arXiv subjects

Bin Wen

Publications and source records attributed to Bin Wen.

At least 37 records · Page 2Linked to original sources

arXiv2026

MindPower: Enabling Theory-of-Mind Reasoning in VLM-based Embodied Agents

Theory of Mind (ToM) refers to the ability to infer others' mental states, such as beliefs, desires, and intentions. Current vision-language embodied agents lack ToM-based decision-making, and existing benchmarks focus solely on human mental states while ignoring the agent's own perspective, hindering coherent decision and action generation. To address this, we propose MindPower, a Robot-Centric framework integrating Perception, Mental Reasoning, Decision Making and Action. Given multimodal inputs, MindPower first perceives the environment and human states, then performs ToM Reasoning to model both self and others, and finally generates decisions and actions guided by inferred mental states. Furthermore, we introduce Mind-Reward, a novel optimization objective that encourages VLMs to produce consistent ToM Reasoning and behavior. Our model outperforms GPT-4o by 12.77% in decision making and 12.49% in action generation.

cs.AI↗

arXiv2026

Breaking Data Efficiency Dilemma: A Federated and Augmented Learning Framework For Alzheimer's Disease Detection via Speech

Early diagnosis of Alzheimer's Disease (AD) is crucial for delaying its progression. While AI-based speech detection is non-invasive and cost-effective, it faces a critical data efficiency dilemma due to medical data scarcity and privacy barriers. Therefore, we propose FAL-AD, a novel framework that synergistically integrates federated learning with data augmentation to systematically optimize data efficiency. Our approach delivers three key breakthroughs: First, absolute efficiency improvement through voice conversion-based augmentation, which generates diverse pathological speech samples via cross-category voice-content recombination. Second, collaborative efficiency breakthrough via an adaptive federated learning paradigm, maximizing cross-institutional benefits under privacy constraints. Finally, representational efficiency optimization by an attentive cross-modal fusion model, which achieves fine-grained word-level alignment and acoustic-textual interaction. Evaluated on ADReSSo, FAL-AD achieves a state-of-the-art multi-modal accuracy of 91.52%, outperforming all centralized baselines and demonstrating a practical solution to the data efficiency dilemma. Our source code is publicly available at https://github.com/smileix/fal-ad.

cs.CL↗

arXiv2026

UniRef-Image-Edit: Towards Scalable and Consistent Multi-Reference Image Editing

We present UniRef-Image-Edit, a high-performance multi-modal generation system that unifies single-image editing and multi-image composition within a single framework. Existing diffusion-based editing methods often struggle to maintain consistency across multiple conditions due to limited interaction between reference inputs. To address this, we introduce Sequence-Extended Latent Fusion (SELF), a unified input representation that dynamically serializes multiple reference images into a coherent latent sequence. During a dedicated training stage, all reference images are jointly constrained to fit within a fixed-length sequence under a global pixel-budget constraint. Building upon SELF, we propose a two-stage training framework comprising supervised fine-tuning (SFT) and reinforcement learning (RL). In the SFT stage, we jointly train on single-image editing and multi-image composition tasks to establish a robust generative prior. We adopt a progressive sequence length training strategy, in which all input images are initially resized to a total pixel budget of $1024^2$, and are then gradually increased to $1536^2$ and $2048^2$ to improve visual fidelity and cross-reference consistency. This gradual relaxation of compression enables the model to incrementally capture finer visual details while maintaining stable alignment across references. For the RL stage, we introduce Multi-Source GRPO (MSGRPO), to our knowledge the first reinforcement learning framework tailored for multi-reference image generation. MSGRPO optimizes the model to reconcile conflicting visual constraints, significantly enhancing compositional consistency. We will open-source the code, models, training data, and reward data for community research purposes.

cs.CV↗

arXiv2026

Spatial Chain-of-Thought: Bridging Understanding and Generation Models for Spatial Reasoning Generation

While diffusion models have shown exceptional capabilities in aesthetic image synthesis, they often struggle with complex spatial understanding and reasoning. Existing approaches resort to Multimodal Large Language Models (MLLMs) to enhance this capability. However, they either incur high computational costs through joint training or suffer from spatial information loss when relying solely on textual prompts. To alleviate these limitations, we propose a Spatial Chain-of-Thought (SCoT) framework, a plug-and-play approach that effectively bridges the reasoning capabilities of MLLMs with the generative power of diffusion models. Specifically, we first enhance the diffusion model's layout awareness by training it on an interleaved text-coordinate instruction format. We then leverage state-of-the-art MLLMs as planners to generate comprehensive layout plans, transferring their spatial planning capabilities directly to the generation process. Extensive experiments demonstrate that our method achieves state-of-the-art performance on image generation benchmarks and significantly outperforms baselines on complex reasoning tasks, while also showing strong efficacy in image editing scenarios.

