202611 hot_news 2026-11-06 hot_news 2026-11-05 hot_news 2026-11-04 hot_news 2026-11-03 hot_news 2026-11-02 hot_news 2026-11-01 202610 hot_news 2026-10-31 hot_news 2026-10-30 hot_news 2026-10-29 hot_news 2026-10-28 hot_news 2026-10-27 hot_news 2026-10-26 hot_news 2026-10-25 hot_news 2026-10-24 hot_news 2026-10-23 hot_news 2026-10-22 hot_news 2026-10-21 hot_news 2026-10-20 hot_news 2026-10-19 hot_news 2026-10-18 hot_news 2026-10-17 hot_news 2026-10-16 hot_news 2026-10-15 hot_news 2026-10-14 hot_n ...

数据来源：ArXiv Domain LLM Domain Papers1. FD-VAD: Semantic Endpoint Detection for Streaming Full-Duplex SpeechAbstract:Natural turn-taking in full-duplex voice interaction requires determining from partial speech whether a pause reflects hesitation or a completed conversational intent. Acoustic voice activity detection lacks this semantic information, while cascaded ASR-based endpointing introduces transcription dependence and additional processing stages. We formulate semantic endpoint detection ...

数据来源：ArXiv Domain LLM Domain Papers1. On-Device Named-Entity Recognition: A Deployability Study of Accuracy, Cost, Reliability, and ConfidenceAbstract:Named-entity recognition (NER) is increasingly wanted on-device (no API, low latency, data kept local). The practitioner’s question is not the leaderboard but which model is deployable, how to evaluate it without human annotation, and whether its confidence can be trusted. We answer these jointly. We place nine systems across three paradigms and ...

数据来源：ArXiv Domain LLM Domain Papers1. On-Device Named-Entity Recognition: A Deployability Study of Accuracy, Cost, Reliability, and ConfidenceAbstract:Named-entity recognition (NER) is increasingly wanted on-device (no API, low latency, data kept local). The practitioner’s question is not the leaderboard but which model is deployable, how to evaluate it without human annotation, and whether its confidence can be trusted. We answer these jointly. We place nine systems across three paradigms and ...

数据来源：ArXiv Domain LLM Domain Papers1. On-Device Named-Entity Recognition: A Deployability Study of Accuracy, Cost, Reliability, and ConfidenceAbstract:Named-entity recognition (NER) is increasingly wanted on-device (no API, low latency, data kept local). The practitioner’s question is not the leaderboard but which model is deployable, how to evaluate it without human annotation, and whether its confidence can be trusted. We answer these jointly. We place nine systems across three paradigms and ...

数据来源：ArXiv Domain LLM Domain Papers1. HakemBench: A Turkish Benchmark of Typed DecisionsAbstract:HakemBench is a Turkish benchmark of typed decisions, in which the model under test reads a text, a question and a fixed set of options and returns a probability for every option. Version 1.0 is released fully open under CC BY 4.0, with 2,346 items and 4,275 choice, yes/no and score questions in seven tracks (fact-check triage, education, guardrails, legal routing, moderation, spam and phishing, an ...

数据来源：ArXiv Domain LLM Domain Papers1. HakemBench: A Turkish Benchmark of Typed DecisionsAbstract:HakemBench is a Turkish benchmark of typed decisions, in which the model under test reads a text, a question and a fixed set of options and returns a probability for every option. Version 1.0 is released fully open under CC BY 4.0, with 2,346 items and 4,275 choice, yes/no and score questions in seven tracks (fact-check triage, education, guardrails, legal routing, moderation, spam and phishing, an ...

数据来源：ArXiv Domain LLM Domain Papers1. Zero-Shot Visualization: Exploring Text Corpora with User-Prompted AxesAbstract:We study the application of large language models (LLMs) to the visual exploration of textual corpora. We introduce zero-shot visualization (ZSV), a task in which users specify concepts in natural language and documents are mapped onto the corresponding concept axes for visualization. Building a ZSV system of practical value is non-trivial, as it requires choices at the interse ...

数据来源：ArXiv Domain LLM Domain Papers1. Tokka-Bench: Evaluating Tokenizers Across 100 Natural and 20 Programming LanguagesAbstract:Large language models rely on subword tokenizers whose quality varies across languages, yet no standardized multi-metric framework exists for broad comparative evaluation. We introduce Tokka-Bench, an open-source framework that evaluates tokenizers on five complementary metrics — bytes per token, unique token coverage, subword fertility, word-split rate, and vocabula ...

数据来源：ArXiv Domain LLM Domain Papers1. Diffu-LoRA: A Novel Low-Rank Adaptation for Personalized Diffusion ModelsAbstract:Personalizing text-to-image diffusion models from a few reference images requires preserving subject identity while following prompts that describe new contexts. Full-model fine-tuning is parameter-intensive, whereas low-rank adaptation (LoRA) reduces the number of trainable parameters but leaves open how adaptation capacity should be distributed across layers. We introduce D ...

数据来源：ArXiv Domain LLM Domain Papers1. Diffu-LoRA: A Novel Low-Rank Adaptation for Personalized Diffusion ModelsAbstract:Personalizing text-to-image diffusion models from a few reference images requires preserving subject identity while following prompts that describe new contexts. Full-model fine-tuning is parameter-intensive, whereas low-rank adaptation (LoRA) reduces the number of trainable parameters but leaves open how adaptation capacity should be distributed across layers. We introduce D ...

数据来源：ArXiv Domain LLM Domain Papers1. Diffu-LoRA: A Novel Low-Rank Adaptation for Personalized Diffusion ModelsAbstract:Personalizing text-to-image diffusion models from a few reference images requires preserving subject identity while following prompts that describe new contexts. Full-model fine-tuning is parameter-intensive, whereas low-rank adaptation (LoRA) reduces the number of trainable parameters but leaves open how adaptation capacity should be distributed across layers. We introduce D ...

数据来源：ArXiv Domain LLM Domain Papers1. AutoIndexer: Flexible-Order Decoding by Training Causal Models on Chains of EditsAbstract:Autoregressive decoding is less suited to non-causally ordered data, e.g., cross-references or future dependencies, since their outputs cannot be revised post hoc, unlike iterative human reasoning. Diffusion LLMs partially mitigate this limitation but still cannot flexibly insert or remove arbitrary numbers of tokens from a pre-generated context. We design AutoIndexer ...

数据来源：ArXiv Domain LLM Domain Papers1. AutoIndexer: Flexible-Order Decoding by Training Causal Models on Chains of EditsAbstract:Autoregressive decoding is less suited to non-causally ordered data, e.g., cross-references or future dependencies, since their outputs cannot be revised post hoc, unlike iterative human reasoning. Diffusion LLMs partially mitigate this limitation but still cannot flexibly insert or remove arbitrary numbers of tokens from a pre-generated context. We design AutoIndexer ...

数据来源：ArXiv Domain LLM Domain Papers1. AutoIndexer: Flexible-Order Decoding by Training Causal Models on Chains of EditsAbstract:Autoregressive decoding is less suited to non-causally ordered data, e.g., cross-references or future dependencies, since their outputs cannot be revised post hoc, unlike iterative human reasoning. Diffusion LLMs partially mitigate this limitation but still cannot flexibly insert or remove arbitrary numbers of tokens from a pre-generated context. We design AutoIndexer ...