Web This site Trusted
30 result(s) for “okapi bm25 site terms com pp site levin ca site ccitt cl site:arxiv.org” of 74 matched · page 2 · 468 ms
Scope: Nishi’s own index (our crawl + Common Crawl) — not the whole live web. Some sites block all automated crawlers (anti-bot walls), so their pages may be absent here even though we never filter lawful content.
Freshness: no result on this page carries a fetch time yet (indexed before the fetch epoch was stored beside the doc)
https://arxiv.org/src/2006.01318
[lQAc5)oK/[msr^!睮4пuk6 4 jk7j ~YF9iD2F+D(6'5֢?U4$S$'Xb^sK7iR5*hwb!Y ?%yZ-yrVvroVXٜp|
https://arxiv.org/src/2006.02464
>>!ŧ/h4>!BO28w/ # ,l4I ~˥ ]Jo ?t&;Iԋiz3f6-O4}z,(L$MD4~\4J7K%( @WubL,4| bG bU\j)cL W^ SKB;
https://arxiv.org/pdf/2608.02666
'd$ WU )]Wu}~1J Д&Y{S.i臿Exiy=U%]REYy[tE.zK]::( .Yy9_b\_odGva-KF){:^>^ou_^GmϟooޤS9TQNR2)ۢ\[NUtE:dM&UYb-@u%
https://arxiv.org/html/2205.01882v5
2 Details of the DVD Dataset
M Additional Empirical Application: Fishing-site Choice
M
https://arxiv.org/html/2608.03048v1
CL] 04 Aug 2026
PI-Mem: Pushing Long-Context Reasoning to 3
https://arxiv.org/list/cs.CL/new
We evaluate five open-weight readers with Vanilla context, BM25-RAG, Oracle retrieval, Memobase, and MemSearch as memory backends
https://arxiv.org/pdf/2608.01785
B%pp7w}^t3>/nN y@IvonG
https://arxiv.org/html/2501.13956v1
com
Abstract
We introduce Zep, a novel memory layer service for AI agents that outperforms the current state-of-the-art system, MemGPT, in the Deep Memory Retrieval (DMR) benchmark
https://arxiv.org/html/2608.03138v1
Struct-Aware Policy Learning
Report GitHub Issue
×
Title:
Content selection saved. Describe the issue below:
Description:
Submit without GitHub Submit in GitHub
arXiv is now an independent nonprofit! Learn more ×
Back to arXiv
Why
https://arxiv.org/list/cs.AI/new
CL)
Recent studies have identified an ``Artificial Hivemind'' effect in Large Language Models (LLMs) causing models to converge on a narrow, homogenized consensus even for open questions
https://arxiv.org/pdf/2006.02602
^b⇷E(8A⚞X@D6hg7u[ -0 L*:h$ V pP/O퓩-~ɉMI5&Bd]$ԣv9d̾i@͝j0pX "Ihg> stream xuvܸ_;ܚQ323~o4ADE
https://arxiv.org/src/2212.07841
A}يF>WTٶgCAo
https://arxiv.org/pdf/2407.17789
ȇ)d`$ gៀAHP; s=1PhpPe0f(h, @F%;
https://arxiv.org/pdf/2212.07841
%*fcXPp@A|bd"8hnb
https://arxiv.org/pdf/2407.02395
߯jD岻fc;Z̫MfG} q]/ޭmޯo⣩0Z^x]fkn{E+{*ʧypg6;5PVpH8$hmڢ*߄zR:")3qXysO'H)-"}[˺s 3 4{pYdrK+ a }ѫW{ Fvm7344AGc
https://arxiv.org/pdf/2608.00028
ffLl!i[ ,1$JOKj>j,K0LD>SL*u]2ϑ,b^ p`JT?bc+Y$K(ğ c,fm5bXMVrXOQڊ x So+j,FWHSQ`+ҝ_e+ ݖ yQR1 K>LEi!l-vVXݸH2 ' vq.Wy8͢vr
https://arxiv.org/abs/2608.03883
Our systems combine sparse BM25 retrieval, evidence-aware rescoring for self-referential symptom reports, embedding-based reranking, query-prototype expansion, and LLM-based reranking
https://arxiv.org/list/cs.IR/recent
CL) [pdf, html, other]
Title: SciRet: A Compute-Aware Empirical Study of Retrieval and Reranking for Scientific RAG
Kaysarul Anas Apurba, Md
https://arxiv.org/abs/2608.03860
The pipeline combines sentence-window chunking, BM25, BGE-M3 dense retrieval, reciprocal rank fusion, optional cross-encoder reranking, and grounded answer generation
https://arxiv.org/list/cs.IR/new
CL)
Existing deep-research agents use a search-visit workflow that retrieves and reads whole pages, without considering the addressable structure that web sources expose through titles, headings, sections, and metadata
https://arxiv.org/list/cs.CY/current
251-256
Showing up to 50 entries per page: fewer | more | all
[1] arXiv:2608
https://arxiv.org/html/2609.03027v1
Report GitHub Issue
Description:
arXiv is now an independent nonprofit
https://arxiv.org/src/2608.04009
p@VE WEQG ( zPQY9?!{_UuWuw3̞=3}8t{w*UU ḾŚ"9*IOԓDPbo|:CD{%F9F"FI#2odDz#+$>EElȊIE $x'$%xGXLFt*&wXuʂMRiֳkT/E$E&5 z= 0x\årGK
https://arxiv.org/pdf/2506.01844
SmolVLA: A Vision-Language-Action Model for Affordable and Efficient RoboticsMustafa ShukorDana AubakirovaFrancesco CapuanoPepijn KooijmansSteven PalmaAdil ZouitineMichel AractingiCaroline PascalMartino RussiAndres MarafiotiSimon
https://arxiv.org/pdf/2608.03086
[H5I__D$ɬ*.{fV2+ψ/"#"lTҍSNYW*ཊ*6^%ب(m, ҮFb_4wJz1;>/?}XUoKAUG?1>Ϗ&_ގhJa_lIhF]05JF(md` -*Pb4Wr~>8:|zׇuA%5ϵ ^jnTY4 eS*
https://arxiv.org/abs/2104.08663
Our results show BM25 is a robust baseline and re-ranking and late-interaction-based models on average achieve the best zero-shot performances, however, at high computational costs
https://arxiv.org/html/2407.16741v3
com/All-Hands-AI/OpenHands
Slack http://bit
https://arxiv.org/list/cs.CL/2022-01
451-453
Showing up to 50 entries per page: fewer | more | all
[1] arXiv:2201
https://arxiv.org/list/cs.CL/2021-01
451-469
Showing up to 50 entries per page: fewer | more | all
[1] arXiv:2101
https://arxiv.org/html/2607.27070v1
org perpetual non-exclusive license
arXiv:2607