cs.CV↗

arXiv2026

OpenOneRec Technical Report

While the OneRec series has successfully unified the fragmented recommendation pipeline into an end-to-end generative framework, a significant gap remains between recommendation systems and general intelligence. Constrained by isolated data, they operate as domain specialists-proficient in pattern matching but lacking world knowledge, reasoning capabilities, and instruction following. This limitation is further compounded by the lack of a holistic benchmark to evaluate such integrated capabilities. To address this, our contributions are: 1) RecIF Bench & Open Data: We propose RecIF-Bench, a holistic benchmark covering 8 diverse tasks that thoroughly evaluate capabilities from fundamental prediction to complex reasoning. Concurrently, we release a massive training dataset comprising 96 million interactions from 160,000 users to facilitate reproducible research. 2) Framework & Scaling: To ensure full reproducibility, we open-source our comprehensive training pipeline, encompassing data processing, co-pretraining, and post-training. Leveraging this framework, we demonstrate that recommendation capabilities can scale predictably while mitigating catastrophic forgetting of general knowledge. 3) OneRec-Foundation: We release OneRec Foundation (1.7B and 8B), a family of models establishing new state-of-the-art (SOTA) results across all tasks in RecIF-Bench. Furthermore, when transferred to the Amazon benchmark, our models surpass the strongest baselines with an average 26.8% improvement in Recall@10 across 10 diverse datasets (Figure 1). This work marks a step towards building truly intelligent recommender systems. Nonetheless, realizing this vision presents significant technical and theoretical challenges, highlighting the need for broader research engagement in this promising direction.

cs.IR↗

arXiv2025

CookAnything: A Framework for Flexible and Consistent Multi-Step Recipe Image Generation

Cooking is a sequential and visually grounded activity, where each step such as chopping, mixing, or frying carries both procedural logic and visual semantics. While recent diffusion models have shown strong capabilities in text-to-image generation, they struggle to handle structured multi-step scenarios like recipe illustration. Additionally, current recipe illustration methods are unable to adjust to the natural variability in recipe length, generating a fixed number of images regardless of the actual instructions structure. To address these limitations, we present CookAnything, a flexible and consistent diffusion-based framework that generates coherent, semantically distinct image sequences from textual cooking instructions of arbitrary length. The framework introduces three key components: (1) Step-wise Regional Control (SRC), which aligns textual steps with corresponding image regions within a single denoising process; (2) Flexible RoPE, a step-aware positional encoding mechanism that enhances both temporal coherence and spatial diversity; and (3) Cross-Step Consistency Control (CSCC), which maintains fine-grained ingredient consistency across steps. Experimental results on recipe illustration benchmarks show that CookAnything performs better than existing methods in training-based and training-free settings. The proposed framework supports scalable, high-quality visual synthesis of complex multi-step instructions and holds significant potential for broad applications in instructional media, and procedural content creation.

cs.CV↗

arXiv2025

CAPability: A Comprehensive Visual Caption Benchmark for Evaluating Both Correctness and Thoroughness

Visual captioning benchmarks have become outdated with the emergence of modern multimodal large language models (MLLMs), as the brief ground-truth sentences and traditional metrics fail to assess detailed captions effectively. While recent benchmarks attempt to address this by focusing on keyword extraction or object-centric evaluation, they remain limited to vague-view or object-view analyses and incomplete visual element coverage. In this paper, we introduce CAPability, a comprehensive multi-view benchmark for evaluating visual captioning across 12 dimensions spanning six critical views. We curate nearly 11K human-annotated images and videos with visual element annotations to evaluate the generated captions. CAPability stably assesses both the correctness and thoroughness of captions with \textit{precision} and \textit{hit} metrics. By converting annotations to QA pairs, we further introduce a heuristic metric, \textit{know but cannot tell} ($K\bar{T}$), indicating a significant performance gap between QA and caption capabilities. Our work provides a holistic analysis of MLLMs' captioning abilities, as we identify their strengths and weaknesses across various dimensions, guiding future research to enhance specific aspects of their capabilities.

