← 전체 목록

2026-09-28 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

SemMSA: Latent Semantic-Aided Robust Multimodal Sentiment Analysis with Incomplete Data

Paper arXiv cs.CV (recent)

Recent research on Multimodal Sentiment Analysis (MSA) has focused on learning from language, visual, and acoustic modalities with incomplete data to infer human sentiment. Most studies typically compensate for missing information by reconstructing modality features or designing complicated fusion mechanisms. However, these methods still suffer from spurious generation and noisy guidance due to the lack of high-level semantic grounding in partially observed multimodal evidence. To address these issues, we propose SemMSA, a latent semantic-aided framework that constructs rich sentiment-relevant semantics with LLMs, fully integrating with all modalities via anchor-free spectral alignment. It mainly consists of Cross-modal Semantic Refinement (CSR) and Cross-modal Spectral Alignment (CSA). Specifically, CSR first adaptively extracts visual and acoustic representations by corresponding adapters to form a unified multimodal prefix with language in the frozen LLM embedding space. It then iteratively produces continuous discriminative semantic states through a token-efficient latent refinement process without decoding explicit text. Next, CSA simultaneously aligns the refined semantics with all modalities by enhancing the dominant spectral component of their kernel Gram matrix. This captures global nonlinear dependencies among all representations without relying on a predefined anchor modality. In addition, an instance-level spectral separation constraint preserves cross-sample discriminability and mitigates representation collapse. Extensive experiments on SIMS, MOSI, and MOSEI benchmarks demonstrate that SemMSA achieves state-of-the-art performance.

원문 보기

OmniFabric: Coherent UV Space Texture Synthesis for 3D Garment Reconstruction

Paper arXiv cs.CV (recent)

Automated generation of production-ready 3D garment assets from a single image is a central challenge in digital content creation. While recent generative models have significantly advanced 3D geometry reconstruction, synthesizing high-quality textures remains a bottleneck. Existing methods often bake environmental illumination and shadows directly into the texture map, or they fail to maintain global structural coherence, making the resulting assets unusable for physical simulation and relighting. In this work, we introduce OmniFabric, a novel approach that synthesizes globally coherent texture maps directly within the 2D sewing pattern space. Given a single reference image, our pipeline utilizes an estimated 3D mesh and generative priors of powerful Vision-Language Models (VLM) to establish a complete but coarse texture initialization across the unwrapped sewing patterns. We then leverage a specialized diffusion transformer, trained via an automated synthetic data engine and conditioned on 3D positional features, to refine this initialization directly in the canonical UV domain. This effectively removes distortion and baked-in artifacts to extract a clean and normalized texture map that preserves the original garment design. Extensive experiments demonstrate that OmniFabric significantly outperforms state-of-the-art baselines, yielding photorealistic 3D garments with high-quality textures.

원문 보기

sLLM 트렌드

경량화·효율화를 위한 스몰 LLM 연구

Towards Practical Compression of 3D Gaussian Splatting

Paper arXiv cs.CV (recent)

3D Gaussian Splatting (3DGS) enables high-quality novel-view synthesis but requires substantial storage. Existing compression methods often rely on spatial context modeling over irregular 3D representations, increasing the complexity of training and coding. Meanwhile, floating-point context inference can introduce numerical inconsistencies across platforms, causing entropy-decoding failures. To address these practical challenges, we propose COSA-GS, which constructs context without spatial aggregation through anchor-wise causal factorization. Specifically, we use geometry context derived from each anchor's coordinates to model a compact learnable anchor latent. The anchor latent is then fused with the geometry context to form an anchor context for attribute coding. The resulting context model features a simple architecture composed solely of linear transformations and activations. We train COSA-GS using rate--distortion optimization with adaptive Gaussian pruning. Further, we develop quantization-aware training and integer inference for the context model to achieve bit-exact consistency of entropy-decoded symbols across platforms. Experiments demonstrate that COSA-GS achieves state-of-the-art compression performance while retaining fast and consistent cross-platform decoding, providing a simple yet effective framework for practical 3DGS compression. Code is available at https://github.com/pengpeng-yu/COSA-GS.

원문 보기

AI 뉴스 & 리서치

기업/연구기관의 주요 발표와 블로그 업데이트

Training Object Permanence in World Models

Paper Hugging Face Papers

Training Object Permanence in World Models에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs

Paper Hugging Face Papers

Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

WanPE: Towards Cinematic Prompt Enhancement for Modern Text-to-Video Generation

Paper Hugging Face Papers

WanPE: Towards Cinematic Prompt Enhancement for Modern Text-to-Video Generation에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

OmniEcho: Spatial Audio Understanding for Embodied Agents

Paper Hugging Face Papers

OmniEcho: Spatial Audio Understanding for Embodied Agents에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

Agent-Editing World Model: Rethinking World Modeling for LLM Agents

Paper Hugging Face Papers

Agent-Editing World Model: Rethinking World Modeling for LLM Agents에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

