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。
598 篇论文 · 按点赞排序
Matanel Oren, Michael Hassid, Yossi Adi +1 authors
Decoder-only transformers can be conceptualized as finite multi-state RNNs, and a new cache compression technique, TOVA, significantly reduces their computational cost while maintaining high performance.
Xing Han Lù, Zdeněk Kasner, Siva Reddy
A benchmark and retrieval-inspired model for efficient conversational web navigation by digital agents across diverse real-world websites is introduced, highlighting challenges in generalization to unseen sites.
Philip Anastassiou, Jiawei Chen, Jitong Chen +43 authors
Seed-TTS is a family of large-scale TTS models that generate high-quality speech with in-context learning, superior controllability, and a non-autoregressive variant using diffusion-based architecture that does not rely on pre-estimated phoneme durations.
Fangfu Liu, Hanyang Wang, Shunyu Yao +3 authors
Physics3D uses a video diffusion model to learn and simulate the physical properties of 3D objects, enabling realistic behavior prediction in virtual environments.
Rachit Bansal, Bidisha Samanta, Siddharth Dalmia +6 authors
CALM, a composition method for large language models, enhances capabilities by integrating cross-attention with specialized models, demonstrating improvements on translation and coding tasks.
Yikang Shen, Zhen Guo, Tianle Cai +1 authors
JetMoE-8B, a cost-effective large language model with 8 billion parameters, achieves impressive performance using a Sparsely-gated Mixture-of-Experts architecture, demonstrating efficient use of resources and computational savings.
Abhijit Bendale, Michael Sapienza, Steven Ripplinger +3 authors
SUTRA, a multilingual Large Language Model architecture, achieves superior performance on multilingual tasks by decoupling conceptual understanding from language-specific processing using a Mixture of Experts framework.
Dongzhi Jiang, Renrui Zhang, Ziyu Guo +10 authors
MMSearch-Engine enables multimodal search capabilities in Large Multimodal Models (LMMs) using a comprehensive benchmark and demonstrates improved performance over commercial products.
Yang Sui, Yanyu Li, Anil Kag +7 authors
A weight quantization method reduces the size of diffusion-based image generation models while improving generation quality.
Wenbo Hu, Xiangjun Gao, Xiaoyu Li +5 authors
DepthCrafter generates temporally consistent depth sequences for open-world videos using a video-to-depth model derived from a pre-trained image-to-video diffusion model.
Yunfei Xie, Juncheng Wu, Haoqin Tu +6 authors
OpenAI's o1 demonstrates strong performance in medical tasks but shows weaknesses in reasoning, multilinguality, and evaluation metrics compared to GPT-4.
Sihang Li, Jin Huang, Jiaxi Zhuang +7 authors
A hybrid approach combining continual pre-training and supervised fine-tuning creates specialized LLMs for scientific literature, addressing challenges in constructing corpora and generating instructions.
Zhuoyi Yang, Jiayan Teng, Wendi Zheng +16 authors
CogVideoX is a large-scale diffusion transformer model using a 3D Variational Autoencoder and expert transformer for generating high-quality, coherent videos from text prompts.
Jiacheng Liu, Sewon Min, Luke Zettlemoyer +2 authors
Modernized n-gram models, specifically $\infty$-gram models, enhance text analysis and neural LLMs by providing high accuracy in next-token prediction and reducing language modeling perplexities.
Jian Xie, Kai Zhang, Jiangjie Chen +5 authors
TravelPlanner is a new benchmark for evaluating the planning capabilities of language agents in complex, real-world travel planning scenarios, demonstrating that current models still struggle with information gathering and constraint management.
Kuang-Huei Lee, Xinyun Chen, Hiroki Furuta +2 authors
ReadAgent, an LLM-based prompting system, enhances effective context length up to 20x through memory episodes and gist memories, outperforming baselines on long-document reading comprehension tasks.
Shubham Toshniwal, Ivan Moshkov, Sean Narenthiran +3 authors
A new math instruction tuning dataset, OpenMathInstruct-1, leverages the Mixtral model to achieve competitive performance on math reasoning benchmarks using open-source LLMs.
Shenghai Yuan, Jinfa Huang, Xianyi He +5 authors
ConsisID is a tuning-free, DiT-based IPT2V model that uses frequency-aware identity control to generate high-quality, identity-preserving videos by decomposing facial features into low and high-frequency elements.
Alaaeldin El-Nouby, Michal Klein, Shuangfei Zhai +5 authors
Autoregressive pre-training for vision models (AIM) scales similarly to LLMs, showing improved performance with more data and parameters, and does not exhibit performance saturation.
Chaochao Lu, Chen Qian, Guodong Zheng +33 authors
A qualitative study evaluates the generalizability, trustworthiness, and causal reasoning capabilities of MLLMs across text, code, image, and video modalities to understand their reliability for downstream applications.
Junliang Ye, Fangfu Liu, Qixiu Li +5 authors
A framework called DreamReward uses human preference feedback to enhance text-to-3D generation, producing high-fidelity and aligned 3D models.
Dang Nguyen, Viet Dac Lai, Seunghyun Yoon +9 authors
A new LLM agent framework enables dynamic action creation and reuse by generating and executing programs, offering greater flexibility and improved performance in complex, real-world scenarios.
Haolin Chen, Yihao Feng, Zuxin Liu +8 authors
LaTent Reasoning Optimization (LaTRO) enhances LLMs' reasoning capabilities through variational optimization of latent distributions, improving zero-shot accuracy on complex reasoning tasks.
Noam Rotstein, Gal Yona, Daniel Silver +3 authors
Image editing is improved using pretrained video models to ensure accurate edits and preserve image fidelity by reformulating the process as a smooth temporal transition.
Tianle Li, Ge Zhang, Quy Duc Do +2 authors
LIConBench evaluates long-context LLMs on extreme-label classification tasks with sequences up to 50K tokens, highlighting performance dips beyond 20K tokens and favoring of recent labels.
Aman Singh Thakur, Kartik Choudhary, Venkat Srinik Ramayapally +2 authors
LLM-as-a-judge method for evaluating LLMs shows promise but varies in performance and alignment with human judges, with smaller models like JudgeLM-7B sometimes outperforming larger ones in ranking tasks.
Andreas Koukounas, Georgios Mastrapas, Michael Günther +11 authors
A novel multi-task contrastive training method improves CLIP model performance on both text-image and text-text retrieval tasks.
Zeqian Ju, Yuancheng Wang, Kai Shen +16 authors
NaturalSpeech 3, using factorized diffusion models, outperforms other TTS systems by generating disentangled speech attributes in a zero-shot manner.
Xiaohan Wang, Yuhui Zhang, Orr Zohar +1 authors
VideoAgent, an agent-based system using a large language model, significantly enhances long-form video understanding through interactive reasoning and efficient zero-shot accuracy on EgoSchema and NExT-QA benchmarks.
Saba Sturua, Isabelle Mohr, Mohammad Kalim Akram +9 authors
jina-embeddings-v3, a large-scale text embedding model, achieves state-of-the-art performance in multilingual and long-context retrieval tasks using Low-Rank Adaptation and Matryoshka Representation Learning.
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