Numerous diffusion models have been developed for 2D image synthesis and editing, and recently they are extended to 3D scene editing tasks. However, editing 3D scenes is still in its early stages, and the challenges of scene representations and multi-view consistency need to be addressed. A notable limitation of existing approaches is the need for specific modules for different edits and model retraining for each scene. To tackle these issues, we propose a novel and versatile text-driven 3D scene editing method, termed DN2N, which allows for the direct acquisition of the editing results without the requirement for retraining. Our method employs off-the-shelf text-based editing models of 2D images to modify the multi-view images of a 3D scene. A content filtering process is then applied to discard poorly edited images that disrupt 3D consistency. We consider the remaining inconsistency as a problem of removing noise perturbations and solve it by generating data with similar perturbation characteristics for training. We develop a versatile NeRF model structure and propose two novel cross-view regularization terms to help the DN2N mitigate these perturbations. Empirical results show that our method achieves multiple editing types based solely on text prompts, including but not limited to appearance editing, weather transition, object changing, and style transfer. Most importantly, DN2N exhibits a versatility of editing capabilities, eliminating the need to customize or retrain editing models for specific scenes or editing types. Namely, DN2N achieves comparable total editing time to the 3DGS-based editing method, enhancing its practical value.

A core aspect of human perception is situated awareness, the ability to relate ourselves to the surrounding physical environment and reason over possible actions in context. However, most existing benchmarks for multimodal foundation models (MFMs) emphasize environment-centric spatial relations (relations among objects in a scene), while largely overlooking observer-centric relationships that require reasoning relative to agent's viewpoint, pose, and motion. To bridge this gap, we introduce SAW-Bench (Situated Awareness in the Real World), a novel benchmark for evaluating egocentric situated awareness using real-world videos. SAW-Bench comprises 786 self-recorded videos captured with Ray-Ban Meta (Gen 2) smart glasses spanning diverse indoor and outdoor environments, and over 2,071 human-annotated question-answer pairs. It probes a model's observer-centric understanding with six different awareness tasks. Our comprehensive evaluation reveals a human-model performance gap of 37.66

In this work, we present a simple yet theoretically motivated improvement to Supervised Fine-Tuning (SFT) for the Large Language Model (LLM), addressing its limited generalization compared to reinforcement learning (RL). Through mathematical analysis, we reveal that standard SFT gradients implicitly encode a problematic reward structure that may severely restrict the generalization capabilities of model compared to RL. To rectify this, we propose Dynamic Fine-Tuning (DFT), stabilizing gradient updates for each token by dynamically rescaling the objective function with the probability of this token. With just a single-line change, the method outperforms standard SFT on multiple difficult benchmarks and base models, from math reasoning to code generation and multi-modal tasks, demonstrating improved generalization. Additionally, DFT achieves competitive results in offline RL settings, and further boosts the effectiveness of subsequent RL training, providing an effective yet streamlined alternative. The experiments further demonstrate that DFT not only strengthens SFT performance but also consistently improves the effectiveness of subsequent RL training. By bridging theoretical insights with practical solutions, this work advances the state of SFT. The source code will be publicly released.

High-dimensional structural MRI (sMRI) images are widely used for Alzheimer's Disease (AD) diagnosis. Most existing methods for sMRI representation learning rely on 3D architectures (e.g., 3D CNNs), slice-wise feature extraction with late aggregation, or apply training-free feature extractions using 2D foundation models (e.g., DINO). However, these three paradigms suffer from high computational cost, loss of cross-slice relations, and limited ability to extract discriminative features, respectively. To address these challenges, we propose Multimodal Visual Surrogate Compression (MVSC). It learns to compress and adapt large 3D sMRI volumes into compact 2D features, termed as visual surrogates, which are better aligned with frozen 2D foundation models to extract powerful representations for final AD classification. MVSC has two key components: a Volume Context Encoder that captures global cross-slice context under textual guidance, and an Adaptive Slice Fusion module that aggregates slice-level information in a text-enhanced, patch-wise manner. Extensive experiments on three large-scale Alzheimer's disease benchmarks demonstrate our MVSC performs favourably on both binary and multi-class classification tasks compared against state-of-the-art methods.

