Learning to Search: A Decision-Based Agent for Knowledge-Based Visual Question Answering

Knowledge-based visual question answering (KB-VQA) requires vision-language models to understand images and use external knowledge, especially for rare entities and long-tail facts. Most existing retrieval-augmented generation (RAG) methods adopt a fixed pipeline that sequentially retrieves information, filters it, and then produces an answer. Such a design makes it difficult to adapt to diverse question types. Moreover, it separates retrieval from reasoning, making it hard for the model to decide when to search, how to refine queries, or when to stop. As a result, the retrieved evidence is often poorly aligned with the question. To address these limitations, we reformulate KB-VQA as a search-agent problem and model the solving process as a multi-step decision-making procedure. At each step, the agent selects one of four actions-Answer, Image Retrieval, Text Retrieval, and Caption-based on its current information state. We further design an automated pipeline to collect multi-step trajectories that record the agent's reasoning process, tool usage, and intermediate decisions. These trajectories are then used as supervision for fine-tuning. Experiments on InfoSeek and E-VQA demonstrate that our method achieves state-of-the-art performance, consistently outperforming prior baselines and confirming the effectiveness of our framework.

Stabilizing Unsupervised Self-Evolution of MLLMs via Continuous Softened Retracing reSampling

In the unsupervised self-evolution of Multimodal Large Language Models, the quality of feedback signals during post-training is pivotal for stable and effective learning. However, existing self-evolution methods predominantly rely on majority voting to select the most frequent output as the pseudo-golden answer, which may stem from the model's intrinsic biases rather than guaranteeing the objective correctness of the reasoning paths. To counteract the degradation, we propose \textbf{C}ontinuous \textbf{S}oftened \textbf{R}etracing re\textbf{S}ampling (\textbf{CSRS}) in MLLM self-evolution. Specifically, we introduce a Retracing Re-inference Mechanism (\textbf{RRM}) that the model re-inferences from anchor points to expand the exploration of long-tail reasoning paths. Simultaneously, we propose Softened Frequency Reward (\textbf{SFR}), which replaces binary rewards with continuous signals, calibrating reward based on the answers' frequency across sampled reasoning sets. Furthermore, incorporated with Visual Semantic Perturbation (\textbf{VSP}), CSRS ensures the model prioritizes mathematical logic over visual superficiality. Experimental results demonstrate that CSRS significantly enhances the reasoning performance of Qwen2.5-VL-7B on benchmarks such as MathVision. We achieve state-of-the-art (SOTA) results in unsupervised self-evolution on geometric tasks. Our code is avaible at https://github.com/yyy195/CSRS.

When Models Judge Themselves: Unsupervised Self-Evolution for Multimodal Reasoning

Recent progress in multimodal large language models has led to strong performance on reasoning tasks, but these improvements largely rely on high-quality annotated data or teacher-model distillation, both of which are costly and difficult to scale.To address this, we propose an unsupervised self-evolution training framework for multimodal reasoning that achieves stable performance improvements without using human-annotated answers or external reward models. For each input, we sample multiple reasoning trajectories and jointly model their within group structure.We use the Actor's self-consistency signal as a training prior, and introduce a bounded Judge based modulation to continuously reweight trajectories of different quality.We further model the modulated scores as a group level distribution and convert absolute scores into relative advantages within each group, enabling more robust policy updates. Trained with Group Relative Policy Optimization (GRPO) on unlabeled data, our method consistently improves reasoning performance and generalization on five mathematical reasoning benchmarks, offering a scalable path toward self-evolving multimodal models.The code are available at https://dingwu1021.github.io/SelfJudge/.

Efficient Long-Horizon GUI Agents via Training-Free KV Cache Compression

Large Vision-Language Models (VLMs) have emerged as powerful engines for autonomous GUI agents, yet their deployment is severely constrained by the substantial memory footprint and latency of the Key-Value (KV) cache during long-horizon interactions. While existing cache compression methods have proven effective for LLMs, we empirically demonstrate that they suffer from suboptimal performance in GUI scenarios due to a fundamental misalignment: unlike general visual tasks where attention sparsity varies across layers, GUI attention patterns exhibit uniform high-sparsity across all transformer layers. Motivated by this insight, we propose ST-Lite, a training-free KV cache compression framework tailored for efficient GUI agents that explicitly addresses the dynamic spatio-trajectory dependencies within GUI data streams. ST-Lite introduces a novel dual-branch scoring policy incorporating Component-centric Spatial Saliency (CSS) and Trajectory-aware Semantic Gating (TSG). Specifically, CSS preserves the structural integrity of interactive UI elements by evaluating local neighborhood saliency, while TSG mitigates historical redundancy by dynamically filtering visually repetitive KV pairs within the interaction trajectory. Extensive evaluations demonstrate that with only a 10-20% cache budget, ST-Lite achieves a 2.45x decoding acceleration while maintaining comparable or even superior performance compared to full-cache baselines, offering a scalable solution for resource-constrained GUI agents.

R3G: A Reasoning--Retrieval--Reranking Framework for Vision-Centric Answer Generation

Vision-centric retrieval for VQA requires retrieving images to supply missing visual cues and integrating them into the reasoning process. However, selecting the right images and integrating them effectively into the model's reasoning remains challenging.To address this challenge, we propose R3G, a modular Reasoning-Retrieval-Reranking framework.It first produces a brief reasoning plan that specifies the required visual cues, then adopts a two-stage strategy, with coarse retrieval followed by fine-grained reranking, to select evidence images.On MRAG-Bench, R3G improves accuracy across six MLLM backbones and nine sub-scenarios, achieving state-of-the-art overall performance. Ablations show that sufficiency-aware reranking and reasoning steps are complementary, helping the model both choose the right images and use them well. We release code and data at https://github.com/czh24/R3G.

