Frozen Contrastive Language-Image Pre-Training Visual Encoder

Prompt learning adapts vision-language models, such as CLIP, by adjusting a small set of context tokens. However, under few-shot supervision, even moderate label noise can disrupt prompt optimization. To address this issue, we propose TecoPrompt, a closed-loop robust prompt-learning framework that revisits optimal transport (OT) pseudo-labeling from a temporal perspective. TecoPrompt employs an entropic OT plan in the CLIP semantic space to obtain globally consistent label candidates. It verifies the reliability of these candidates by examining trajectory stability: a noisy label is only rewritten if the OT candidate remains unchanged within a K-epoch temporal stability window and passes a confidence gate based on Exponential Moving Average (EMA). This approach helps reduce confirmation bias. The rewritten labels are then integrated back into prompt training using a tri-group objective that includes three loss functions aligned with clean, mid, and noisy subsets. Experiments on seven datasets with synthetic symmetric and asymmetric noise, as well as Food101N, demonstrate significant performance improvements. For example, on the OxfordPets dataset, with 50% asymmetric noise, TecoPrompt achieves an accuracy of 0.843, up from 0.775.

Generative models trained on a single image often struggle to balance global structural integrity and local diversity. Existing single-image generation methods commonly rely on random noise to drive the generation process and lack explicit global structural constraints, making the generated results prone to spatial structural misalignment when structural variations occur. To address the issue, Feature Rearrangement in Pre-Shape Space for Single-Image Generation (FRPSS) is proposed in this paper. The core of FRPSS is the Manifold Structural Rearrangement with Feature Augmentation on Geodesic Surface (MSR-FAGS) module. MSR-FAGS replaces the randomly initialized features of the low-scale generator with rearranged Pre-Shape features and uses the features to guide image generation at subsequent scales, thereby reducing the risk of structural misalignment. To support downstream tasks such as stylization, a Scale-adaptive Sliding-window Patch Extraction (SSPE) strategy is further designed, and a directional Contrastive Language-Image Pre-training supervision module with SSPE (CLIP-SSPE) is constructed. Qualitative and quantitative experiments demonstrate that FRPSS achieves the best Single Image Fréchet Inception Distance (SIFID) scores on all three datasets while maintaining competitive Learned Perceptual Image Patch Similarity (LPIPS). Further qualitative experiments verify the effectiveness of FRPSS across multiple downstream tasks with the CLIP-SSPE module.

Training-free collaborative pipelines that integrate Vision Foundation Models such as CLIP, SAM, and DINO achieve strong open-vocabulary dense prediction and are increasingly deployed in safety-critical applications. The security of these systems is commonly assumed to follow from the robustness of their individual models. We challenge this assumption. We identify a vulnerability shared by every collaborative pipeline: each model consumes the intermediate output of another without verifying semantic consistency, an unverified premise that we term the semantic-spatial alignment dependency. Existing adversarial attacks target a single model and overlook this premise, leaving the inter-model interface entirely unguarded. We propose CrACK (Cross-model Adversarial Consistency attack), an inference-time attack that exploits this interface without modifying any input pixel, model weight, or training data. CrACK operates in two stages: Adversarial Affinity Contradiction Injection corrupts the cross-modal affinity matrix by inverting SAM encoder features under the guidance of CLIP patch-level semantics, and Semantic Interface Poisoning steers the prediction through a max-distance label permutation derived from CLIP text embeddings. Experiments on four collaborative pipelines across eight benchmarks show that CrACK causes catastrophic degradation while every individual model continues to produce its unchanged standalone output, rendering per-model defenses structurally blind. The corruption further cascades into large vision-language model reasoning, driving models such as LLaVA to produce erroneous responses from visually intact inputs. Our results show that the security of a collaborative AI system cannot be reduced to the robustness of its components, and that inter-model feature interfaces must be treated as first-class security boundaries.

Reducing the modality gap between image and text representations in CLIP is widely expected to improve cross-modal alignment and downstream performance. However, a smaller average image-text gap does not necessarily lead to consistent accuracy gains. We analyze this mismatch from the perspective of the decision structure in zero-shot classification, i.e. selecting the most similar class-text prototype for an input image. Zero-shot accuracy depends not only on average image--text alignment, but also on class-wise decision margins. Using Linear correction as an analytically tractable case, we show that modality gap correction can alter the relative decision structure among classes and cause predictions to concentrate on a small subset of classes. We refer to this output-space failure mode as prediction-level hubness. Furthermore, experiments across multiple datasets show that accuracy degradation under gap correction is consistently associated with increased prediction concentration, both for Linear correction and for learning-based correction methods. This provides a systematic explanation of why modality gap reduction does not consistently improve CLIP zero-shot accuracy from the perspective of downstream decision structure. Our results suggest that gap correction should be evaluated not only by average alignment, but also by its impact on downstream prediction structure.

