← 전체 목록

2026-10-10 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

OuroWorld: Bringing Any 3D World Alive as Diverse, Endlessly Looping 3D Cinemagraphs

Paper arXiv cs.CV (recent)

Recent 3D world models generate photorealistic, explorable scenes that remain frozen in time. OuroWorld is a mask-free framework that turns any static 3D Gaussian Splatting scene into a 3D cinemagraph: a dynamic scene with vivid, diverse motion looping seamlessly from any viewpoint. A vision-language model infers plausible dynamics and guides a video model to synthesize a reference video, which we lift and complete into multi-view videos. To learn from this imperfect supervision, we propose Inconsistency-Robust Periodic 4DGS: a Fourier-series deformation field guarantees looping by construction, while a Grounded Drift Field anchored at the reference view absorbs cross-view inconsistency. Unlike prior Eulerian methods limited to fluid-like motion, we capture general deformation, object motion, and illumination change. We introduce a ground-truth-free evaluation covering vividness, naturalness, loop seam coherence, and scene quality. On 39 reconstructed and generated scenes, OuroWorld outperforms all baselines and wins 70.8%-99.0% of user-study comparisons. Project page: https://ouroworld.userwei.com

원문 보기

sLLM 트렌드

경량화·효율화를 위한 스몰 LLM 연구

Dex-One2Many: Learning Dexterous Manipulation from a Single Human Demonstration

Paper arXiv cs.CV (recent)

While learning dexterous manipulation from a single human video offers a promising alternative to costly robot demonstrations, many recent methods predominantly imitate demonstrated motions. Such strict motion matching often limits generalization to initial object poses, goal poses, and grasps not shown in the video. Alternatively, discovering a policy via reinforcement learning (RL) allows for broad generalization, but without prior guidance, it struggles with high-dimensional exploration in complex, multi-stage tasks. To address these coupled generalization and exploration challenges, we present Dex-One2Many, a real-to-sim-to-real framework that learns a generalizable dexterous manipulation policy from a single human video. Our key insight is to abstract the video into sequential scene graphs that guide RL, enabling efficient exploration while preserving broad generalizability. The graphs serve as generative constraints for sampling diverse reset states and provide dense rewards for each stage. Because the graphs constrain relations rather than exact poses, these reset states cover object poses and grasps beyond the video, while initializing each stage from them with dense rewards keeps exploration short and guided. Trained entirely in simulation, Dex-One2Many transfers zero-shot to a real multi-fingered hand. Across five tool-use and manipulation tasks, Dex-One2Many exceeds baselines by 6.5% in seen configurations, while its robust generalization widens this gap to 71% in unseen scenarios.

원문 보기

Rubric-CEPR: Self-Evolving Image Editing via Reward-Verified Self-Distillation

Paper arXiv cs.CV (recent)

Instruction-guided image editors have become highly capable, yet improving them further still depends on human-edited training pairs or external reward models. Such supervision is costly to obtain and can reward plausible failures: a realistic output may leave the requested change undone or alter content that should be preserved. In this work, we strive to improve a pretrained image editor using only its own generations, without human-edited targets or an external training-time reward model. To this end, we propose a self-evolving framework, named Rubric-CEPR, that verifies the editor's own samples with its internal representations through a rubric-augmented Contrastive Edit-Preservation Reward (CEPR). A Planner proposes structured edit instructions from unlabeled images, the Editor samples multiple candidate edits, and a frozen Critic scores each candidate with decomposed rubric checks for edit realization, removal of the old state, and content preservation, using features already exposed by the editor. Non-compensatory gates reject infeasible candidates, and the best verified candidate is distilled into the editor through lightweight adapter training. On Qwen-Image-Edit, Rubric-CEPR improves ImgEdit from 4.36 to 4.60 (+5.5%), with a +24.9% gain on object isolation, and transfers to GEdit-Bench and Complex-Edit. The same procedure also improves Step1X-Edit by +7.8% on ImgEdit. We hope our approach will serve as a solid baseline for image editors that improve themselves from their own verified samples. Our code is publicly available at $\href{https://riteshthawkar.github.io/Rubric-CEPR/}{\text{this URL}}$

원문 보기

AI 뉴스 & 리서치

기업/연구기관의 주요 발표와 블로그 업데이트

AgentGarten: Code Worlds for Evolving Agents

Paper Hugging Face Papers

AgentGarten: Code Worlds for Evolving Agents에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

TokenRouter: Efficient Serving System for Token-Level LLM Routing

Paper Hugging Face Papers

TokenRouter: Efficient Serving System for Token-Level LLM Routing에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation

Paper Hugging Face Papers

From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?

Paper Hugging Face Papers

Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

SuperNav: An Agentic Navigation System for Any Task in Any Scene

Paper Hugging Face Papers

SuperNav: An Agentic Navigation System for Any Task in Any Scene에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

DreamTrue: Action-Faithful Robot World Model with Counterfactual Post-Training

Paper arXiv cs.CV (recent)

We present DreamTrue, a multi-view, cross-embodiment robot world model for action-faithful and physically plausible video prediction. Training such a model on existing robot datasets faces two obstacles: imprecise calibration can impair action following, while limited coverage of unsuccessful interactions can bias predictions toward successful outcomes. To improve action following across embodiments, we render action trajectories into image-space conditions and introduce offline geometric calibration to align these conditions with the target videos. To broaden interaction coverage, we introduce counterfactual post-training, modifying recorded action trajectories and generating future videos under a wider range of actions and contact configurations. To provide feedback on these predictions without paired ground-truth futures, we construct a human-annotated video dataset covering robot, object, and interaction defects and use it to train an embodied video reward model. Its scores guide reinforcement-learning post-training toward more physically plausible interaction outcomes. On AgiBot, DreamTrue attains state-of-the-art action following, while reducing the human-assessed interaction defect rate from from 48.12% to 6.25%. Notably, our model ranks first in the world model track of the AgiBot World Challenge 2026. The project page can be found at https://brave-eai.github.io/DreamTrue.

원문 보기

What 30,000 Hours of Ego-centric Video Does Not Teach

Paper arXiv cs.CV (recent)

World models offer a promising alternative to physics-based simulators, yet remain far from practical deployment. We ask how far scaling ego-centric human video takes them, using a dataset of 30,000 hours spanning over 1,000 scene types and 14,000 contributors. Rather than relying on opaque downstream metrics, we directly evaluate agent and object-interaction fidelity on a challenging out-of-distribution benchmark. Increasing training data by 100x improves both, but unevenly: the agent is modeled well, while object fidelity remains far lower and improves slowly. We show that the agent gains need not come from data, and a careful visual conditioning design saturates fidelity with a fraction of it, which lets us measure object fidelity on its own and discover its saturation point. We then introduce a supervision scheme that shifts capacity from scene appearance toward object dynamics, improving object fidelity though a substantial gap remains. Finally, our conclusions transfer to downstream humanoid modeling. Overall, our results suggest that scaling ego-centric data brings agent modeling close to its limit while leaving its effects on the world far behind, and that closing this gap will depend on how models are trained, not only on how much data they see.

원문 보기

참고한 소스