IIR-VLM: In-Context Instance-level Recognition for Large Vision-Language Models

Instance-level recognition (ILR) concerns distinguishing individual instances from one another, with person re-identification as a prominent example. Despite the impressive visual perception capabilities of modern VLMs, we find their performance on ILR unsatisfactory, often dramatically underperforming domain-specific ILR models. This limitation hinders many practical application of VLMs, e.g. where recognizing familiar people and objects is crucial for effective visual understanding. Existing solutions typically learn to recognize instances one at a time using instance-specific datasets, which not only incur substantial data collection and training costs but also struggle with fine-grained discrimination. In this work, we propose IIR-VLM, a VLM enhanced for In-context Instance-level Recognition. We integrate pre-trained ILR expert models as auxiliary visual encoders to provide specialized features for learning diverse instances, which enables VLMs to learn new instances in-context in a one-shot manner. Further, IIR-VLM leverages this knowledge for instance-aware visual understanding. We validate IIR-VLM's efficacy on existing instance personalization benchmarks. Finally, we demonstrate its superior ILR performance on a challenging new benchmark, which assesses ILR capabilities across varying difficulty and diverse categories, with person, face, pet and general objects as the instances at task.

Diffusion-DRF: Differentiable Reward Flow for Video Diffusion Fine-Tuning

Direct Preference Optimization (DPO) has recently improved Text-to-Video (T2V) generation by enhancing visual fidelity and text alignment. However, current methods rely on non-differentiable preference signals from human annotations or learned reward models. This reliance makes training label-intensive, bias-prone, and easy-to-game, which often triggers reward hacking and unstable training. We propose Diffusion-DRF, a differentiable reward flow for fine-tuning video diffusion models using a frozen, off-the-shelf Vision-Language Model (VLM) as a training-free critic. Diffusion-DRF directly backpropagates VLM feedback through the diffusion denoising chain, converting logit-level responses into token-aware gradients for optimization. We propose an automated, aspect-structured prompting pipeline to obtain reliable multi-dimensional VLM feedback, while gradient checkpointing enables efficient updates through the final denoising steps. Diffusion-DRF improves video quality and semantic alignment while mitigating reward hacking and collapse -- without additional reward models or preference datasets. It is model-agnostic and readily generalizes to other diffusion-based generative tasks.

Rethinking Fine-Tuning: Unlocking Hidden Capabilities in Vision-Language Models

Explorations in fine-tuning Vision-Language Models (VLMs), such as Low-Rank Adaptation (LoRA) from Parameter Efficient Fine-Tuning (PEFT), have made impressive progress. However, most approaches rely on explicit weight updates, overlooking the extensive representational structures already encoded in pre-trained models that remain underutilized. Recent works have demonstrated that Mask Fine-Tuning (MFT) can be a powerful and efficient post-training paradigm for language models. Instead of updating weights, MFT assigns learnable gating scores to each weight, allowing the model to reorganize its internal subnetworks for downstream task adaptation. In this paper, we rethink fine-tuning for VLMs from a structural reparameterization perspective grounded in MFT. We apply MFT to the language and projector components of VLMs with different language backbones and compare against strong PEFT baselines. Experiments show that MFT consistently surpasses LoRA variants and even full fine-tuning, achieving high performance without altering the frozen backbone. Our findings reveal that effective adaptation can emerge not only from updating weights but also from reestablishing connections among the model's existing knowledge. Code available at: https://github.com/Ming-K9/MFT-VLM

SimpleCall: A Lightweight Image Restoration Agent in Label-Free Environments with MLLM Perceptual Feedback

Complex image restoration aims to recover high-quality images from inputs affected by multiple degradations such as blur, noise, rain, and compression artifacts. Recent restoration agents, powered by vision-language models and large language models, offer promising restoration capabilities but suffer from significant efficiency bottlenecks due to reflection, rollback, and iterative tool searching. Moreover, their performance heavily depends on degradation recognition models that require extensive annotations for training, limiting their applicability in label-free environments. To address these limitations, we propose a policy optimization-based restoration framework that learns an lightweight agent to determine tool-calling sequences. The agent operates in a sequential decision process, selecting the most appropriate restoration operation at each step to maximize final image quality. To enable training within label-free environments, we introduce a novel reward mechanism driven by multimodal large language models, which act as human-aligned evaluator and provide perceptual feedback for policy improvement. Once trained, our agent executes a deterministic restoration plans without redundant tool invocations, significantly accelerating inference while maintaining high restoration quality. Extensive experiments show that despite using no supervision, our method matches SOTA performance on full-reference metrics and surpasses existing approaches on no-reference metrics across diverse degradation scenarios.

