← 전체 목록

2026-10-14 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

Splat2Act: From Captured Scenes to Personalized VLA Manipulation

Paper arXiv cs.CV (recent)

A user who brings a generalist manipulation policy into their home or office wants it to pick up their objects from their shelves, counters, and tables. Yet even a strong generalist like $π_{0.5}$ achieves 0% pickup success in our captured deployment scenes without adaptation, and collecting real demonstrations in every user's environment is prohibitively expensive. We present Splat2Act, an automated real-to-sim-to-real pipeline that personalizes a pretrained vision-language-action (VLA) policy to a specific scene and object set using only a handheld phone scan and images of the user's objects. Unlike prior real-to-sim work that reconstructs individual tabletops, Splat2Act operates on building-scale indoor environments: it builds a photorealistic digital twin with 3D Gaussian Splatting and collision geometry, automatically discovers tabletop and non-tabletop receptacles, constructs feasible pickup tasks, and generates successful demonstrations with a privileged simulation oracle, with only scene and object capture required from a human. Applied to 101 scanned campus environments with a median navigable area of 104.87 m$^2$ and 7 receptacles, the pipeline yields 852 receptacles and over 68,000 pickup demonstrations. We fine-tune $π_{0.5}$ in two stages: Stage 1 adapts to hundreds of public object assets, drawn either from the deployment scene alone or from all 101 scenes; Stage 2 personalizes to the user's own objects on the deployment scene's receptacles. Our strongest personalized policy reaches 62.5% aggregate pickup success in the target scene. Deployed on a real Stretch 3, the same policy achieves 63.9% success on a 12-task subset, closely tracking its 66.7% simulated success on those tasks. These results suggest that automated real-to-sim-to-real training can personalize VLA manipulation policies using only simulation-oracle data.

원문 보기

Images Talk Back: Guiding MMDiTs by Suppressing Image-to-Text Feedback

Paper arXiv cs.CV (recent)

Multimodal diffusion transformers (MMDiTs) allow the evolving image to update internal text representations through joint attention. These representations then guide subsequent image updates, raising a question: does this feedback help correct deviations from the prompt, or preserve them? We find that image-to-text (I2T) feedback can preserve the objects and attributes already represented in the evolving image, including errors. Transplanting I2T messages can rescue failures or disrupt successes. At matched intervention strengths, suppressing the influence of I2T feedback improves generation, whereas opposite controls degrade it. These findings motivate Semantic Feedback Guidance (SFG), which suppresses the influence of I2T feedback by guiding away from an auxiliary branch that strengthens this feedback and weakens text-to-image conditioning. The in-place variant, iSFG, directly suppresses I2T feedback and strengthens text-to-image conditioning, requiring no extra model evaluations. Temporal interventions motivate running the SFG branch during the first 20% of image sampling steps, requiring about $1.2\times$ the base NFE without classifier-free guidance (CFG). Experiments across three image-generation backbones show gains in alignment and preference-model scores. On FLUX, adding SFG to CFG raises GenEval from $0.6661$ to $0.7479$; on SD3.5M, iSFG adds $+1.33$ HPSv2.1 over CFG at zero extra NFE. The control also transfers to text-to-video and image-to-video generation, improving VBench scores. Code is available at https://github.com/yyc1215lll-creator/SFG.

원문 보기

sLLM 트렌드

경량화·효율화를 위한 스몰 LLM 연구

InstantFusion: A Shared Latent Interface for Heterogeneous Image Generators

Paper arXiv cs.CV (recent)

Diffusion/flow models have emerged as the de facto paradigms for image generation, giving rise to a diverse family of modern generators with increasingly heterogeneous architectures and representations. Despite their remarkable generation capabilities, the cross-model alignment of latent representations and the consistency of their underlying denoising dynamics remain underexplored. In this work, we uncover an intriguing cross-model compatibility: independently trained generators exhibit similar latent spatial organization, while directly handing off intermediate states between unaligned models can still preserve coarse visual content. Motivated by these observations, we propose InstantFusion, a lightweight shared latent interface that connects the denoising trajectories of heterogeneous image generators. Specifically, to enable flexible cross-model state translation, model-specific Latent AutoEncoders (LAEs) are introduced to project intermediate states from different generators into a shared latent space and decode them into the latent space of a target generator. This shared space is constrained by two complementary objectives: aligning intermediate states derived from the same image at matched noise levels and synchronizing their corresponding local denoising velocities. Once trained, InstantFusion allows denoising to seamlessly transition across frozen generators without requiring a dedicated mapping for every model pair. The versatility of InstantFusion is demonstrated across acceleration, multi-preference composition, cross-architecture on-policy distillation, and cross-model composition, achieving competitive performance across these diverse settings.

원문 보기

On-Device AI

디바이스 내 추론 및 엣지 최적화 동향

October 2, 2026 Toward provably private learning from federated data Mobile Systems · Security, Privacy and Abuse Prevention · Software Systems & Engineering

News Google Research Blog

October 2, 2026 Toward provably private learning from federated data Mobile Systems · Security, Privacy and Abuse Prevention · Software Systems & Engineering에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

AI 뉴스 & 리서치

기업/연구기관의 주요 발표와 블로그 업데이트

GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives

Paper Hugging Face Papers

GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

Thinking Inertia: LLMs Keep Thinking When Told Not To

Paper Hugging Face Papers

Thinking Inertia: LLMs Keep Thinking When Told Not To에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

AgentSWE: Can Coding Agents Build the Agent You Actually Want?

