We introduce MediX-R1, an open-ended Reinforcement Learning (RL) framework for medical multimodal large language models (MLLMs) that enables clinically grounded...

We present a scalable 3D reconstruction model that addresses a critical limitation in offline feed-forward methods: their computational and memory requirements ...

We identify occlusion reasoning as a fundamental yet overlooked aspect for 3D layout-conditioned generation. It is essential for synthesizing partially occluded...

A dataset server must often distribute the same large payload to many clients, incurring massive communication costs. Since clients frequently operate on divers...

Bio-inspired event cameras have recently attracted significant research due to their asynchronous and low-latency capabilities. These features provide a high dy...

The lack of reasoning capabilities in Vision-Language Models (VLMs) has remained at the forefront of research discourse. We posit that this behavior stems from ...

Open-vocabulary segmentation (OVS) extends the zero-shot recognition capabilities of vision-language models (VLMs) to pixel-level prediction, enabling segmentat...

Omni-modal reasoning is essential for intelligent systems to understand and draw inferences from diverse data sources. While existing omni-modal large language ...

Medical diagnosis requires the effective synthesis of visual manifestations and clinical metadata. However, existing methods often treat metadata as isolated ta...

In recent times, large datasets hinder efficient model training while also containing redundant concepts. Dataset distillation aims to synthesize compact datase...

AI/SWE Intern Now and Summer 2026 – Bild AI W25 Location: San Francisco, CA, US Compensation: $3 K – $10 K per month Type: Internship US citizen/visa only Abou...

Bumble announced that it’s adding a series of AI‑driven features intended to help turn matches into lasting connections, including tools that offer feedback and...

Craniofacial Superimposition is a forensic technique for identifying skeletal remains by comparing a post-mortem skull with ante-mortem facial photographs. A cr...

Temporally consistent surface reconstruction of dynamic 3D objects from unstructured point cloud data remains challenging, especially for very long sequences. E...

Egocentric manipulation videos are highly challenging due to severe occlusions during interactions and frequent object entries and exits from the camera view as...

Existing action-conditioned video generation models (video world models) are limited to single-agent perspectives, failing to capture the multi-agent interactio...

Advances in Generative AI (GenAI) have led to the development of various protection strategies to prevent the unauthorized use of images. These methods rely on ...

In recent years, a standard computational pathology workflow has emerged where whole slide images are cropped into tiles, these tiles are processed using a foun...

Arbitrary-Scale SR (ASISR) remains fundamentally limited by cross-scale distribution shift: once the inference scale leaves the training range, noise, blur, and...

Unified conditional image generation remains difficult because different tasks depend on fundamentally different internal representations. Some require conceptu...

Object hallucination is a critical issue in Large Vision-Language Models (LVLMs), where outputs include objects that do not appear in the input image. A natural...

Medical vision-language pretraining increasingly relies on medical reports as large-scale supervisory signals; however, raw reports often exhibit substantial st...

Recent advances in Multimodal Large Language Models have greatly improved visual understanding and reasoning, yet their quadratic attention and offline training...

'Cleaned Markdown Version

Test-time training (TTT) with KV binding as sequence modeling layer is commonly interpreted as a form of online meta-learning that memorizes a key-value mapping...

Visual reinforcement learning is appealing for robotics but expensive -- off-policy methods are sample-efficient yet slow; on-policy methods parallelize well bu...

We study efficient multi-vector retrieval for late interaction in any modality. Late interaction has emerged as a dominant paradigm for information retrieval in...

Embodied LLMs endow robots with high-level task reasoning, but they cannot reflect on what went wrong or why, turning deployment into a sequence of independent ...

Cryo-electron tomography (cryo-ET) enables high resolution, three-dimensional reconstruction of biological structures, including membranes and membrane proteins...

Recent diffusion methods have made significant progress in generating videos from single images due to their powerful visual generation capabilities. However, c...

While Vision-Language Models (VLMs) exhibit exceptional 2D visual understanding, their ability to comprehend and reason about 3D space--a cornerstone of spatial...

Graph-based medical image segmentation represents anatomical structures using boundary graphs, providing fixed-topology landmarks and inherent population-level ...

Deep learning has significantly advanced automated brain tumor diagnosis, yet clinical adoption remains limited by interpretability and computational constraint...

Text-to-image retrieval is a fundamental task in vision-language learning, yet in real-world scenarios it is often challenged by short and underspecified user q...

Vision-Language-Action (VLA) models are advancing autonomous driving by replacing modular pipelines with unified end-to-end architectures. However, current VLAs...

Medical image processing demands specialized software that handles high-dimensional volumetric data, heterogeneous file formats, and domain-specific training pr...

!소상공인 매장 업무 효율화 AI 솔루션 ‘모코플렉스’, AI 헤어 스타일링 ‘스타일싱크’ 출시https://besuccess.com/wp-content/uploads/2026/02/%EC%9D%B4%EB%AF%B8%EC%A7%80-%EB%AA%A8%EC%BD%94%ED%94%8C%EB...

Unified multimodal models can both understand and generate visual content within a single architecture. Existing models, however, remain data-hungry and too hea...

We propose tttLRM, a novel large 3D reconstruction model that leverages a Test-Time Training (TTT) layer to enable long-context, autoregressive 3D reconstructio...

Rapid progress in video models has largely focused on visual quality, leaving their reasoning capabilities underexplored. Video reasoning grounds intelligence i...

Current feed-forward 3D/4D reconstruction systems rely on dense geometry and pose supervision -- expensive to obtain at scale and particularly scarce for dynami...

Estimating simulation-ready scenes from real-world observations is crucial for downstream planning and policy learning tasks. Regretfully, existing methods stru...

Data visualization rules-derived from decades of research in design and perception-ensure trustworthy chart communication. While prior work has shown that large...

Solving long-horizon tasks requires robots to integrate high-level semantic reasoning with low-level physical interaction. While vision-language models (VLMs) a...

Research in machine unlearning (MU) has gained strong momentum: MU is now widely regarded as a critical capability for building safe and fair AI. In parallel, r...

The dependence on expert annotation has long constituted the primary rate-limiting step in the application of artificial intelligence to biomedicine. While supe...

Edge-based representations are fundamental cues for visual understanding, a principle rooted in early vision research and still central today. We extend this pr...

We introduce a diagonalization-based optimization for Linear Echo State Networks (ESNs) that reduces the per-step computational complexity of reservoir state up...