Recent progress in large language models (LLMs) has shown that reasoning improves when intermediate thoughts are externalized into explicit workspaces, such as chain-of-thought traces or tool-augmented reasoning. Yet, visual language models (VLMs) lack an analogous mechanism for spatial reasoning, limiting their ability to generate images that accurately reflect geometric relations, object identities, and compositional intent. We introduce the concept of a spatial scratchpad -- a 3D reasoning substrate that bridges linguistic intent and image synthesis. Given a text prompt, our framework parses subjects and background elements, instantiates them as editable 3D meshes, and employs agentic scene planning for placement, orientation, and viewpoint selection. The resulting 3D arrangement is rendered back into the image domain with identity-preserving cues, enabling the VLM to generate spatially consistent and visually coherent outputs. Unlike prior 2D layout-based methods, our approach supports intuitive 3D edits that propagate reliably into final images. Empirically, it achieves a 32% improvement in text alignment on GenAI-Bench, demonstrating the benefit of explicit 3D reasoning for precise, controllable image generation. Our results highlight a new paradigm for vision-language models that deliberate not only in language, but also in space. Code and visualizations at https://oindrilasaha.github.io/3DScratchpad/
论文检索
输入标题、作者或关键词，从 9,654 篇学术成果中精准定位
Concept-Guided Fine-Tuning: Steering ViTs away from Spurious Correlations to Improve Robustness
PDF ↗Vision Transformers (ViTs) often degrade under distribution shifts because they rely on spurious correlations, such as background cues, rather than semantically meaningful features. Existing regularization methods, typically relying on simple foreground-background masks, which fail to capture the fine-grained semantic concepts that define an object (e.g., "long beak" and "wings" for a "bird"). As a result, these methods provide limited robustness to distribution shifts. To address this limitation, we introduce a novel finetuning framework that steers model reasoning toward concept-level semantics. Our approach optimizes the model's internal relevance maps to align with spatially grounded concept masks. These masks are generated automatically, without manual annotation: class-relevant concepts are first proposed using an LLM-based, label-free method, and then segmented using a VLM. The finetuning objective aligns relevance with these concept regions while simultaneously suppressing focus on spurious background areas. Notably, this process requires only a minimal set of images and uses half of the dataset classes. Extensive experiments on five out-of-distribution benchmarks demonstrate that our method improves robustness across multiple ViT-based models. Furthermore, we show that the resulting relevance maps exhibit stronger alignment with semantic object parts, offering a scalable path toward more robust and interpretable vision models. Finally, we confirm that concept-guided masks provide more effective supervision for model robustness than conventional segmentation maps, supporting our central hypothesis.
Large vision-language models (VLMs) show strong multimodal understanding but still struggle with 3D spatial reasoning, such as distance estimation, size comparison, and cross-view consistency. Existing 3D-aware methods either depend on auxiliary 3D information or enhance RGB-only VLMs with geometry encoders through shallow feature fusion. We propose SpaceMind, a multimodal large language model trained on SpaceMind-700K for spatial reasoning from RGB inputs. The model adopts a dual-encoder architecture integrating VGGT as a spatial understanding encoder and InternViT as a 2D visual encoder. The key idea is to treat the camera representation as an active guiding modality rather than passive metadata. Specifically, SpaceMind introduces a lightweight Camera-Guided Modality Fusion module before the language model to replace shallow fusion. It applies camera-conditioned biasing to spatial tokens, assigns query-independent weights reflecting their geometric importance, and uses the camera embedding to gate the fused representation. Empirically, SpaceMind establishes new state-of-the-art results on VSI-Bench, SQA3D and SPBench, surpassing both open and proprietary systems on VSI-Bench and SPBench by large margins and achieving state-of-the-art performance on SQA3D. These results demonstrate that camera-guided modality fusion is an effective and practical inductive bias for equipping VLMs with genuinely spatially grounded intelligence. We will release code and model checkpoints to support future research.
