Web This site Trusted
30 result(s) for “okapi bm25 site hotchips pp site github com site via do unit it site by network site:arxiv.org” of 38 matched · 716 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 26 d ago · median age of these results 26 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
It must search through weeks of daily conversations, find relevant mentions of the appointment, distinguish which parts of information shared by Alice are visible to Charlie, and determine whether Alice later changed her mind
https://arxiv.org/list/cs.AI/new
Inspired by this principle, we introduce Self-Organising Digital Circuits, framing functional logic generation and maintenance as a meta-learning problem on graphs
https://arxiv.org/html/2510.03215v2
It further outperforms the text communication paradigm by approximately 3
https://arxiv.org/html/2608.03011v1
AS] 04 Aug 2026
Towards Real-world Environment-aware Zero-shot Text-to-speech Synthesis via Disentangled Audio Infilling
Ye-Xin Lu, Xin Wang, Yang Ai, Hui-Peng Du, Zhen-Hua Ling, and Junichi Yamagishi This work is the extended version of our conference paper [1] published at IEEE International Conference on
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/html/2608.02668v1
com/hazdzz/deep_connection \ncudata[Correspondence]Jie Zhang (),
Correspondence: Cheng-Fang Su ()
“Geometry is not true, it is advantageous
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/html/2608.03486v1
3 Specification of the natural parameters
3 Identification via independent innovation analysis
3
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/2608.02918v1
Next, to handle the enhancement of audio signals that have been highly compressed by lossy coding, it is further proposed AEROMambaPS¯\textrm{AEROMamba}_{\textrm{P}\bar{\textrm{S}}}, which applies the same framework but replaces STFT reconstruction losses with the PAQM loss, specifically to enhance MP3 encoded
https://arxiv.org/html/2608.03063v1
On MovieLens and Amazon, it outperforms the strong User-LLM baseline by up to 32% relative Recall@5 while retaining markedly stronger language ability
https://arxiv.org/html/2509.22186v2
In the second stage, guided by the global layout, it performs targeted content recognition on native-resolution crops extracted from the original image, preserving fine-grained details in dense text, complex formulas, and tables
https://arxiv.org/html/2508.16279v1
By interacting with the environment, LLM-based agents have demonstrated immense potential in a wide range of applications (Hong et al
https://arxiv.org/html/2608.03077v1
Abstract
Multi-domain machine translation (MDMT) requires more than fluent generation: it demands domain-sensitive translation decisions such as domain disambiguation, terminology control, and stylistic adaptation
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
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/list/cs.IR/new
In a live A/B test on Shopee Homepage Search, it increases GMV per user by 1
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/html/2508.19205v1
Abstract
This report presents VibeVoice, a novel model designed to synthesize long-form speech with multiple speakers by employing next-token diffusion SBW+ (24), which is a unified method for modeling continuous data by autoregressively generating latent vectors via diffusion
https://arxiv.org/html/2608.02616v1
com
Abstract
We present the first independent, systematic evaluation of OpenAI’s Privacy Filter (OPF), a 1
https://arxiv.org/html/2608.02612v1
4 Isolating Search Space Quality
Aggressive Dimensionality Reduction by Advanced LLMs
https://arxiv.org/html/2607.22511v2
In theoretical work, it presents a more direct risk: an incorrect theorem may be indistinguishable from a correct one until it is verified by an expert, but expert verification is slow and costly
https://arxiv.org/html/2608.02609v1
(2021); we mitigate it by explicitly labeling all machine-generated Akkadian as approximate
https://arxiv.org/html/2608.03372v1
5 Scoring a production memory system
8 What it does not catch
The deterministic gate has bounded recall, by construction
https://arxiv.org/html/2607.26245v1
We do not claim trading profitability—the central empirical finding is the opposite, and that negative result is published with the data that produced it
https://arxiv.org/html/2407.03956v3
We also introduce an automated grid puzzle grader to assess the correctness of our puzzle solutions and show that the automated grader is reliable by evaluating it in a user-study
https://arxiv.org/html/2608.00785v1
2 Failure Cases Analysis
License: CC BY 4
https://arxiv.org/html/2403.08299v1
The landscape of software development has witnessed a paradigm shift with the advent of AI-powered assistants, exemplified by GitHub Copilot