← 전체 목록

2026-10-25 AI 리서치 브리핑

최신 VLM, sLLM, on-device AI 논문과 연구 블로그를 한눈에 정리합니다. 중복 기사 방지를 위해 URL 기준으로 추적합니다.

총 18건 요약 자동 생성

VLM 업데이트

멀티모달 비전-언어 모델의 최신 논문과 리더보드 변화

Sensorimotor Alignment: A Platonic Proxy for Embodied Policy Success

Paper arXiv cs.CV (recent)

Robotic foundation models are typically evaluated through costly closed-loop rollouts, which motivates cheap offline proxies for model capability. The Platonic Representation Hypothesis (PRH) suggests that as representations improve, different modalities such as vision and language converge toward a shared statistical model of reality. We ask whether motion trajectories form another such modality: as embodied models become more capable, should their sensory representations converge toward the structure of physical motion? To examine this, we propose Sensorimotor Alignment ($S^2$), a training-free offline metric that measures how well a model's sensory representation aligns with the geometry of physical motion. We find that $S^2$ correlates positively with downstream robot task success across embodied model families, making it a low-cost offline proxy for prioritizing models before closed-loop evaluation. $S^2$ can also identify promising vision-language model (VLM) backbones even before costly fine-tuning into vision-language-action models (VLAs). Beyond this correlation, $S^2$ offers representation-level explanations for phenomena observed in VLAs and world action models (WAMs). With $S^2$, we extend PRH to embodied models and make sensorimotor alignment empirically measurable, offering insight into why an embodied model succeeds beyond its closed-loop success rate.

원문 보기

sLLM 트렌드

경량화·효율화를 위한 스몰 LLM 연구

Editing Images into Reusable Layers via Compositional Edit-Prior Distillation

Paper Hugging Face Papers

Editing Images into Reusable Layers via Compositional Edit-Prior Distillation에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

Reading, Writing, Sharing, and Interacting with the World through Video

Paper arXiv cs.CV (recent)

Video foundation models have advanced rapidly in understanding and generating visual sequences, while video world models seek to capture the underlying dynamics of the world they depict. Despite their different objectives, both concern the relationship between video observations and an evolving world. This survey adopts world modeling as a unifying lens for examining these developments. Viewing an observed video as a partial, lossy, and temporally ordered projection of a latent temporal world, we organize the literature around four complementary operations: reading infers world properties from observed video; writing synthesizes video from specified or learned world conditions; sharing integrates understanding and generation through common modeling mechanisms; and interacting predicts and updates world states under actions and evolving observations. This perspective distinguishes temporal coherence in observed or generated sequences from consistency in the underlying world state. Across tasks, representations, models, datasets, and benchmarks, we trace a shift in emphasis from clip-level recognition and perceptual fidelity toward persistent state, controllable evolution, physical and causal validity, and evaluation grounded in interaction and downstream decisions, and we distill the open challenges that follow.

원문 보기

On-Device AI

디바이스 내 추론 및 엣지 최적화 동향

A Unified Framework for Image-to-3D Part Generation via Variable Granularity

Paper arXiv cs.CV (recent)

Controllable 3D part generation is pivotal for digital asset creation, yet existing methods lack the flexibility to accommodate diverse user workflows requiring varying levels of control. In this paper, we introduce FlexPart, a unified image-to-3D part generation framework that supports variable-granularity geometric conditions within a single model. By seamlessly integrating heterogeneous inputs, ranging from sparse points to dense bounding boxes and masks, via gated adaptive modulation, FlexPart unlocks a powerful cross-modal synergy. We also propose an asymmetric geometric guidance mechanism that leverages strong spatial priors to align representations across granularities, improving geometric consistency and facilitating inter-task synergy. Under mask conditioning on PartVerseXL, FlexPart reduces Part CD by 16.6% relative to TripoSG + SAM3D and by 10.5% relative to OmniPart, while maintaining competitive whole-mesh quality. The code can be found at https://github.com/Gucci233/FlexPart

원문 보기

BrickWright: Agentic Creation of Physically Feasible Brick Builds

Paper arXiv cs.CV (recent)

Frontier coding agents are becoming increasingly adept at 3D modeling. Yet, they still face challenges when building objects meant to be assembled in the physical world, often creating invalid assemblies with floating, colliding, or disconnected parts. We argue that providing agents with tools for assembling builds and verifying their physical feasibility is sufficient for them to produce physically valid assemblies that still adhere to input prompts. Focusing on the domain of LEGO brick builds, we present BrickWright, a framework for generating physically feasible brick builds from text or image prompts using pre-trained agents, where a build is physically feasible if it uses only real parts, has no colliding or floating parts, and forms a connected structure if possible. BrickWright guides agents to create builds by writing code with BrickLayer, a Python toolkit with two main components: an ergonomic brick assembly API that halves inference cost compared to working in raw LDraw, and a validator that provides feedback on physical feasibility. Whereas baseline agents achieve physical validity rates ranging from only 9% (GPT-6 Luna) to 69% (GPT-6 Astra), BrickWright-guided agents achieve 100% validity on a sample of 512 prompts, while improving prompt adherence for lightweight agents and maintaining it for stronger agents. Additionally, they outperform specialized models on the text-to-brick task. Code is available on our project page: https://avalovelace1.github.io/brickwright/