Generative models can produce images nearly indistinguishable from real data, yet rigorous and interpretable evaluation remains challenging. Conventional metrics such as FID provide only scalar scores with limited diagnostic insight. Widely adopted CLIP-based metrics enable semantic evaluation beyond simple training class labels, but inherit limitations from CLIP's training paradigm that restrict attribute-wise analysis. We propose RA-CLIPScore, a novel metric that mitigates these issues and extends CLIP-based evaluation to spatial distribution alignment, measuring whether generated objects adhere to the positional priors found in the training data. RA-CLIPScore introduces dual prompts to decouple competing attributes and leverages local patch tokens to capture fine-grained regional semantics. We evaluate image generative models on their ability to match both attribute and spatial distributions of the training data. Extensive experiments show that RA-CLIPScore provides more robust and interpretable evaluations than prior methods, particularly under distribution misalignment or partially irrelevant textual attributes. We further demonstrate how it reveals spatial biases in generative models. User evaluations confirm that Regional Single Attribute Divergence based on our RA-CLIPScore aligns more closely with human perception of visual diversity than existing semantic metrics.

Training-free open-vocabulary segmentation remains limited by a missing inference abstraction. Frozen vision-language features are produced at patch level, yet dense prediction requires a unit that simultaneously governs feature interaction, spatial support, contextual recovery, and retrieval-based correction. We present SCI-CLIP, a segment-centric inference framework built around the principle that the same region abstraction should organize all stages of dense open-vocabulary prediction. SCI-CLIP first induces a region-consistent interaction graph over frozen visual tokens, then reconstructs dense features by propagating values over this graph, augmenting them with selective cross-window support only where local evidence is insufficient. The same segment abstraction is subsequently used to construct and query an offline reference memory, aligning exemplar retrieval with the units on which prediction is made. SCI-CLIP turns frozen CLIP-style features into spatially coherent, context-aware, and retrieval-compatible dense predictions without any training. SCI-CLIP consistently improves the structural quality of dense predictions, the robustness of contextual reasoning, and the alignment of exemplar-based correction, yielding stronger open-vocabulary segmentation across eight benchmarks. Project code is available at: https://github.com/mzamini92/SCICLIP.

While text-to-image diffusion models achieve impressive visual quality, they frequently struggle to maintain precise alignment with complex compositional prompts. An effective strategy is to improve the inference process of diffusion models, thereby better leveraging their pretrained priors to address misalignment. Existing training-free methods can be divided into two categories. The first category focuses on improving the randomly sampled initial noise, either performing costly search over noise pools or manipulating sampled noise without ensuring reliable semantic injection. The second category focuses on improving the denoising trajectory, lacking explicit mechanisms to timely diagnose and correct semantic errors. we propose \textbf{AnchorSteer}, a training-free framework that exerts fine-grained control over \textbf{both initialization} and \textbf{the denoising trajectory}. AnchorSteer consists of two synergistic components: \textbf{Semantic Anchoring} replaces uninformative Gaussian noise with text-aligned initializations via CLIP-based prior extraction and a novel Latent-Prior Score Distillation Sampling (LP-SDS) objective. Specifically, LP-SDS distills CLIP visual priors into the knowledge distribution of diffusion models, mitigating the domain gap between CLIP-based priors and diffusion-based priors. \textbf{Reflective Steering} transforms passive denoising with an active Think--Erase--Retouch loop that enables mid-generation self-correction. It leverages VLM-based diagnosis to detect semantic deviations and performs targeted latent refinement to suppress erroneous content and recover missing attributes. Extensive experiments on GenEval and T2I-CompBench++ demonstrate that AnchorSteer consistently outperforms existing baselines in text--image alignment while preserving high visual quality.

Dense vision-language understanding, including object localization, region recognition, and open-vocabulary semantic segmentation, requires associating language concepts with spatially grounded visual regions. CLIP provides a strong foundation for these tasks by learning a shared image-text embedding space from large-scale contrastive pre-training. However, its image-level objective aligns text with a CLS-derived global representation, leaving local vision-language correspondence only indirectly constrained. Existing methods either introduce additional supervision, external models, or task-specific adaptation, while training-free approaches mainly recover dense responses from existing patch features without examining where local semantics become most accessible within CLIP. We introduce TraceCLIP, a training-free framework that recovers latent patch-level semantic evidence by isolating the patch-specific terms written into the CLS attention output. TraceCLIP further converts contribution-derived semantic responses into a semantic-geodesic topology gate that calibrates final-layer patch affinity for dense feature reconstruction. Diagnostic experiments show that these contribution features exhibit strong local semantic discrimination and text-conditioned spatial alignment. On eight zero-shot semantic segmentation benchmarks, TraceCLIP achieves gains of 1.3 to 4.5 points in average mIoU over the strongest prior training-free methods across both backbones and background settings, without additional training, external vision foundation models, or region-level supervision. More broadly, these findings suggest that spatially localized semantics may remain accessible within the internal construction of globally aligned representations.

