Web This site Trusted
21 result(s) for “okapi bm25 site www eyespy cz site may may cz site dspace cui cz site:arxiv.org” · 421 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)
0Uuc̛CZD]; >{5L( G
from the top result below
https://arxiv.org/pdf/2608.02854v1
0Uuc̛CZD]; >{5L( G
https://arxiv.org/html/2608.03048v1
The read step processes all chunks in parallel, with each chunk-level read conditioned on the same global memory, thereby avoiding sequential memory overwrites that may discard earlier evidence and reducing inference latency through parallel chunk processing
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
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/2501.13956v1
2 Knowledge Graph Construction
2.1 Episodes
2.2 Semantic Entities and Facts
2.2.1 Entities
2.2.2 Facts
2.2.3 Temporal Extraction and Edge Invalidation
2.3 Communities
3 Memory Retrieval
3.1 Search
3.2 Reranker
4 Experiments
4.1 Choice
https://arxiv.org/html/2407.16741v3
2 OpenHands Architecture
2.1 Agent Definition and Implementation
2.2 Agent Runtime: How Execution of Actions Results in Observations
2.3 Agent Skills: The Extensible Agent-Computer Interface
2.4 Agent Delegation: Cooperative Multi-agent
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/2607.26327v3
'-~} HZ$ {-0B/pF '|HBI-EJ+-0$sJ( #,5BKZb' 0v A ,:i82 #Mh0i-aMB[aVF 0 K 3J8F8 t 9 2a5Qa}.!PIJp^J 6;Z# Nea>6 EpYJ
https://arxiv.org/list/cs.IR/new
For what to learn, conventional next-token prediction treats adjacency as dependency and may encode spurious transitions across unrelated sessions
https://arxiv.org/html/2608.03204v1
Standard autoregressive decoding makes locally optimal choices that may lead to errors
https://arxiv.org/html/2503.11576v1
Furthermore, relying on LVLMs may introduce common issues associated with such models, including hallucinations and the use of significant computational resources, making them impractical from both a quality and cost perspective
https://arxiv.org/html/2407.00419v1
Any realistic set of assumptions must account for the fact that other agents may be just as adaptable as our agent is
https://arxiv.org/list/cs.IR/recent
IR)
Tue, 4 Aug 2026 (showing first 34 of 45 entries )
[17] arXiv:2608
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.CV/current
1601-1623
Showing up to 50 entries per page: fewer | more | all
[1] arXiv:2608
https://arxiv.org/html/2508.16279v1
org perpetual non-exclusive license
arXiv:2508
https://arxiv.org/html/2608.03494v1
org perpetual non-exclusive license
arXiv:2608
https://arxiv.org/html/2509.22186v2
-Resolution Document Parsing
1 Introduction
2 Related Work
2.1 Traditional Pipelines
2.2 General-Purpose Vision Language Models
2.3 Domain-Specific Vision Language Models
End-to-End Approaches.
Multi-Stage Approaches.
3 MinerU2.5
3.1
https://arxiv.org/html/2506.01844v1
2 Related work
Vision-language models (VLMs).
Vision-language-action models (VLAs).
3 SmolVLA: small, efficient and capable
Overview.
3.1 Model architecture
Vision-language model (VLM).
State, action, and feature projectors.
Visual