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。
Shaobo Wang, Xuan Ouyang, Tianyi Xu +9 authors
OPUS is a dynamic data selection framework that improves pre-training efficiency by scoring data candidates based on optimizer-induced update projections in a stable proxy-derived target space, achieving superior performance with reduced computational overhead.
50 篇论文 · 按点赞排序
Zehao Chen, Gongxun Li, Tianxiang Ai +8 authors
WMSS is a post-training paradigm that uses weak model checkpoints to identify and fill learning gaps, enabling continued improvement beyond conventional saturation points in large language models.
Kaijie Zhu, Yuzhou Nie, Yijiang Li +10 authors
TermiGen introduces a pipeline for generating verifiable terminal environments and resilient trajectories to improve open-weight LLMs' ability to execute complex tasks and recover from runtime errors.
Ailin Huang, Ang Li, Aobo Kong +212 authors
Step 3.5 Flash is a sparse Mixture-of-Experts model that achieves frontier-level agentic intelligence through efficient parameter utilization and optimized attention mechanisms, demonstrating strong performance across multiple benchmarks.
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.
Chenxu Wang, Chaozhuo Li, Songyang Liu +10 authors
Multi-agent LLM systems face fundamental limitations in achieving continuous self-improvement while maintaining safety alignment due to inherent statistical blind spots in isolated evolution.
Jun Han, Shuo Zhang, Wei Li +21 authors
Financial markets are noisy and non-stationary, making alpha mining highly sensitive to noise in backtesting results and sudden market regime shifts. While recent agentic frameworks improve alpha mining automation, they often lack controllable multi-round search and reliable reuse of validated experience. To address these challenges, we propose QuantaAlpha, an evolutionary alpha mining framework that treats each end-to-end mining run as a trajectory and improves factors through trajectory-level mutation and crossover operations. QuantaAlpha localizes suboptimal steps in each trajectory for targeted revision and recombines complementary high-reward segments to reuse effective patterns, enabling structured exploration and refinement across mining iterations. During factor generation, QuantaAlpha enforces semantic consistency across the hypothesis, factor expression, and executable code, while constraining the complexity and redundancy of the generated factor to mitigate crowding. Extensive experiments on the China Securities Index 300 (CSI 300) demonstrate consistent gains over strong baseline models and prior agentic systems. When utilizing GPT-5.2, QuantaAlpha achieves an Information Coefficient (IC) of 0.1501, with an Annualized Rate of Return (ARR) of 27.75% and a Maximum Drawdown (MDD) of 7.98%. Moreover, factors mined on CSI 300 transfer effectively to the China Securities Index 500 (CSI 500) and the Standard & Poor's 500 Index (S&P 500), delivering 160% and 137% cumulative excess return over four years, respectively, which indicates strong robustness of QuantaAlpha under market distribution shifts.
SII-OpenMOSS Team, Donghua Yu, Mingshu Chen +37 authors
MOVA is an open-source model that generates synchronized audio-visual content using a Mixture-of-Experts architecture with 32 billion parameters, supporting image-text to video-audio generation tasks.
Veuns-Team, Changlong Gao, Zhangxuan Gu +24 authors
UI-Venus-1.5 is a unified GUI agent with improved performance through mid-training stages, online reinforcement learning, and model merging techniques.
Xiaomin Yu, Yi Xin, Wenjie Zhang +12 authors
Researchers address the modality gap in multimodal learning by proposing a fixed-frame theory and a training-free alignment method that enables efficient scaling of multimodal models using unpaired data.
Issar Tzachor, Dvir Samuel, Rami Ben-Ari
Generative multimodal large language models are adapted for video-text embedding and retrieval through intermediate-layer analysis and text-based alignment without visual supervision.
Xin Xu, Clive Bai, Kai Yang +7 authors
Composition-RL improves reasoning capabilities by automatically composing multiple problems into new verifiable questions for reinforcement learning training.
Shiyang Feng, Runmin Ma, Xiangchao Yan +54 authors
InternAgent-1.5 is a unified system for autonomous scientific discovery that integrates computational modeling and experimental research through coordinated subsystems for generation, verification, and evolution.