Contrastive vision-language models such as CLIP map semantically opposite phrases (e.g., "a dog" vs. "not a dog") to nearly identical embeddings, rendering them insensitive to negation. We attribute this failure to a phenomenon we call Representational Collapse: by tracking compositional divergence and visual alignment across the CLIP text encoder, we show that middle layers build compositional syntax, but the final layers collapse this structure as visual alignment rises, producing a syntax-blind final representation. To recover the lost negation signal without altering pretrained weights, we propose PeakPatch, a lightweight post-hoc correction system that intercepts the encoder at its compositional peak. An Embedding Correction Network (ECN) uses cross-attention to extract a negation-specific signal from the peak layer, anchored to a stable baseline, and predicts a deviation vector that re-injects the lost syntax into the final-layer embedding space. A complementary Score Correction Network (SCN) predicts bounded scalar score offsets for discriminative tasks. Both modules are trained jointly end-to-end while all CLIP parameters remain frozen, adding only 5.2M parameters (3.5% of the backbone) and preserving the standard cosine similarity interface. On NegBench, PeakPatch achieves 74.3% on COCO MCQ (+35.1 over CLIP, +17.8 over the best encoder fine-tuning method) and 65.5% on VOC MCQ, while outperforming all fine-tuning baselines on fully out-of-distribution negation retrieval despite training only 3.5% of the parameters. The corrected embeddings also transfer to text-to-image generation (+18.4 negation score) and generalize across ViT-B/32, ViT-L/14, and SigLIP backbones. Project URL: https://stevencylu.github.io/PeakPatch/.

Image geolocation aims to infer the geographic origin of an image from visual content alone. However, this task remains challenging in regions where countries share similar urban, roadside, architectural, and environmental characteristics. Many existing geolocation models focus on coordinate level prediction or classification performance while providing limited insight into how visual evidence contributes to location predictions. This study presents an explainable country level image geolocation pipeline for 11 ASEAN countries. First, we collected 4,850 images from GeoGuessr style sources, Google Images, and additional street level imagery. We then evaluated three approaches on this dataset: CLIP zero shot classification, a LightGBM classifier, and an MLP classifier. The MLP achieved the best test performance, attaining an accuracy and F1 score of 85.91%. For explainability, predictions generated by the MLP classifier were analyzed post hoc using CLIP attention rollout, YOLO26 object detection on the original images, and Energy Based Pointing Game (EBPG) overlap metrics. Object level analysis indicates that frequently detected objects are not necessarily associated with the highest attention density, suggesting that object frequency and attention based visual evidence capture different aspects of a scene. These results demonstrate that the proposed model can support accurate regional image geolocation while enabling object level inspection of the visual cues underlying its predictions.

Open-vocabulary dense perception (OVDP) aims to localize objects unseen during training by leveraging textual knowledge. Despite the remarkable progress of recent CLIP-based approaches, we identify a critical limitation: synonym-induced grounding inconsistency, where semantically equivalent expressions yield disparate spatial attention patterns. This inconsistency undermines the robustness and performance of existing methods in real-world OVDP applications. To address this issue, we propose SynCLIP, a Synonym-Coherent Language-Image Pretraining framework that enhances synonym-robust grounding for OVDP. SynCLIP introduces a Semantic-consistent Spatial Attention alignment (SSA) module to enhance spatial attention consistency by minimizing discrepancies between attention maps of original and synonymous expressions. Furthermore, a Spatial Attention Refinement (SAR) module selectively strengthens the most semantically relevant spatial regions within aligned maps for more precise and stable grounding. To support synonym-coherent pretraining, we also construct a Synonym-Enriched Visual Corpus (SEViC), which augments each category with multiple synonyms and textual definitions. Extensive experiments on multiple benchmarks demonstrate that SynCLIP substantially improves grounding consistency under diverse linguistic variants and achieves state-of-the-art performance among CLIP-based OVDP methods. Code is available at https://github.com/Justlovesmile/SynCLIP.

While the growing availability of image data has driven significant advances, labeling datasets remains costly and time-consuming. Therefore, semi-supervised approaches such as Graph Convolutional Networks (GCNs), which learn from both labeled and unlabeled data, have emerged as a promising solution. One of the primary challenges in applying GCNs to image classification is graph construction, since, unlike in citation networks or similar domains, images typically do not come with a predefined structural representation. For visual data, most studies construct graphs based on the similarity between feature vectors from pretrained deep learning backbones, typically by employing kNN or reciprocal kNN algorithms. Although Large Language Models (LLMs) have shown remarkable capability in capturing high-level semantics, their integration with GCNs for image classification remains underexplored. Aiming to fill this gap, our approach uses a Vision Language Model (VLM) to generate textual image descriptions, which are then processed by an LLM to estimate semantic similarity scores between connected images. These scores guide the pruning of edges in kNN and reciprocal kNN graphs, filtering out semantically irrelevant neighbors. Experimental results reveal that leveraging LLMs for graph refinement can improve classification accuracy, particularly for kNN graphs and some backbones. The source code is publicly available at http://gcnllm.lucasvalem.com.

