Searcharxiv⌕ Search

arXiv subjects

Georgios Tzimiropoulos

Publications and source records attributed to Georgios Tzimiropoulos.

At least 19 recordsLinked to original sources

CADMA: Capacity-Aware Coverage Decomposition for Generative Model Assessment

Evaluating generative models requires measuring not only sample fidelity but also how well a generated set covers the real data distribution. Recent work has therefore introduced recall-oriented metrics for distribution-level evaluation. However, existing recall metrics often reduce distributional coverage to geometry-based coverage. This simplifying assumption weakens their diagnostic value and interpretability in two ways: these metrics provide only a single aggregate score that cannot distinguish essential diversity failures such as mode dropping and mode collapse, and geometry-based coverage can provide unreliable estimates by assigning high scores to poorly covered generative distributions. We therefore introduce CADMA, a capacity-aware framework for recall-oriented evaluation and diagnosis. CADMA evaluates distributional coverage through local capacity matching between real and generated samples, separating geometry-based coverage from effective coverage. This yields multi-dimensional coverage diagnostics that quantify mode dropping and mode collapse while reducing the overly optimistic estimates produced by geometry-based metrics. Through extensive experiments on toy data, real-world datasets, and generative models, we show that CADMA provides more reliable coverage estimates and more fine-grained, interpretable diagnostic signals of diversity failures than existing metrics. Our code is available at https://github.com/Open-Debin/CADMA_NeurIPS2026.

cs.CV↗

One Block, Multiple Depths: Recurrent Vision Transformers with Depth-Programmed Experts

In this work, we show that a single Transformer block, applied recurrently, can match the accuracy of a full-depth vision encoder at comparable inference FLOPs without intermediate feature distillation. reViT restores depth-specific transformations by representing the FFN at each recurrent depth as a convex combination of a small shared expert bank. A continuous normalized-depth coordinate programs this mixture, defining a resampleable trajectory through FFN parameter space. We evaluate this design in two regimes: supervised ImageNet-1k training and distillation from a DINOv2 teacher. Across both regimes, controlled adaptations identify weight-space merging as the strongest tested MoE family at a matching one-FFN budget, ahead of the token-dispatch and output-mixture alternatives. Trained from scratch, reViT-B/16 attains DeiT III accuracy with about 70\% fewer stored parameters. An 8-experts model distilled using only the teacher's output features retains nearly all of its DINOv2 teacher's linear-probe accuracy and transfers across classification, segmentation, and depth prediction. Elastic-depth training allows one checkpoint (trained model) to operate at multiple tested depths by resampling the same normalized coordinate interval. For fixed-depth deployment, the recurrent block can be materialized as a conventional dense graph, removing online routing and merging without changing the one-FFN-per-depth compute but expanding deployment storage.

cs.CV↗

What Matters for Latent Reasoning with Flow Matching

Latent reasoning lets a large language model (LLM) think in a continuous space and verbalize only the answer. We argue that an effective latent thought must meet five requirements: it should be useful, helping produce the correct answer rather than merely changing it, diverse, so that resampling yields different reasoning trajectories, explainable, so that a decoded chain of thought (CoT) reflects reasoning the answer actually follows, refinable with more inference compute, and efficient, costing less than an explicit CoT at comparable accuracy. Current methods rarely meet these requirements: they learn shortcuts from the question, distill the explicit CoT into their weights, or imitate it one token at a time. We focus on flow matching in a learned latent space, the family we argue is best placed to meet them, and identify the training choices that make it work. The result is Flow-based Latent Reasoning (FLaRe), a simple recipe covering what the latent space encodes and how to shape it, where to train the flow, how to read out the answer, and a final stage of training on the model's own verified thoughts. A probe for each requirement shows that FLaRe improves on prior latent methods in all five. It also compares favorably with them on arithmetic benchmarks, while reaching 97% of the accuracy of explicit CoT at a quarter of its latency.

