Web This site Trusted
17 result(s) for “okapi bm25 site www eyespy cy site drafts cs1 org site todtechnologies in site:arxiv.org” · 587 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)
In Mini-Flash, inspired by speculative decoding, we introduce speculative correction: Mini drafts a full response, and Flash revises it as an editable initialization
from the top result below
https://arxiv.org/list/cs.CL/new
LG)
Half a million cuneiform clay tablets survive in museums worldwide, yet modern users can neither read nor write in the world's oldest writing system, leaving a 4,000-year cultural barrier that existing NLP tools have only partially addressed
https://arxiv.org/list/cs.AI/new
In practice, many field descriptions remain ambiguous or incomplete, as much of the essential context (e
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/2608.03048v1
To address these issues, we propose PI-Mem (Parallel-Iterative Memory), a mechanism that processes all chunks in parallel and iteratively refines a shared memory over a bounded number of turns
https://arxiv.org/html/2608.02613v1
7 Extrapolation across readers for cache-replay backends
TTFT rows in Table 3
https://arxiv.org/html/2607.22511v2
We present CausalForge, a framework for automated theoretical research in causal inference grounded in the Lean proof assistant
https://arxiv.org/abs/2608.03883
All submitted systems follow a staged retrieval design in which BM25 retrieves candidates at scale and semantic or LLM rerankers refine the final rankings
https://arxiv.org/abs/2104.08663
Benchmark for Zero-shot Evaluation of Information Retrieval Models, by Nandan Thakur and 4 other authors
View PDF HTML (experimental)
Abstract:Existing neural information retrieval (IR) models have often been studied in homogeneous and narrow settings, which has considerably limited insights into their out-of
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/html/2608.01366v2
org perpetual non-exclusive license
arXiv:2608
https://arxiv.org/list/cs.IR/recent
IR)
Tue, 4 Aug 2026 (showing first 34 of 45 entries )
[17] arXiv:2608
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/2407.16741v3
2 Agent Runtime: How Execution of Actions Results in Observations
2
https://arxiv.org/html/2608.02625v1
In mini–flash, inspired by speculative decoding, we introduce speculative correction: LLaDA2
https://arxiv.org/html/2608.03138v1
1 in human evaluation when scaled to Qwen3-32B
https://arxiv.org/html/2504.19413v1
ai
Abstract
Large Language Models (LLMs) have demonstrated remarkable prowess in generating contextually coherent responses, yet their fixed context windows pose fundamental challenges for maintaining consistency over prolonged multi-session dialogues
https://arxiv.org/html/2608.03703v1
4 The Loop Gain: Rebalancing Pressure in One Number
3 A Model of Preying on a Mechanical Rebalancer
3