3D Gaussian Splatting provides an explicit representation that jointly models geometry and appearance, serving as a scalable foundation for 3D representation learning. Existing pre-training methods for Gaussian representations, such as masked Gaussian reconstruction, primarily capture local structures but offer limited semantic supervision. In this paper, we propose GaussFusion, a multimodal pre-training framework for 3D Gaussian representations. GaussFusion integrates image and text supervision into masked Gaussian modeling through cross-modal semantic alignment, enabling the Gaussian encoder to learn both visual and language-level semantic information during pre-training. To better adapt masked modeling to the non-uniform distribution of Gaussian primitives, we further propose Gaussian Salience-guided Multi-scale Hole Masking (GSHM). GSHM constructs spatially continuous masked regions based on Gaussian salience. By applying hole masks at multiple scales, GSHM encourages the encoder to capture both fine-grained local patterns and broader structural dependencies. Extensive experiments on downstream tasks demonstrate that GaussFusion improves the transferability of Gaussian representations. Notably, GaussFusion outperforms Gaussian-MAE on ModelNet40 and ScanObjectNN (PB-T50-RS) by 0.61% and 3.85%, respectively.

Brain decoding aims to uncover neural mechanisms by inferring stimulus-related representations from brain signals. In fMRI studies, this is typically achieved by mapping fMRI responses to the latent representations of computational models. Recently, CLIP has become a popular choice for brain decoding due to its rich vision--language embedding space. However, aligning fMRI signals with CLIP representations remains challenging. As CLIP is not explicitly optimized for neural alignment, its representations may capture statistically predictive cues that are only partially reflected in brain activity, limiting decoding performance. In this paper, we investigate whether adversarially robust representations improve neural decoding with CLIP. Adversarial training suppresses non-robust features and promotes more stable, perceptually structured representations, which may better align with brain activity. We evaluate this by fixing the fMRI decoder and varying only the target representation (standard CLIP vs. robust variants) on fMRI-image retrieval and zero-shot classification tasks across NSD and GOD datasets. Empirical results show that this simple change consistently improves task performance and yields stronger alignment across multiple metrics. Attribution analysis further reveals consistently low agreement between standard CLIP and its robust variants, suggesting that adversarial robustness reorganizes feature importance in the visual representation. These findings suggest that the choice of target representation influences neural decoding performance and that adversarial robustness may serve as a useful criterion for brain decoding.

Models trained via Contrastive Language-Image Pretraining (CLIP) serve as the foundational vision encoders for most modern Large Vision Language Models (LVLMs). Despite their widespread adoption, CLIP models exhibit a critical yet underexplored failure mode: irrelevant text appearing within images confounds visual representations, biasing them toward lexical meaning rather than true visual semantics. This robustness issue, commonly described as a Typographic Attack (TA), exposes a vulnerability that poses a significant risk to safety-critical applications such as autonomous driving. To achieve interpretable and effective robustness against TA, we propose a novel, training-free mechanistic interpretability method. Our method provides sampling-based interpretations of hidden state representations and quantitatively attributes semantic versus lexical focus to individual attention heads. Through probabilistic analysis and circuit mining, we isolate specific Vision Transformer (ViT) components that disproportionately encode lexical information, thereby identifying the mechanistic source of TA. We further show that simple interventions applied directly to the identified circuits, without any additional training, can substantially improve robustness against Typographic Attacks in object classification. These interventions, such as selective adjustment of attention weights, also outperform both supervised and training-free defense methods. Our experiments demonstrate that applying the proposed intervention to the vision encoders of several state-of-the-art LVLMs yields substantial gains in Visual Question Answering accuracy under Typographic Attack interference on RIO-Bench. These results confirm both the efficacy and the generalizability of our mechanistic approach. Code is released at https://github.com/Liu-524/SamplingTAR.

Recent advances in instruction-based image editing have enabled models to perform complex visual edits from natural language instructions. However, in product-centric scenarios where preserving product features, branding, and textual elements are critical, current open and closed source models often struggle to maintain this fine-grained object identity. This issue is further compounded by the lack of datasets for instruction-based product image editing with text fidelity constraints, leaving it largely treated as an implicit capability of instruction-based image editing models. In this work, we introduce the ProductConsistency dataset which is designed to improve product-centric image editing. Our approach includes a supervised fine-tuning (SFT) dataset of 87k samples for product editing, a reinforcement learning (RL) dataset with 869 unique product images, and a new benchmark dataset, the ProductConsistency Benchmark, to allow rigorous and standardized evaluation of editing models. To guide RL training, we propose a Cyclic Consistency reward that enforces semantic preservation of product identity by using caption similarity between the original product description and captions generated from the edited image. We fine-tune both Qwen-Image-Edit-2511 and Flux.1-Kontext-dev using our dataset and demonstrate consistent improvements over baseline models in OCR and Perceptual metrics, and MLLM-based evaluations as well, indicating stronger product consistency, text rendering, and overall visual quality; with the Qwen-Image-Edit-2511 model achieving a 5x reduction in the character error rate. The code and pipeline is available at https://anonymous.4open.science/r/ProductConsistency-6FCC/README.md