Adversarial attacks have evolved from simply disrupting predictions on conventional task-specific models to the more complex goal of manipulating image semantics in Large Vision-Language Models (LVLMs). However, existing methods struggle with controllability and cannot precisely manipulate the semantics of specific concepts in an image. We attribute this limitation to semantic entanglement in the patch-token representations that adversarial attacks typically operate on: global context aggregated by self-attention in the vision encoder dominates patch features, making them unreliable for precise local semantic manipulation. Our systematic investigation reveals a key insight: value features, computed within the transformer attention block, provide much more precise handles for manipulation. We show that these value features suppress global-context channels, allowing them to retain high-entropy, disentangled local semantic information. Building on this discovery, we propose V-Attack, a novel method for precise local semantic attacks. V-Attack targets value features and introduces two core components: (1) a Self-Value Enhancement module to refine the intrinsic semantic richness of value features, and (2) a Text-Guided Value Manipulation module that uses text prompts to locate the source concept and optimize it toward a target concept. By bypassing entangled patch features, V-Attack achieves highly effective semantic control. Extensive experiments across diverse LVLMs, including LLaVA, InternVL, DeepSeek-VL, and GPT-4o, show that V-Attack improves attack success rate by an average of 36% over state-of-the-art methods, exposing critical vulnerabilities in modern vision-language understanding.
We present UniSH, a unified, feed-forward framework for joint metric-scale 3D scene and human reconstruction. A key challenge in this domain is the scarcity of large-scale, annotated real-world data, forcing a reliance on synthetic datasets. This reliance introduces a significant sim-to-real domain gap, leading to poor generalization, low-fidelity human geometry, and poor alignment on in-the-wild videos. To address this, we propose an innovative training paradigm that effectively leverages unlabeled in-the-wild data. Our framework bridges strong, disparate priors from scene reconstruction and HMR, and is trained with two core components: (1) a robust distillation strategy to refine human surface details by distilling high-frequency details from an expert depth model, and (2) a two-stage supervision scheme, which first learns coarse localization on synthetic data, then fine-tunes on real data by directly optimizing the geometric correspondence between the SMPL mesh and the human point cloud. This approach enables our feed-forward model to jointly recover high-fidelity scene geometry, human point clouds, camera parameters, and coherent, metric-scale SMPL bodies, all in a single forward pass. Extensive experiments demonstrate that our model achieves state-of-the-art performance on human-centric scene reconstruction and delivers highly competitive results on global human motion estimation, comparing favorably against both optimization-based frameworks and HMR-only methods. Project page: https://murphylmf.github.io/UniSH/.
Generative video-to-audio (V2A) models produce highly plausible soundtracks, but it remains unclear whether they capture the underlying physical processes. Existing evaluations emphasize perceptual realism and overlook physical correctness under controlled interventions. In this paper, we introduce FlatSounds, a benchmark that audits the physical reasoning of V2A models through: 1) controlled counterfactual pairs in which a single physical factor is varied, and 2) single-video pattern tests that probe internal consistency and directional trends. These settings test whether the generated audio correctly reflects specific physical properties and timings. Our evaluation of state-of-the-art models reveals a consistent trade-off: models rely more on text captions than the visual stream to infer physics and semantics. Captions generally improve physical and semantic accuracy, but paradoxically degrade temporal alignment. Our results highlight the need to move beyond audio quality toward learning physical processes directly from pixels. Finally, we find that our physics-based metrics correlate strongly with human preference tests on our own data.
While diffusion models have shown great potential in portrait generation, generating expressive, coherent, and controllable cinematic portrait videos remains a significant challenge. Existing intermediate signals for portrait generation, such as 2D landmarks and parametric models, have limited disentanglement capabilities and cannot express personalized details due to their sparse or low-rank representation. Therefore, existing methods based on these models struggle to accurately preserve subject identity and expressions, hindering the generation of highly expressive portrait videos. To overcome these limitations, we propose a high-fidelity personalized head representation that more effectively disentangles expression and identity. This representation captures both static, subject-specific global geometry and dynamic, expression-related details. Furthermore, we introduce an expression transfer module to achieve personalized transfer of head pose and expression details between different identities. We use this sophisticated and highly expressive head model as a conditional signal to train a diffusion transformer (DiT)-based generator to synthesize richly detailed portrait videos. Extensive experiments on self- and cross-reenactment tasks demonstrate that our method outperforms previous models in terms of identity preservation, expression accuracy, and temporal stability, particularly in capturing fine-grained details of complex motion.
