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
Sangjin Choi, Sukmin Cho, Yifan Xiong +3 authors
ELDR is an expert-locality-aware decode router for prefill-decode disaggregated Mixture-of-Experts serving that improves performance by predicting expert activations and routing requests accordingly.
Bytedance Seed
Seed2.0 addresses complex real-world tasks by tackling long-tail knowledge and complex instruction following challenges while enhancing reasoning, visual understanding, and search capabilities through a robust evaluation framework grounded in user needs.
Wonjun Kang, Kevin Galim, Seunghyuk Oh +9 authors
Asynchronous on-policy distillation addresses training bottlenecks in large language model post-training by decoupling rollout generation from learner updates, though it introduces challenges with stale policy data that require specialized solutions.
Zhishang Xiang, Zerui Chen, Yunbo Tang +5 authors
Memory plays a crucial role in LLM-based agents, but retrieved memories can cause sycophancy issues where agents over-align with users at the expense of factual accuracy, necessitating new evaluation benchmarks that assess memory's impact on reasoning and decision-making rather than just storage and retrieval.
Shijie Li, Yilin Gao, Siyuan Yang +7 authors
Asymmetric Mutual Variational Learning addresses train-inference mismatch in multimodal reasoning by using bidirectional calibration to prevent answer leakage and improve latent-space stability.
Junha Jung, Minbyul Jeong, Suhyeon Lim +5 authors
A reinforcement learning approach called MRPO is introduced to improve clinical image reasoning by addressing cascading errors through step-wise process rewards, demonstrating superior performance over existing methods.
Siyu Yan, Yizhen Gao, Yilin Wang +2 authors
DataEvolver is a self-evolving multi-agent framework that improves text-rich image generation by leveraging feedback from rejected samples to iteratively enhance data quality.
Gabrielle Kaili-May Liu, Avi Caciularu, Gal Yona +2 authors
Reinforcement learning with metacognitive feedback and metacognitive data selection improve large language model calibration by enabling accurate self-assessment of performance and uncertainty.
Jiazhao Zhang, Gengze Zhou, Hale Yin +31 authors
Qwen-RobotNav is a scalable navigation model with a parameterized interface enabling dynamic task modes and observation parameters, achieving state-of-the-art performance through multi-task training and zero-shot generalization to real-world robotics.
Jiwen Yu, Jianxiong Gao, Jianhong Bai +7 authors
MemLearner improves video world models by using learning-based adaptive context querying with query tokens to enhance scene consistency and memory in long video sequences with occlusions and dynamic objects.
Koorosh Roohi, Javad Rajabi, Andrew Fleet +1 authors
PhotoQuilt is a training-free framework that generates high-resolution photomosaics by combining global layout composition with separate tile generation in latent space, overcoming limitations of diffusion models in balancing local detail and global structure.
Sunqi Fan, Qingle Liu, Runqi Yin +2 authors
A new benchmark evaluates multimodal large language models' ability to understand video content and perform GUI tasks, while a novel keyframe extraction method improves performance on both video question answering and video-guided agentic tasks.
Runyu Lu, Yubo Wu, Ethan Kou +11 authors
ASPIRE is a continual learning system that autonomously develops and refines robot control programs through iterative exploration, achieving superior performance and zero-shot generalization in manipulation and household tasks while enabling sim-to-real transfer.
Hohin Kwan, Hongyu Li, Ray Zhang +5 authors
A new benchmark evaluates multimodal large language models' ability to reason over dynamic visual evidence through controlled temporal-logical operations rather than simple object recognition.
Julia Belikova, Rauf Parchiev, Evgeny Egorov +4 authors
Procedural memory enhances LLM agents on workplace tasks through skill transfer across roles and models, with varying generalization capabilities affecting deployment strategies.
Taewook Kang, Taeheon Kim, Donghyun Shin +1 authors
Vision-Language-Action models can be efficiently adapted to new environments using a single demonstration through weight vector arithmetic that isolates domain-specific information via subspace alignment.
Seohyun Lee, Seoung Choi, Dohwan Ko +2 authors
VideoSearch-R1 is an agentic framework that iteratively retrieves videos and refines search queries using continuous latent space refinement and policy optimization for improved video moment retrieval and temporal grounding.
Zhaojian Yu, Penghao Yin, Shuzheng Gao +3 authors
AutoTrainess enables autonomous language model training by providing structured agent-computer interfaces that guide planning, data preparation, training, evaluation, and logging operations more effectively than traditional command-line approaches.
Wenhan Ma, Jianyu Wei, Liang Zhao +10 authors
Multi-teacher On-Policy Distillation (MOPD) enables efficient integration of multiple domain capabilities in large language models through specialized reinforcement learning teachers and on-policy distillation, achieving superior performance over existing methods.
Philip Zmushko, Egor Petrov, Nursultan Abdullaev +2 authors
Asynchronous pipeline parallelism with PipeDream-2BW can achieve near-synchronous performance through optimizer selection and error feedback correction, overcoming traditional stability concerns.
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