cs.LG↗

TPSO: Training-Free Diverse Image Generation via Semantic Prompt Embedding Optimization

Image diversity remains a fundamental challenge for text-to-image diffusion models. Low-diversity generation often leads to repetitive outputs, increasing sampling redundancy and hindering both creative exploration and downstream applications. A key factor is the tendency of diffusion models to collapse toward strong modes in the learned distribution. Existing attempts to improve diversity, such as steering-based guidance, often introduce distortions that degrade image quality. To address this issue, we propose Token-Prompt Embedding Space Optimization (TPSO), a training-free and model-agnostic module. TPSO introduces learnable parameters to explore underrepresented regions of the token embedding space, reducing the tendency to repeatedly sample from strong modes of the distribution. Meanwhile, a prompt-level semantic constraint regulates distribution shifts, preventing quality degradation while preserving semantic fidelity. Extensive experiments on MS-COCO across three representative diffusion backbones demonstrate that TPSO substantially improves diversity, boosting performance from 1.10 to 4.18, while maintaining image quality with only a modest inference-time overhead of 3.6% to 8.9%. Code is available at: https://github.com/Open-Debin/TPSO.

cs.CV↗

UltraViT: Latency-Optimized On-device Vision Encoder for Large Vision-Language Models

Large Vision-Language Models (LVLMs) remain bottlenecked by massive computational footprints, precluding their deployment on resource-constrained edge devices. While efforts to compress LVLMs focus heavily on vision token reduction or smaller language models, the vision encoder is largely overlooked, typically deployed as a monolithic, computationally heavy feature extractor. Moreover, there is no previous effort that designs a vision encoder for LVLMs directly optimized for on-device latency. In this paper, we present UltraViT, a vision encoder for LVLMs, explicitly designed and optimized for on-device performance. Specifically, by taking into account real on-device latencies, we systematically design a pyramidal architecture that strategically integrates and adapts heterogeneous spatial mixers at the macro-block level. Furthermore, to pre-train UltraViT, we propose a novel two-stage generative pre-training strategy: cultivating rich spatial features via dense distillation, followed by direct generative supervision from a capacity-mixed frozen LLM. Compared to standard contrastive and SSL, we show that our pre-training is much more effective for achieving high-level semantic grounding for UltraViT needed for the subsequent generative multimodal alignment of LVLM training. Extensive experiments demonstrate that our on-device latency-informed design combined with our tailored training strategy establishes a new state-of-the-art for efficient LVLM encoding, significantly outperforming existing encoder-centric baselines while operating on-device at nearly 1.7xthe speed.

cs.CV↗

Hierarchical Image Tokenization for Multi-Scale Image Super Resolution

We introduce a multi-scale Image Super Resolution (ISR) method building on recent advances in Visual Auto-Regressive (VAR) modeling. VAR models break image tokenization into additive, gradually increasing scales, using Residual Quantization (RQ), an approach that aligns perfectly with our target ISR task. Previous works taking advantage of this synergy suffer from two main shortcomings. First, due to the limitations in RQ, they only generate images at a predefined fixed scale, failing to map intermediate outputs to the corresponding image scales. They also rely on large backbones or a large corpus of annotated data to achieve better performance. To address both shortcomings, we introduce two novel components to the VAR training for ISR, aiming at increasing its flexibility and reducing its complexity. In particular, we introduce a) a \textbf{Hierarchical Image Tokenization (HIT)} approach that progressively represents images at different scales while enforcing token overlap across scales, and b) a \textbf{Direct Preference Optimization (DPO) regularization term} that, relying solely on the (LR,HR) pair, encourages the transformer to produce the latter over the former. Our proposed HIT acts as a strong inductive bias for the VAR training, resulting in a small model (300M params vs 1B params of VARSR), that achieves state-of-the-art results without external training data, and that delivers multi-scale outputs with a single forward pass.

