Explore · 每周精选
发现最受关注的研究论文,追踪研究趋势,订阅感兴趣的期刊与关键词。
50 篇论文 · 按点赞排序
Jaward Sesay, Yue Yu, Siwei Dong +3 authors
LectūraAgents is a multi-agent framework that enables personalized learning through adaptive embodied teaching by mimicking professor-student interactions and generating coordinated teaching actions aligned with learner profiles.
Tim Genewein, Matija Franklin, Alexander Lerchner +11 authors
Artificial general intelligence development may lead to artificial general superintelligence through multiple pathways, requiring interdisciplinary global preparation for transformative societal changes.
Yuho Lee, Jisu Shin, Nicole Hee-Yeon Kim +5 authors
VideoRAG systems are extended to handle long egocentric videos with multi-modal retrieval across temporal granularities, addressing limitations in existing benchmarks and methods through a new benchmark and chunk-adaptive reranking approach.
Cheng-You Lu, Yi-Shan Hung, Wei-Ling Chi +6 authors
A large-scale real-world dataset called DF3DV-1K is introduced to address the lack of clean and cluttered image sets for distractor-free radiance field research, containing 1,048 scenes with 89,924 images across 128 distractor types and 161 scene themes, along with a curated subset DF3DV-41 for robustness evaluation, and demonstrates improved performance when used to fine-tune a diffusion-based 2D enhancer for radiance field methods.
Heecheol Yun, Joonhyung Park, Joowon Kim +1 authors
Masked diffusion language models exhibit unique decoding dynamics where reliable trajectories show stable confidence patterns, enabling iterative ensemble methods that transfer partially denoised sequences between models based on confidence evolution.
Xinyue Cai, Chaoyou Fu, Yi-Fan Zhang +2 authors
An automated audio-visual question answering system uses entity-anchored video scripting and clue-guided QA generation to improve cross-modal reasoning and temporal consistency in video analysis.
Guibin Zhang, Xun Xu, Yanwei Yue +4 authors
OPD-Evolver is a self-evolving agent framework that combines slow-fast co-evolution with on-policy self-distillation to enhance memory management and policy learning across multiple domains.
Hyeongwon Jang, Gyouk Chu, Changhun Kim +3 authors
A framework called TRIAGE is proposed to improve clinical early warning systems by training large language models to generate dialectical reasoning for continuous risk scoring with better calibration and interpretability.
Jinghong Lan, Wei Cheng, Yunuo Chen +10 authors
FreeStyle is a scalable dual-reference generation framework that uses community LoRA mining to create large-scale style-content triplets while addressing content leakage through disentanglement mechanisms and a comprehensive benchmark.
Haoqin Tu, Jianwen Chen, Zijun Wang +14 authors
VisualClaw is a self-evolving multimodal agent that reduces deployment costs through hybrid encoding and skill evolution while improving video-QA accuracy across multiple benchmarks.
Yi-Ruei Liu, Jie-Ying Lee, Zheng-Hui Huang +2 authors
BRDFusion combines physical modeling and generative priors to achieve high-quality inverse and forward rendering of urban scenes with precise control and artifact reduction.
Haowen Liu, Xirui Li, Shaoxiong Yao +5 authors
A harness framework for embodied tool use combines high-level reasoning with external modules, enabling compact models to perform complex manipulation tasks with minimal training data.
Chao Chen, Chengzu Li, Zhiwei Li +2 authors
A framework automates environment redesign in reinforcement learning for large language models by having the policy analyze failures and suggest configuration changes, achieving superior performance over larger proprietary models and fixed-environment baselines.
Yiming Ren, Yiran Xu, Zicheng Lin +8 authors
Small-to-Large Policy Optimization framework uses smaller models as natural explorers to enhance policy diversity and improve large language model training efficiency.
Ziyue Li, Yang Li, Tianyi Zhou
Pretrained language models can execute layers dynamically through flexible program-of-layers strategies that improve accuracy while reducing computational overhead compared to standard fixed-depth inference.
Yuyang Zhang, Wenyao Zhang, Zekun Qi +7 authors
ImageWAM demonstrates that pretrained image editing models can effectively replace video generation in world action models for robot control, achieving better performance with reduced computational costs.
Daniel Gilo, Sven Elflein, Ido Sobol +1 authors
FlowBender is a closed-loop framework that addresses constraint satisfaction in diffusion and flow models by training networks to correct alignment errors using inference-time feedback, outperforming traditional supervised and guidance-based approaches across multiple tasks.
Siang-Ling Zhang, Huai-Hsun Cheng, Tsung-Ju Yang +1 authors
A fast, training-free framework generates text-driven 3D visual illusions by decoupling generation into cross-space dual-branch denoising and view-conditioned texture synthesis for seamless geometric fusion and semantic coherence.
Nicolas Beltran-Velez, Felix Friedrich, Zhang Xiaofeng +4 authors
Discriminator-Guided Reinforcement Learning (DRL) addresses alignment issues in score- and flow-matching models by using a pretrained representation space discriminator as an optimal reward signal, improving both visual fidelity and semantic quality without human preferences.
Zhenghao Xing, Ruiyang Xu, Yuxuan Wang +8 authors
OmniAgent is a novel omni-modal agent that addresses long video understanding by using an iterative observation-thought-action cycle with active perception, achieving superior performance compared to larger models through efficient selective processing.
北京市昌平区探索星信息技术及软件开发工作室
京ICP备2026059466号