LinkedOut: Linking World Knowledge Representation Out of Video LLM for Next-Generation Video Recommendation

Video Large Language Models (VLLMs) unlock world-knowledge-aware video understanding through pretraining on internet-scale data and have already shown promise on tasks such as movie analysis and video question answering. However, deploying VLLMs for downstream tasks such as video recommendation remains challenging, since real systems require multi-video inputs, lightweight backbones, low-latency sequential inference, and rapid response. In practice, (1) decode-only generation yields high latency for sequential inference, (2) typical interfaces do not support multi-video inputs, and (3) constraining outputs to language discards fine-grained visual details that matter for downstream vision tasks. We argue that these limitations stem from the absence of a representation that preserves pixel-level detail while leveraging world knowledge. We present LinkedOut, a representation that extracts VLLM world knowledge directly from video to enable fast inference, supports multi-video histories, and removes the language bottleneck. LinkedOut extracts semantically grounded, knowledge-aware tokens from raw frames using VLLMs, guided by promptable queries and optional auxiliary modalities. We introduce a cross-layer knowledge fusion MoE that selects the appropriate level of abstraction from the rich VLLM features, enabling personalized, interpretable, and low-latency recommendation. To our knowledge, LinkedOut is the first VLLM-based video recommendation method that operates on raw frames without handcrafted labels, achieving state-of-the-art results on standard benchmarks. Interpretability studies and ablations confirm the benefits of layer diversity and layer-wise fusion, pointing to a practical path that fully leverages VLLM world-knowledge priors and visual reasoning for downstream vision tasks such as recommendation.

AdaSports-Traj: Role- and Domain-Aware Adaptation for Multi-Agent Trajectory Modeling in Sports

Trajectory prediction in multi-agent sports scenarios is inherently challenging due to the structural heterogeneity across agent roles (e.g., players vs. ball) and dynamic distribution gaps across different sports domains. Existing unified frameworks often fail to capture these structured distributional shifts, resulting in suboptimal generalization across roles and domains. We propose AdaSports-Traj, an adaptive trajectory modeling framework that explicitly addresses both intra-domain and inter-domain distribution discrepancies in sports. At its core, AdaSports-Traj incorporates a Role- and Domain-Aware Adapter to conditionally adjust latent representations based on agent identity and domain context. Additionally, we introduce a Hierarchical Contrastive Learning objective, which separately supervises role-sensitive and domain-aware representations to encourage disentangled latent structures without introducing optimization conflict. Experiments on three diverse sports datasets, Basketball-U, Football-U, and Soccer-U, demonstrate the effectiveness of our adaptive design, achieving strong performance in both unified and cross-domain trajectory prediction settings.

MTS-DMAE: Dual-Masked Autoencoder for Unsupervised Multivariate Time Series Representation Learning

Unsupervised multivariate time series (MTS) representation learning aims to extract compact and informative representations from raw sequences without relying on labels, enabling efficient transfer to diverse downstream tasks. In this paper, we propose Dual-Masked Autoencoder (DMAE), a novel masked time-series modeling framework for unsupervised MTS representation learning. DMAE formulates two complementary pretext tasks: (1) reconstructing masked values based on visible attributes, and (2) estimating latent representations of masked features, guided by a teacher encoder. To further improve representation quality, we introduce a feature-level alignment constraint that encourages the predicted latent representations to align with the teacher's outputs. By jointly optimizing these objectives, DMAE learns temporally coherent and semantically rich representations. Comprehensive evaluations across classification, regression, and forecasting tasks demonstrate that our approach achieves consistent and superior performance over competitive baselines.