cs.CV↗

Restore, Assess, Repeat: A Unified Framework for Iterative Image Restoration

Image restoration aims to recover high quality images from inputs degraded by various factors, such as adverse weather, blur, or low light. While recent studies have shown remarkable progress across individual or unified restoration tasks, they still suffer from limited generalization and inefficiency when handling unknown or composite degradations. To address these limitations, we propose RAR, a Restore, Assess and Repeat process, that integrates Image Quality Assessment (IQA) and Image Restoration (IR) into a unified framework to iteratively and efficiently achieve high quality image restoration. Specifically, we introduce a restoration process that operates entirely in the latent domain to jointly perform degradation identification, image restoration, and quality verification. The resulting model is fully trainable end to end and allows for an all-in-one assess and restore approach that dynamically adapts the restoration process. Also, the tight integration of IQA and IR into a unified model minimizes the latency and information loss that typically arises from keeping the two modules disjoint, (e.g. during image and/or text decoding). Extensive experiments show that our approach consistent improvements under single, unknown and composite degradations, thereby establishing a new state-of-the-art.

cs.CV↗

VISion On Request: Enhanced VLLM efficiency with sparse, dynamically selected, vision-language interactions

Existing approaches for improving the efficiency of Large Vision-Language Models (LVLMs) are largely based on the concept of visual token reduction. This approach, however, creates an information bottleneck that impairs performance, especially on challenging tasks that require fine-grained understanding and reasoning. In this work, we challenge this paradigm by introducing VISion On Request (VISOR), a method that reduces inference cost without discarding visual information. Instead of compressing the image, VISOR improves efficiency by sparsifying the interaction between image and text tokens. Specifically, the language model attends to the full set of high-resolution visual tokens through a small, strategically placed set of attention layers: general visual context is provided by efficient cross-attention between text-image, while a few well-placed and dynamically selected self-attention layers refine the visual representations themselves, enabling complex, high-resolution reasoning when needed. Based on this principle, we first train a single universal network on a range of computational budgets by varying the number of self-attention layers, and then introduce a lightweight policy mechanism that dynamically allocates visual computation based on per-sample complexity. Extensive experiments show that VISOR drastically reduces computational cost while matching or exceeding state-of-the-art results across a diverse suite of benchmarks, and excels in challenging tasks that require detailed visual understanding.

cs.CV↗

CycleCap: Improving VLMs Captioning Performance via Self-Supervised Cycle Consistency Fine-Tuning

Visual-Language Models (VLMs) have achieved remarkable progress in image captioning, visual question answering, and visual reasoning. Yet they remain prone to vision-language misalignment, often producing overly generic or hallucinated descriptions. Existing approaches address this via instruction tuning-requiring costly, large-scale annotated datasets or via complex test-time frameworks for caption refinement. In this work, we revisit image-text alignment through the lens of cycle consistency: given an image and a caption generated by an image-to-text model, the backward mapping through a text-to-image model should reconstruct an image that closely matches the original. In our setup, a VLM serves as the image-to-text component, while a pre-trained text-to-image model closes the loop by reconstructing the image from the generated caption. Building on this, we introduce CycleCap, a fine-tuning scheme to improve image captioning using Group Relative Policy Optimization (GRPO) with a reward based on the similarity between the original and reconstructed images, computed on-the-fly. Unlike previous work that uses cycle consistency loss for preference dataset construction, our method leverages cycle consistency directly as a self-supervised training signal. This enables the use of raw images alone, eliminating the need for curated image-text datasets, while steering the VLM to produce more accurate and grounded text descriptions. Applied to four VLMs ranging from 1B to 7B parameters, CycleCap yields consistent improvements across captioning and hallucination benchmarks, surpassing state-of-the-art methods that rely on supervised cycle consistency training.