Dianyi Wang, Ruihang Li, Feng Han +17 authors
DeepGen 1.0 is a lightweight 5B unified multimodal model that achieves superior performance in image generation and editing through advanced alignment techniques and progressive training strategies.
Alisia Lupidi, Bhavul Gauri, Thomas Simon Foster +34 authors
AIRS-Bench presents a comprehensive benchmark suite for evaluating LLM agents across diverse scientific domains, demonstrating current limitations while providing open-source resources for advancement.
Peng Xia, Jianwen Chen, Hanyang Wang +10 authors
SkillRL enables LLM agents to improve through hierarchical skill discovery and recursive policy evolution, achieving superior performance on complex tasks while reducing computational overhead.
Daniil Plyusov, Alexey Gorbatovski, Boris Shaposhnikov +3 authors
RLVR methods using group sampling suffer from bias toward likely trajectories and missed rare-correct ones; a difficulty-aware advantage scaling technique improves performance on benchmarks without increasing computational cost.
Tianyi Jiang, Arctanx An, Hengyi Feng +12 authors
A novel training-free framework called Chain of Mindset enables step-level adaptive mindset orchestration for large language models by integrating spatial, convergent, divergent, and algorithmic reasoning approaches.
Tiwei Bie, Maosong Cao, Xiang Cao +47 authors
LLaDA2.1 introduces a novel token-to-token editing approach with speed and quality modes, enhanced through reinforcement learning for improved reasoning and instruction following in large language diffusion models.
Yalcin Tur, Jalal Naghiyev, Haoquan Fang +4 authors
RD-VLA introduces a recurrent architecture for vision-language-action models that adapts computational depth through latent iterative refinement, achieving constant memory usage and improved task success rates.
Wenkai Yang, Weijie Liu, Ruobing Xie +3 authors
On-policy distillation is extended through a generalized framework that introduces flexible reference models and reward scaling factors, demonstrating improved performance through reward extrapolation and reward correction techniques.
Georgii Aparin, Tasnima Sadekova, Alexey Rukhovich +5 authors
Sparse Autoencoders trained on Whisper and HuBERT models demonstrate stable feature extraction and effective disentanglement of acoustic and semantic information, showing practical applications in audio processing and correlation with human neural activity.
GigaBrain Team, Boyuan Wang, Chaojun Ni +22 authors
A vision-language-action model enhanced with world model-based reinforcement learning demonstrates improved performance and long-horizon execution capabilities for robotic manipulation tasks.
Baichuan-M3 Team, Chengfeng Dou, Fan Yang +15 authors
Baichuan-M3 is a medical-enhanced large language model designed for clinical decision support with capabilities in proactive information gathering, long-horizon reasoning, and hallucination suppression.
Fangzhi Xu, Hang Yan, Qiushi Sun +16 authors
OdysseyArena presents a new framework for evaluating large language models on long-horizon, inductive agent tasks that emphasize autonomous discovery of environmental transition laws.
Yun Luo, Futing Wang, Qianjia Cheng +28 authors
Physics-oriented vision-language models leverage curriculum reinforcement learning and agentic augmentation to achieve state-of-the-art scientific reasoning performance while maintaining physical consistency through multimodal perception.
Shumin Wang, Yuexiang Xie, Wenhao Zhang +4 authors
The paper establishes a theoretical framework for analyzing entropy dynamics in reinforcement fine-tuning of large language models, deriving expressions for entropy change and proposing entropy control methods based on discriminant analysis.
Hongzhi Zang, Shu'ang Yu, Hao Lin +14 authors
USER is a unified systems framework that enables scalable, asynchronous online policy learning in physical robots by treating them as first-class hardware resources and supporting diverse learning paradigms including VLA models.
Ruichuan An, Sihan Yang, Ziyu Guo +8 authors
GENIUS evaluates multimodal models' generative fluid intelligence through pattern induction, constraint execution, and contextual adaptation tasks, revealing deficiencies in context comprehension rather than generative capability.
Tianyi Xiong, Shihao Wang, Guilin Liu +5 authors
PhyCritic is a multimodal critic model designed for physical AI tasks through a two-stage RLVR pipeline that enhances perception and reasoning capabilities.
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