← 전체 목록

2026-10-28 AI 리서치 브리핑

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

총 11건 요약 자동 생성

VLM 업데이트

멀티모달 비전-언어 모델의 최신 논문과 리더보드 변화

VibeVideoBench:Evaluating Multimodal Agents on Code-Driven Video Generation

Paper arXiv cs.CV (recent)

Diffusion video models produce striking clips, but they cannot reliably render an exact formula, a correct chart, a ruleconsistent game or narration synchronized to on-screen events. A different route is emerging: multimodal agents that write code to render every frame and synthesize every sound. We introduce VibeVideoBench, a benchmark for evaluating agents on code-driven video generation. Its 239 self-contained tasks in English and Chinese span 12 categories, from data stories and music-driven pieces to classroom lessons and paper explainers; each asks an agent, running in its native harness inside a sandbox, to deliver a finished MP4 with sound within one hour. Evaluation is hierarchical and evidence-based: program checks of the delivery spec, about 13k task-specific rubric checks traced to the requirements they enforce, and five quality dimensions anchored per task, judged by three VLM judge panels and validated with blind human preferences. Across nine frontier agent systems and 2,151 scored rollouts, the benchmark is far from solved: GPT-6 Astra and Claude Opus 5.5 lead clearly, yet even the best system fails a core requirement on about a quarter of tasks. Whether a video arrives at all matters as much as its quality, and three quarters of the lost videos are final renders started too late, run too slowly or never started. The judges agree with each other and with human preferences on system rankings, but only moderately on individual videos.

원문 보기

MedVTok: A General-Purpose Medical Visual Tokenizer

Paper arXiv cs.CV (recent)

Multimodal medical AI requires a common visual interface for encoding heterogeneous imaging evidence for patient condition modeling. However, existing medical visual tokenizers are often tied to a specific dimension and imaging modality, forcing multimodal systems to rely on fragmented and poorly reusable representations. We introduce MedVTok, a general-purpose visual tokenizer that maps 2D images and 3D volumes from diverse imaging modalities into a unified token space. Building such a tokenizer poses two key challenges: preserving anatomical structure across dimensions and capturing clinical semantics across modalities. To this end, MedVTok introduces (i) slice differential regularization, which explicitly models inter-slice anatomical coherence missing in previous per-pixel/per-voxel supervision, and (ii) multi-expert representation alignment, which integrates knowledge from multiple medical expert encoders while retaining modality-specific complementary knowledge. Trained on 28M images and 70K volumes across 9 imaging modalities, MedVTok supports classification, retrieval, segmentation, synthesis, visual question answering, and medical report generation through a single tokenizer. Across 24 benchmarks, MedVTok achieves state-of-the-art performance, demonstrating a scalable token interface that unifies medical image dimension, modality, and task usage.

원문 보기

sLLM 트렌드

경량화·효율화를 위한 스몰 LLM 연구

OSWAM: An Effective World Action Model with One-Step Action Generation

Paper arXiv cs.CV (recent)

Direct-policy World Action Models (WAM) have demonstrated the benefits of decoupling action generation from explicit future visual prediction for efficient inference in autonomous driving and embodied control. However, they still require tens of denoising steps to achieve competitive action quality, incurring substantial latency and hindering real-time deployment. Simply reducing the number of denoising steps will collapse the nonlinear multi-step denoising trajectory into coarse updates, substantially degrading action quality. To reduce the denoising steps while enabling real-time action generation, we present an effective world action model with one-step action generation, namely OSWAM, for autonomous driving and embodied control. We argue that it is the absence of structured action priors in random noise initialization that forces direct-policy WAMs to recover coherent action sequences through iterative denoising. Hence, we construct imagination tokens to initialize the diffusion process, providing physical priors and action-conditioned representations. We further introduce privileged information distillation with future conditioning to enhance future-aware action generation. As a result, OSWAM can efficiently and effectively generate high quality actions in just one diffusion step. Our experiments demonstrate that OSWAM achieves comparable or even better results in both autonomous driving and embodied control than direct-policy WAM and Joint-WAM that require tens of steps. It obtains approximately $3\times$ speedup over direct-policy WAM baselines and supports real-time compiled inference with latency as low as 40ms on an NVIDIA RTX 5090 GPU. The project page is available at https://gwenzhang.github.io/OSWAM/

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

Trajectory2Gym: Decision-Grounded Compositional Interaction Synthesis for Tool-Use Agents

Paper Hugging Face Papers

Trajectory2Gym: Decision-Grounded Compositional Interaction Synthesis for Tool-Use Agents에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

Trial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure Attribution

Paper Hugging Face Papers

Trial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure Attribution에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

StreamVibe: Proactive Video Agents for Evolving User Intent

Paper Hugging Face Papers

StreamVibe: Proactive Video Agents for Evolving User Intent에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

DynaFlow: Learning Free-Form Multi-Agent Orchestration

Paper Hugging Face Papers

DynaFlow: Learning Free-Form Multi-Agent Orchestration에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

InteractiveWorld: A Verifiable Human-Centric Environment for Building Better Interactive MLLM Assistants

Paper Hugging Face Papers

InteractiveWorld: A Verifiable Human-Centric Environment for Building Better Interactive MLLM Assistants에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

Do vision models know that three is three?

Paper arXiv cs.CV (recent)

Do vision models encode the transition $2{\to}3$ the same way whether it appears in handwritten digits or in hand gestures, and do they "understand" that clean${\to}$dirty is the same transformation regardless of whether it is applied to a kitchen or a carpet? The linear representation hypothesis (LRH) answers this for language models: concept changes correspond to directions in (language) embedding space. In vision, the same concept can manifest in visually unrelated "regimes" that rarely co-occur: images of digits and hands do not share much in common in pixel space. To understand whether vision models still encode the underlying abstract concepts, we study 46 vision encoders across architectures, training objectives, and scales, on 10 concept families including numerosity, age, object identity, and MIT-States attributes. Within each regime, we find statistically significant concept directions near-universally across our tested models. However, two distinct regimes do not always share the same concept direction. Several models learn multiple linear structures for the same concept transition, split across regimes. We call this phenomenon "fragmented linearity": strong local linearity coexisting with near-absent global linearity. Fragmentation is, however, not fixed: models with stronger local linearity progressively escape it (local-global linearity correlated with $τ\in [0.38, 0.89]$ across all concepts), and where global linearity does emerge, concept directions can transfer as linear probes across regimes.

원문 보기

FL4N: Feed-forward Latent Model for 4D Novel View Synthesis

Paper arXiv cs.CV (recent)

4D novel view synthesis (NVS) aims to render dynamic scenes across viewpoints and timestamps, which requires jointly inferring 3D structure and temporal dynamics. Existing monocular feed-forward methods often rely on explicit 4D Gaussian representations, which are prone to temporal inconsistency and severe rendering artifacts. We present FL4N, the first feed-forward latent 4D NVS model. Instead of relying on explicit 4D primitives, FL4N encodes a 4D scene prior into a unified latent representation across space and time. Our core insight is that learning temporal dynamics as residuals on top of a pretrained static latent prior enables effective 4D modeling with limited dynamic training data. To this end, we introduce a lightweight dynamic encoder that leverages static scene features to disentangle object motion from camera-induced parallax. Trained solely with an image synthesis objective, FL4N achieves state-of-the-art 4D NVS quality while rendering in real time. Its learned latent representation generalizes to real-world videos and disentangles viewpoint from time.

원문 보기

참고한 소스