cs.CV↗

Deconstructing the Failure of Ideal Noise Correction: A Three-Pillar Diagnosis

Statistically consistent methods based on the noise transition matrix ($T$) offer a theoretically grounded solution to Learning with Noisy Labels (LNL), with guarantees of convergence to the optimal clean-data classifier. In practice, however, these methods are often outperformed by empirical approaches such as sample selection, and this gap is usually attributed to the difficulty of accurately estimating $T$. The common assumption is that, given a perfect $T$, noise-correction methods would recover their theoretical advantage. In this work, we put this longstanding hypothesis to a decisive test. We conduct experiments under idealized conditions, providing correction methods with a perfect, oracle transition matrix. Even under these ideal conditions, we observe that these methods still suffer from performance collapse during training. This compellingly demonstrates that the failure is not fundamentally a $T$-estimation problem, but stems from a more deeply rooted flaw. To explain this behaviour, we provide a unified analysis that links three levels: macroscopic convergence states, microscopic optimisation dynamics, and information-theoretic limits on what can be learned from noisy labels. Together, these results give a formal account of why ideal noise correction fails and offer concrete guidance for designing more reliable methods for learning with noisy labels.

cs.LG↗

More Images, More Problems? A Controlled Analysis of VLM Failure Modes

Large Vision Language Models (LVLMs) have demonstrated remarkable capabilities, yet their proficiency in understanding and reasoning over multiple images remains largely unexplored. While existing benchmarks have initiated the evaluation of multi-image models, a comprehensive analysis of their core weaknesses and their causes is still lacking. In this work, we introduce MIMIC (Multi-Image Model Insights and Challenges), a new benchmark designed to rigorously evaluate the multi-image capabilities of LVLMs. Using MIMIC, we conduct a series of diagnostic experiments that reveal pervasive issues: LVLMs often fail to aggregate information across images and struggle to track or attend to multiple concepts simultaneously. To address these failures, we propose two novel complementary remedies. On the data side, we present a procedural data-generation strategy that composes single-image annotations into rich, targeted multi-image training examples. On the optimization side, we analyze layer-wise attention patterns and derive an attention-masking scheme tailored for multi-image inputs. Experiments substantially improved cross-image aggregation, while also enhancing performance on existing multi-image benchmarks, outperforming prior state of the art across tasks. Data and code will be made available at https://github.com/anurag-198/MIMIC.

cs.CV↗

Vision-Free Retrieval: Rethinking Multimodal Search with Textual Scene Descriptions

Contrastively-trained Vision-Language Models (VLMs), such as CLIP, have become the standard approach for learning discriminative vision-language representations. However, these models often exhibit shallow language understanding, manifesting bag-of-words behaviour. These limitations are reinforced by their dual-encoder design, which induces a modality gap. Additionally, the reliance on vast web-collected data corpora for training makes the process computationally expensive and introduces significant privacy concerns. To address these limitations, in this work, we challenge the necessity of vision encoders for retrieval tasks by introducing a vision-free, single-encoder retrieval pipeline. Departing from the traditional text-to-image retrieval paradigm, we migrate to a text-to-text paradigm with the assistance of VLLM-generated structured image descriptions. We demonstrate that this paradigm shift has significant advantages, including a substantial reduction of the modality gap, improved compositionality, and better performance on short and long caption queries, all attainable with only a few hours of calibration on two GPUs. Additionally, substituting raw images with textual descriptions introduces a more privacy-friendly alternative for retrieval. To further assess generalisation and address some of the shortcomings of prior compositionality benchmarks, we release two benchmarks derived from Flickr30k and COCO, containing diverse compositional queries made of short captions, which we coin subFlickr and subCOCO. Our vision-free retriever matches and often surpasses traditional multimodal models. Importantly, our approach achieves state-of-the-art zero-shot performance on multiple retrieval and compositionality benchmarks, with models as small as 0.3B parameters. Code is available at: https://github.com/IoannaNti/LexiCLIP

cs.CV↗

VLLMs Provide Better Context for Emotion Understanding Through Common Sense Reasoning