Dense Video Understanding with Gated Residual Tokenization

High temporal resolution is essential for capturing fine-grained details in video understanding. However, current video large language models (VLLMs) and benchmarks mostly rely on low-frame-rate sampling, such as uniform sampling or keyframe selection, discarding dense temporal information. This compromise avoids the high cost of tokenizing every frame, which otherwise leads to redundant computation and linear token growth as video length increases. While this trade-off works for slowly changing content, it fails for tasks like lecture comprehension, where information appears in nearly every frame and requires precise temporal alignment. To address this gap, we introduce Dense Video Understanding (DVU), which enables high-FPS video comprehension by reducing both tokenization time and token overhead. Existing benchmarks are also limited, as their QA pairs focus on coarse content changes. We therefore propose DIVE (Dense Information Video Evaluation), the first benchmark designed for dense temporal reasoning. To make DVU practical, we present Gated Residual Tokenization (GRT), a two-stage framework: (1) Motion-Compensated Inter-Gated Tokenization uses pixel-level motion estimation to skip static regions during tokenization, achieving sub-linear growth in token count and compute. (2) Semantic-Scene Intra-Tokenization Merging fuses tokens across static regions within a scene, further reducing redundancy while preserving dynamic semantics. Experiments on DIVE show that GRT outperforms larger VLLM baselines and scales positively with FPS. These results highlight the importance of dense temporal information and demonstrate that GRT enables efficient, scalable high-FPS video understanding.

Out-of-Sight Trajectories: Tracking, Fusion, and Prediction

Trajectory prediction is a critical task in computer vision and autonomous systems, playing a key role in autonomous driving, robotics, surveillance, and virtual reality. Existing methods often rely on complete and noise-free observational data, overlooking the challenges associated with out-of-sight objects and the inherent noise in sensor data caused by limited camera coverage, obstructions, and the absence of ground truth for denoised trajectories. These limitations pose safety risks and hinder reliable prediction in real-world scenarios. In this extended work, we present advancements in Out-of-Sight Trajectory (OST), a novel task that predicts the noise-free visual trajectories of out-of-sight objects using noisy sensor data. Building on our previous research, we broaden the scope of Out-of-Sight Trajectory Prediction (OOSTraj) to include pedestrians and vehicles, extending its applicability to autonomous driving, robotics, surveillance, and virtual reality. Our enhanced Vision-Positioning Denoising Module leverages camera calibration to establish a vision-positioning mapping, addressing the lack of visual references, while effectively denoising noisy sensor data in an unsupervised manner. Through extensive evaluations on the Vi-Fi and JRDB datasets, our approach achieves state-of-the-art performance in both trajectory denoising and prediction, significantly surpassing previous baselines. Additionally, we introduce comparisons with traditional denoising methods, such as Kalman filtering, and adapt recent trajectory prediction models to our task, providing a comprehensive benchmark. This work represents the first initiative to integrate vision-positioning projection for denoising noisy sensor trajectories of out-of-sight agents, paving the way for future advances. The code and preprocessed datasets are available at github.com/Hai-chao-Zhang/OST

ExpertGen: Training-Free Expert Guidance for Controllable Text-to-Face Generation

Recent advances in diffusion models have significantly improved text-to-face generation, but achieving fine-grained control over facial features remains a challenge. Existing methods often require training additional modules to handle specific controls such as identity, attributes, or age, making them inflexible and resource-intensive. We propose ExpertGen, a training-free framework that leverages pre-trained expert models such as face recognition, facial attribute recognition, and age estimation networks to guide generation with fine control. Our approach uses a latent consistency model to ensure realistic and in-distribution predictions at each diffusion step, enabling accurate guidance signals to effectively steer the diffusion process. We show qualitatively and quantitatively that expert models can guide the generation process with high precision, and multiple experts can collaborate to enable simultaneous control over diverse facial aspects. By allowing direct integration of off-the-shelf expert models, our method transforms any such model into a plug-and-play component for controllable face generation.