omni e-commerce benchmark spanning 6 tasks. Experimental results show that Valley3 consistently outperforms strong baselines on our in-house and open-source e-commerce benchmarks, while remaining competitive on general-domain benchmarks.

Huanjin Yao, Qixiang Yin, Min Yang et al.

We aim to develop a multimodal research agent capable of explicit reasoning and planning, multi-tool invocation, and cross-modal information synthesis, enabling it to conduct deep research tasks. However, we observe three main challenges in developing such agents: (1) scarcity of search-intensive multimodal QA data, (2) lack of effective search trajectories, and (3) prohibitive cost of training with online search APIs. To tackle them, we first propose Hyper-Search, a hypergraph-based QA generation method that models and connects visual and textual nodes within and across modalities, enabling to generate search-intensive multimodal QA pairs that require invoking various search tools to solve. Second, we introduce DR-TTS, which first decomposes search-involved tasks into several categories according to search tool types, and respectively optimize specialized search tool experts for each tool. It then recomposes tool experts to jointly explore search trajectories via tree search, producing trajectories that successfully solve complex tasks using various search tools. Third, we build an offline search engine supporting multiple search tools, enabling agentic reinforcement learning without using costly online search APIs. With the three designs, we develop MM-DeepResearch, a powerful multimodal deep research agent, and extensive results shows its superiority across benchmarks. Code is available at https://github.com/HJYao00/MM-DeepResearch

Huanjin Yao, Qixiang Yin, Jingyi Zhang et al.

In this work, we aim to incentivize the reasoning ability of Multimodal Large Language Models (MLLMs) via reinforcement learning (RL) and develop an effective approach that mitigates the sparse reward and advantage vanishing issues during RL. To this end, we propose Share-GRPO, a novel RL approach that tackle these issues by exploring and sharing diverse reasoning trajectories over expanded question space. Specifically, Share-GRPO first expands the question space for a given question via data transformation techniques, and then encourages MLLM to effectively explore diverse reasoning trajectories over the expanded question space and shares the discovered reasoning trajectories across the expanded questions during RL. In addition, Share-GRPO also shares reward information during advantage computation, which estimates solution advantages hierarchically across and within question variants, allowing more accurate estimation of relative advantages and improving the stability of policy training. Extensive evaluations over six widely-used reasoning benchmarks showcase the superior performance of our method. Code will be available at https://github.com/HJYao00/R1-ShareVL.

Qixiang Yin, Huanjin Yao, Jianghao Chen et al.

Although Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities across diverse tasks, they encounter challenges in terms of reasoning efficiency, large model size and overthinking. However, existing lightweight MLLMs lack the capability to balance high efficiency and performance at a small scale. To this end, we propose Tiny-R1V, a novel lightweight 3B model that achieves faster inference and higher accuracy via a two-stage optimization, while unifying multimodal reasoning across multiple tasks with fewer inference tokens. In the first stage, Tiny-R1V introduces Length-Informed Relative Policy Optimization (LIPO), a new reinforcement learning method, to train each reasoning model, including mathematical reasoning, chart reasoning, and OCR capability. The LIPO dynamically adjusts the advantages of responses within groups by prioritizing concise yet high-quality responses to encourage the generation of shorter and more accurate responses. In the second stage, we propose Adaptive Model Merging (AMM), a training-free model merging method that merges multiple specialist models into a unified architecture. Specifically, AMM adaptively adjusts the weights of task vectors via a novel gradient projection regularization loss function, thus mitigating redundant conflicts between them. Extensive evaluations on ten widely-used reasoning benchmarks covering mathematics, structured data (charts, tables, documents), OCR, and general capabilities showcase the superior performance of Tiny-R1V, enabling lightweight models to excel in diverse multimodal reasoning tasks. Code will be available at \href{https://github.com/buptyqx/Tiny-R1V}{https://github.com/buptyqx/Tiny-R1V}

Jianghao Chen, Wei Sun, Qixiang Yin et al.