Recognising emotions in context involves identifying an individual's apparent emotions while considering contextual cues from the surrounding scene. Previous approaches to this task have typically designed explicit scene-encoding architectures or incorporated external scene-related information, such as captions. However, these methods often utilise limited contextual information or rely on intricate training pipelines to decouple noise from relevant information. In this work, we leverage the capabilities of Vision-and-Large-Language Models (VLLMs) to enhance in-context emotion classification in a more straightforward manner. Our proposed method follows a simple yet effective two-stage approach. First, we prompt VLLMs to generate natural language descriptions of the subject's apparent emotion in relation to the visual context. Second, the descriptions, along with the visual input, are used to train a transformer-based architecture that fuses text and visual features before the final classification task. This method not only simplifies the training process but also significantly improves performance. Experimental results demonstrate that the textual descriptions effectively guide the model to constrain the noisy visual input, allowing our fused architecture to outperform individual modalities. Our approach achieves state-of-the-art performance across three datasets, BoLD, EMOTIC, and CAER-S, without bells and whistles. The code will be made publicly available on github: https://github.com/NickyFot/EmoCommonSense.git

cs.CV↗

Multi-scale Image Super Resolution with a Single Auto-Regressive Model

In this paper we tackle Image Super Resolution (ISR), using recent advances in Visual Auto-Regressive (VAR) modeling. VAR iteratively estimates the residual in latent space between gradually increasing image scales, a process referred to as next-scale prediction. Thus, the strong priors learned during pre-training align well with the downstream task (ISR). To our knowledge, only VARSR has exploited this synergy so far, showing promising results. However, due to the limitations of existing residual quantizers, VARSR works only at a fixed resolution, i.e. it fails to map intermediate outputs to the corresponding image scales. Additionally, it relies on a 1B transformer architecture (VAR-d24), and leverages a large-scale private dataset to achieve state-of-the-art results. We address these limitations through two novel components: a) a Hierarchical Image Tokenization approach with a multi-scale image tokenizer that progressively represents images at different scales while simultaneously enforcing token overlap across scales, and b) a Direct Preference Optimization (DPO) regularization term that, relying solely on the LR and HR tokenizations, encourages the transformer to produce the latter over the former. To the best of our knowledge, this is the first time a quantizer is trained to force semantically consistent residuals at different scales, and the first time that preference-based optimization is used to train a VAR. Using these two components, our model can denoise the LR image and super-resolve at half and full target upscale factors in a single forward pass. Additionally, we achieve \textit{state-of-the-art results on ISR}, while using a small model (300M params vs ~1B params of VARSR), and without using external training data.

cs.CV↗

VladVA: Discriminative Fine-tuning of LVLMs

Contrastively-trained Vision-Language Models (VLMs) like CLIP have become the de facto approach for discriminative vision-language representation learning. However, these models have limited language understanding, often exhibiting a "bag of words" behavior. At the same time, Large Vision-Language Models (LVLMs), which combine vision encoders with LLMs, have been shown to be capable of detailed vision-language reasoning, yet their autoregressive nature renders them less suitable for discriminative tasks. In this work, we propose to combine "the best of both worlds": a new training approach for discriminative fine-tuning of LVLMs that results in strong discriminative and compositional capabilities. Essentially, our approach converts a generative LVLM into a discriminative one, unlocking its capability for powerful image-text discrimination combined with enhanced language understanding. Our contributions include (1) a carefully designed training/optimization framework that utilizes image-text pairs of variable length and granularity for training the model with both contrastive and next-token prediction losses. This is accompanied by ablation studies that justify the necessity of our framework's components; (2) a parameter-efficient adaptation method using a combination of soft prompting and LoRA adapters; (3) significant improvements over state-of-the-art CLIP-like models of similar size, including standard image-text retrieval benchmarks and notable gains in compositionality.

