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。
606 篇论文 · 按点赞排序
Weiyu Li, Xuanyang Zhang, Zheng Sun +15 authors
Step1X-3D addresses challenges in 3D generation through a hybrid VAE-DiT geometry generator and diffusion-based texture synthesis, achieving state-of-the-art results with an open-source framework.
Junjie Wu, Jiangnan Li, Yuqing Li +6 authors
A new training paradigm and situated embedding models (SitEmb) enhance retrieval performance by conditioning short text chunks on broader context windows, outperforming state-of-the-art models with fewer parameters.
Zechen Bai, Hai Ci, Mike Zheng Shou
IPV-Bench evaluates video generation and understanding models on creating and interpreting impossible videos, highlighting their limitations and guiding future advancements.
Yadong Li, Jun Liu, Tao Zhang +90 authors
Baichuan-Omni-1.5 is an omni-modal model with end-to-end audio generation, featuring a comprehensive data pipeline, audio-tokenizer, and multi-stage training strategy for superior performance across multimodal tasks.
Nuo Chen, Zhiyuan Hu, Qingyun Zou +4 authors
JudgeLRM models trained with reinforcement learning outperform existing models, especially in tasks requiring deep reasoning.
Yue Wang, Qiuzhi Liu, Jiahao Xu +11 authors
A new decoding strategy addresses underthinking in large language models by penalizing frequent thought switching, improving accuracy without fine-tuning.
Fanqing Meng, Lingxiao Du, Zongkai Liu +11 authors
MM-Eureka extends rule-based reinforcement learning to multimodal reasoning, achieving strong capabilities in data-efficient multimodal tasks without supervised fine-tuning.
Jintao Zhang, Chendong Xiang, Haofeng Huang +4 authors
SpargeAttn is a universal sparse and quantized attention method that accelerates diverse models by predicting the attention map and using an online softmax-aware filter to skip unnecessary matrix multiplications.
Yash Savani, Asher Trockman, Zhili Feng +4 authors
Antidistillation sampling modifies a model's next-token probability distribution to disrupt the generation of reasoning traces for distillation without affecting model performance.
Yunhan Yang, Yufan Zhou, Yuan-Chen Guo +7 authors
OmniPart generates part-aware 3D objects with high semantic decoupling and structural cohesion using an autoregressive structure planning module and a spatially-conditioned rectified flow model.
Zehuan Huang, Haoran Feng, Yangtian Sun +3 authors
AnimaX creates multi-skeleton 3D animations by blending video diffusion model priors with skeleton-based control, using joint video-pose diffusion and shared positional encodings.
Tianchen Zhao, Ke Hong, Xinhao Yang +8 authors
PAROAttention reorganizes visual attention patterns to enable efficient sparsification and quantization, reducing memory and computational costs with minimal impact on performance.
Pratyush Maini, Vineeth Dorna, Parth Doshi +26 authors
BeyondWeb, a synthetic data generation framework, outperforms existing datasets and accelerates training for large language models by optimizing multiple factors.
Yafu Li, Xuyang Hu, Xiaoye Qu +2 authors
TPO refines LLM outputs in real-time using textual critiques, achieving preference alignment without retraining.
Fei Tian, Xiangyu Tony Zhang, Yuxin Zhang +14 authors
Step-Audio-R1, using the Modality-Grounded Reasoning Distillation framework, achieves strong reasoning capabilities in audio, outperforming previous models and demonstrating the transferability of reasoning across modalities.
Zichen Liu, Changyu Chen, Wenjun Li +5 authors
A study of R1-Zero training identifies pretraining effects on RL performance and proffers Dr. GRPO to enhance token efficiency, achieving superior accuracy on AIME 2024.
Maksim Kuprashevich, Grigorii Alekseenko, Irina Tolstykh +4 authors
An automated pipeline mines high-fidelity image editing triplets using generative models and a task-tuned validator, enabling large-scale training without human labeling.
Lingfei Qian, Weipeng Zhou, Yan Wang +3 authors
A study evaluates 16 large language models on complex financial tasks, finding that domain-specific CoT fine-tuning and reinforcement learning improve performance and highlight the need for further research on long-context and multi-table reasoning.
Daniil Laptev, Nikita Balagansky, Yaroslav Aksenov +1 authors
A new data-free cosine similarity method maps and steers features across layers of large language models, enhancing interpretability and targeted control in text generation.
Chin-Yang Lin, Cheng Sun, Fu-En Yang +3 authors
LongSplat improves novel view synthesis from long videos with irregular motion through joint optimization, robust pose estimation, and efficient anchor formation.
Chris, Yichen Wei, Yi Peng +10 authors
Skywork R1V2 enhances multimodal reasoning through a hybrid reinforcement learning approach that balances reward-model guidance and rule-based strategies, improving training efficiency with the Selective Sample Buffer mechanism and mitigating visual hallucinations.
Bin Lin, Zongjian Li, Xinhua Cheng +9 authors
A unified generative framework called UniWorld uses semantic features from visual-language models for image perception and manipulation, outperforming BAGEL with reduced data.
Gemma Team, Aishwarya Kamath, Johan Ferret +213 authors
Gemma 3 introduces vision capabilities, broader language coverage, and extended context length, featuring an optimized architecture and post-training enhancements to outperform previous versions.
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).
Liang Wang, Haonan Chen, Nan Yang +3 authors
CoRAG, a multi-step retrieval and reasoning approach, enhances RAG models by dynamically refining queries and using rejection sampling to improve performance, especially in multi-hop question answering.
Zelai Xu, Zhexuan Xu, Xiangmin Yi +5 authors
VS-Bench is a multimodal benchmark designed to evaluate Vision Language Models' strategic reasoning and decision-making in complex multi-agent environments.
Lin Long, Yichen He, Wentao Ye +5 authors
M3-Agent, a multimodal agent with long-term memory, performs multi-turn reasoning and outperforms baselines on a new long-video question answering benchmark.
Jianwei Yang, Reuben Tan, Qianhui Wu +10 authors
Magma is a multimodal foundation model with both verbal intelligence and spatial-temporal intelligence, trained on diverse datasets to perform agentic tasks like UI navigation and robotic manipulation, outperforming specialized models.
Lijie Liu, Tianxiang Ma, Bingchuan Li +4 authors
A unified video generation framework called Phantom integrates text and image inputs to produce subject-consistent videos, focusing on human generation and leveraging cross-modal alignment.
Zijun Liu, Peiyi Wang, Runxin Xu +5 authors
Self-Principled Critique Tuning enhances pointwise generative reward modeling for large language models, improving scalability and quality compared to existing methods.
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