Search posts, papers, and topics
Hackers removed a Flock license‑plate reader camera, copied its storage, extracted an on‑device encryption key, and released ~1.6 M images and logs covering 21 days of operation. Analysis shows the device captures ~28 images per vehicle, detects people, and stores raw media in unencrypted partitions. License‑plate detection runs on the cloud, and the camera’s software can mis‑identify graphics as…
Alibaba's Damo Academy open-sourced Damo Radar, an AI model that detects nearly 150 abdominal conditions, including cancers, from CT scans. It achieved an average AUC of 0.913 across 146 clinical findings and outperformed most human radiologists in a comparative study.
This paper introduces a novel evaluation framework to assess the physical world reasoning capabilities of omni-modal generative models like MiniMax-H3. It found that MiniMax-H3 achieved an overall success rate of 41.97% across 517 instances, with significant performance variations depending on the input modalities and reasoning tasks.
Action tokenizers for autoregressive VLA models often fail to preserve subtle action adjustments, despite good pointwise reconstruction. This paper introduces Physical Rank Consistency (PRC) to measure relational fidelity and ActionPiece, a new tokenizer that uses joint supervision to preserve these physical relationships, significantly improving policy success on robotics benchmarks.
FAMOS is a feed-forward model that predicts 3D articulation, including movable-part segmentation and joint parameters, from sparse, unordered point clouds. It leverages multiple observations through a Multi-state Articulation Transformer and a novel observed articulation span objective, outperforming existing baselines.
MintAct is a family of vision-language models (2B-8B) that unifies UI grounding, multi-step navigation, and visual tool use across mobile, desktop, and web environments. It achieves state-of-the-art performance by leveraging a scalable environment and an asynchronous reinforcement learning infrastructure.
Vision‑RL2 trains a lightweight proposal network via region‑level reinforcement learning to select high‑resolution evidence for multimodal LLMs, allowing coarse‑resolution localization and fine‑resolution recognition. Across six fine‑grained vision benchmarks it reduces visual token count by ~4× while matching or surpassing full‑resolution accuracy.
Paint-Anything introduces a unified hex‑prompt interface that lets diffusion models generate or edit images with any 24‑bit color per object. Using a mixed supervision pipeline and a new benchmark, it boosts object‑level color fidelity on FLUX.2‑4B by up to 85 % for text‑to‑image and 28 % for editing.
UFO introduces an Atomized Chain‑of‑Evaluation (AEU) framework that breaks omni‑condition alignment in multi‑modal image generation into a sequential set of fine‑grained checks, achieving a 15.25 % boost in correlation with human judgments. The authors also release UFO‑Bench, a benchmark for testing how well models satisfy combined textual and visual conditions.
VA‑Bench is a new benchmark that evaluates general‑purpose multimodal LLMs on the full observe‑reason‑act‑revise loop in embodied robotics, using RGB demonstrations, active camera control, and metric Cartesian commands. The best model reaches 53.9% average task success, showing active perception helps but long‑horizon tasks remain unsolved.
OmniVBench is a new benchmark and the Omni‑R2V Dataset, offering 7 task families, 18 fine‑grained reference‑to‑video generation tasks and a factor‑grounded evaluation checklist of over 12 k items. The dataset provides 340 k industrial‑grade video samples and pipelines for constructing reference‑target pairs, exposing large performance gaps in current R2V models.
Srijika is a system for restyling OpenType fonts across nine Indic scripts by reusing existing template font layout data (GSUB, GPOS). This approach ensures complex script features like conjuncts remain consistent, addressing a major challenge in Indic font generation.
PANORAMA introduces a VLM that grounds each phrase of a caption to pixel masks by selecting from a phrase‑conditioned pool of mask proposals, trained jointly with caption generation. It sets a new benchmark on the PanoCaps dataset and outperforms prior methods on several pixel‑level grounding tasks.
FLAT is a pre‑training framework that encodes images and text into a shared 1D token sequence with variable length via nested dropout, enabling the same embeddings for cross‑modal retrieval and generation. It attains state‑of‑the‑art scores on COCO and Flickr30K for captioning, retrieval, and text‑to‑image generation, and supports interpolation and zero‑shot composed retrieval.
EventEgoHands++ adds an instance‑aware hand detector and an Adaptive Attention module to event‑camera egocentric hand‑mesh reconstruction, distinguishing left/right hands and modeling their interaction. The authors also release EEH‑R, a ~1 M‑frame real dataset, and report consistent gains over prior baselines on synthetic and real tests.
The paper proposes a retention‑constrained post‑training quantization benchmark for Cellpose‑SAM, showing that weight‑only W8A16 and a mixed W4/W8 scheme keep instance F1 scores while cutting model size 6.76×, whereas ternary quantization fails on most images.
This paper introduces a training-adaptive Convolutional Sparse Coding (CSC) framework where the sparsity coefficient is learned end-to-end via FISTA unfolding. It uses an information bottleneck perspective to balance representation compression and content preservation, showing improved robustness to input perturbations on CIFAR and ImageNet.
RelateAnything is a 53 M‑parameter model that predicts arbitrary textual relations between any supplied image regions, using a text‑embedding bank instead of a fixed classifier. Trained on a new 4.3 M‑relation dataset, it outperforms prior open‑vocab methods by 2.3‑3.5× mean recall while running in ~20 ms per frame.
This paper introduces HEAL, a method to identify and mitigate hallucinations in Multimodal Large Language Models (MLLMs). It finds that hallucinations stem from information distribution drift in "synergy heads" within the attention mechanism and proposes dynamic calibration to steer output towards factual evidence.
This paper introduces Movement Trend Guidance (MTG), a method to provide foresight to 3D diffusion policies for robotic manipulation without explicit trajectory planning. MTG learns a compact latent representation of interaction evolution, significantly improving performance on various benchmarks with minimal parameter overhead.
PhysStream introduces a two‑stage autoregressive video generator that uses online‑derived positional and tracking maps (structured scene memory) and sparse velocity‑increment signals to enable fine‑grained, physics‑grounded control of multi‑object tabletop scenes. It cuts motion distribution error by 33 % and trajectory error by 12 % versus strong baselines, and wins 85 % of human preference test…
RefineEdit is a training‑free framework that edits images by refining binary image codes through a generative refinement network, using probability differences to pick edit locations. It outperforms prior methods on background preservation and CLIP scores across nine editing categories without extra training or masks.
The paper presents SNAP3D, a physics‑guided pipeline that converts a single image into a set of 3D parts that can be assembled without interpenetration. By using simulation‑driven connector placement and a new physics‑based evaluation, the method yields assemblies that are both geometrically accurate and stable enough for 3D printing.
ModaLens introduces a paired image-swap audit to measure how radiology report availability affects image sensitivity in medical VLMs. It found that MedGemma-27B's answers changed significantly more often when the image was swapped if the report was not available, indicating reports reduce image reliance.
The paper dissects which aspects of synthetic Thai OCR data (typeface diversity, 2‑D layout, real handwriting glyphs) actually help transfer to real documents. Using those insights they train Wayu-Paxa-OCR-Zero without any real OCR labels and achieve character error rates comparable to or better than supervised baselines.
Paper evaluates a standard 3‑D nnU‑Net on the new BraTS‑GoAT benchmark, training on 1,351 cases with five‑fold cross‑validation and test‑time mirroring. It reports Dice scores of 0.78/0.83/0.89 (ET/TC/WT) and shows a ~0.07 drop on heterogeneous validation, with limited benefit from ensembling or mirroring and failure linked to small, fragmented tumors.