Vision-language models like CLIP can provide rich semantic priors for open-vocabulary object detection. However, jointly integrating both textual and visual knowledge into detection architectures remains challenging. In this paper, we propose VL-DINO, an open-vocabulary detector that enhances DINO through more effective exploitation of CLIP's vision-language knowledge. Specifically, a Query-guided Positive Sample Construction (QPSC) module is first developed to construct additional high-quality positive samples, enabling the vanilla DINO framework to better accommodate mixed training across heterogeneous data sources while providing more vision-language alignment signals, thereby incorporating richer textual knowledge during training. A Visual Semantic Encoder (VSE) module is then introduced to distill CLIP visual knowledge into backbone-extracted features, producing fused features for subsequent encoder refinement. Based on the fused features, an Object-Region Semantic Alignment (ORSA) module extracts object-centric region features and aligns them with the corresponding textual embeddings, further incorporating textual cues. In the zero-shot setting, VL-DINO-T and VL-DINO-L achieve 36.3 and 38.1 AP on the LVIS benchmark, respectively, consistently outperforming prior advanced approaches. Extensive experiments demonstrate the effectiveness and competitive performance of the proposed design.

Semantic image segmentation assigns a predefined category label to each pixel, has achieved significant progress lately. Open-Vocabulary Segmentation (OVS) extends the segmentation task from a fixed set to an open set, enabling the identification and segmentation of novel concepts based on arbitrary text inputs, such as category names or descriptions. In this paper, we propose a novel Semantic Calibration Network (SCN) for open-vocabulary semantic segmentation. Different from prior approaches that focus on feature aggregation or simple fine-tuning of pre-trained models, SCN refines the mask classification process by explicitly modeling the semantic correlations between classes, aiming to enhance the model's discriminative power while effectively preserving the generalization abilities of the pre-trained CLIP model. Specifically, SCN comprises two core components: Class Disambiguation (CD) and Logits Fusion (LF). First, a cross-attention mechanism is utilized to transform the text embeddings into visually aware pseudo-text embeddings, in order to derive an enhanced similarity score that complements the original mask-text similarity score. Subsequently, the Class Disambiguation module captures implicit inter-class dependencies through a residual architecture to effectively resolve semantic ambiguities. Finally, the Logits Fusion module dynamically integrates multifaceted semantic evidence to ensure that the model achieves a robust semantic consensus while maintaining CLIP's inherent generalization capability. Comprehensive experimental results on mainstream benchmarks demonstrate that the proposed method achieves significant performance improvements compared to state-of-the-art algorithms.

Few-shot cross-category 3D anomaly detection aims to determine whether an unknown point cloud belongs to a target normal category using only a few normal references. Existing training-based methods usually require category-wise optimization, while recent training-free methods based on multi-view CLIP visual features mainly rely on visual similarity and may be confused by geometrically similar categories. In this paper, we propose VT-3DAD, a training-free framework for cross-category 3D anomaly detection via Visual-Text Normal Space Alignment. Given few-shot normal references and a test point cloud, VT-3DAD first generates realistic multi-view depth maps and extracts view-wise features using a frozen CLIP visual encoder. The visual branch measures reference-test deviation in the multi-view feature space. In parallel, depth-aware and 3D-aware prompts are encoded by the frozen CLIP text encoder to construct textual normal anchors, which provide semantic normality constraints for the target category. The final anomaly score is obtained by fusing visual deviation from normal references and semantic deviation from the textual normal space. Experiments on the ShapeNetPart dataset demonstrate that VT-3DAD achieves state-of-the-art performance. In particular, VT-3DAD improves the one-shot average AUC-ROC from 92.49% to 94.80% compared with the visual-only baseline, while also reducing the average standard deviation from 5.64 to 3.41.

Humans easily determine which color belongs to which shape in multi-object scenes, an ability known as concept binding. Vision-language embedding models such as CLIP struggle with binding: they recognize individual concepts but fail to represent which concepts form which objects. Although CLIP behaves like a bag-of-concepts model in cross-modal retrieval, object information is recoverable from its image and text embeddings separately. We study this tension through the binding function, which maps concepts to scene embeddings. We find that scene embeddings decompose additively into object representations, explaining why uni-modal probes can recover object information. However, CLIP's binding function is high-complexity, which likely prevents the image and text encoders from learning a shared binding mechanism that generalizes to unseen concept combinations. We then ask whether this limitation is fundamental. We show that it is not. In controlled transformer models trained from scratch, binding generalization emerges with sufficient data coverage. These models learn low-complexity binding functions characterized by multiplicative interactions between concepts, enabling systematic generalization. Code is publicly available at https://github.com/oshapio/binding-concepts-complexity.