Paper Hugging Face Papers

AgentSWE: Can Coding Agents Build the Agent You Actually Want?에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

Scaling Agentic Data for Long-Horizon Terminal Intelligence

Paper Hugging Face Papers

Scaling Agentic Data for Long-Horizon Terminal Intelligence에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

VIS-Ground: Video Interactive Storytelling with Contextual Grounding

Paper Hugging Face Papers

VIS-Ground: Video Interactive Storytelling with Contextual Grounding에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

Towards Physically Grounded Articulated 3D Assets: A Multi-Agent Pipeline and Benchmark

Paper arXiv cs.CV (recent)

In this paper, we study physically grounded articulated 3D asset generation---moving the goal from reproducing how objects look to capturing how they move and function. Inspired by the literature on procedural and agentic generation, we present Artisan, a system that extends the latest method Articraft by introducing a multi-agent pipeline with physical simulation feedback, enabling comprehensive attributes beyond geometry, appearance, and physically plausible articulation, such as collision-free motion, stability under gravity, and accurate mass and material properties. Furthermore, we construct a unified benchmark spanning four key aspects: spatial fidelity, physical plausibility, downstream task performance, and overall quality. The benchmark encompasses 100 reference assets from ArtVIP and LightWheel, 50 stability prompts, and 50 ABO objects with reference masses, with protocols evaluating various metrics. Through extensive evaluation of more than 10 representative models, Artisan achieves competitive spatial fidelity while attaining the lowest collision rates and highest stability rates among the evaluated methods. Together, our system and benchmark establish insights for advancing 3D generation towards physically plausible, functionally usable assets.

원문 보기

Evolving Hybrid Quantum-Classical Architectures for Image Classification

Paper arXiv cs.CV (recent)

Hybrid quantum classical neural networks integrate parameterized quantum circuits (PQCs) with established deep learning architectures, but their performance depends strongly on the choice of quantum circuit architecture, a choice that remains largely manual. Most existing approaches rely on hand-designed or fixed circuit ansätze, requiring circuit structure, gate composition, and qubit connectivity to be specified in advance with no guarantee that they suit the task. This limitation is especially acute in image classification, where quantum circuits must transform features extracted by classical networks while remaining compact enough for practical training, requirements that generic, task-agnostic ansätze are unlikely to satisfy simultaneously. We extend EXAQC, an evolutionary framework for automated quantum circuit discovery, to image classification. EXAQC evolves PQCs as intermediate processing modules while retaining classical feature-extraction and prediction layers. On MNIST, Fashion-MNIST, and CIFAR-10, EXAQC achieves 98.42%, 90.62%, and 85.47% accuracy, respectively, while using comparable gate counts to other quantum architecture-search methods. Against classical networks, evolved hybrid models maintain comparable accuracy with substantially fewer trainable parameters, reaching 85.68% on CIFAR-10 with over 25$\times$ fewer parameters than a 10-layer CNN. Encoding choice also matters: rotation-based encodings (RX, RY, U3) outperform amplitude encoding by 22-25 points on CIFAR-10. These results demonstrate that automated circuit discovery yields compact quantum modules that can replace larger classical components in vision architectures while retaining competitive accuracy.

원문 보기

October 7, 2026 Does better work always mean better workers?

News Google Research Blog

October 7, 2026 Does better work always mean better workers?에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

October 6, 2026 Unlocking Earth AI’s planetary geospatial foundation models for global public health Earth AI · Global · Health & Bioscience

News Google Research Blog

October 6, 2026 Unlocking Earth AI’s planetary geospatial foundation models for global public health Earth AI · Global · Health & Bioscience에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

October 5, 2026 Open and Emergent Problems in Agentic Privacy and Security: A Contextual Angle Generative AI · Natural Language Processing · Security, Privacy and Abuse Prevention

News Google Research Blog

October 5, 2026 Open and Emergent Problems in Agentic Privacy and Security: A Contextual Angle Generative AI · Natural Language Processing · Security, Privacy and Abuse Prevention에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

September 29, 2026 How Diffusion Controller unifies and simplifies AI image generation Algorithms & Theory · Machine Intelligence

News Google Research Blog

September 29, 2026 How Diffusion Controller unifies and simplifies AI image generation Algorithms & Theory · Machine Intelligence에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

Simulating student learning for better AI tutoring

News Microsoft Research Blog

Simulating student learning for better AI tutoring에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses

News Microsoft Research Blog

Agent Lightning v1.0은 실제 하네스를 사용하여 에이전트를 훈련하기 위한 3,500줄의 경량 에이전트 RL 프레임워크입니다. 이 프레임워크에 대한 최신 업데이트가 공개되었으며, 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

Forecasting space weather risks on power grids

News Microsoft Research Blog

전력망에 대한 우주 기상 위험을 예측하는 방법에 대한 최신 정보가 있습니다. 이 주제에 대한 더 자세한 내용은 원문 링크를 통해 확인할 수 있습니다.

원문 보기

참고한 소스