NishiSearch

Web This site Trusted

30 result(s) for “okapi bm25 site hotchips pp site hotchips pl site www lac com site:arxiv.org” of 39 matched · 580 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)

c=ks6_:7G6)yώST.;B$$L ~ۍ" 5

https://arxiv.org/src/2211.10435
Com4 Ž(MW"_x;;Bu85'UN;h&H0ԐP/^/3KO`GC/ +ӄ3jGIt, ;]"}3ъ_w˓s&s]b%#-Ic:9Pb(RGl+̏GGK~XA/(ׅd CbBUCG8tY[|A]['ꍤQ[SSMl`/Jn'퉪|;x V|߶;~0\h[z)G՘> ~X

%PDF-1.5 % 152 0 obj > stream xmTˎ0+$$0  a#A%

https://arxiv.org/pdf/2402.03300
{aXP&τ[&q_pBcduOPVPlq$a(\N[tkЋ>X;带 C=%F5ms~JfoW޷~fdpLft ;@2ɯ8u(+/L&pPtߗrq#b~^ǻ'DE~QyǸRm#q{3 b0pA۵Dbll[9kKQ8YElyzS9ʚVFP85S{=m5[W=lO{Ï`Y('>

%PDF-1.5 % 1 0 obj > >> endobj 2 0 obj > endobj 3 0 obj > stream

https://arxiv.org/pdf/2508.11152
com three Proceedings of ACM Conference (Conference'17) book 1 1 9 9 Tianjiao ZhaoJingrao LyuStokes JonesHarrison GarberStefano PasqualiDhagash Mehtahttp://arxiv

Report GitHub Issue

https://arxiv.org/html/2608.02613v1
We evaluate five open-weight readers with Vanilla context, BM25-RAG, Oracle retrieval, Memobase, and MemSearch as memory backends

%PDF-1.5 % 152 0 obj > stream xڭ[Yܸ~ׯЃ:Fh8^X?

https://arxiv.org/pdf/2102.13654
48#vBB҈ mt={v ֳĉ{Wkv_rORu>YS\+V,LqO8--gϞMqJLLTwv͛7O߷o_pp8Mҥ >uּSN +V,]kVre ; y)񄿀pW[Y'0A=zxX,={VfE$0Q[JH*4Z|do߾

%PDF-1.5 % 15 0 obj > /ProcSet [ /PDF /ImageB /ImageC /ImageI ]

https://arxiv.org/pdf/2101.00190
/XObject > >> >> stream x+TT(T0B K33 3Tp> stream xw$U/aIWTDE3Q aq9g]̺ݼauװ-9vx|S'= @ @ @ @ @ @ @ @

rj;srY9靟OO߰ޟ4'}Ʊڅ'o1d{l

https://arxiv.org/src/2608.03883
lއxG&JWXԴ&[v @V[uԇF7vz%N`pP \>$kb {K/05 U0[|ʋXcc S-bQEAE

%PDF-1.7 % 1 0 obj > stream xZms6~4&Nb{v\Xe^

https://arxiv.org/pdf/2607.26405v1
e8s`Wg+`#)S%~8NTҌYE, (6*3FӪr44P#Yf͞hhӰCkE88+j"7G9~PpC+R2C#`p˜1q EE5=F]=7z&`qp&bð| _/cSMrΤ f/%m Ȱw \ԉCb֓x5cfw(:Kzgqf1iXg3Np y/hHS>W#/5ferTapC

%PDF-1.7 % 1 0 obj > stream x}Mo0 H =΃ 8(

https://arxiv.org/pdf/2608.04008
6>Ȍ6=RBmLLXƇM_|VNe]V[Rª{‚5X68$T`="03[R/u C*JsI)u8WqMI|WG0hZ5+ާl* pair 3z } Bx׏J ߣۡjy ŃE"eSPL0}O;ﮍk;_E滳6")sr\#UxtQ 2~'wgrxW]pp*c )>VNbQW'Z]

Zzc\msFguT$#oYo'sξ홮x Yb3

https://arxiv.org/src/2211.10435v1
HIķR&8ק_e]&K{n>{'~O޹s;O&'>Q>$Q.tzӺ}W;8Y]+s ߿߽~OǓO#qSoʺ|L C3fzf-|ȶ jZ|17vDٝ59@"0l3b0GYs 3 Wt ->

_uTe' Cakaw( /p{uνt;otxo?