Vision-Language Models (VLMs) such as CLIP demonstrate strong zero-shot generalization, but their performance significantly degrades in cross-domain scenarios with scarce target-domain training data (Cross-Domain Few-Shot Learning, CDFSL). In this paper, we focus on the target-domain few-shot finetuning in the CLIP-based CDFSL task. Prevailing finetuning paradigms uniformly align all image patch tokens with their corresponding textual embeddings. However, we find a counterintuitive phenomenon: actively pushing away certain low-similarity image tokens, termed "tail tokens", from their textual embeddings consistently improves target-domain performance. We delve into this phenomenon and provide a novel interpretation: under great domain shifts and scarce training data, the model can hardly extract semantic information from visual inputs; therefore, the common belief of alignment is valid only for tokens already containing sufficient semantic information; for tail tokens, forcing the alignment would lead to excessive overfitting to the scarce training, while breaking the alignment is more useful. Motivated by this, we propose Adaptive Tail-Head Alignment (ATHA), a novel fine-tuning strategy for CLIP that transforms the conventional uniform alignment paradigm to an adaptive alignment paradigm, with both alignment strengthening and weakening. Extensive experiments on four challenging CDFSL benchmarks validate our state-of-the-art performance. Our code is available at https://github.com/shuaiyi308/ATHA.

Contrastively trained vision-language models such as CLIP provide strong zero-shot transfer by aligning images and text in a shared embedding space. However, adapting these models to downstream tasks without degrading their open-vocabulary generalization remains challenging. Existing parameter-efficient adaptation methods typically improve task specialization through learned prompts, adapters, or multimodal transformations, where adaptation capacity is primarily expressed through additional trainable parameters. Inspired by recent latent reasoning methods in language models, we investigate a complementary perspective: can adaptation emerge from iterative reasoning on latent representations rather than from increasing parameter count alone? We introduce PERL (Parameter-Efficient Reasoning in CLIP Latent Space), a lightweight adaptation framework that augments a frozen CLIP model with a compact shared reasoning module applied recurrently across refinement steps. At each step, PERL generates a latent reasoning token conditioned on the current representation and injects it into an intermediate encoder layer, progressively refining higher-level semantic representations while preserving CLIP's pretrained multimodal structure. Across 15 benchmarks spanning base-to-novel generalization, cross-dataset transfer, and out-of-distribution ImageNet variants, PERL achieves the best parameter-performance trade-off among the compared methods under a fast-adaptation few-shot setting, combining strong novel-class accuracy and competitive transfer performance with only about 6K trainable parameters, up to 817x fewer than the largest compared approach. Overall, our results suggest that iterative latent reasoning provides a complementary adaptation mechanism to parameter scaling in discriminative vision-language models.

Vision-language models like CLIP have demonstrated remarkable zero-shot transfer capabilities. However, their susceptibility to imperceptible adversarial perturbations remains a critical security concern. While test-time defenses offer a pragmatic solution for deployed models, existing approaches typically rely on gradient-based optimization during inference, incurring significant computational overhead. In this paper, we revisit the role of data augmentation in CLIP robustness and observe that augmentations are not equally effective: specific augmentations consistently provide robust geometric cues that align with correct class semantics in the hyperspherical feature space. Based on this, we propose Adaptive Geodesic Correction (AGC), a training-free defense mechanism that requires no parameter updates. AGC identifies a reliable augmentation as a geometric anchor and corrects the input feature towards it, utilizing an adaptive step size to balance robustness against clean accuracy preservation. AGC achieves superior performance across eight fine-grained datasets and three CLIP backbones, improving average robust accuracy by 44.4% over state-of-the-art baseline while delivering a 10$\times$ reduction in inference latency. Our findings reveal a fundamental geometric property of CLIP features, offering a highly efficient and effective paradigm for robust multimodal deployment.

Multimodal video summarization requires visual features that align semantically with language generation. Traditional approaches rely on CNN features trained for object classification, which represent visual concepts as discrete categories not aligned with natural language. We propose ClipSum, a framework that leverages frozen CLIP vision-language features with explicit temporal modeling and dimension-adaptive fusion for instructional video summarization. CLIP's contrastive pre-training on 400M image-text pairs yields visual features semantically aligned with the linguistic concepts that text decoders generate, bridging the vision-language gap at the representation level. On YouCook2, ClipSum achieves 33.0% ROUGE-1 versus 30.5% for ResNet-152 with 4x lower dimensionality (512 vs. 2048), demonstrating that semantic alignment matters more than feature capacity. Frozen CLIP (33.0%) surpasses fine-tuned CLIP (32.3%), showing that preserving pre-trained alignment is more valuable than task-specific adaptation. https://github.com/aqeeelmirza/clipsum

We study full-reference image quality assessment from a machine-centric perspective, where images are evaluated by how well they preserve information for downstream models. We formulate machine-oriented quality as a latent machine utility and approximate it through pairwise predictive-consistency comparisons. To this end, we construct PCMP, a dataset of PSNR-matched distortion pairs labeled by consistency votes from multiple pretrained models. We further propose ML-CLIPSim, a differentiable quality metric built on a frozen CLIP visual encoder, which aggregates intermediate patch-token similarities and global image embeddings. Experiments on machine-preference benchmarks, human-IQA datasets, and learned image compression show that ML-CLIPSim better aligns with machine-oriented preferences than conventional fidelity and perceptual metrics, while remaining competitive for human quality prediction. Used as a compression distortion term, it improves rate--task trade-offs across multiple downstream tasks.