cs.CV↗

arXiv2025

LiveStar: Live Streaming Assistant for Real-World Online Video Understanding

Despite significant progress in Video Large Language Models (Video-LLMs) for offline video understanding, existing online Video-LLMs typically struggle to simultaneously process continuous frame-by-frame inputs and determine optimal response timing, often compromising real-time responsiveness and narrative coherence. To address these limitations, we introduce LiveStar, a pioneering live streaming assistant that achieves always-on proactive responses through adaptive streaming decoding. Specifically, LiveStar incorporates: (1) a training strategy enabling incremental video-language alignment for variable-length video streams, preserving temporal consistency across dynamically evolving frame sequences; (2) a response-silence decoding framework that determines optimal proactive response timing via a single forward pass verification; (3) memory-aware acceleration via peak-end memory compression for online inference on 10+ minute videos, combined with streaming key-value cache to achieve 1.53x faster inference. We also construct an OmniStar dataset, a comprehensive dataset for training and benchmarking that encompasses 15 diverse real-world scenarios and 5 evaluation tasks for online video understanding. Extensive experiments across three benchmarks demonstrate LiveStar's state-of-the-art performance, achieving an average 19.5% improvement in semantic correctness with 18.1% reduced timing difference compared to existing online Video-LLMs, while improving FPS by 12.0% across all five OmniStar tasks. Our model and dataset can be accessed at https://github.com/yzy-bupt/LiveStar.

cs.CV↗

arXiv2025

Decoupling Contrastive Decoding: Robust Hallucination Mitigation in Multimodal Large Language Models

Although multimodal large language models (MLLMs) exhibit remarkable reasoning capabilities on complex multimodal understanding tasks, they still suffer from the notorious hallucination issue: generating outputs misaligned with obvious visual or factual evidence. Currently, training-based solutions, like direct preference optimization (DPO), leverage paired preference data to suppress hallucinations. However, they risk sacrificing general reasoning capabilities due to the likelihood displacement. Meanwhile, training-free solutions, like contrastive decoding, achieve this goal by subtracting the estimated hallucination pattern from a distorted input. Yet, these handcrafted perturbations (e.g., add noise to images) may poorly capture authentic hallucination patterns. To avoid these weaknesses of existing methods, and realize robust hallucination mitigation (i.e., maintaining general reasoning performance), we propose a novel framework: Decoupling Contrastive Decoding (DCD). Specifically, DCD decouples the learning of positive and negative samples in preference datasets, and trains separate positive and negative image projections within the MLLM. The negative projection implicitly models real hallucination patterns, which enables vision-aware negative images in the contrastive decoding inference stage. Our DCD alleviates likelihood displacement by avoiding pairwise optimization and generalizes robustly without handcrafted degradation. Extensive ablations across hallucination benchmarks and general reasoning tasks demonstrate the effectiveness of DCD, i.e., it matches DPO's hallucination suppression while preserving general capabilities and outperforms the handcrafted contrastive decoding methods.

cs.LG↗

arXiv2025

StreamingCoT: A Dataset for Temporal Dynamics and Multimodal Chain-of-Thought Reasoning in Streaming VideoQA

The rapid growth of streaming video applications demands multimodal models with enhanced capabilities for temporal dynamics understanding and complex reasoning. However, current Video Question Answering (VideoQA) datasets suffer from two critical limitations: 1) Static annotation mechanisms fail to capture the evolving nature of answers in temporal video streams, and 2) The absence of explicit reasoning process annotations restricts model interpretability and logical deduction capabilities. To address these challenges, We introduce StreamingCoT, the first dataset explicitly designed for temporally evolving reasoning in streaming VideoQA and multimodal Chain-of-Thought (CoT) tasks. Our framework first establishes a dynamic hierarchical annotation architecture that generates per-second dense descriptions and constructs temporally-dependent semantic segments through similarity fusion, paired with question-answer sets constrained by temporal evolution patterns. We further propose an explicit reasoning chain generation paradigm that extracts spatiotemporal objects via keyframe semantic alignment, derives object state transition-based reasoning paths using large language models, and ensures logical coherence through human-verified validation. This dataset establishes a foundation for advancing research in streaming video understanding, complex temporal reasoning, and multimodal inference. Our StreamingCoT and its construction toolkit can be accessed at https://github.com/Fleeting-hyh/StreamingCoT.