Streaming video understanding often involves time-sensitive scenarios where models need to answer exactly when the supporting visual evidence appears: answering before the evidence reflects speculation, answering after it has passed reduces real-time utility. To capture this behavior, we introduce a readiness-aware formulation of streaming video understanding with the **Answer Readiness Score (ARS)**, a timing-aware objective with asymmetric early and late penalties. When combined with correctness, ARS defines an effective accuracy that measures not just whether a model is right, but whether it answers at the appropriate moment. Building on this formulation, we introduce **StreamReady**, a framework to unify temporal reasoning with on-time answering through a lightweight readiness mechanism that decides if sufficient evidence has been observed before responding. To evaluate this capability, we further introduce **ProReady-QA**, a benchmark with annotated answer evidence windows and proactive multi-turn questions across local and global contexts. StreamReady achieves superior performance on ProReady-QA, and consistently outperforms prior methods across eight additional streaming and offline long-video benchmarks, demonstrating robust and broadly generalizable video understanding capability.
Retrieval-augmented diffusion models (RAG-DMs) have been increasingly deployed across applications, reflecting a broader trend of adopting retrieval-augmented pipelines in AI agent systems and the emerging OpenClaw framework. Despite the success, their trustworthiness remains underexplored. Existing backdoor attacks focus on either manipulating the generation phase or the retrieval phase under the white-box setting, which suffer from knowledge conflicts between retrieved images and user prompts. To bridge this gap, we propose a novel red-teaming approach JOB, which is the first jointly optimized backdoor attack tailored to black-box RAG-DMs. Specifically, JOB poisons the knowledge base with a small number of target class images and learns a trigger through multi-objective optimization, steering retrieval toward poisoned images and aligning the generated outputs with the target class, while preserving benign performance. Experiments show that JOB effectively attacks black-box RAG-DMs, achieving high success rates and outperforming state-of-the-art baselines.
Towards Open Environments and Instructions: General Vision-Language Navigation via Fast-Slow Interactive Reasoning
PDF ↗Vision-Language Navigation (VLN) aims to enable agents to navigate to a target location based on language instructions. Traditional VLN often follows a close-set assumption, i.e., training and test data share the same style of the input images and instructions. However, the real world is open and filled with various unseen environments, posing enormous difficulties for close-set methods.To this end, we focus on the General Scene Adaptation (GSA-VLN) task, aiming to learn generalized navigation ability by introducing diverse environments and inconsistent intructions.Towards this task, when facing unseen environments and instructions, the challenge mainly lies in how to enable the agent to dynamically produce generalized strategies during the navigation process. Recent research indicates that by means of fast and slow cognition systems, human beings could generate stable policies, which strengthen their adaptation for open world. Inspired by this idea, we propose the slow4fast-VLN, establishing a dynamic interactive fast-slow reasoning framework.The fast-reasoning module, an end-to-end strategy network, outputs actions via real-time input. It accumulates execution records in a history repository to build memory.The slow-reasoning module analyze the memories generated by the fast-reasoning module. Through deep reflection, it extracts experiences that enhance the generalization ability of decision-making. These experiences are structurally stored and used to continuously optimize the fast-reasoning module. Unlike traditional methods that treat fast-slow reasoning as independent mechanisms, our framework enables fast-slow interaction. By leveraging the experiences from slow reasoning, it continually improves the accuracy and generalization ability of fast decisions. This interaction allows the system to continuously adapt and efficiently execute navigation tasks when facing unseen scenarios. Extensive experiments demonstrate the superiorities of our method.