Face swapping has witnessed significant progress in recent years, largely driven by advances in deep generative models such as GANs and diffusion models.Despite these advances, existing methods remain fragmented across different paradigms, and their evaluation is highly inconsistent due to the lack of standardized datasets and protocols. Moreover, prior surveys primarily focus on broader deepfake generation or detection, leaving face swapping insufficiently studied as a standalone problem. In this paper, we present a comprehensive survey and benchmark for face swapping. We provide a structured review of existing methods, organizing them into five major paradigms and systematically analyzing their design principles, strengths, and limitations. To enable fair and controlled evaluation, we introduce CASIA FaceSwapping, a high-quality benchmark with balanced demographic distributions and explicit attribute variations, and establish standardized protocols to assess the robustness of different face swapping methods. Extensive experiments on representative approaches yield new insights into the performance characteristics and limitations of current techniques. Overall, our work provides a unified perspective and a principled evaluation framework to facilitate the development of more robust and controllable face swapping methods. More results can be found at https://github.com/CASIA-NLPRAI/face-swapping-survey.

Existing visual trackers mainly operate in a non-interactive, fire-and-forget manner, making them impractical for real-world scenarios that require human-in-the-loop adaptation. To overcome this limitation, we introduce Interactive Tracking, a new paradigm that allows users to guide the tracker at any time using natural language commands. To support research in this direction, we make three main contributions. First, we present InteractTrack, the first large-scale benchmark for interactive tracking, containing 150 videos with dense bounding box annotations and timestamped language instructions. Second, we propose a comprehensive evaluation protocol and evaluate 25 representative trackers, showing that state-of-the-art methods fail in interactive scenarios—strong performance on conventional benchmarks does not transfer. Third, we introduce Interactive Memory-Augmented Tracking (IMAT), a new baseline that employs a dynamic memory mechanism to learn from user feedback and update tracking behavior accordingly. Our benchmark, protocol, and baseline establish a foundation for developing more intelligent, adaptive, and collaborative tracking systems, bridging the gap between automated perception and human guidance.

Large Language Models (LLMs) exhibit strong reasoning abilities for planning long-horizon, real-world tasks, yet existing agent benchmarks focus on task completion while neglecting time efficiency in parallel and asynchronous operations. To address this, we present ParaCook, a benchmark for time-efficient collaborative planning. Inspired by the Overcooked game, ParaCook provides an environment for various challenging interaction planning of multi-agent systems that are instantiated as cooking tasks, with a simplified action space to isolate the core challenge of strategic parallel planning. Through a comprehensive evaluation of state-of-the-art LLMs, we find that current approaches achieve suboptimal plans, which struggle with parallel actions or coordination. Our analysis also reveals LLMs' potential on abstract tasks where they can focus on high-level parallel optimization. ParaCook provides a scalable evaluation framework with adjustable complexity, establishing a foundation for developing and assessing time efficiency-aware multi-agent planning. The code and data are available at https://github.com/zsq259/ParaCook.

Instruction-guided image editing is becoming a general interface for visual work, yet existing benchmarks still focus largely on narrow appearance edits and do not fully capture the diversity of real-image tasks in professional workflows. Here, we define instructional computer vision problem solving as a broader formulation of image editing: given a real input image and a natural-language instruction, a system must produce an edited output that realizes the requested transformation while satisfying explicit preservation, geometric, physical, and usability constraints. We introduce CV-Arena, an open benchmark designed to evaluate this capability at professional scales. CV-Arena contains 12K high-resolution real-image instruction pairs spanning 16 instruction-based visual task types, constructed using CogRetriever, a dual-track retrieval-and-curation pipeline that combines targeted web search, agentic query refinement, verification, and traceability. To evaluate models at scale while preserving human fidelity, we propose Active Elo, a human-AI collaborative preference protocol that leverages CV-Judge, a logic-gated, multi-dimensional VLM evaluator, to reject clear failures and resolve high-confidence comparisons; and to route close, high-quality comparisons to expert raters. Mixed human and AI supervision is then aggregated through reliability-weighted Elo updates. Our comprehensive evaluation of 21 systems, including proprietary, open-source, and agentic models, on CV-Arena reveals persistent gaps in instruction adherence, physical reasoning, structural control, and fine-grained detail preservation. We further develop CV-Agent, a lightweight agentic model that combines planning, editing, and verification, and demonstrate that closed-loop reasoning is a promising direction for professional-grade instruction-following visual editing.