Language-Guided and Motion-Aware Gait Representation for Generalizable Recognition

Gait recognition is emerging as a promising technology and an innovative field within computer vision. However, existing methods typically rely on complex architectures to directly extract features from images and apply pooling operations to obtain sequence-level representations. Such designs often lead to overfitting on static noise (e.g., clothing), while failing to effectively capture dynamic motion regions.To address the above challenges, we present a Language guided and Motion-aware gait recognition framework, named LMGait.In particular, we utilize designed gait-related language cues to capture key motion features in gait sequences.

Taming Hallucinations: Boosting MLLMs' Video Understanding via Counterfactual Video Generation

Multimodal Large Language Models (MLLMs) have made remarkable progress in video understanding. However, they suffer from a critical vulnerability: an over-reliance on language priors, which can lead to visual ungrounded hallucinations, especially when processing counterfactual videos that defy common sense. This limitation, stemming from the intrinsic data imbalance between text and video, is challenging to address due to the substantial cost of collecting and annotating counterfactual data. To address this, we introduce DualityForge, a novel counterfactual data synthesis framework that employs controllable, diffusion-based video editing to transform real-world videos into counterfactual scenarios. By embedding structured contextual information into the video editing and QA generation processes, the framework automatically produces high-quality QA pairs together with original-edited video pairs for contrastive training. Based on this, we build DualityVidQA, a large-scale video dataset designed to reduce MLLM hallucinations. In addition, to fully exploit the contrastive nature of our paired data, we propose Duality-Normalized Advantage Training (DNA-Train), a two-stage SFT-RL training regime where the RL phase applies pair-wise $\ell_1$ advantage normalization, thereby enabling a more stable and efficient policy optimization. Experiments on DualityVidQA-Test demonstrate that our method substantially reduces model hallucinations on counterfactual videos, yielding a relative improvement of 24.0% over the Qwen2.5-VL-7B baseline. Moreover, our approach achieves significant gains across both hallucination and general-purpose benchmarks, indicating strong generalization capability. We will open-source our dataset and code.

EchoMotion: Unified Human Video and Motion Generation via Dual-Modality Diffusion Transformer

Video generation models have advanced significantly, yet they still struggle to synthesize complex human movements due to the high degrees of freedom in human articulation. This limitation stems from the intrinsic constraints of pixel-only training objectives, which inherently bias models toward appearance fidelity at the expense of learning underlying kinematic principles. To address this, we introduce EchoMotion, a framework designed to model the joint distribution of appearance and human motion, thereby improving the quality of complex human action video generation. EchoMotion extends the DiT (Diffusion Transformer) framework with a dual-branch architecture that jointly processes tokens concatenated from different modalities. Furthermore, we propose MVS-RoPE (Motion-Video Syncronized RoPE), which offers unified 3D positional encoding for both video and motion tokens. By providing a synchronized coordinate system for the dual-modal latent sequence, MVS-RoPE establishes an inductive bias that fosters temporal alignment between the two modalities. We also propose a Motion-Video Two-Stage Training Strategy. This strategy enables the model to perform both the joint generation of complex human action videos and their corresponding motion sequences, as well as versatile cross-modal conditional generation tasks. To facilitate the training of a model with these capabilities, we construct HuMoVe, a large-scale dataset of approximately 80,000 high-quality, human-centric video-motion pairs. Our findings reveal that explicitly representing human motion is complementary to appearance, significantly boosting the coherence and plausibility of human-centric video generation.

Measuring and Controlling the Spectral Bias for Self-Supervised Image Denoising

Current self-supervised denoising methods for paired noisy images typically involve mapping one noisy image through the network to the other noisy image. However, after measuring the spectral bias of such methods using our proposed Image Pair Frequency-Band Similarity, it suffers from two practical limitations. Firstly, the high-frequency structural details in images are not preserved well enough. Secondly, during the process of fitting high frequencies, the network learns high-frequency noise from the mapped noisy images. To address these challenges, we introduce a Spectral Controlling network (SCNet) to optimize self-supervised denoising of paired noisy images. First, we propose a selection strategy to choose frequency band components for noisy images, to accelerate the convergence speed of training. Next, we present a parameter optimization method that restricts the learning ability of convolutional kernels to high-frequency noise using the Lipschitz constant, without changing the network structure. Finally, we introduce the Spectral Separation and low-rank Reconstruction module (SSR module), which separates noise and high-frequency details through frequency domain separation and low-rank space reconstruction, to retain the high-frequency structural details of images. Experiments performed on synthetic and real-world datasets verify the effectiveness of SCNet.

DreamSwapV: Mask-guided Subject Swapping for Any Customized Video Editing

With the rapid progress of video generation, demand for customized video editing is surging, where subject swapping constitutes a key component yet remains under-explored. Prevailing swapping approaches either specialize in narrow domains--such as human-body animation or hand-object interaction--or rely on some indirect editing paradigm or ambiguous text prompts that compromise final fidelity. In this paper, we propose DreamSwapV, a mask-guided, subject-agnostic, end-to-end framework that swaps any subject in any video for customization with a user-specified mask and reference image. To inject fine-grained guidance, we introduce multiple conditions and a dedicated condition fusion module that integrates them efficiently. In addition, an adaptive mask strategy is designed to accommodate subjects of varying scales and attributes, further improving interactions between the swapped subject and its surrounding context. Through our elaborate two-phase dataset construction and training scheme, our DreamSwapV outperforms existing methods, as validated by comprehensive experiments on VBench indicators and our first introduced DreamSwapV-Benchmark.