Aesthetic image cropping aims to enhance the aesthetic quality of an image by improving its composition through spatial cropping. Previous methods often rely on saliency prediction or retrieval augmentation, ignoring the task's core requirement: a deep understanding of composition and aesthetics. Consequently, saliency-based methods struggle to make compositional trade-offs in complex scenes, while retrieval-based methods blindly refer to similar cases, lacking adaptive reasoning for unique scenes. Both approaches fail to align their automated cropping results with those of human experts. To address the above issues, we propose a novel paradigm that reformulates aesthetic cropping as a multimodal reasoning task, aiming to activate the VLM's analytical and comprehension capabilities in aesthetics. We design a Compositional Reasoning and Optimizing Preference method (CROP) that directs the VLM to think like a professional photographer. It deconstructs a complex and subjective aesthetic problem into an "analysis-proposal-decision" process, reasoning step by step through the analysis of scene elements and compositional principles. Meanwhile, our expert preference alignment module makes the model's decision consistent with human expert aesthetics. Extensive experiments across multiple datasets validate our method's superiority and component effectiveness.

Recent advances in learned image compression (LIC) have enabled practical deployments, spurring active research into image compression for machines and progressive coding schemes. However, their integration remains under-explored: prior works on progressive machine codec predominantly target sample-level difficulty adaptation (i.e., easy-to-hard), without considering semantic-level scalability. In this work, we introduce a semantic hierarchy-aware progressive codec that enables semantic scalability (i.e., coarse-to-fine) from a single bitstream. We first systematically categorize ImageNet-1K classes into CLIP embedding-based semantic hierarchies. Based on a channel-wise autoregressive framework, we decompose latent representations into hierarchically ordered channel blocks, each explicitly optimized for a corresponding semantic hierarchy. Extensive experiments demonstrate that our approach substantially improves coarse-level recognition at low bitrates while maintaining fine-grained accuracy at higher bitrates. By reframing progressive transmission through the lens of semantic scalability, our work provides an efficient and interpretable solution for task-adaptive image coding, outperforming existing progressive codecs under hierarchical evaluation.

We introduce Ilov3Splat, a novel framework for instance-level open-vocabulary 3D scene understanding built on 3D Gaussian Splatting (3D-GS). Most prior work depends on 2D rendering-based matching or point-level semantic association, which undermines cross-view consistency, lacks coherent instance-level reasoning, and limits precision in downstream 3D tasks. To address these limitations, our method jointly optimizes scene geometry and semantic representations by augmenting Gaussian splats with view-consistent feature fields. Specifically, we leverage multi-resolution hash embedding to efficiently encode language-aligned CLIP features, enabling dense and coherent language grounding in 3D space. We further train an instance feature field using contrastive loss over SAM masks, supporting fine-grained object distinction across views. At inference time, CLIP-encoded queries are matched against the learned features, followed by two-stage 3D clustering to retrieve relevant Gaussian groups. This enables our framework to identify arbitrary objects in 3D scenes based on natural language descriptions, without requiring category supervision or manual annotations. Experiments on standard benchmarks demonstrate that Ilov3Splat outperforms prior open-vocabulary 3D-GS methods in both object selection and instance segmentation, offering a flexible and accurate solution for language-driven 3D scene understanding. Project page: https://csiro-robotics.github.io/Ilov3Splat.

Contrastive Language-Image Pretraining (CLIP) models excel at understanding image-text relationships but struggle with adapting to new data without forgetting prior knowledge. To address this, models are typically fine-tuned using both new task data and a memory buffer of past tasks. However, CLIP's contrastive loss suffers when the memory buffer is small, leading to performance degradation on previous tasks. We propose a memory-efficient, distributionally robust method that dynamically reweights losses per class during training. Our approach, tested on class incremental settings (CIFAR-100, ImageNet1K) and a domain incremental setting (DomainNet) adapts CLIP models quickly while minimizing catastrophic forgetting, even with minimal memory usage.

Image-based Joint-Embedding Predictive Architecture (I-JEPA) offers a promising approach to visual self-supervised learning through masked feature prediction. However with the inherent visual uncertainty at masked positions, feature prediction remains challenging and may fail to learn semantic representations. In this work, we propose Text-Conditional JEPA (TC-JEPA) that uses image captions to reduce the prediction uncertainty. Specifically, we modulate the predicted patch features using a fine-grained text conditioner that computes sparse cross-attention over input text tokens. With such conditioning, patch features become predictable as a function of text, thus are more semantically meaningful. We show TC-JEPA improves downstream performance and training stability, with promising scaling properties. TC-JEPA also offers a new vision-language pretraining paradigm based on feature prediction only, outperforming contrastive methods on diverse tasks, especially those requiring fine-grained visual understanding and reasoning.