Many autonomous driving systems are increasingly incorporating foundation models to improve generalization and handle long-tail scenarios. However, this trend introduces two key challenges: (i) the manual and labor-intensive process of designing and integrating new models, and (ii) the lack of intelligent, dynamic scheduling mechanisms to meet strict real-time constraints. While Large Language Model (LLM)-based agents offer a promising avenue for automation, existing frameworks are ill-suited for autonomous driving. Specifically, they fail to distinguish between the fundamentally different requirements of system design and real-time scheduling, treat modules as opaque black boxes, and are not designed for continuous operation. To address these limitations, we propose DrivingAgent, a novel agent framework tailored to the dual challenges of autonomous driving system design and scheduling. In the design phase, DrivingAgent automates module development by interpreting system architecture, generating code, and validating modules via super-network training. In the scheduling phase, it employs a lightweight LLM trained with reinforcement learning to dynamically orchestrate system modules in real time, supported by a structured memory that integrates long-term storage with timestamped short-term context. Experimental results demonstrate that DrivingAgent achieves a superior speed–accuracy trade-off on both the nuScenes and Bench2Drive benchmarks.

We introduce FaceCam, a system that generates video under customizable camera trajectories for monocular human portrait video input. Recent camera control approaches based on large video-generation models have shown promising progress but often exhibit geometric distortions and visual artifacts on portrait videos due to scale-ambiguous camera representations or 3D reconstruction errors. To overcome these limitations, we propose a face-tailored scale-aware representation for camera transformations that provides deterministic conditioning without relying on 3D priors. We train a video generation model on both multi-view studio captures and in-the-wild monocular videos, and introduce two camera-control data generation strategies: synthetic camera motion and multi-shot stitching, to exploit stationary training cameras while generalizing to dynamic, continuous camera trajectories at inference time. Experiments on Ava-256 dataset and diverse in-the-wild videos demonstrate that FaceCam achieves superior performance in camera controllability, visual quality, identity and motion preservation.

Multi-object tracking (MOT) aims to track multiple objects while maintaining consistent identities across frames of a given video. In unmanned aerial vehicle (UAV) recorded videos, frequent viewpoint changes and complex UAV-ground relative motion dynamics pose significant challenges, which often lead to unstable affinity measurement and ambiguous association. Existing methods typically model motion and appearance cues separately, overlooking their spatio-temporal interplay and resulting in suboptimal tracking performance. In this work, we propose AMOT, which jointly exploits appearance and motion cues through two key components: an Appearance-Motion Consistency (AMC) matrix and a Motion-aware Track Continuation (MTC) module. Specifically, the AMC matrix computes bi-directional spatial consistency under the guidance of appearance features, enabling more reliable and context-aware identity association. The MTC module complements AMC by reactivating unmatched tracks through appearance-guided predictions that align with Kalman-based predictions, thereby reducing broken trajectories caused by missed detections. Extensive experiments on three UAV benchmarks, including VisDrone2019, UAVDT, and VT-MOT-UAV, demonstrate that our AMOT outperforms current state-of-the-art methods and generalizes well in a plug-and-play and training-free manner.

Recent advancements in omnimodal large language models (OmniLLMs) have significantly improved the comprehension of audio and video inputs. However, current evaluations primarily focus on short audio and video clips ranging from 10 seconds to 5 minutes, failing to reflect the demands of real-world applications, where videos typically run for tens of minutes. To address this critical gap, we introduce LVOmniBench, a new benchmark designed specifically for the cross-modal comprehension of long-form audio and video. This dataset comprises high-quality videos sourced from open platforms that feature rich audio-visual dynamics. Through rigorous manual selection and annotation, LVOmniBench comprises 275 videos, ranging in duration from 10 to 90 minutes, and 1,014 question-answer (QA) pairs. LVOmniBench aims to rigorously evaluate the capabilities of OmniLLMs across domains, including long-term memory, temporal localization, fine-grained understanding, and multimodal perception. Our extensive evaluation reveals that current OmniLLMs encounter significant challenges when processing extended audio-visual inputs. Open-source models generally achieve accuracies below 35

