Trends · 研究趋势
数据来自 Hugging Face 论文的 AI 提取关键词,按月统计研究方向的增长与热度。
Yuhao Zheng, Li'an Zhong, Yi Wang +6 authors
Code2World enables autonomous GUI agents to predict next visual states through renderable code generation, achieving high visual fidelity and structural controllability while improving navigation performance.
Yafu Li, Runzhe Zhan, Haoran Zhang +25 authors
A systematic approach transforms post-trained reasoning models into rigorous olympiad-level solvers through reverse-perplexity curriculum, two-stage reinforcement learning, and test-time scaling, achieving gold-medal performance on mathematical and physics competitions.
Aviral Kumar, Vincent Zhuang, Rishabh Agarwal +15 authors
The multi-turn online reinforcement learning approach SCoRe improves LLM self-correction using self-generated data and regularization, achieving state-of-the-art performance.
Xingxuan Li, Yao Xiao, Dianwen Ng +15 authors
The MiroMind-M1 series, built on Qwen-2.5, introduces fully open-source reasoning language models with state-of-the-art performance in mathematical reasoning through Context-Aware Multi-Stage Policy Optimization.
Ning Shang, Yifei Liu, Yi Zhu +12 authors
rStar2-Agent, a 14B math reasoning model trained with agentic reinforcement learning, achieves state-of-the-art performance by efficiently handling complex problem-solving with advanced cognitive behaviors and minimal computational resources.
Shuang Chen, Kaituo Feng, Hangting Chen +7 authors
OpenSearch-VL presents an open-source framework for training advanced multimodal search agents using reinforcement learning, featuring specialized data curation, diverse tool environments, and a novel training algorithm that improves performance across multiple benchmarks.
Yizhou Wang, Chen Tang, Han Deng +29 authors
A scientific reasoning foundation model pre-trained on diverse scientific data supports multiple tasks and enhances cross-domain generalization and fidelity through specialized training techniques.
Minki Kang, Shizhe Diao, Ryo Hachiuma +4 authors
Agents using vision-language models with extended reasoning face challenges in tool utilization, which are addressed through AXPO, a method that improves performance by optimizing thinking prefixes and tool call resampling.
Tiwei Bie, Maosong Cao, Kun Chen +28 authors
LLaDA2.0 converts auto-regressive models into discrete diffusion large language models with a novel training scheme, achieving superior performance and efficiency at scale.
Chen Hu, Haikuo Du, Heng Wang +64 authors
Step-DeepResearch, an end-to-end agent enhanced with a data synthesis strategy and progressive training, achieves expert-level capabilities in deep research scenarios, outperforming established models.
Yi-Fan Zhang, Xingyu Lu, Shukang Yin +17 authors
Thyme, a novel paradigm, enables MLLMs to autonomously perform image manipulations and computations, enhancing performance in perception and reasoning tasks through a two-stage training strategy and GRPO-ATS algorithm.
Cheng Yang, Haiyuan Wan, Yiran Peng +8 authors
VR-Bench evaluates video models' spatial reasoning capabilities through maze-solving tasks, demonstrating that these models excel in spatial perception and reasoning, outperforming VLMs and benefiting from diverse sampling during inference.
Zhengyi Wang, Jonathan Lorraine, Yikai Wang +4 authors
The work demonstrates the capability of LLMs to generate 3D meshes from text by introducing a novel approach to tokenize 3D mesh data, allowing the unification of 3D and text modalities without expanding the model's vocabulary.
Yifu Luo, Zeyu Chen, Haoyu Wang +4 authors
d-OPSD introduces a novel on-policy self-distillation framework for diffusion language models by adapting self-teacher construction and supervision mechanisms to match the non-autoregressive nature of diffusion models.
Zhangchen Xu, Fengqing Jiang, Luyao Niu +4 authors
Magpie, a self-synthesis method, generates high-quality instruction data from aligned LLMs, enabling competitive performance in alignment benchmarks compared to models fine-tuned with larger, supervised datasets.
Yu Gao, Lixue Gong, Qiushan Guo +28 authors
Seedream 3.0 improves Chinese-English bilingual image generation by enhancing data training, pre-training techniques, and post-training aesthetics, resulting in higher visual quality and faster image generation.
Hanze Dong, Wei Xiong, Bo Pang +7 authors
Online iterative reinforcement learning from human feedback achieves state-of-the-art performance in large language models using open-source datasets and proxy preference models.
Yue Liu, Shengfang Zhai, Mingzhe Du +9 authors
GuardReasoner-VL enhances VLM safety through a reasoning-based guard model trained with SFT and online RL, using diverse datasets and a length-aware safety reward.
Yubo Wang, Xiang Yue, Wenhu Chen
Critique Fine-Tuning (CFT) improves language model performance by training them to critique noisy responses, showing better reasoning ability than standard Supervised Fine-Tuning (SFT).
Alex Havrilla, Yuqing Du, Sharath Chandra Raparthy +6 authors
Multiple RLHF algorithms, including Expert Iteration, PPO, and Return-Conditioned RL, similarly improve LLM reasoning with similar sample complexity, with Expert Iteration slightly outperforming others.
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