Web This site Trusted
30 result(s) for “okapi bm25 site hotchips pp site github com site via do unit it site help qld site:arxiv.org” of 42 matched · 881 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
A million-token cloud context window does not help here, as it requires off-device upload, which privacy-sensitive personal memory management is meant to avoid
https://arxiv.org/list/cs.AI/new
Extending the pattern-generation paradigm of Neural Cellular Automata (NCA), it navigates the degenerate Boolean search space to satisfy a computational task, rather than regenerating a fixed target state
https://arxiv.org/html/2608.03048v1
6 million tokens and find that it outperforms the recurrent-memory baseline by +6
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
With the interaction history, it co-generates ground truth over six recall, reasoning, and trustworthiness evaluation dimensions
https://arxiv.org/html/2407.16741v3
edu
Abstract
Software is one of the most powerful tools that we humans have at our disposal; it allows a skilled programmer to interact with the world in complex and profound ways
https://arxiv.org/src/2608.04003
drj [Fo=EqlDuWq '@H3FD$)KAy}}9UHj$Y 0"~sͫ/''ϧtɒxߺ :J'yRfɟe׆n>)42&zm^VVlu
https://arxiv.org/html/2508.16279v1
Following this trend, the focus of LLM-based agent frameworks has shifted from relying solely on intrinsic reasoning to empowering agents to perceive and interact with environments via an array of tools
https://arxiv.org/pdf/2608.01934
7zZ~ lb_uwr > stream xmTn@Cx ^"#&W)R CfqTcfޛ|{NۻItճ;urnn: ];pvA= ]u7Ŧm;J۹v'k^Sn_ܯI
https://arxiv.org/pdf/2005.14165
U%SSYo1l& _ v){;hL'q 8X* BhMEPp > ]5 [ ިay9*l-J՚|D aOxJT"wcW@L=HxaFH&09k{2bN}2"g'~
https://arxiv.org/pdf/2407.00225
q&}r*lan*hQta3_W)6nC87$$ CA6acD۶²c\azaG&6;>SBmR [(ɒ\ ;$iT[J
https://arxiv.org/pdf/2006.15704
@ Pefjͬ*@ ygVw/wO }. ̲.(L𣸼{ }/Z! $ m1L@8K|ںWP4k F'bP4Jꏴ8yu8/q Eꗹ=?tU?TsE \tMpj{Asjk'N˓A' ߛz ]#csM_&cY +B7q^
https://arxiv.org/pdf/2608.02122
ؑEH%|K .y1m. \4#D&Db" Kc.I)QDF`%'f(#RrF11H$" M)xq "xRx0',M6ur)~f5"x !-kq{sǥANjǿ-lz~7㉁Udag0b?] Mffv m\(\B]nG
https://arxiv.org/src/2407.17789
"P Әny@ab&ųlp?;hZnZ1*}:Xr(VI c9vX^\)B :j, p߅ 9C6k orpJ: Iboh@yt*[ЅI'Ԕw@3 6ύxkb دuf] #Z2s ڍz㰹g7FA 4. ++YP ܚ
https://arxiv.org/pdf/2608.03709
IL%[&0$ږ^&)Yf\I&-s}2wbc0qn[O .% t s| 0!$"´!ae/\$:OU2|X&Z!`,ok7=8_ xUXيU`XzwӋb`:K7 ^u>^( dƅ0\6
https://arxiv.org/pdf/2608.03118
ZT$X /)n)#Wo(oRZ $Kp4Z-b\1ܰJ P"GXQi/8k^Zq:Zs9dB )sL-7xJ`aɽ)f$1 dъcCZC> stream xmTn@Cx ^"#&W)R CfqTcfޛ|{NۻItճ;urnn: ];pvA= ]u7Ŧm;J۹v'k^Sn_ܯI
https://arxiv.org/src/2005.13905
M}Z]zi=3]/pp I)6H&_NH째G h@ %Yn)$AlW*tE6J4G 0CbXE>LYS
https://arxiv.org/src/2405.20232
g~&5doYTIT4p* b@@\Uzꖦ:>Ͳta`{9 I
https://arxiv.org/src/2006.01354
TdIjǖI,D ? =x`],Ă3֯v;!픻֭.t-W8I{參&-{s/}+Yp"X&v*i ; b"^ |aǶ >!ZQ}N?}=c߳? b? {.؏ '3'ѱ^[ͦa.ll X{,c7-ي}
https://arxiv.org/pdf/2005.13905
&Q,l@2`0!`01 $4g*S9g9~Pj?}7Z+7/m_^m7?GS_9Y,|?qAB JU$+ {aFB%5|!_F04 0k Ğt:fJ5^c`츾yZ IFv[Yb4 hE9''HC&3hj|w擒cM}iG{X
https://arxiv.org/src/2006.01598
Ǐ]tIq-A$'V nwR1HAX {1G$ niT93bETåq] Rx| +k#ܾHE6{i -ntyKYe\%抖 JGL "ׅ}YG"ꑞ OR4x
https://arxiv.org/pdf/2608.02918
uuu3do*4iEpMƻE Hg>G 3>:nУS 4R"6M'§%5 8K#pΑ92B1*8, +*87b V5C>Ýc4
https://arxiv.org/pdf/2508.07408
-Aware Sentiment Factors from LLM-Augmented Financial Tweets: A Transparent Framework for Interpretable Quant TradingYueyi WangQiyao Weihttp://creativecommons.org/licenses/by/4.0/q-fin.STcs.CLcs.LG endstream endobj 4 0 obj > endobj 5 0 obj
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/list/cs.IR/new
To handle it, KGD assigns them to separate parameter sets: a refreshable encoder owns behavioral knowledge, while a task learner reads contextualized encoder states through read-only cross-attention and writes task-specific geometry through Anchored Calibration Residual (ACR) orthogonal to the pretrained embedding
https://arxiv.org/pdf/2006.00441
Ծx-#=`7FX5|YOt% dM LD7#9ܔɸ2QpH ߐʩ8r0S ʙZqjx*%ňxkuB؎})vQME+ Owʂˈ6h it;|YMe\k#kqI%h[a [}:%tKTuN M:Fk]2vNZgRUr9v%0 l:
https://arxiv.org/pdf/2210.00045
Nߥpp A ~YAZ^E {{ѵ;