Every story across every category, newest first. Each card links to the original publisher; daily-brief posts open as editorial pages.
arXiv:2502.06606v3 Announce Type: replace Abstract: Manipulating the material appearance of objects in images is critical for applications like augmented reality, virtual prototyping, and digital content creation.…
arXiv:2608.02835v1 Announce Type: new Abstract: Historical lenticular films, such as those created with the Kodacolor process, encode color information in a distinctive spatial format. This structure…
arXiv:2608.03450v1 Announce Type: cross Abstract: Reasoning in Multimodal Large Language Models (MLLMs) requires both fine-grained visual perception and rigorous logical deduction. Explicit text-based Chain-of-Thought (CoT) is…
arXiv:2608.02833v1 Announce Type: new Abstract: Chart question answering (CQA) requires multimodal large language models (MLLMs) to integrate visual comprehension with logical reasoning, yet current models struggle…
arXiv:2608.03165v1 Announce Type: cross Abstract: Invisible image watermarks are increasingly used for deepfake detection and provenance tracking, where they must survive not only incidental distortions but…
arXiv:2608.02762v1 Announce Type: new Abstract: Fine-grained wildlife classification in aerial imagery is limited not only by model performance, but also by unreliable labels: animals occupy few…
arXiv:2608.02790v1 Announce Type: new Abstract: Vision-language models (VLMs), including medical specialists, are increasingly proposed for medical imaging, yet their stated confidence is rarely evaluated separately from…
arXiv:2608.02791v1 Announce Type: new Abstract: MLLM-based segmentation faces a core segmentation trilemma: high segmentation performance, preserved dialogue ability, and fast inference. Embedding-prediction methods may disrupt language…
arXiv:2608.02803v1 Announce Type: new Abstract: Attention-based multiple instance learning (ABMIL) is the predominant approach for slide-level prediction in computational pathology, yet its attention maps provide only…
arXiv:2608.02792v1 Announce Type: new Abstract: Self-supervised Vision Foundation Models (VFMs) have become essential backbones for downstream tasks due to their strong and transferable visual representations. However,…
arXiv:2608.02830v1 Announce Type: new Abstract: Many-shot in-context learning (ICL) lets vision-language models (VLMs) adapt from image--label demonstrations without weight updates, and is widely assumed to improve…
arXiv:2608.02805v1 Announce Type: new Abstract: In previous work, we integrated large language models (LLMs) into the lesion segmentation model based on the ULS23 DeepLesion dataset, using…
arXiv:2508.15169v4 Announce Type: replace Abstract: Mesh models have become increasingly accessible for numerous cities; however, the lack of realistic textures restricts their application in virtual urban…
arXiv:2608.03926v1 Announce Type: cross Abstract: Time series anomaly detection (TSAD) underpins applications in predictive maintenance, finance, and cloud computing, however performance remains sensitive to representation choices,…
arXiv:2606.27741v3 Announce Type: replace Abstract: Recent advances in video diffusion models have greatly improved visual fidelity, yet their generated motions often violate physical plausibility. We observe…
arXiv:2603.29368v2 Announce Type: replace Abstract: Driven by the advancement of 3D devices, stereo vision tasks including stereo matching and stereo conversion have emerged as a critical…
arXiv:2603.16548v2 Announce Type: replace-cross Abstract: In light of globalized hardware supply chains, the assurance of hardware components has gained significant interest, particularly in cryptographic applications and…
arXiv:2608.00094v2 Announce Type: replace Abstract: Pretrained video diffusion models can act as renderers when the desired scene state is already specified by an animated mesh, a…
arXiv:2608.02612v1 Announce Type: new Abstract: Formulating an optimization problem strongly affects the quality of the final solution, yet good formulations usually require substantial expertise. Recent studies…
arXiv:2608.02867v1 Announce Type: new Abstract: Although reinforcement learning with verifiable rewards (RLVR) has improved the performance of large language models (LLMs) across a variety of reasoning…
arXiv:2604.04468v3 Announce Type: replace-cross Abstract: Evaluating retail strategies before deployment is difficult, as outcomes are determined across multiple stages, from seller-side persuasion through buyer-seller interaction to…
arXiv:2608.02807v1 Announce Type: new Abstract: How can we better represent the impact of sociocultural structures on decision making in computational cognitive models? Modeling this impact requires…
arXiv:2608.01269v2 Announce Type: replace Abstract: Hierarchical Graph Retrieval-Augmented Generation (GraphRAG) organizes corpus knowledge at multiple levels of granularity, yet fixed context construction may fail to translate…
arXiv:2608.02703v1 Announce Type: new Abstract: Weight-only quantization substantially reduces the storage of large language model (LLM) transformer blocks, but practical backends often retain the final language-modeling…