The dream of instantly creating rich 360-degree panoramic worlds from text is rapidly becoming a reality, yet a crucial gap exists in our ability to reliably evaluate their semantic alignment. Contrastive Language-Image Pre-training (CLIP) models, standard AI evaluators, predominantly trained on perspective image-text pairs, face an open question regarding their understanding of the unique characteristics of 360-degree panoramic image-text pairs. This paper addresses this gap by first introducing two concepts: \emph{360-degree textual semantics}, semantic information conveyed by explicit format identifiers, and \emph{360-degree visual semantics}, invariant semantics under horizontal circular shifts. To probe CLIP's comprehension of these semantics, we then propose novel evaluation methodologies using keyword manipulation and horizontal circular shifts of varying magnitudes. Rigorous statistical analyses across popular CLIP configurations reveal that: (1) CLIP models effectively leverage explicit textual identifiers, demonstrating an understanding of 360-degree textual semantics; and (2) CLIP models fail to robustly preserve semantic alignment under horizontal circular shifts, indicating limited comprehension of 360-degree visual semantics. To address this limitation, we propose a LoRA-based fine-tuning framework that explicitly instills invariance to circular shifts. Our fine-tuned models exhibit improved comprehension of 360-degree visual semantics, though with a slight degradation in original semantic evaluation performance, highlighting a fundamental trade-off in adapting CLIP to 360-degree panoramic images. Code is available at https://github.com/littlewhitesea/360Semantics.

Recent advances in representation learning have shown that hyperbolic geometry can offer a more expressive alternative to the Euclidean embeddings used in CLIP models, capturing hierarchical structures and leading to better-organized representations. However, current hyperbolic CLIP variants are trained entirely from scratch, which is computationally expensive and resource-intensive. In this work, we propose HAC (Hyperbolic Adaptation of CLIP), a parameter-efficient framework that enables pretrained CLIP models to transition into hyperbolic space via lightweight fine-tuning. We apply HAC to Visual Question Answering (VQA), where models must interpret visual elements and align them with textual queries. Notably, HAC's training is performed on a dataset with no overlap with any VQA benchmark, resulting in a strict zero-shot evaluation paradigm that underscores HAC's task-agnostic adaptability. We evaluate HAC across a diverse suite of VQA benchmarks spanning General, Reasoning, and OCR categories. Both HAC-S (small) and HAC-B (medium) consistently surpass Euclidean baselines and prior hyperbolic approaches, with HAC-B delivering up to a +1.9 point average improvement over CLIP-B on reasoning-intensive tasks. Our code is available at https://github.com/fdibiton/HAC

The functions of different regions of the human brain are closely linked to their distinct cytoarchitecture, which is defined by the spatial arrangement and morphology of the cells. Identifying brain regions by their cytoarchitecture enables various scientific analyses of the brain. However, delineating these areas manually in brain histological sections is time-consuming and requires specialized knowledge. An automated approach is necessary to minimize the effort needed from human experts. To address this, we propose CytoCLIP, a suite of vision-language models derived from pre-trained Contrastive Language-Image Pre-Training (CLIP) frameworks to learn joint visual-text representations of brain cytoarchitecture. CytoCLIP comprises two model variants: one is trained using low-resolution whole-region images to understand the overall cytoarchitectural pattern of an area, and the other is trained on high-resolution image tiles for detailed cellular-level representation. The training dataset is created from NISSL-stained histological sections of developing fetal brains of different gestational weeks. It includes 86 distinct regions for low-resolution images and 379 brain regions for high-resolution tiles. We evaluate the model's understanding of the cytoarchitecture and generalization ability using region classification and cross-modal retrieval tasks. Multiple experiments are performed under various data setups, including data from samples of different ages and sectioning planes. Experimental results demonstrate that CytoCLIP outperforms existing methods. It achieves a weighted F1 score of 0.87 for whole-region classification and 0.91 for high-resolution image tile classification.

Object-oriented embodied navigation tasks require agents to locate specific objects, either defined by category or images, in unseen environments. While recent methods have made progress in extending closed-set models to open-vocabulary scenarios with foundation models, they typically rely on training-free large language models (LLMs) or finetuning with end-to-end reinforcement learning (RL). However, they face challenges in efficiency (e.g., the overhead and cost of LLM inference) and limited generalization from intensive RL training. In this paper, we propose OVExp, a training-efficient framework for open-vocabulary exploration. We make the first effort to demonstrate the generalization capabilities of semantic map-based goal prediction networks using Dense CLIP models. A major challenge is that preserving both precise point-wise object locations and generalizable visual representations in the semantic map leads to unaffordable training costs. To address this, we design a Cross-Modal Transfer on Semantic Mapping strategy which adapts an intriguing text-only training and transfer to multi-model semantic mapping and goals in test-time. Despite relying on text-based spatial layouts with limited objects, OVExp demonstrates robust generalization to unseentargets on established ObjectNav benchmarks.