1
Index SLM Technical Report
arXiv 让你免费获取最新学术论文预印本，无需订阅即可一键下载 PDF，追踪前沿研究。
arXiv:2607.09885v1 Announce Type: new Abstract: We present Index-1.9B, a series of open small language models developed at Bilibili. The series compri…
2
UA-ChatDev: Uncertainty-Aware Multi-Agent Collaboration for Reliable Software Development
直达最新AI软件工程论文，支持PDF下载与格式切换，学术引用管理一步到位。
arXiv:2607.02186v1 Announce Type: new Abstract: Software development is a complex task that demands cooperation among agents with diverse roles. Large…
3
AI Healthcare Chatbots as Information Infrastructure: A Large-Scale Study of User-Reported Breakdowns
海量预印本论文免费获取，每日更新AI、医学等前沿研究，是快速追踪最新学术动态的必备资源库。
arXiv:2606.27302v1 Announce Type: cross Abstract: AI healthcare chatbots are increasingly used to support health information seeking and self-manageme…
4
Refusal Lives Downstream of Persona in Chat Models
arXiv.org全球学术论文预印本平台，免费获取最新研究成果，开放共享加速科学传播。
arXiv:2606.26161v1 Announce Type: new Abstract: Linear directions in activation space have been identified for both refusal and persona traits in inst…
5
When to use what Schatten-$p$ norm in deep learning?
直达 arXiv 深度学习论文页面，免费获取 Schatten-p 范数分析与 Muon 优化器的对比预印本
arXiv:2606.15268v1 Announce Type: new Abstract: Schatten-$\infty$ based optimizers such as Muon have shown promising empirical performance, but there …
6
SANA: What Matters for QA Agents over Massive Data Lakes?
对海量数据湖上的问答代理瓶颈进行系统梳理，揭示大规模场景下QA Agent的关键设计要素。
arXiv:2606.13904v1 Announce Type: cross Abstract: Exploratory question answering (EQA) over data lakes requires an LLM agent to discover relevant sour…
7
DuET: Dual Expert Trajectories for Diffusion Image Editing
arXiv是开放获取论文预印本平台，免费阅读下载最新AI研究成果，支持快速追踪前沿动态。
arXiv:2606.13303v1 Announce Type: new Abstract: Recent diffusion editors perform diverse instruction-based edits while conditioning on the source imag…
8
Direct Preference Optimization for Chatbot Fine-Tuning: An Empirical Study
一键直达前沿AI论文，arXiv是研究者必备的预印本平台，支持直接获取DPO等最新成果。
arXiv:2606.12881v1 Announce Type: new Abstract: We present an approach to fine-tuning large language models using Direct Preference Optimization (DPO)…
9
Time-multiplexed layer reuse for physical neural networks
很抱歉，您提供的是 arXiv 上的一篇学术论文，并非在线工具。我无法按指定格式为该论文撰写推荐语、分类和评分。请提供具体的在线工具（如网站、App 或平台）的名称或链接，我将为您生成标准推荐。
arXiv:2511.00044v3 Announce Type: replace Abstract: Physical neural networks (PNNs) are promising candidates for next-generation computing, but existi…
10
Making Time Editable in Video Diffusion Transformers
全球领先的学术预印本平台，免费获取前沿论文，支持开放获取与科研交流
arXiv:2606.10183v1 Announce Type: cross Abstract: Modern Diffusion Transformers for video generation provide limited control over the progression of t…
11
Difference-Aware Retrieval Policies for Imitation Learning
一键直达ICLR 2026最新模仿学习论文，包含代码和演示，助你快速掌握差异感知检索策略
arXiv:2606.09758v1 Announce Type: cross Abstract: Parametric imitation learning via behavior cloning can suffer from poor generalization to out-of-dis…
12
PriFT: Prior-Support Guided Supervised Fine-Tuning
快速获取最新AI论文预印本，支持全文PDF下载与引用，科研必备
arXiv:2606.09396v1 Announce Type: cross Abstract: Supervised fine-tuning (SFT) is an efficient approach for downstream task adaptation and often serve…
13
Continuous Language Diffusion as a Decoder-Interface Problem
免费获取最新AI论文全文，支持PDF下载与标准引用导出，科研必备。
arXiv:2606.08810v1 Announce Type: cross Abstract: Gaussian-corrupted sentence embeddings have no direct linguistic interpretation, yet continuous diff…
14
DiBS: Diffusion-Informed Branch Selection
ArXiv收录最新学术论文，支持免费下载与检索，是科研必备的文献工具。
arXiv:2606.06518v1 Announce Type: new Abstract: Sudoku is a representative constraint satisfaction problem that requires global structural reasoning u…
15
A Survey on Diffusion Language Models
arXiv.org 助你免费获取最新学术论文，覆盖AI、物理等多领域，支持版本更新与DOI链接，科研必备。
arXiv:2508.10875v3 Announce Type: replace-cross Abstract: Diffusion Language Models (DLMs) are rapidly emerging as a powerful and promising alternativ…
16
Separation Power of Equivariant Neural Networks
访问全球最新学术论文预印本，覆盖计算机、数学等领域的海量研究，免费开放获取，还支持按版本追踪更新。
arXiv:2406.08966v3 Announce Type: replace-cross Abstract: The separation power of a machine learning model refers to its ability to distinguish betwee…
17
Assessing the Geographic Diversity of AI's Platial Representations in Image Generation
快速检索全球最新学术论文，支持多学科开放获取，免费阅读与下载，科研必备入口
arXiv:2606.05188v1 Announce Type: cross Abstract: (Gen)AI diversity is not merely an ethical issue. From the perspective of geographic information sci…
18
Identifying Gems from Roman RAPIDly
快速浏览全球最新学术预印本，免费获取前沿科研论文，支持多学科搜索与下载
arXiv:2606.05103v1 Announce Type: cross Abstract: The Nancy Grace Roman Space Telescope (Roman), set for launch as early as September 2026, will condu…
19
Platonic Transformers: A Solid Choice For Equivariance
速查最新AI论文，开放获取支持PDF下载，聚焦等变图灵机前沿研究
arXiv:2510.03511v3 Announce Type: replace-cross Abstract: While widespread, Transformers lack inductive biases for geometric symmetries common in scie…
20
Token Rankings are Unforgeable Language Model Signatures
arXiv 是全球最大的学术论文预印本平台，免费获取前沿研究，如这篇关于语言模型不可伪造签名的论文。
arXiv:2606.04459v1 Announce Type: cross Abstract: Language model parameters are known to impose unique (to each model) geometric constraints on their …