← 전체 목록

2026-11-01 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

Look Only When Needed: Certificate-Guided Visual Routing for Efficient Diffusion VLMs

Paper Hugging Face Papers

Look Only When Needed: Certificate-Guided Visual Routing for Efficient Diffusion VLMs에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

A-RSI: Adaptive Task Refresh for Zero-Data Multimodal Self-Improvement

Paper Hugging Face Papers

A-RSI: Adaptive Task Refresh for Zero-Data Multimodal Self-Improvement에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

sLLM 트렌드

경량화·효율화를 위한 스몰 LLM 연구

SonoWorld4D: From One Video to a 4D Audio-Visual Scene via Diffusion Synchronization

Paper arXiv cs.CV (recent)

Recent progress in visual scene generation has extended beyond static 3D scenes toward the more challenging problem of generating dynamic 4D scenes from minimal input. However, sound, despite being intrinsically coupled with dynamic objects and events, remains largely unmodeled in prior work. We introduce Video-to-4DAVScene, a new task that turns a video into an explorable, time-varying 4D audio-visual scene, and present the SonoWorld4D framework for this task. Given a monocular video, our method generates a 360 static background, reconstructs explicit motion trajectories of dynamic, sound-emitting foreground objects, and synthesizes a physically-grounded sound field consistent across multiple sources through dual-space audio diffusion synchronization. The resulting 4D scene supports real-time novel-view visual and spatial audio rendering. Evaluation on real-world dynamic scenes and a user study demonstrates SonoWorld4D generates 4D audio-visual scenes with perceptually realistic, physically grounded spatial audio consistent with scene geometry and visual content.

원문 보기

On-Device AI

디바이스 내 추론 및 엣지 최적화 동향

October 27, 2026 The sleep framework: A new way for LLMs to retain knowledge in continual learning Education Innovation · General Science · Machine Intelligence · Natural Language Processing

News Google Research Blog

October 27, 2026 The sleep framework: A new way for LLMs to retain knowledge in continual learning Education Innovation · General Science · Machine Intelligence · Natural Language Processing에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

AI 뉴스 & 리서치

기업/연구기관의 주요 발표와 블로그 업데이트

Youtu-Parsing-Omni: One Encoder, One Schema, All Modalities

Paper Hugging Face Papers

Youtu-Parsing-Omni: One Encoder, One Schema, All Modalities에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

Proving and Improving the Platonic Representation Hypothesis with JEPAs

Paper Hugging Face Papers

Proving and Improving the Platonic Representation Hypothesis with JEPAs에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

L3G-World: Real-Time Infinite World Generation with Latent 3D Gaussian Memory

Paper Hugging Face Papers

L3G-World: Real-Time Infinite World Generation with Latent 3D Gaussian Memory에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

Micro-Edits: Computational Support for Fine-Scale Edits in Film

Paper arXiv cs.CV (recent)

In film editing, every frame matters. While macro, content-level edits shape the high-level narrative of a film, small local edits often control timing and direct visual attention. For example, editors can adjust the precise timing of clips to control the length of a meaningful silence, or cut to shots that highlight a specific character's reactions to important moments. These small, detailed edits are slow and tedious to make in standard editing tools because users have to map high-level narrative goals to low-level frame-by-frame adjustments. At the same time, these fine-scale adjustments, which we call micro-edits, can be nuanced and expressive, with different choices serving different creative goals. In this work, we start by conducting a formative study with professional editors to understand the structure of micro-edits and how they are used. We then derive a mathematical formalization for this structure to develop tools that leverage AI and optimization to make exploring micro-edits simpler and more efficient for users. Finally, we validate our tools in multiple user studies and a wide range of video examples.

원문 보기

Rethinking Neural Thickets Without Weight Perturbations

Paper arXiv cs.CV (recent)

The Neural Thickets hypothesis posits that pretrained language models lie in dense neighborhoods of task-specific experts in weight space, which random Gaussian perturbations can uncover. We reproduce the reported gains, but show that they do not require this geometric explanation. Perturbing a single decoder block already recovers much of the improvement, while keeping the model entirely frozen and adding a random bias to its output logits matches or exceeds full-weight perturbations on most reasoning tasks. This suggests an alternative explanation based on output diversity, validation-based selection, and voting. We formalize this view as Perturb-Select-Vote (PSV), a general procedure that generates perturbed predictors, selects high-performing members on a small validation set, and aggregates their predictions. This interpretation connects Neural Thickets to established inference-time methods, including sampling, self-consistency, and verifier-guided selection. A first-order analysis further shows that small weight perturbations act primarily through their induced logit shifts. We extend this analysis to vision, where logit PSV substantially improves performance under domain shift, including on Earth observation, while full-weight perturbations provide little additional benefit. Together, these results suggest that the gains attributed to nearby weight-space experts can instead be obtained through output diversity, selection, and voting. Logit PSV realizes these benefits with a fully frozen model, providing a simple, training-free alternative to full-weight perturbation ensembles across language and vision.

원문 보기

Read, Allocate, Route: Role-Coupled Tokenization for Pixel-Space Generative Transformers

Paper arXiv cs.CV (recent)

Pixel-space generative Transformers typically use one token per image patch, so capturing finer detail requires more tokens and makes global attention increasingly expensive. We observe that finer detail does not necessarily require more global communication: low-frequency structure benefits from global exchange, while high-frequency detail can be modeled locally. Based on this insight, we introduce SpecSlot, a pixel-space rectified-flow Transformer that decouples output detail from the length of the global attention sequence. SpecSlot expands each spatial anchor into multiple slots, each assigned a disjoint band of DCT coefficients; this separates anchor density from spectral subdivision. Only the lowest-frequency slot from each anchor participates in global attention, while all slots interact locally. This allows the model to increase spectral detail without enlarging the global sequence. A spatial head further adds a local correction to the spectral prediction, while the generative state, target, and loss remain in pixel space. On ImageNet-256, SpecSlot achieves a comparable final FID to a FLOPs-matched JiT control while converging faster. On ImageNet-512, it improves FID by 2.84 over the control with 3.9% fewer FLOPs, and comes within only 0.69 FID of JiT-B/16 at 38.2% lower cost. On text-to-image generation, SpecSlot surpasses JiT-B/8 on DPG-Bench by 1.06 at 40.6% lower forward cost.

원문 보기

Luggage re-identification: A study of strategies towards a real-world application

Paper arXiv cs.CV (recent)

Luggage re-identification (ReID) is a critical task in video surveillance for forensics, security or border management (suspicious or abandoned luggage recognition), as well as luggage management (lost luggage recovery). It enables the association of observations of the same luggage across disjoint camera views in complex environments such as airports, train stations and border crossing. While existing approaches primarily focus on appearance-based cropped image matching under relatively clean conditions, real-world scenarios are characterized by frequent occlusions, cluttered background and crowded scenes which significantly degrade performance. Yet, strategies leveraging the complementarity of multiple shots and views from different video streams is overlooked. In this paper, we study strategies for an end-to-end pipeline that operates from multiple video streams to detect and re-identify luggage. We evaluate different variants on a benchmark dataset acquired in real-world environments to address the questions of selecting and merging different views and shots of the same luggage as well as training on different environment datasets for an overall ReID performance improvement in practical applications.

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

From synthetic enterprise data evaluations to real Microsoft Copilot AI confidence

News Microsoft Research Blog

From synthetic enterprise data evaluations to real Microsoft Copilot AI confidence에 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

Solving a 31-year-old grand challenge in mathematics – the KLS conjecture에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

참고한 소스