We present Franca (pronounced Fran-ka): free one; the first fully open-source (data, code, weights) vision foundation model that matches and in many cases surpasses the performance of state-of-the-art proprietary models, e.g., DINOv2, CLIP, SigLIPv2, etc. Our approach is grounded in a transparent training pipeline inspired by Web-SSL and uses publicly available data: ImageNet-21K and a subset of ReLAION-2B. Beyond model release, we tackle critical limitations in self-supervised learning clustering methods. Existing approaches assign image features to large codebooks via clustering algorithms such as Sinkhorn-Knopp, but they often overlook the inherent ambiguity in cluster semantics. To address this, we introduce a multi-head clustering projector based on nested Matryoshka representations. This design progressively refines features into increasingly fine-grained clusters without increasing the model size, producing higher-quality dense representations. Additionally, we propose a novel positional disentanglement strategy that explicitly removes positional biases from dense representations.This leads to consistent gains on several downstream benchmarks, demonstrating the utility of cleaner feature spaces. Our contributions establish a new standard for transparent, high-performance vision models and open a path toward more reproducible and generalizable foundation models for the broader AI community.
Radiance field representations have recently been explored in the latent space of VAEs that are commonly used by diffusion models. This direction offers efficient rendering and seamless integration with diffusion-based pipelines. However, these methods face a fundamental limitation: The VAE latent space lacks multi-view consistency, leading to blurred textures and missing details during 3D reconstruction. Existing approaches attempt to address this by fine-tuning the VAE, at the cost of reconstruction quality, or by relying on pre-trained diffusion models to recover fine-grained details, at the risk of some hallucinations. We present Splatent, a diffusion-based enhancement framework designed to operate on top of 3D Gaussian Splatting (3DGS) in the latent space of VAEs. Our key insight departs from the conventional 3D-centric view: rather than reconstructing fine-grained details in 3D space, we recover them in 2D from input views through multi-view attention mechanisms. This approach preserves the reconstruction quality of pretrained VAEs while achieving faithful detail recovery.Evaluated across multiple benchmarks, Splatent establishes a new state-of-the-art for VAE latent radiance field reconstruction. We further demonstrate that integrating our method with existing feed-forward frameworks, consistently improves detail preservation, opening new possibilities for high-quality sparse-view 3D reconstruction. Code is available on our project page.
3D semantic occupancy prediction is crucial for autonomous driving, yet vision-only approaches suffer from weak geometric cues, and existing multi-modal frameworks often depend on dense voxel or BEV tensors that impose heavy computational cost. We present Gau-Occ, a multi-modal framework that models the scene as a compact collection of semantic 3D Gaussians, enabling geometry-guided fusion without dense volumetric processing. To enhance geometric completeness, a learned LiDAR Completion Diffuser (LCD) trained on real-world priors recovers missing structures from sparse LiDAR, and the completed points are encoded as semantic Gaussian anchors. To further integrate multi-view image semantics, we introduce Gaussian Anchor Fusion (GAF), a geometry-aligned aggregation module that performs anchor-guided 2D sampling, local neighborhood encoding, and cross-modal alignment. By constructing locally aggregated Gaussian descriptors that capture spatial consistency and semantic discriminability, GAF facilitates accurate feature association across modalities. Through anchor-driven refinement of Gaussian attributes, Occ-GS supports detailed 3D occupancy prediction. Extensive experiments across challenging benchmarks demonstrate that Occ-GS achieves state-of-the-art performance.