Spatio-temporal reasoning in vision-language models requires visual representations that preserve physical geometry rather than merely semantic appearance. Recent multimodal models incorporate geometric information through structural branches, 3D-aware supervision, reasoning-stage fusion, or long-horizon memory. While these approaches demonstrate the importance of geometry for spatial intelligence, they typically treat geometric cues as a shared signal across all visual tokens. We note that this overlooks a finer-grained challenge: different visual tokens require different geometric evidence depending on their spatial roles. To address this limitation, we introduce GeoWeaver, a pre-reasoning geometric grounding framework that treats geometry as a representational prerequisite for spatio-temporal reasoning. GeoWeaver constructs a multi-level geometry bank from a frozen geometry encoder and performs token-adaptive geometric evidence allocation, enabling each visual token to retrieve the most relevant geometric abstractions. The selected evidence is incorporated into visual tokens via a residual grounding operation prior to language modeling, yielding geometry-grounded representations for downstream reasoning. Extensive evaluations on spatial reasoning benchmarks demonstrate that GeoWeaver consistently enhances geometry-aware reasoning while retaining general multimodal capabilities. This indicates that geometric information yields the greatest benefit not as a late-fusion auxiliary signal but as a fundamental prerequisite that shapes the representational foundation on which large language models perform reasoning. All source code and models will be released at https://github.com/yahooo-m/GeoWeaver .

The fundamental challenge in scaling Video Large Language Models (Video LLMs) to long-form video lies in managing the explosion of visual-token context length. Existing strategies predominantly focus on "post-hoc" token reduction – reducing visual tokens after feature extraction to alleviate the LLM's computational overhead. While these methods effectively reduce the number of visual tokens, we observe that the primary latency bottleneck then shifts from the LLM to the expensive per-frame processing of the vision encoder. To address this, we introduce LiteFrame, a strong, yet highly efficient video encoder backbone for Video LLMs. To train LiteFrame, we propose Compressed Token Distillation (CTD), a novel training framework that teaches a compact student vision encoder to directly predict information-dense, spatio-temporally compressed representations produced by a large teacher vision model, effectively bypassing redundant computation. When coupled with further Language Model Adaptation (LMA), this approach results in a new latency-accuracy Pareto frontier – compared with InternVL3-8B, LiteFrame provides a 35

The rapid advancement of Artificial Intelligence Generated Content (AIGC) has revolutionized video generation, enabling systems ranging from proprietary pioneers like OpenAI's Sora, Google's Veo3, and Bytedance's Seedance to powerful open-source contenders like Wan and HunyuanVideo to synthesize temporally coherent and semantically rich videos. These advancements pave the way for building "world models" that simulate real-world dynamics, with applications spanning entertainment, education, and virtual reality. However, existing reviews on video generation often focus on narrow technical fields, e.g., Generative Adversarial Networks (GAN) and diffusion models, or specific tasks (e. g., video editing), lacking a comprehensive perspective on the field's evolution, especially regarding Auto-Regressive (AR) models and integration of multimodal information. To address these gaps, this survey firstly provides a systematic review of the development of video generation technology, tracing its evolution from early GANs to dominant diffusion models, and further to emerging AR-based and multimodal techniques. We conduct an in-depth analysis of the foundational principles, key advancements, and comparative strengths/limitations. Then, we explore emerging trends in multimodal video generation, emphasizing the integration of diverse data types to enhance contextual awareness. Finally, by bridging historical developments and contemporary innovations, this survey offers insights to guide future research in video generation and its applications, including virtual/augmented reality, personalized education, autonomous driving simulations, digital entertainment, and advanced world models, in this rapidly evolving field. For more details, please refer to the project at https://github.com/sjtuplayer/Awesome-Video-Foundations.