Large Language Models (LLMs) have demonstrated remarkable progress in long-context understanding, yet they face significant challenges in high-quality long-form generation. Existing studies primarily suffer from two limitations: (1) A heavy reliance on scarce, high-quality long-form response data for supervised fine-tuning (SFT) or for pairwise preference reward in reinforcement learning (RL). (2) Focus on coarse-grained quality optimization dimensions, such as relevance, coherence, and helpfulness, overlooking the fine-grained specifics inherent to diverse long-form generation scenarios. To address this issue, we propose a framework using Adaptive Constraint-Enhanced reward for long-form generation Reinforcement Learning (ACE-RL). ACE-RL first automatically deconstructs each instruction into a set of fine-grained, adaptive constraint criteria by identifying its underlying intents and demands. Subsequently, we design a reward mechanism that quantifies the quality of long-form responses based on their satisfaction over corresponding constraints, converting subjective quality evaluation into constraint verification. Finally, we utilize reinforcement learning to guide models toward superior long-form generation capabilities. Experimental results demonstrate that our ACE-RL framework significantly outperforms existing SFT and RL baselines by 20.70% and 7.32% on WritingBench, and our top-performing model even surpasses proprietary systems like GPT-4o by 7.10%, providing a more effective training paradigm for LLMs to generate high-quality content across diverse long-form generation scenarios.

Jiaye Feng, Qixiang Yin, Yuankun Liu et al.

Scene Graph Generation (SGG) structures visual scenes as graphs of objects and their relations. While Multimodal Large Language Models (MLLMs) have advanced end-to-end SGG, current methods are hindered by both a lack of task-specific structured reasoning and the challenges of sparse, long-tailed relation distributions, resulting in incomplete scene graphs characterized by low recall and biased predictions. To address these issues, we introduce SGG-R$^{\rm 3}$, a structured reasoning framework that integrates task-specific chain-of-thought (CoT)-guided supervised fine-tuning (SFT) and reinforcement learning (RL) with group sequence policy optimization (GSPO), designed to engage in three sequential stages to achieve end-to-end unbiased scene graph generation. During the SFT phase, we propose a relation augmentation strategy by leveraging an MLLM and refined via embedding similarity filtering to alleviate relation sparsity. Subsequently, a stage-aligned reward scheme optimizes the procedural reasoning during RL. Specifically, we propose a novel dual-granularity reward which integrates fine-grained and coarse-grained relation rewards, simultaneously mitigating the long-tail issue via frequency-based adaptive weighting of predicates and improving relation coverage through semantic clustering. Experiments on two benchmarks show that SGG-R$^{\rm 3}$ achieves superior performance compared to existing methods, demonstrating the effectiveness and generalization of the framework.

Weize Li, Yunhao Du, Qixiang Yin et al.

Referring Multi-Object Tracking (RMOT) aims to localize target trajectories in videos specified by natural language expressions. Despite recent progress, the intrinsic relationship between the two subtasks of tracking and referring in RMOT has not been fully studied. In this paper, we present a systematic analysis of their interdependence, revealing that current two-stage Referring-by-Tracking (RBT) frameworks remain fundamentally limited by insufficient modeling of subtask interactions and inflexible reliance on semantic alignment modules like CLIP. To this end, we propose JustHook, a novel two-stage RBT framework where a Hook module is firstly designed to redefine the linkage between subtasks. The Hook is built centered on grid sampling at the feature-level and is used for context-aware target feature extraction. Moreover, we propose a Parallel Combined Decoder (PCD) that learns in a unified joint feature space rather than relying on pre-defined cross-modal embeddings. Our design not only enhances the interpretability and modularity but also significantly improves the generalization. Extensive experiments on Refer-KITTI, Refer-KITTI-V2, and Refer-Dance demonstrate that JustHook achieves state-of-the-art performance, improving the HOTA by +6.9\% on Refer-KITTI-V2 with superior efficiency. Code will be available soon.