← 전체 목록

2026-11-03 AI 리서치 브리핑

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

총 10건 요약 자동 생성

VLM 업데이트

멀티모달 비전-언어 모델의 최신 논문과 리더보드 변화

Latent Reasoning in Continuous Space for Unified Multimodal Models

Paper arXiv cs.CV (recent)

Unified Multimodal Models (UMMs) achieve remarkable success on diverse multimodal understanding and generation tasks, yet they still struggle to effectively leverage language-based chain-of-thought reasoning for image generation. As a result, existing reasoning-augmented UMMs often fail to inherit the test-time scaling and fine-grained controllability observed in large language models. We attribute this failure to a fundamental modality mismatch: reasoning is performed in a discrete token space, whereas image generation operates in a continuous space. To bridge this gap, we introduce a Latent Reasoning framework in Continuous space (LARC), which alleviates the token-level bottleneck by reasoning over continuous hidden states. Specifically, the training framework consists of two stages: (i) curriculum supervised fine-tuning (SFT), and (ii) information-gain reinforcement learning (RL). First, the curriculum SFT stage gradually converts token-level reasoning into latent reasoning. Subsequently, the information-gain RL stage self-evolves latent reasoning without ground truth supervision. Experiments across diverse text-to-image generation benchmarks show that LARC consistently improves generation quality, prompt following, and compositional fidelity. Notably, LARC achieves state-of-the-art performance on GenEval with a 7%p gain over BAGEL and demonstrates clear test-time scaling behavior, outperforming token-based generation under both parallel and sequential test-time scaling strategies.

원문 보기

On-Device AI

디바이스 내 추론 및 엣지 최적화 동향

SemEllipsoid: Semantic-aware Shape Abstraction with Ellipsoid

Paper arXiv cs.CV (recent)

Representing 3D shapes using a set of primitives - known as shape abstraction - is an actively studied problem in computer graphics with wide applications in shape understanding, analysis, and simulation due to the compactness and computational efficiency of the primitive-based representation. Prior work has primarily focused on geometry-aware shape abstraction, where the objective is to approximate the input shape with a minimal set of primitives while preserving geometric fidelity. However, these methods often overlook semantic consistency, inevitably leading to primitives that span across multiple semantic parts. Such inconsistency can cause undesirable artifacts in downstream tasks such as part-level shape editing or manipulation. In this paper, we introduce a new task - semantic-aware shape abstraction, where the goal is to produce abstractions that are both geometrically faithful and semantically consistent, ensuring that each primitive adheres strictly to a single semantic part without crossing semantic boundaries. We propose SemEllipsoid, a novel method to address this problem using ellipsoidal primitives. The core idea is to inject semantic constraints into the primitive optimization process leveraging the availability of semantic cues from large-scale foundation models. We design a fully differentiable projection-blending-evaluation scheme to measure semantic divergence against input semantic masks, and formulate an alternating optimization strategy to iteratively solve for optimal semantic assignment and primitive configurations. Our method is non-learning-based, requiring no data collection or network training, and generalizes well to shapes from arbitrary categories. It also supports different levels of abstraction according to user demand. Extensive experiments and evaluations validate the effectiveness of our approach across several 3D shape collections.

원문 보기

ReLift: Dense 3D Tracking as Lifted Trajectory Repair

Paper arXiv cs.CV (recent)

Dense 3D tracking from monocular video requires establishing point correspondences over time, estimating their depth, and inferring their trajectories during occlusion. Existing methods typically learn these tasks jointly, a demanding objective given the scarcity of 4D supervision. We show that strong pretrained 2D trackers and 3D geometry models provide an effective foundation: lifted trajectories, with occluded segments simply interpolated, already rival dedicated 3D trackers using the same geometry. However, lifted trajectories inherit correspondence and depth errors, and under occlusion, their depth comes from the occluder rather than the tracked point. We introduce ReLift, an efficient feed-forward framework that recasts dense 3D tracking as geometric trajectory repair and completion. At its core, a trajectory corrector alternates attention along and across trajectories to preserve reliable observations, repair corrupted positions, and complete missing motion. Using only geometric inputs allows us to train directly on 3D trajectories with simulated lifting errors, decoupling training from images and from any specific tracker or geometry model. Concentrating 4D supervision on trajectory refinement yields a reusable model that consistently improves lifted trajectories across trackers and geometry providers without retraining, so it benefits directly from future advances in either component. On WorldTrack, ReLift achieves state-of-the-art mean accuracy, improving on the strongest baselines by 2.1 APD on all points and 3.0 on dynamic points, with faster configurations remaining competitive with leading 3D trackers while running faster than 4RC. Visit our supplementry page for more examples and code.