Natural language video localization (NLVL), a crucial task in video understanding, localizes target moments in videos corresponding to a language description. The point-supervised paradigm, which requires only a single annotated frame instead of complete temporal boundaries, offers a favorable balance between performance and annotation cost. However, the absence of full annotations impedes effective video-language alignment, thereby reducing prediction accuracy. To overcome this limitation, we propose COTEL (COllaborative Temporal consistEncy Learning), a framework that enhances alignment by leveraging the synergy between saliency detection and moment localization. COTEL integrates frame-level and segment-level consistency learning branches, which are trained to reinforce each other via a cross-consistency guidance scheme. Furthermore, we introduce a hierarchical contrastive alignment loss that combines intra-video positive alignment with inter-video negative mining to achieve comprehensive video-text matching. Extensive experiments on three widely used benchmarks demonstrate that our method performs favorably against state-of-the-art approaches. All source code will be released.

Inference-time compute has re-emerged as a practical way to improve LLM reasoning. Most test-time scaling (TTS) algorithms rely on autoregressive decoding, which is ill-suited to discrete diffusion language models (dLLMs) due to their parallel decoding over the entire sequence. As a result, developing effective and efficient TTS methods to unlock dLLMs' full generative potential remains an underexplored challenge. To address this, we propose Prism (Pruning, Remasking, and Integrated Self-verification Method), an efficient TTS framework for dLLMs that (i) performs Hierarchical Trajectory Search (HTS) which dynamically prunes and reallocates compute in an early-to-mid denoising window, (ii) introduces Local branching with partial remasking to explore diverse implementations while preserving high-confidence tokens, and (iii) replaces external verifiers with Self-Verified Feedback (SVF) obtained via self-evaluation prompts on intermediate completions. Across four mathematical reasoning and code generation benchmarks on three dLLMs, including LLaDA 8B Instruct, Dream 7B Instruct, and LLaDA 2.0-mini, our Prism achieves a favorable performance-efficiency trade-off, matching best-of-N performance with substantially fewer function evaluations (NFE). The code is released at https://github.com/viiika/Prism.

The increasing reliance on large-scale datasets imposes significant storage and computational burdens on training deep learning models. Dataset distillation methods, particularly those based on sample generation, aim to condense large original datasets into compact synthetic sets while preserving essential information. Existing subset synthesis approaches typically minimize a homogeneous distance, assigning uniform contributions from all real instances to the construction of each synthetic sample. We show that such equal allocation neglects instance-level relationships between real-synthetic pairs, leading to inadequate modeling of the geometric structural discrepancies between the distilled and original datasets. In this work, we reformulate homogeneous distance minimization as a bi-level optimization problem via a matching-and-approximating paradigm. In the matching stage, we employ an optimal transport matrix to dynamically allocate contributions from real instances. Building upon this transport-based allocation, we further introduce a difficulty-aware marginal reweighting mechanism to emphasize informative instances while preserving global geometric consistency. In the subsequent approximation stage, synthetic samples are refined according to the established allocation scheme to better approximate the real data distribution. This strategy enables a more faithful characterization of intricate geometric structures and improved handling of intra-class variations, thereby enhancing distillation fidelity. Extensive experiments across diverse architectures, modalities, and learning paradigms demonstrate that the proposed framework consistently improves performance, with gains observed in standard supervised, federated, continual, and multimodal learning settings.

In this paper, we ask whether vision foundation models construct representations that reflect the intrinsic properties of 3D Euclidean space. Unlike previous works that probe 3D awareness of vision features by regressing image-centric quantities such as depth or normals, we investigate the relation between the structure of the space of visual features and the group of Euclidean transformations SE(3). We propose a set of probes to evaluate this relation from both topological and geometric perspectives: a mutual neighborhood metric that measures the alignment between feature neighborhoods and spatial topology, and a Poincaré Adapter to test the linear accessibility of the geometry of camera motion from latent displacements in static scenes. We show that self-supervised vision models, which, in principle, have not been trained with direct 3D supervision or active agency, possess latent subspaces that are remarkably strongly correlated with three-dimensional Euclidean space, when probed correctly. Building on this insight we propose a new class of "Latent-Space Navigation" techniques that perform visual odometry and localization purely in the latent space, bypassing the need for explicit 3D reconstruction.