2026-06-15 AI 리서치 브리핑

Hallucinations in Large Vision-Language Models (LVLMs) remain a persistent challenge, often stemming from inadequate integration of visual information during multimodal reasoning. A key cause is the model's over-reliance on textual priors and underutilization of visual cues, leading to outputs that are linguistically fluent but visually inaccurate. For example, given an image of an empty kitchen countertop, an LVLM might hallucinate a "bowl of fruit" or "cup of coffee", relying on language associations rather than visual evidence. Most LVLMs incorporate visual features by appending them to the input stream of a pre-trained LLM and training on large-scale vision-language datasets. Our systematic analysis reveals that this strategy often leads to over-dependence on textual information due to the inherent bias of LLMs towards language-dominant representations. This imbalance skews attention towards the text over visual content, weakening the model's ability to ground outputs in visual inputs. To address this, we propose a simple yet effective visual feature incorporation method that encourages the model to learn visually-informed textual embeddings distinct from those of the base LLM and promotes a more balanced attention distribution. Experimental results across multiple hallucination benchmarks demonstrate that our method significantly reduces hallucinations and fosters more balanced multimodal reasoning. Notably, our approach achieves substantial gains, including +9.33% on MMVP-MLLM, +2.99% on POPE-AOKVQA, up to +3.4% on Merlin, and +3% on the hard-data split of HallusionBench.

Earth observation (EO) data spans a wide range of spatial, spectral, and temporal resolutions, from high-resolution optical imagery to low resolution multispectral products or radar time series. While recent foundation models have improved multimodal integration for learning meaningful representations, they often expect fixed input resolutions or are based on sensor-specific encoders limiting generalization across heterogeneous EO modalities. To overcome these limitations we introduce RAMEN, a resolution-adjustable multimodal encoder that learns a shared visual representation across EO data in a fully sensor-agnostic manner. RAMEN treats the modality and spatial and temporal resolutions as key input data features, enabling coherent analysis across modalities within a unified latent space. Its main methodological contribution is to define spatial resolution as a controllable output parameter, giving users direct control over the desired level of detail at inference and allowing explicit trade-offs between spatial precision and computational cost. We train a single, unified transformer encoder reconstructing masked multimodal EO data drawn from diverse sources, ensuring generalization across sensors and resolutions. Once pretrained, RAMEN transfers effectively to both known and unseen sensor configurations and outperforms larger state-of-the-art models on the community-standard PANGAEA benchmark, containing various multi-sensor and multi-resolution downstream tasks. Our code and pretrained model are available at https://github.com/nicolashoudre/RAMEN.

EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

MiniMax Sparse Attention에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

InterleaveThinker: Reinforcing Agentic Interleaved Generation에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

In this work, we propose StereoGeo, an end-to-end network-based approach for stereo camera calibration. Our method estimates the focal lengths and gravity directions of the left and right cameras, as well as the relative extrinsic transformation relating them. Existing methods often rely on calibration patterns in structured environments or address only a single camera configuration, being limited to either intrinsic or extrinsic estimation, and depending on a multi-view setups. StereoGeo extends the GeoCalib algorithm, integrating deep neural network feature extraction with a differentiable optimizer. Extensive experiments on real-world benchmarks demonstrate that StereoGeo achieves competitive performance for intrinsic calibration and provides accurate stereo extrinsic estimation, outperforming existing methods that are limited to monocular settings. The dataset used in this work is partially publicly available at https://github.com/meddourimane/StereoGeo-dataset.

Increasing evidence supports watch-and-wait (WW) surveillance for patients with rectal cancer who show clinical complete response (cCR) at restaging following total neoadjuvant treatment (TNT). However, accurate methods to early detect local regrowth (LR) from follow-up endoscopy images during WW are essential to manage care and prevent distant metastases. Hence, we developed a Siamese Swin Transformer with Dual Cross-Attention (SSDCA) to combine longitudinal endoscopic images at restaging and follow-up and distinguish cCR from LR. SSDCA leverages pretrained Swin Transformers to extract domain agnostic features and enhance robustness to imaging variations. Dual cross attention is implemented to emphasize features from the paired scans without requiring any spatial alignment to predict response. SSDCA as well as Swin-based baselines were trained using image pairs from 135 patients and evaluated on a held-out set of image pairs from 62 patients. SSDCA produced the best balanced accuracy (81.76% $\pm$ 0.04), sensitivity (90.07% $\pm$ 0.08), and specificity (72.86% $\pm$ 0.05). Robustness analysis showed stable performance irrespective of artifacts including blood, stool, telangiectasia, and poor image quality. UMAP clustering of extracted features showed maximal inter-cluster separation (1.45 $\pm$ 0.18) and minimal intra-cluster dispersion (1.07 $\pm$ 0.19) with SSDCA, confirming discriminative representation learning. Code and weights available at: https://github.com/Jotanator/SSDCA

Current representation learning paradigms force a fundamental compromise: self-supervised methods scale to massive datasets but yield opaque features, whereas interpretable models remain bottlenecked by the need for dense human annotation. We introduce Self-Supervised Concept discOvery via Preference lEarning (\model), a label-free framework that resolves this dilemma. Instead of treating Vision-Large-Language Models (VLLMs) as static feature extractors, \model leverages them as active participants in a self-supervised preference optimization loop. By autonomously hypothesizing, validating, and reinforcing candidate visual attributes directly from raw imagery, our framework discovers novel, structured concepts without a single label. Extensive experiments across natural, medical, and physics domains demonstrate that \model successfully extracts domain-specific concepts where standard VLLMs often fail to generate. By amortizing concept discovery directly into the VLLM backbone through our self-supervised preference objective -- rather than relying on static generation and disjoint filtering -- we achieve up to a 24-point absolute improvement in downstream top-1 classification accuracy on unseen data. Our work suggest that interpretability can emerge through a model's autonomous interaction with incidental visual structures, without any human supervision.

June 12, 2026 Research into how AI can help users understand skin conditions Health & Bioscience · Human-Computer Interaction and Visualization에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

June 12, 2026 A low-carbon computing platform from your retired phones Climate & Sustainability · Distributed Systems & Parallel Computing에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

June 10, 2026 New framework for auditing machine unlearning Algorithms & Theory · Responsible AI · Security, Privacy and Abuse Prevention에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

June 5, 2026 Unlocking dependable responses with Gemini Enterprise Agent Platform’s Agentic RAG Data Management · Machine Intelligence · Natural Language Processing · Product에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

June 4, 2026 Towards passive heart health monitoring via smartphone camera Health & Bioscience · Human-Computer Interaction and Visualization · Machine Intelligence에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

Microsoft Research blog에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

Ire identifies another LOTUSLITE specimen에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

Data Formulator 0.7은 AI 기반 엔터프라이즈 데이터 분석 도구의 최신 업데이트입니다. 이 버전은 기업 데이터 분석을 위한 새로운 기능을 제공하며, 자세한 내용은 원문 링크에서 확인할 수 있습니다.