2026-04-09 AI 리서치 브리핑

Large vision-language models can produce object hallucinations in image descriptions, highlighting the need for effective detection and mitigation strategies. Prior work commonly relies on the model's attention weights on visual tokens as a detection signal. We reveal that coarse-grained attention-based analysis is unreliable due to hidden confounders, specifically token position and object repetition in a description. This leads to Simpson's paradox: the attention trends reverse or disappear when statistics are aggregated. Based on this observation, we introduce HaloProbe, a Bayesian framework that factorizes external description statistics and internal decoding signals to estimate token-level hallucination probabilities. HaloProbe uses balanced training to isolate internal evidence and combines it with learned prior over external features to recover the true posterior. While intervention-based mitigation methods often degrade utility or fluency by modifying models' internals, we use HaloProbe as an external scoring signal for non-invasive mitigation. Our experiments show that HaloProbe-guided decoding reduces hallucinations more effectively than state-of-the-art intervention-based methods while preserving utility.

Vision-Language Models (VLMs) rely heavily on pretrained vision encoders to support downstream tasks such as image captioning, visual question answering, and zero-shot classification. Despite their strong performance, these encoders remain highly vulnerable to imperceptible adversarial perturbations, which can severely degrade both robustness and semantic quality in multimodal reasoning. In this work, we introduce Sim-CLIP, an unsupervised adversarial fine-tuning framework that enhances the robustness of the CLIP vision encoder while preserving overall semantic representations. Sim-CLIP adopts a Siamese training architecture with a cosine similarity objective and a symmetric stop-gradient mechanism to enforce semantic alignment between clean and adversarial views. This design avoids large-batch contrastive learning and additional momentum encoders, enabling robust training with low computational overhead. We evaluate Sim-CLIP across multiple Vision-Language Models and tasks under both targeted and untargeted adversarial attacks. Experimental results demonstrate that Sim-CLIP consistently outperforms state-of-the-art robust CLIP variants, achieving stronger adversarial robustness while maintaining or improving semantic fidelity. These findings highlight the limitations of existing adversarial defenses and establish Sim-CLIP as an effective and scalable solution for robust vision-language representation learning.

Most digital videos are stored in 8-bit low dynamic range (LDR) formats, where much of the original high dynamic range (HDR) scene radiance is lost due to saturation and quantization. This loss of highlight and shadow detail precludes mapping accurate luminance to HDR displays and limits meaningful re-exposure in post-production workflows. Although techniques have been proposed to convert LDR images to HDR through dynamic range expansion, they struggle to restore realistic detail in the over- and underexposed regions. To address this, we present DiffHDR, a framework that formulates LDR-to-HDR conversion as a generative radiance inpainting task within the latent space of a video diffusion model. By operating in Log-Gamma color space, DiffHDR leverages spatio-temporal generative priors from a pretrained video diffusion model to synthesize plausible HDR radiance in over- and underexposed regions while recovering the continuous scene radiance of the quantized pixels. Our framework further enables controllable LDR-to-HDR video conversion guided by text prompts or reference images. To address the scarcity of paired HDR video data, we develop a pipeline that synthesizes high-quality HDR video training data from static HDRI maps. Extensive experiments demonstrate that DiffHDR significantly outperforms state-of-the-art approaches in radiance fidelity and temporal stability, producing realistic HDR videos with considerable latitude for re-exposure.

World action models (WAMs) have emerged as a promising direction for robot policy learning, as they can leverage powerful video backbones to model the future states. However, existing approaches often rely on separate action modules, or use action representations that are not pixel-grounded, making it difficult to fully exploit the pretrained knowledge of video models and limiting transfer across viewpoints and environments. In this work, we present Action Images, a unified world action model that formulates policy learning as multiview video generation. Instead of encoding control as low-dimensional tokens, we translate 7-DoF robot actions into interpretable action images: multi-view action videos that are grounded in 2D pixels and explicitly track robot-arm motion. This pixel-grounded action representation allows the video backbone itself to act as a zero-shot policy, without a separate policy head or action module. Beyond control, the same unified model supports video-action joint generation, action-conditioned video generation, and action labeling under a shared representation. On RLBench and real-world evaluations, our model achieves the strongest zero-shot success rates and improves video-action joint generation quality over prior video-space world models, suggesting that interpretable action images are a promising route to policy learning.

Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

Learning to Retrieve from Agent Trajectories에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

GBQA: A Game Benchmark for Evaluating LLMs as Quality Assurance Engineers에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

The Character Error Rate (CER) is a key metric for evaluating the quality of Optical Character Recognition (OCR). However, this metric assumes that text has been perfectly parsed, which is often not the case. Under page-parsing errors, CER becomes undefined, limiting its use as a metric and making evaluating page-level OCR challenging, particularly when using data that do not share a labelling schema. We introduce the Character Error Vector (CEV), a bag-of-characters evaluator for OCR. The CEV can be decomposed into parsing and OCR, and interaction error components. This decomposability allows practitioners to focus on the part of the Document Understanding pipeline that will have the greatest impact on overall text extraction quality. The CEV can be implemented using a variety of methods, of which we demonstrate SpACER (Spatially Aware Character Error Rate) and a Character distribution method using the Jensen-Shannon Distance. We validate the CEV's performance against other metrics: first, the relationship with CER; then, parse quality; and finally, as a direct measure of page-level OCR quality. The validation process shows that the CEV is a valuable bridge between parsing metrics and local metrics like CER. We analyse a dataset of archival newspapers made of degraded images with complex layouts and find that state-of-the-art end-to-end models are outperformed by more traditional pipeline approaches. Whilst the CEV requires character-level positioning for optimal triage, thresholding on easily available values can predict the main error source with an F1 of 0.91. We provide the CEV as part of a Python library to support Document understanding research.

April 8, 2026 Improving the academic workflow: Introducing two AI agents for better figures and peer review Generative AI · Natural Language Processing에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.