Despite achieving state-of-the-art generation quality, diffusion models are hindered by the substantial computational burden of their iterative sampling process. While feature caching techniques achieve effective acceleration at higher step counts (e.g., 50 steps), they exhibit critical limitations in the practical low-step regime of 20-30 steps. As the interval between steps increases, polynomial-based extrapolators like TaylorSeer suffer from error accumulation and trajectory drift. Meanwhile, conventional caching strategies often overlook the distinct dynamical properties of different denoising phases. To address these challenges, we propose Trajectory-Consistent Pade(TC-Pade) approximation, a feature prediction framework grounded in Pade approximation. By modeling feature evolution through rational functions, our approach captures asymptotic and transitional behaviors more accurately than Taylor-based methods. To enable stable and trajectory-consistent sampling under reduced step counts, TC-Pade incorporates (1) adaptive coefficient modulation that leverages historical cached residuals to detect subtle trajectory transitions, and (2) step-aware prediction strategies tailored to the distinct dynamics of early, mid, and late sampling stages. Extensive experiments on DiT-XL/2, FLUX.1-dev, and Wan2.1 across both image and video generation demonstrate the effectiveness of TC-Pade. For instance, TC-Pade achieves 2.88xacceleration on FLUX.1-dev and 1.72xon Wan2.1 while maintaining high quality across FID, CLIP, Aesthetic, and VBench-2.0 metrics, substantially outperforming existing feature caching methods.
Feature matching is a critical task in geometric perception, yet existing methods often struggle under domain shifts and illumination changes due to reliance on visual-only learning and expensive 3D supervision. In this paper, we present TextFM, the first language-guided feature matching framework that incorporates domain-invariant semantic information from vision-language models (VLMs). Built upon a detector-free architecture, TextFM leverages textual embeddings as instance-level queries to provide global semantic context during coarse-level matching, enhancing robustness in challenging scenarios such as textureless surfaces and cross-domain shifts. Additionally, we integrate illumination-invariant physical priors and apply Low-Rank Adaptation (LoRA) to efficiently fine-tune Vision Foundation Models (VFMs) for more robust visual feature extraction. Extensive experiments on outdoor and indoor datasets show that our method outperforms other state-of-the-art methods. In addition, we contribute a synthetic day-night matching benchmark for rigorous evaluation under extreme lighting conditions. Together, our method and dataset establish a strong foundation for robust and generalizable feature matching under real-world constraints.
Diffusion Forcing Planner: History-Annealed Planning with Time-Dependent Guidance for Autonomous Driving
PDF ↗Learning-based motion planners, despite recent progress, often suffer from temporal inconsistency. Small perturbations across frames can accumulate into unstable trajectories, degrading comfort and safety in closed-loop driving. Several methods attempt to inject history as a static conditioning signal to stabilize outputs, only to induce the planner to copy historical patterns instead of adapting to environment contexts. To address this limitation, we propose Diffusion Forcing Planner (DFP), a diffusion-based planning framework driven by history-guided control. Specifically, DFP decomposes the full trajectory into history, current and future segments, and assign independent noise levels to each segment. The model jointly denoises the historical and the future segments, enforcing a heterogeneous joint diffusion process. At inference, classifier-free guidance (CFG) is applied to steer future sampling using annealed history in a controllable manner. Closed-loop evaluation and comprehensive ablations on nuPlan show that DFP achieves competitive performance while producing continuous, stable, and controllable motion plans in complex driving scenarios.
From Feature Learning to Spectral Basis Learning: A Unifying and Flexible Framework for Efficient and Robust Shape Matching
PDF ↗Shape matching is a fundamental task in computer graphics and vision, with deep functional maps becoming a prominent paradigm. However, existing methods primarily focus on learning informative feature representations by constraining pointwise and functional maps, while neglecting the optimization of the spectral basis--a critical component of the functional map pipeline. This oversight often leads to suboptimal matching results. Furthermore, many current approaches rely on conventional, time-consuming functional map solvers, incurring significant computational overhead. To bridge these gaps, we introduce Advanced Functional Maps, a framework that generalizes standard functional maps by replacing fixed basis functions with learnable ones, supported by rigorous theoretical guarantees. Specifically, the spectral basis is optimized through a set of learned inhibition functions. Building on this, we propose the first unsupervised spectral basis learning method for robust non-rigid 3D shape matching, enabling the joint, end-to-end optimization of feature extraction and basis functions. Our approach incorporates a novel heat diffusion module and an unsupervised loss function, alongside a streamlined architecture that bypasses expensive solvers and auxiliary losses. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art feature-learning approaches, particularly in challenging non-isometric and topological noise scenarios, while maintaining high efficiency. Finally, we reveal that optimizing basis functions is equivalent to spectral convolution, where inhibition functions act as filters. This insight enables enhanced representations inspired by spectral graph networks, opening new avenues for future research. Our code is available at https://github.com/LuoFeifan77/Unsupervised-Spectral-Basis-Learning.