원문 보기

AI 뉴스 & 리서치

기업/연구기관의 주요 발표와 블로그 업데이트

FrameForge: Harnessing Priors of Video Foundation Models for Unified Image Generation

Paper Hugging Face Papers

FrameForge: Harnessing Priors of Video Foundation Models for Unified Image Generation에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

R^2Orch: Recursive Self-Improvement for Agent Orchestration via Self-Play within a Skill-Internalization Loop

Paper Hugging Face Papers

R^2Orch: Recursive Self-Improvement for Agent Orchestration via Self-Play within a Skill-Internalization Loop에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

Does Scaling Toward AGI Depend on What System-1 Lets System-2 Execute?

Paper Hugging Face Papers

Does Scaling Toward AGI Depend on What System-1 Lets System-2 Execute?에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

REA: A Routed Embodied Agent Runtime for Asynchronous Brain-Cerebellum Control

Paper Hugging Face Papers

REA: A Routed Embodied Agent Runtime for Asynchronous Brain-Cerebellum Control에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

Apriel Voice 27B Preview: An Open Model for Speech, Reasoning, and Tool Use

Paper Hugging Face Papers

Apriel Voice 27B Preview: An Open Model for Speech, Reasoning, and Tool Use에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

GazeRIB: Systematic Evaluation of Multi-Reader Gaze-Guided Chest X-ray Learning

Paper arXiv cs.CV (recent)

Radiologists' visual attention can supervise medical image learning, but how reader panel composition affects its value remains untested. We evaluated GazeRIB (Gaze-guided Radiologist-Informed Blackout), which masks unviewed regions during training and uses unmasked images at inference. Eight experts repeatedly read the same 80 chest X-rays (CXRs). We compared individual readers with three-, five- and eight-reader panels across seven architectures and 10 seeds, evaluating 910 models on a separate 2,897-CXR cohort for four-class severity prediction. Every panel improved macro F1 over the no-gaze baseline by 5.33-7.47 percentage points (pp; Bonferroni-adjusted p < 0.007); no individual reader reached significance on this endpoint. Three readers captured 73-80% of the eight-reader gain in macro F1, the area under the receiver-operating-characteristic curve (ROC-AUC) and the area under the precision-recall curve (AU-PRC). On external validation without retraining, all four panels improved ROC-AUC on SIIM-FISABIO-RSNA by +1.93 to +4.24 pp (p <= 0.004); on MIMIC-Eye no panel differed significantly from baseline, whereas the single-reader average declined (-1.40 pp, p = 0.008). Reader composition therefore influenced performance, although transfer depended on the cohort.

원문 보기

RoboArchitect: Automating the Design of Robotic Agents with Persistent Memory

Paper arXiv cs.CV (recent)

Recent work shows that a frozen robot policy performs far better inside an agent harness, where control code decides when to query the policy, consult vision tools, or command the arm directly. Yet today these harnesses are built by hand and redesigned for each new robot or benchmark. We show that harness design can be automated, offering a strong alternative to finetuning on a novel setup. In RoboArchitect, a coding model observes a robot's rollouts, diagnoses failures, and iteratively revises the harness around the frozen policy. The harness evolves on a set of episodes for its optimization and is evaluated on held-out scenes and tasks. Without updating any model weights, RoboArchitect raises average success from 9.7% to 43.3% on unseen scenes (4.5x) and from 12.7% to 40.2% on unseen tasks (3.2x), across multiple benchmarks and policies. The gains are largest where the benchmark is far from the policy's training data: wrapping a general-purpose policy, the evolved harness yields a specialist that often outperforms even the finetuned version. Intuitive control strategies are automatically designed, such as lifting a jammed arm clear or reaching in horizontally when an obstacle blocks the way from above. The harness also evolves its own persistent memory, carrying learned experience, such as effective grasp depths, into later decisions. These results suggest that substantial headroom in robotic manipulation lies in the agent harness, and its design can be effectively automated and optimized without weight updates.

원문 보기

참고한 소스