원문 보기

AI 뉴스 & 리서치

기업/연구기관의 주요 발표와 블로그 업데이트

WeVisOne-VL: Unified Visual Perception from Objects to Pixels

Paper Hugging Face Papers

WeVisOne-VL: Unified Visual Perception from Objects to Pixels에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

Making MLLM Latents Matter: Factor-Aware Predictive Learning for Cinematic Video Generation

Paper Hugging Face Papers

Making MLLM Latents Matter: Factor-Aware Predictive Learning for Cinematic Video Generation에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

Deep Search in Real-World Web Environments

Paper Hugging Face Papers

Deep Search in Real-World Web Environments에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

IQuest-Q1: Advancing Foundation Capabilities for Agentic CLI Systems

Paper Hugging Face Papers

IQuest-Q1: Advancing Foundation Capabilities for Agentic CLI Systems에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

SpectralCanary: Embarrassingly Simple Low-Frequency Traces for T2I Dataset-Use Auditing

Paper arXiv cs.CV (recent)

Auditing whether a text-to-image (T2I) model was fine-tuned on a particular image collection is difficult: a model can absorb collection-level visual characteristics without reproducing training images. Proactive dataset-use auditing plants a shared signal in a dataset before release, then later checks whether that signal appears in a suspect model's generated outputs. Existing approaches often trade off verifiability, fidelity, robustness, and deployability. We introduce $\textbf{SpectralCanary}$, which uses a smooth low-pass mask to blend a fixed canary image into every collection image while leaving captions unchanged and requiring neither auxiliary generation nor per-image optimization. A lightweight verifier detects the transferred signal in suspect-model outputs. Across eight tests on the Pokemon dataset and three realistic data transformations, spanning two architectures families, SpectralCanary achieves the highest average per-generation TPR@$1\%$ FPR ($91.1\%$) and fixed threshold model-level accuracy using 30 generations ($94.8\%$) among the evaluated methods. Across five datasets spanning artistic, medical, satellite, and fashion domains with SD3.5, SpectralCanary averages $92.4\%$ per-generation TPR@$1\%$ FPR while preserving the released images (SSIM $0.989$, LPIPS $0.022$) with a near-zero mean change FID (mean $Δ$FID $0.05$) across datasets. Matched-energy ablations on Pokemon and ROCOv2 support our design choice, low-frequency placement transfers more reliably compared to mid/high-frequency placement. Under the evaluated adaptive attacks, the most effective removal requires aggressive modification and incurs more than $25$ $Δ$FID points. These results identify low-frequency visual signals as effective carriers for collection-level T2I audit traces.

원문 보기

October 23, 2026 Bringing foundational models to the front lines of TB screening Generative AI · Health & Bioscience

News Google Research Blog

October 23, 2026 Bringing foundational models to the front lines of TB screening Generative AI · Health & Bioscience에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

October 21, 2026 Empowering frontline maternal care with AI-assisted ultrasound Health & Bioscience · Machine Perception

News Google Research Blog

October 21, 2026 Empowering frontline maternal care with AI-assisted ultrasound Health & Bioscience · Machine Perception에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

October 16, 2026 Grounding AI agents in biological reality: Building blocks for autonomous wet labs General Science · Health & Bioscience · Robotics

News Google Research Blog

October 16, 2026 Grounding AI agents in biological reality: Building blocks for autonomous wet labs General Science · Health & Bioscience · Robotics에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

October 14, 2026 Research@ 2026: 10 ways we're amplifying human ingenuity General Science · Generative AI · Health & Bioscience

News Google Research Blog

October 14, 2026 Research@ 2026: 10 ways we're amplifying human ingenuity General Science · Generative AI · Health & Bioscience에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

October 14, 2026 Analyzing technical documents with Deep Review General Science · Machine Intelligence · Natural Language Processing

News Google Research Blog

October 14, 2026 Analyzing technical documents with Deep Review General Science · Machine Intelligence · Natural Language Processing에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

Flint-interactive: A language for creating interactive data visualizations

News Microsoft Research Blog

Flint-interactive: A language for creating interactive data visualizations에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

Solving a 31-year-old grand challenge in mathematics – the KLS conjecture

News Microsoft Research Blog

수학 분야의 31년 묵은 난제였던 KLS 추측이 최근 해결되었습니다. 이 소식은 해당 분야의 중요한 진전을 알립니다.

원문 보기

Proof-based general-purpose computing with Magnetar

News Microsoft Research Blog

Magnetar를 활용하여 증명 기반 범용 컴퓨팅을 구현하는 방법에 대한 새로운 정보가 공개되었습니다. 이는 컴퓨팅 분야의 혁신적인 접근 방식을 제시합니다.

원문 보기

참고한 소스