https://arxiv.org/src/2006.03594
GaViA䥖*&,1fA/CXP~PL̑&x1p*XK$M"d[:c6Ge"&b)\MYn

rrjw\S?   ! fI{,D^^B 5@ $Jl

https://arxiv.org/src/2608.04008
4H"%`H $̉Sϼg^o5Grrk^{G}+B5/Gz_q%riJU8VvlEFaaQ?:)666¢#~qoy%p:|p򷨰Gbm8gȉ#'d`H芨#q낤ewyqBqu

1 Introduction

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

Report GitHub Issue

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

%PDF-1.7 % 1 0 obj > stream xMO@.$M1ZZ6

https://arxiv.org/pdf/2608.02942
+e,L}Ëuh{ǀHJ'>N>NA-z*ky nx ZZ{I3qF_z MJӠPp

%PDF-1.5 % 7 0 obj > stream xP(endstream endobj 9 0 obj >

https://arxiv.org/pdf/2407.17789
ȇ)d`$gៀAHP; s=1PhpPe0f(h,@F%;

%PDF-1.5 % 153 0 obj > stream xڭ]o=B,\>q$6@DD

https://arxiv.org/pdf/2109.12196
$!8C{gvfdݥ/9ooz!/NEB^aBſZ ])A仲-Q  ȧ(޽~qzw旲g׹?^}H/0KdEk)T27ąL?̴@Oe@W޲xe{ZԂ76r͢6MPMP4, #г}3Bn^

%PDF-1.3 % 3 0 obj > stream x]ksu_̂ modRVֲ+b

https://arxiv.org/pdf/2601.04660
ˍqU9ݷCbMJUq_ #}#*}!-q,V~/՘uU{-˶I?hGk!&yJ%柽L4]Jn뙽{qie'?O\1=PKe 'wGiu0'NX?/s:21Á7/[KLc

%PDF-1.7 % 1 0 obj > stream x[is۸~?Nޔ bRuV%v8N

https://arxiv.org/pdf/2608.02615
mNJ3mDbwF=Ml;x,qq,ޣ^}ZXy:wWW|

Mapping the City Through the Lens of Language Models

https://arxiv.org/html/2608.02971v1
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 HTML? Report Issue Back to

%PDF-1.5 % 7 0 obj > stream xP(endstream endobj 9 0 obj >

https://arxiv.org/pdf/2407.00215
9/$#pF-f߮)PL~3$G 1%Bn CR zt6:3

%PDF-1.7 % 1 0 obj > stream xXYo6~] x@&hҧ"Zz.

https://arxiv.org/pdf/2608.03340
S_J&983HB89HxJR F2ӄEJhBd* $eI x !f10 ,O  'Ĺ!#\ L[ t""Ⴐ2AAH9Cnㄈn?mtjwk[®@5B5cuTeS&|81*;rՋ6 c¡`̘ ,`+|

%PDF-1.5 % 5 0 obj > stream xZn}Wc{sA'݋i?(2%

https://arxiv.org/pdf/2407.02095
n6C z΢n$8Fum+ۏByD^C*:s$a"2A0 ;~E-H؛ 8XWg)plIHnWY2H ĤAaƥu%YQriCqG

%PDF-1.5 % 1 0 obj > endobj 2 0 obj > endobj 3 0 obj > stream

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

Computation and Language

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

1 Introduction

https://arxiv.org/html/2407.16741v3
com/All-Hands-AI/OpenHands Slack http://bit

%PDF-1.5 % 153 0 obj > stream xڭZKs -Tf?I#)m+kWuF 

https://arxiv.org/pdf/2503.11576
r2$}HCJqh44޾Zqǹ"bۇOѯܤѶݷ$TlXl{zm6ubWqx(k؞l6}L SL@5mtE ۛ޾ ^Lqas%/7~M2G0{t4 .~h|?j,73oתq"yh4Nt~q{-^Wl$

%PDF-1.7 % 1 0 obj > stream xZksJb>&rFRn-` l ~fVJ25F

https://arxiv.org/pdf/2608.02872
~ MChutϙ :Ә,L6,f36 `.35y̴a&;SD rYMi"{.|kksσBbz7=9'9Q-kӰ*5xb+U)VKfQv BdҒ KQ$tNn[ ZEcʌ3+$.xktܖ7reX\W0|z

Artificial Intelligence

https://arxiv.org/list/cs.AI/new
PL) Knowledge graph engineering often distributes accepted state, observations, constraints, processes, and hypothetical scenarios across artifacts whose combined execution contract remains external

%PDF-1.5 % 222 0 obj > stream xڍZYܶ~ׯ7qI4|KϿ!*

https://arxiv.org/pdf/2210.00045
Nߥpp A~YAZ^E {{ѵ;