RAPID: Robot Agentic Programming from Demonstrations

Paper arXiv cs.CV (recent)

Coding agents have demonstrated enormous success in solving complex programming problems. To leverage their potential for robot systems, this work introduces Robot Agentic Programming from Demonstrations (RAPID), which automatically generates, verifies, and refines robot programs, given a single visual human demonstration. The iterative agentic loop of code refinement requires several key ingredients: (i) a testable task specification, (ii) action primitives for robot execution, and (iii) an interactive environment for program execution and verification. RAPID infers all three from the demonstration automatically. To make the resulting program reusable beyond the demonstration setting, RAPID uses an object-centric relational program representation that focuses on the underlying structure of the demonstrated strategy rather than the specific motion per se: it expresses the action primitives as trajectory-optimization programs that realize object-level motion effects, while composing them through relational constraints that capture scene-specific geometry at run time. We evaluated RAPID in simulation on eight challenging contact-rich nonprehensile manipulation tasks as well as general prehensile manipulation tasks in the LIBERO-Pro benchmark. We also successfully deployed it on a real Franka arm and evaluated on all eight nonprehensile tasks. In all experiments, RAPID demonstrated strong performance, with generalization over object pose, shape, material, and environment. Website: https://yuyaoliu.me/projects/rapid.

원문 보기

Rolling-WAM: World Action Models with Rolling Imagination

Paper arXiv cs.CV (recent)

World Action Models (WAMs) couple action generation with future visual prediction for robotic manipulation. However, completing the joint video-action denoising process at each replanning cycle incurs substantial latency, delaying action updates and limiting closed-loop responsiveness. We present Rolling-WAM, a formulation that distributes joint denoising across successive replanning cycles. Our method maintains a sliding window of video-action chunks at staggered noise levels. At each step, a rolling noise schedule fully denoises the imminent action chunk for execution, while partially refining farther-future chunks. As the window advances with new camera observations, the retained future chunks continue their denoising process. This distributes the computational cost over time while carrying an evolving visual-action context across chunk boundaries. Evaluations on LIBERO, RoboTwin, and a real-world Unitree G1 humanoid show that Rolling-WAM achieves competitive manipulation performance. By removing the need to denoise the entire prediction horizon from scratch, it delivers a 4.5x steady-state replanning speedup over standard joint WAMs.

원문 보기

September 24, 2026 Automating coherent long-form video generation Generative AI · Machine Intelligence

News Google Research Blog

September 24, 2026 Automating coherent long-form video generation Generative AI · Machine Intelligence에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

September 18, 2026 MilleMiglia: A realistic instance generator for middle-mile logistics Algorithms & Theory

News Google Research Blog

September 18, 2026 MilleMiglia: A realistic instance generator for middle-mile logistics Algorithms & Theory에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

September 17, 2026 The future of practice: Enabling teachers to create learning interactives with generative UI Education Innovation · Generative AI · Machine Intelligence

News Google Research Blog

September 17, 2026 The future of practice: Enabling teachers to create learning interactives with generative UI Education Innovation · Generative AI · Machine Intelligence에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

September 15, 2026 Bypassing inference bottlenecks: Accelerating complex AI search with Retrieve-for-Train Algorithms & Theory · Data Mining & Modeling · Generative AI

News Google Research Blog

September 15, 2026 Bypassing inference bottlenecks: Accelerating complex AI search with Retrieve-for-Train Algorithms & Theory · Data Mining & Modeling · Generative AI에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

September 10, 2026 ToolGrad: Efficient tool-use dataset generation with textual "gradients" Machine Intelligence · Natural Language Processing

News Google Research Blog

September 10, 2026 ToolGrad: Efficient tool-use dataset generation with textual "gradients" Machine Intelligence · Natural Language Processing에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

Offloaded inference for real-world physical AI robotics

News Microsoft Research Blog

Offloaded inference for real-world physical AI robotics에 관한 최근 업데이트입니다. 자세한 내용은 원문 링크에서 확인할 수 있습니다.

원문 보기

Improving synthesis prediction of small molecules at scale with RetroChimera

News Microsoft Research Blog

이 뉴스는 RetroChimera를 활용하여 소분자 합성 예측을 대규모로 개선하는 방법에 대해 다룹니다. RetroChimera는 소분자 합성 예측의 효율성과 정확도를 높이는 데 기여합니다.

원문 보기

GigaPath-Flash and GigaTIME-Flash: Toward population-scale discovery with efficient pathology foundation models

News Microsoft Research Blog

이 뉴스는 효율적인 병리학 기반 모델인 GigaPath-Flash와 GigaTIME-Flash에 대해 소개합니다. 이 모델들은 인구 규모의 발견을 목표로 하며, 병리학 연구에 새로운 가능성을 제시합니다.

원문 보기

참고한 소스