1
华为余承东发布会 PPT 鸿蒙智行“五界”品牌顺序重排，AITO 问界被移至最右
IT之家 9 月 28 日消息，在今天的智界 RX 及鸿蒙智行新品发布会上，华为常务董事、产品投资委员会主任、终端 BG 董事长余承东重申，问界是鸿蒙智行合作的第一个品牌，现在是华为赋能，交给赛力斯主导，车主所有权益不受影响。 IT之家注意到，在余承东背后的 PPT 上，鸿蒙智行“五界”品牌迎来重新…
2
Multi-Modal Semantic Expansion with Constrained LLM Reranking for Conversational Music Recommendation
用多模态检索加约束重排搞定音乐对话推荐，参赛方案干货满满，值得算法人细读。
arXiv:2608.23484v1 Announce Type: new Abstract: We present Team Semiintelligencn's solution for the ACM RecSys 2026 TalkPlayData Challenge, addressing…
3
Rust 1.98 发布：打破代数运算性能瓶颈，编译器可重排更多运算
Rust 1.98 正式发布，新增代数浮点运算优化，可重排更多运算，大幅提升性能并稳定多项API。
IT之家 8 月 22 日消息，科技媒体 Linuxiac 昨日（8 月 21 日）发布博文，报道称 Rust 团队更新推出 1.98 版本， 重点加入面向 f32 和 f64 浮点类型的“代数浮点”（algebraic floating-point）方法，同时加快整数格式化，并稳定多项标准库 AP…
4
Beyond Representational Similarity: Source-Conditioned Description-Length Gain for Generative Plagiarism Detection and Candidate Source Reranking
用信息论新指标精准识别生成式抄袭，还能重排候选来源，直击AI时代学术诚信痛点。
arXiv:2608.03859v1 Announce Type: new Abstract: Large language models (LLMs) pose challenges to academic integrity and peer review. Yet generative pla…
5
X-KGRank: A Knowledge Graph RAG Framework for Explainable Recommendations via Pattern Mining and LLM Re-Ranking
用知识图谱模式挖掘+LLM重排，给推荐系统装上可解释的“思维链”，直击黑箱痛点。
arXiv:2608.01732v1 Announce Type: cross Abstract: Modern recommender systems produce predictions that users cannot interrogate. The two dominant impro…
6
SciClaimSeekers at CheckThat! 2026: Retrieving Scientific Sources for Social Media Claims with LLM Reranking
用 LLM 重排序提升社交媒体言论的科学源检索精度，为事实核查提供高效方案。
arXiv:2607.24803v1 Announce Type: cross Abstract: Scientific claims often spread on social media faster than they can be verified, while posts rarely …
7
TabRank: Chain-of-Thought Distillation for Table Re-Rankers
用思维链蒸馏提升表格重排序效果，TabRank创新方法亮相。
arXiv:2607.25182v1 Announce Type: cross Abstract: The ability to retrieve relevant tables for answering questions is a key task for structured informa…
8
Show HN: PDF reflow in the browser with local AI model
用本地AI在浏览器里直接重排PDF，无需上传，隐私友好，文档阅读更顺手。
Article URL: https://www.appblit.com/pdfreflow/demo Comments URL: https://news.ycombinator.com/item?id=48804162 Points: 5 # Comments: 0
9
Optimizing RAG Rerankers with LLM Feedback via Reinforcement Learning
利用强化学习与LLM反馈优化RAG重排序器，解决静态标注与生成脱节的关键难题。
arXiv:2604.02091v2 Announce Type: replace-cross Abstract: Rerankers play a pivotal role in refining retrieval results for Retrieval-Augmented Generati…
10
Diffusion-GR2: Diffusion Generative Reasoning Re-ranker
扩散生成式重排器，用扩散模型替代自回归推理，大幅提速同时保持推荐精度，适合大规模场景
arXiv:2607.01170v1 Announce Type: cross Abstract: Generative reasoning re-rankers achieve strong recommendation accuracy by emitting a chain-of-though…
11
When Reranking Hurts: Uncertainty-Based Gating for Few-Shot Reranking
推翻重排序必有益的假设，提出无训练门控机制：只有不确定性高时再重排序，反而提升性能。
arXiv:2606.31087v1 Announce Type: cross Abstract: Few-shot selection typically assumes that reranking retrieved examples always improves performance. …
12
5ting at SemEval-2026 Task 8: Strong End-to-End Multi-Turn RAG via LLM-Based Reranking and Faithfulness Control
首次公开多轮RAG端到端强基线：用LLM重排序+忠诚度控制，在SemEval-2026上验证有效性。
arXiv:2606.28737v1 Announce Type: new Abstract: We introduce 5ting, our system for the SemEval2026 Task 8 (MTRAGEval), which evaluates multi-turn Retr…
13
Show HN: ReflowPDF – browser PDF editor where tables reflow
直接在浏览器里编辑PDF表格，删除行后自动重排，告别文本框错位难题
posted an early version of this here a while back when it was just a waitlist. it's fully live now, and i wanted to show the part that's actually hard…
14
MemRerank: Preference Memory for Personalized Product Reranking
MemRerank提出用偏好记忆机制增强个性化产品重排序，在冷启动与行为稀疏场景下显著提升推荐精准性。
arXiv:2603.29247v3 Announce Type: replace-cross Abstract: LLM-based shopping agents increasingly rely on long purchase histories and multi-turn intera…
15
Multimodal LLM-Empowered Re-Ranking for Generalizable Person Re-Identification
多模态大语言模型如何提升行人重识别的泛化能力？本文提出全新重排序框架，为计算机视觉领域带来突破性思路。
arXiv:2606.16161v1 Announce Type: new Abstract: Domain Generalizable (DG) person re-identification (Re-ID) has attracted growing research interest due…
16
Classical RAG vs Agentic RAG: a practical decision guide
经典RAG与Agentic RAG优劣对比，帮你避开“检索坑”做出明智选择
"Should I use RAG or an agent?" comes up in almost every LLM project I work on. The honest answer is that they are not competing choices. Classical RA…
17
LLM-Assisted Reranking to Operationalize Nuanced Objectives in Recommender Systems
用LLM辅助推荐系统重排序，实现更细致的目标优化，论文来自arXiv 2606.02883。
arXiv:2606.02883v1 Announce Type: cross Abstract: Recommender systems have grown from content-organization tools into sophisticated systems that shape…
18
Can LLM Rerankers Predict Their Own Ranking Performance?
探索LLM重排序器如何自我预测排序性能，挑战模型自省边界的新研究。
arXiv:2606.03535v1 Announce Type: cross Abstract: Retrieval effectiveness varies substantially across queries, making it important to estimate ranking…
19
Ocean4Rec: Offline LLM-Derived OCEAN Profiles for Request-Time VOD Reranking
利用大语言模型离线生成OCEAN人格画像，实现视频点播实时重排，精准提升推荐效果
arXiv:2605.27429v1 Announce Type: cross Abstract: Industrial video-on-demand (VOD) recommenders need richer content understanding, but LLM-as-reranker…
20
How Reliable are LLMs for Reasoning on the Re-ranking task?
评估大语言模型在重排序任务中的推理可靠性，揭示其当前能力上限与潜在风险
arXiv:2508.18444v2 Announce Type: replace-cross Abstract: With the improving semantic understanding capability of Large Language Models (LLMs), they e…