Web This site Trusted
30 result(s) for “okapi bm25 site hotchips pp site github com site test org de site race builder tls site:arxiv.org” of 37 matched · 924 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)
The query asks the model to recall the topic of an earlier conversation about Tesla; the gold answer is anchored in one specific session about Pooja’s dig site
from the top result below
https://arxiv.org/html/2608.02613v1
Yet, existing memory benchmarks often under-test the combination of activity-dense interaction, ego-centric perspective, and coherent multi-session worlds
https://arxiv.org/html/2407.16741v3
com/All-Hands-AI/OpenHands
Slack http://bit
https://arxiv.org/list/cs.AI/new
Skip to main content
System maintenance August 4th and 5th Learn more ×
Search Submit Donate Log in
Search arXiv
Press Enter to search · Advanced search
Artificial Intelligence
New submissions
Cross-lists
Replacements
See recent
https://arxiv.org/html/2608.03048v1
com/JetAstra/PI-Mem
Introduction
The ability to reason over long contexts is increasingly important for large language models (LLMs), supporting applications such as long-document question answering (Gemini Team 2025; Yang et al
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/list/cs.CL/new
Yet, existing memory benchmarks often under-test the combination of activity-dense interaction, ego-centric perspective, and coherent multi-session worlds
https://arxiv.org/pdf/2407.00225
5 % 1 0 obj > endobj 2 0 obj > endobj 3 0 obj > stream Large-scale, Independent and Comprehensive study of the power of LLMs for test case generationWendkûuni C
https://arxiv.org/pdf/2407.02510
JXH'> 4EQM/j4~z}7O_}jv. ;i(Sq9C>Tm m ~.3 Tеx(=)g;>7K}&4秿Ӑ ʼn|C[ռ? te^W+ $@GP& lmQvZz8 %e^cŔ~O0N7uy Zn Vz) "M!
https://arxiv.org/pdf/2407.02402
߯jD岻fc;Z̫MfG} q]/ޭmޯo⣩0Z^x]fkn{E+{*ʧypg6;5PVpH8$hmڢ*߄zR:")3qXysO'H)-"}[˺s 3 4{pYdrK+ a }ѫW{ Fvm7344AGc
https://arxiv.org/src/2006.02230
2+45(@;KQ&5HS+DD~:Q7X0]""n@h|P_a&%Bqr^݊'|V}W4 nGo>h(F?)SxCƗz^G_A +|CHurX$=ҜnR ߵ-T SZ^a } /_SS`]2f|m0Ui@S75Ј4
https://arxiv.org/src/2608.03883
5-jAa4 1:j~Є5QFS:T:; &h89c3@EE deE)vQ{| fuoIc~̆gІ e3IVk+'RHUI5G
https://arxiv.org/pdf/2608.04008
6>Ȍ6= RBmLLXƇM_ |VNe]V[Rª{5X68$T`="03[R/u C*JsI)u8WqMI|WG0hZ5+ާl* pair 3z } BxJ ߣۡjy ŃE"eSPL0 }O;ﮍk;_E 滳6") sr\#UxtQ 2~'wgrxW]pp*c )>VNbQW'Z]
https://arxiv.org/pdf/2608.03118
Zz|PG-T*1P8Y v k-'Nğ`PM $&] L'|* p7k7mE7nry09U=PP#'#ބv2Z$t;Ʀlr5
https://arxiv.org/src/2006.00508
6t[Þ9{ʞ{Wwb {ޱ #;X/ŭIf30q6g d ]3,dE=YRvVl>H:OAib vĆlĎ٘Sv ;!"H )5Naxzj 8џ7 4 y jHx:_yf!~Noi2VoZ
https://arxiv.org/pdf/2608.03411
6applМe~-y2Gi&pf3KjGKe ,"&:w|ҶP"rfr\xqF=/ܖn*>]zJX-w_0}0(B5&2
https://arxiv.org/pdf/2006.01402
_8b/UYyWѻyn̳/?4oIܼvF7ina>M){WlY}]~pPdSvD?f[۸/,3OM% >N9.t ^hsu Y}ǛVZ+ *5ڰ2b.mZ6M {@|Pܠ;Y>i?
https://arxiv.org/src/2005.14165
0鮪GeZ ON!N\磻 =9'Ebkc>iBh'Xfܺ7:{w 1ÓORq/7uuZuguuoIx[Knv~;oNNL!:.9m7EB xBc~[*
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/pdf/2608.02935
0 rFBLS^C#)^ku7qy dZ1% rF>2tK0(OB{յ;7] GJӽpM Gpp-dR-|qd
https://arxiv.org/pdf/2006.04122
/Width 614 >> stream x XkǏ=D!D6"ZT$E%BEgQ)tJ{hU(J+!V) D~s)Ie_5ͼ P( j BP(D& BP iӦAP( E# ȄBP(hDP( BP("BP(D& %%X B~; ߿[^
https://arxiv.org/src/2006.02085
r٥]+ZWǧ' -tf|| zmE{:o=W l. o;0?SƑb EP y ojz0H'OJ Dv]+i@ WOÏeV^1AggNn υO| îdΒ`$rC
https://arxiv.org/list/cs.IR/new
In a live A/B test on Shopee Homepage Search, it increases GMV per user by 1
https://arxiv.org/html/2508.20108v2
However, existing methods often fail to handle distribution shifts effectively, focusing on scaling or representation adaptation without fully addressing distributional discrepancies and shape misalignments between training and test data
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/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/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/recent
Skip to main content
System maintenance August 4th and 5th Learn more ×
Search Submit Donate Log in
Search arXiv
Press Enter to search · Advanced search
Information Retrieval
Authors and titles for recent submissions
Wed, 5 Aug 2026
https://arxiv.org/pdf/2006.00441
m*h:yg)DyF5ۊO*wƗ sQ %[R}27xde29L Yp 3#Qɳ^ŁʒTBWqSy;㫓GV&2^-\8M%څxŦj,}KV0e hwOxul &\J
https://arxiv.org/pdf/2608.02942
+e,L}Ëuh{ǀHJ'>N>NA-z*ky nx ZZ{I3qF_z MJӠPp
https://arxiv.org/pdf/2310.19147
% ;Cr. ^̛B)VE?cPN9kW@WQQ`/ fc(,g'r ='HVG/#("FdZ^Rd1*NIA',q:4E09,`[_:ިe, MtN+_KܐfDd(gO+?6g{='$D ࢌ َA,A&K%