cs.CV↗

Edge-SD-SR: Low Latency and Parameter Efficient On-device Super-Resolution with Stable Diffusion via Bidirectional Conditioning

There has been immense progress recently in the visual quality of Stable Diffusion-based Super Resolution (SD-SR). However, deploying large diffusion models on computationally restricted devices such as mobile phones remains impractical due to the large model size and high latency. This is compounded for SR as it often operates at high res (e.g. 4Kx3K). In this work, we introduce Edge-SD-SR, the first parameter efficient and low latency diffusion model for image super-resolution. Edge-SD-SR consists of ~169M parameters, including UNet, encoder and decoder, and has a complexity of only ~142 GFLOPs. To maintain a high visual quality on such low compute budget, we introduce a number of training strategies: (i) A novel conditioning mechanism on the low resolution input, coined bidirectional conditioning, which tailors the SD model for the SR task. (ii) Joint training of the UNet and encoder, while decoupling the encodings of the HR and LR images and using a dedicated schedule. (iii) Finetuning the decoder using the UNet's output to directly tailor the decoder to the latents obtained at inference time. Edge-SD-SR runs efficiently on device, e.g. it can upscale a 128x128 patch to 512x512 in 38 msec while running on a Samsung S24 DSP, and of a 512x512 to 2048x2048 (requiring 25 model evaluations) in just ~1.1 sec. Furthermore, we show that Edge-SD-SR matches or even outperforms state-of-the-art SR approaches on the most established SR benchmarks.

cs.CV↗

Fwd2Bot: LVLM Visual Token Compression with Double Forward Bottleneck

In this work, we aim to compress the vision tokens of a Large Vision Language Model (LVLM) into a representation that is simultaneously suitable for (a) generative and (b) discriminative tasks, (c) is nearly lossless, and (d) is storage-efficient. We propose a novel compression approach, called Fwd2Bot, that uses the LVLM itself to compress the visual information in a task-agnostic manner. At the core of Fwd2bot there exists a "double-forward pass" training strategy, whereby, during the first forward pass, the LLM (of the LVLM) creates a bottleneck by condensing the visual information into a small number of summary tokens. Then, using the same LLM, the second forward pass processes the language instruction(s) alongside the summary tokens, used as a direct replacement for the image ones. The training signal is provided by two losses: an autoregressive one applied after the second pass that provides a direct optimization objective for compression, and a contrastive loss, applied after the first pass, that further boosts the representation strength, especially for discriminative tasks. The training is further enhanced by stage-specific adapters. We accompany the proposed method by an in-depth ablation study. Overall, Fwd2Bot results in highly-informative compressed representations suitable for both generative and discriminative tasks. For generative tasks, we offer a 2x higher compression rate without compromising the generative capabilities, setting a new state-of-the-art result. For discriminative tasks, we set a new state-of-the-art on image retrieval and compositionality.

cs.CV↗

DiffusionAct: Controllable Diffusion Autoencoder for One-shot Face Reenactment

Video-driven neural face reenactment aims to synthesize realistic facial images that successfully preserve the identity and appearance of a source face, while transferring the target head pose and facial expressions. Existing GAN-based methods suffer from either distortions and visual artifacts or poor reconstruction quality, i.e., the background and several important appearance details, such as hair style/color, glasses and accessories, are not faithfully reconstructed. Recent advances in Diffusion Probabilistic Models (DPMs) enable the generation of high-quality realistic images. To this end, in this paper we present DiffusionAct, a novel method that leverages the photo-realistic image generation of diffusion models to perform neural face reenactment. Specifically, we propose to control the semantic space of a Diffusion Autoencoder (DiffAE), in order to edit the facial pose of the input images, defined as the head pose orientation and the facial expressions. Our method allows one-shot, self, and cross-subject reenactment, without requiring subject-specific fine-tuning. We compare against state-of-the-art GAN-, StyleGAN2-, and diffusion-based methods, showing better or on-par reenactment performance.

cs.CV↗