cs.CV↗

arXiv2025

Kwai Keye-VL 1.5 Technical Report

In recent years, the development of Large Language Models (LLMs) has significantly advanced, extending their capabilities to multimodal tasks through Multimodal Large Language Models (MLLMs). However, video understanding remains a challenging area due to the dynamic and information-dense nature of videos. Existing models struggle with the trade-off between spatial resolution and temporal coverage when processing video content. We present Keye-VL-1.5, which addresses fundamental challenges in video comprehension through three key innovations. First, we introduce a novel Slow-Fast video encoding strategy that dynamically allocates computational resources based on inter-frame similarity, processing key frames with significant visual changes at higher resolution (Slow pathway) while handling relatively static frames with increased temporal coverage at lower resolution (Fast pathway). Second, we implement a progressive four-stage pre-training methodology that systematically extends the model's context length from 8K to 128K tokens, enabling processing of longer videos and more complex visual content. Third, we develop a comprehensive post-training pipeline focusing on reasoning enhancement and human preference alignment, incorporating a 5-step chain-of-thought data construction process, iterative GSPO-based reinforcement learning with progressive prompt hinting for difficult cases, and alignment training. Through extensive evaluation on public benchmarks and rigorous internal human assessment, Keye-VL-1.5 demonstrates significant improvements over existing models, particularly excelling in video understanding tasks while maintaining competitive performance on general multimodal benchmarks.

cs.CV↗

arXiv2025

EffiFusion-GAN: Efficient Fusion Generative Adversarial Network for Speech Enhancement

We introduce EffiFusion-GAN (Efficient Fusion Generative Adversarial Network), a lightweight yet powerful model for speech enhancement. The model integrates depthwise separable convolutions within a multi-scale block to capture diverse acoustic features efficiently. An enhanced attention mechanism with dual normalization and residual refinement further improves training stability and convergence. Additionally, dynamic pruning is applied to reduce model size while maintaining performance, making the framework suitable for resource-constrained environments. Experimental evaluation on the public VoiceBank+DEMAND dataset shows that EffiFusion-GAN achieves a PESQ score of 3.45, outperforming existing models under the same parameter settings.

cs.SD↗

arXiv2025

PGF-Net: A Progressive Gated-Fusion Framework for Efficient Multimodal Sentiment Analysis

We introduce PGF-Net (Progressive Gated-Fusion Network), a novel deep learning framework designed for efficient and interpretable multimodal sentiment analysis. Our framework incorporates three primary innovations. Firstly, we propose a Progressive Intra-Layer Fusion paradigm, where a Cross-Attention mechanism empowers the textual representation to dynamically query and integrate non-linguistic features from audio and visual streams within the deep layers of a Transformer encoder. This enables a deeper, context-dependent fusion process. Secondly, the model incorporates an Adaptive Gated Arbitration mechanism, which acts as a dynamic controller to balance the original linguistic information against the newly fused multimodal context, ensuring stable and meaningful integration while preventing noise from overwhelming the signal. Lastly, a hybrid Parameter-Efficient Fine-Tuning (PEFT) strategy is employed, synergistically combining global adaptation via LoRA with local refinement through Post-Fusion Adapters. This significantly reduces trainable parameters, making the model lightweight and suitable for resource-limited scenarios. These innovations are integrated into a hierarchical encoder architecture, enabling PGF-Net to perform deep, dynamic, and interpretable multimodal sentiment analysis while maintaining exceptional parameter efficiency. Experimental results on MOSI dataset demonstrate that our proposed PGF-Net achieves state-of-the-art performance, with a Mean Absolute Error (MAE) of 0.691 and an F1-Score of 86.9%. Notably, our model achieves these results with only 3.09M trainable parameters, showcasing a superior balance between performance and computational efficiency.

cs.LG↗

arXiv2025

Thyme: Think Beyond Images

Following OpenAI's introduction of the ``thinking with images'' concept, recent efforts have explored stimulating the use of visual information in the reasoning process to enhance model performance in perception and reasoning tasks. However, to the best of our knowledge, no open-source work currently offers a feature set as rich as proprietary models (O3), which can perform diverse image manipulations and simultaneously enhance logical reasoning capabilities through code. In this paper, we make a preliminary attempt in this direction by introducing Thyme (Think Beyond Images), a novel paradigm for enabling MLLMs to transcend existing ``think with images'' approaches by autonomously generating and executing diverse image processing and computational operations via executable code. This approach not only facilitates a rich, on-the-fly set of image manipulations (e.g., cropping, rotation, contrast enhancement) but also allows for mathematical computations, all while maintaining high autonomy in deciding when and how to apply these operations. We activate this capability through a two-stage training strategy: an initial SFT on a curated dataset of 500K samples to teach code generation, followed by a RL phase to refine decision-making. For the RL stage, we manually collect and design high-resolution question-answer pairs to increase the learning difficulty, and we propose GRPO-ATS (Group Relative Policy Optimization with Adaptive Temperature Sampling), an algorithm that applies distinct temperatures to text and code generation to balance reasoning exploration with code execution precision. We conduct extensive experimental analysis and ablation studies. Comprehensive evaluations on nearly 20 benchmarks show that Thyme yields significant and consistent performance gains, particularly in challenging high-resolution perception and complex reasoning tasks.

