Web This site Trusted
30 result(s) for “okapi bm25 site terms com pp site levine ca site github com site can kernel org site:arxiv.org” of 63 matched · 945 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: newest result fetched 25 d ago · median age of these results 25 d · 1 of 30 carry a fetch time
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
We evaluate five open-weight readers with Vanilla context, BM25-RAG, Oracle retrieval, Memobase, and MemSearch as memory backends
https://arxiv.org/html/2407.16741v3
com/All-Hands-AI/OpenHands
Slack http://bit
https://arxiv.org/html/2608.03063v1
8 pp in a production fraud detector serving billion-scale transaction traffic
https://arxiv.org/html/2506.01844v1
7 Ablation Study
Cross-attention (CA) vs
https://arxiv.org/list/cs.AI/new
We demonstrate that it can self-assemble functional circuits from scratch and rapidly re-route logic around permanent, previously unseen hardware faults
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/html/2609.03027v1
Report GitHub Issue
Description:
arXiv is now an independent nonprofit
https://arxiv.org/html/2609.03103v1
Report GitHub Issue
Description:
arXiv is now an independent nonprofit
https://arxiv.org/html/2607.27099v1
org perpetual non-exclusive license
arXiv:2607
https://arxiv.org/html/2609.02852v1
Report GitHub Issue
Description:
arXiv is now an independent nonprofit
https://arxiv.org/list/cs.LG/2022-12
Lee, Claire Tomlin, Sergey Levine, Stephen Tu, Nikolai Matni
Comments: Appeared in L4DC 2023
https://arxiv.org/html/2607.22511v2
A statement can be free of sorry and still be mathematically uninformative: a definition may reduce to True; or an unproven step may be introduced as an axiom that the kernel accepts
https://arxiv.org/html/2608.03545v1
org perpetual non-exclusive license
arXiv:2608
https://arxiv.org/html/2608.03099v1
For each role, we trace the path from linguistic content to its embodied consumer and identify the observations or interventions that can test the claimed responsibility
https://arxiv.org/html/2508.19205v1
com/microsoft/VibeVoice
Hugging Face: microsoft/VibeVoice
Demo: aka
https://arxiv.org/html/2407.03956v3
Due to their complexity, solving Zebra puzzles effectively requires the use of a constraint solver; a solver can efficiently determine the feasible and infeasible solution space within the given constraints
https://arxiv.org/html/2608.00426v1
Safety degradation can accumulate across communication rounds
https://arxiv.org/html/2402.03300v3
com/deepseek-ai/DeepSeek-Math
Abstract
Mathematical reasoning poses a significant challenge for language models due to its complex and structured nature
https://arxiv.org/html/2407.19144v1/
To overcome this limitation, we present the Collaborative Adaptation (CA) framework, highlighting its unique capability to operate in both continuous and discrete domains
https://arxiv.org/html/2608.02612v1
org perpetual non-exclusive license
arXiv:2608
https://arxiv.org/html/2407.02518v2
com
Abstract
Large language models (LLMs) for code are typically trained to align with natural language instructions to closely follow their intentions and requirements
https://arxiv.org/html/2407.01757v1
Pasadena (CA) 91109, USA Saptarshi Bandyopadhyay Jet Propulsion Laboratory - California Institute of Technology
4800 Oak Grove Dr
https://arxiv.org/list/cs.SE/new
Through an analysis of 1,966 open source projects, 1,355 Github issues, 444 CVE reports, and 361 StackOverflow posts, we systematically map the feature support and real-world usage of globs across six common ecosystems that utilize globs
https://arxiv.org/list/math/new
Their finite iterates can develop rapidly increasing numbers of linear pieces, making them a natural test case for the expressive power of deep neural networks
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/list/cs.LG/2022-11
Dennis, Yawen Duan, Viktor Pogrebniak, Sergey Levine, Stuart Russell
Comments: Accepted to ICML 2023, see paper for changelog
Subjects: Machine Learning (cs
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/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/html/2608.02851v1
The design relies on two affine Volterra transformations involving both Fredholm- and Volterra-type integral terms, which results in a four-PIDE kernel equations