Perceiving and reconstructing 3D scene geometry from visual inputs is crucial for autonomous driving. However, there still lacks a driving-targeted dense geometry perception model that can adapt to different scenarios and camera configurations. To bridge this gap, we propose a Driving Visual Geometry Transformer (DVGT), which reconstructs a global dense 3D point map from a sequence of unposed multi-view visual inputs. We first extract visual features for each image using a DINO backbone, and employ alternating intra-view local attention, cross-view spatial attention, and cross-frame temporal attention to infer geometric relations across images. We then use multiple heads to decode a global point map in the ego coordinate of the first frame and the ego poses for each frame. Unlike conventional methods that rely on precise camera parameters, DVGT is free of explicit 3D geometric priors, enabling flexible processing of arbitrary camera configurations. DVGT directly predicts metric-scaled geometry from image sequences, eliminating the need for post-alignment with external sensors. Trained on a large mixture of driving datasets including nuScenes, OpenScene, Waymo, KITTI, and DDAD, DVGT significantly outperforms existing models on various scenarios.
Graphical User Interface (GUI) Agents, benefiting from recent advances in multimodal large language models (MLLM), have achieved significant development. However, due to the frequent updates of GUI applications, adapting to new tasks without forgetting old tasks in GUI continual learning remains an open problem. In this work, we reveal that while Supervised Fine-Tuning (SFT) facilitates fast adaptation, it often triggers knowledge overwriting, whereas Reinforcement Learning (RL) demonstrates an inherent resilience that shields prior interaction logic from erasure. Based on this insight, we propose a Continual GUI Learning (CGL) framework that dynamically balances adaptation efficiency and skill retention by enhancing the synergy between SFT and RL. Specifically, we introduce an SFT proportion adjustment mechanism guided by policy entropy to dynamically control the weight allocation between the SFT and RL training phases. To resolve explicit gradient interference, we further develop a specialized gradient surgery strategy. By projecting exploratory SFT gradients onto GRPO-based anchor gradients, our method explicitly clips the components of SFT gradients that conflict with GRPO. On top of that, we establish an AndroidControl-CL benchmark, which divides GUI applications into distinct task groups to effectively simulate and evaluate the performance of continual GUI learning. Experimental results demonstrate the effectiveness of our proposed CGL framework across continual learning scenarios. The benchmark, code, and model will be made publicly available.
Recent advances in CLIP-based continual learning have shown the potential of leveraging pre-trained vision-language models for sequential tasks. However, existing methods overlook a key problem we call Asymmetric Drift. In unimodal CLIP-based continual learning, the visual branch undergoes stronger adaptation because the visual distribution shifts significantly, whereas the text branch remains relatively stable due to the low variance of textual prompts. This imbalance increases the modality distance and degrades cross-modal alignment over time. To address this issue, we propose CCA-CL, a framework that accumulates visual-textual covariance statistics across tasks and solves Canonical Correlation Analysis to compute a shared subspace. In this subspace, the distance between visual and textual features is minimized, enabling better alignment without modifying CLIP parameters. This also makes our method naturally compatible with exemplar-free CL settings. To further capture nonlinear relationships that linear Canonical Correlation Analysis is hard to model, we introduce Random Fourier Projection as an extension. Experimental results demonstrate that CCA-CL effectively mitigates the asymmetric drift problem and achieves state-of-the-art performance on several benchmarks.