cs.CV↗

arXiv2025

Request-Only Optimization for Recommendation Systems

Deep Learning Recommendation Models (DLRMs) represent one of the largest machine learning applications on the planet. Industry-scale DLRMs are trained with petabytes of recommendation data to serve billions of users every day. To utilize the rich user signals in the long user history, DLRMs have been scaled up to unprecedented complexity, up to trillions of floating-point operations (TFLOPs) per example. This scale, coupled with the huge amount of training data, necessitates new storage and training algorithms to efficiently improve the quality of these complex recommendation systems. In this paper, we present a Request-Only Optimizations (ROO) training and modeling paradigm. ROO simultaneously improves the storage and training efficiency as well as the model quality of recommendation systems. We holistically approach this challenge through co-designing data (i.e., request-only data), infrastructure (i.e., request-only based data processing pipeline), and model architecture (i.e., request-only neural architectures). Our ROO training and modeling paradigm treats a user request as a unit of the training data. Compared with the established practice of treating a user impression as a unit, our new design achieves native feature deduplication in data logging, consequently saving data storage. Second, by de-duplicating computations and communications across multiple impressions in a request, this new paradigm enables highly scaled-up neural network architectures to better capture user interest signals, such as Generative Recommenders (GRs) and other request-only friendly architectures.

cs.IR↗

arXiv2025

TIME: Temporal-Sensitive Multi-Dimensional Instruction Tuning and Robust Benchmarking for Video-LLMs

Video large language models have achieved remarkable performance in tasks such as video question answering, however, their temporal understanding remains suboptimal. To address this limitation, we curate a dedicated instruction fine-tuning dataset that focuses on enhancing temporal comprehension across five key dimensions. In order to reduce reliance on costly temporal annotations, we introduce a multi-task prompt fine-tuning approach that seamlessly integrates temporal-sensitive tasks into existing instruction datasets without requiring additional annotations. Furthermore, we develop a novel benchmark for temporal-sensitive video understanding that not only fills the gaps in dimension coverage left by existing benchmarks but also rigorously filters out potential shortcuts, ensuring a more accurate evaluation. Extensive experimental results demonstrate that our approach significantly enhances the temporal understanding of video-LLMs while avoiding reliance on shortcuts.

cs.CV↗

arXiv2025

Kwai Keye-VL Technical Report

While Multimodal Large Language Models (MLLMs) demonstrate remarkable capabilities on static images, they often fall short in comprehending dynamic, information-dense short-form videos, a dominant medium in today's digital landscape. To bridge this gap, we introduce \textbf{Kwai Keye-VL}, an 8-billion-parameter multimodal foundation model engineered for leading-edge performance in short-video understanding while maintaining robust general-purpose vision-language abilities. The development of Keye-VL rests on two core pillars: a massive, high-quality dataset exceeding 600 billion tokens with a strong emphasis on video, and an innovative training recipe. This recipe features a four-stage pre-training process for solid vision-language alignment, followed by a meticulous two-phase post-training process. The first post-training stage enhances foundational capabilities like instruction following, while the second phase focuses on stimulating advanced reasoning. In this second phase, a key innovation is our five-mode ``cold-start'' data mixture, which includes ``thinking'', ``non-thinking'', ``auto-think'', ``think with image'', and high-quality video data. This mixture teaches the model to decide when and how to reason. Subsequent reinforcement learning (RL) and alignment steps further enhance these reasoning capabilities and correct abnormal model behaviors, such as repetitive outputs. To validate our approach, we conduct extensive evaluations, showing that Keye-VL achieves state-of-the-art results on public video benchmarks and remains highly competitive on general image-based tasks (Figure 1). Furthermore, we develop and release the \textbf{KC-MMBench}, a new benchmark tailored for real-world short-video scenarios, where Keye-VL shows a significant advantage.

cs.CV↗

arXiv2025

RecipeGen: A Step-Aligned Multimodal Benchmark for Real-World Recipe Generation

Creating recipe images is a key challenge in food computing, with applications in culinary education and multimodal recipe assistants. However, existing datasets lack fine-grained alignment between recipe goals, step-wise instructions, and visual content. We present RecipeGen, the first large-scale, real-world benchmark for recipe-based Text-to-Image (T2I), Image-to-Video (I2V), and Text-to-Video (T2V) generation. RecipeGen contains 26,453 recipes, 196,724 images, and 4,491 videos, covering diverse ingredients, cooking procedures, styles, and dish types. We further propose domain-specific evaluation metrics to assess ingredient fidelity and interaction modeling, benchmark representative T2I, I2V, and T2V models, and provide insights for future recipe generation models. Project page is available now.

cs.CV↗