AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:Modern Large Language Models achieve impressive reasoning capabilities with long Chain of Thoughts, but they incur substantial computational cost during inference, and this motivates techniques to improve the performance-cost ratio. Among these techniques, Speculative Decoding accelerates inference by employing a fast but inaccurate draft model to auto-regressively propose tokens, which are then verified in parallel by a more capable target model. However, due to unnecessary rejections caused by token mismatches in semantically equivalent steps, traditional token-level Speculative Decoding…
AI 服務暫時不可用,系統已先保留來源內容與降級元數據。
Modern Large Language Models achieve impressive reasoning capabilities with long Chain of Thoughts, but they incur substantial computational cost during inference, and this motiva…
AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:Large Language Models (LLMs) have achieved state-of-the-art performance on a broad range of Natural Language Processing (NLP) tasks, including document processing and code generation. Autoregressive Language Models (ARMs), which generate tokens sequentially conditioned on all previous tokens, have been the predominant paradigm for LLMs. While these models have achieved high accuracy across a range of downstream tasks, they exhibit low arithmetic intensity due to the inherent sequential dependency in next-token prediction. Recently, Diffusion Language Models (DLMs) have emerged as a promising…
AI 服務暫時不可用,系統已先保留來源內容與降級元數據。
Large Language Models (LLMs) have achieved state-of-the-art performance on a broad range of Natural Language Processing (NLP) tasks, including document processing and code generat…
AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:Continuous diffusion and flow matching models could represent a powerful alternative to autoregressive approaches for language modelling (LM), as they unlock a host of advantages currently reserved for continuous modalities, including accelerated sampling and tilting. Recently, several works have demonstrated the possibility of generating discrete data continuously by a simple flow matching process between a Gaussian and the one-hot encoded data distribution. They have further shown the feasibility of accelerated sampling via Categorical Flow Maps (CFMs), resulting in competitive sample…
AI 服務暫時不可用,系統已先保留來源內容與降級元數據。
Continuous diffusion and flow matching models could represent a powerful alternative to autoregressive approaches for language modelling (LM), as they unlock a host of advantages…
AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:Large language models (LLMs) with integrated search tools show strong promise in open-domain question answering (QA), yet they often struggle to produce complete answer set to complex questions such as “Which actor from the film Heat won at least one Academy Award?”, which requires (1) distinguishing between multiple films sharing the same title and (2) reasoning across a large set of actors to gather and integrate evidence. Existing QA benchmarks rarely evaluate both challenges jointly. To address this, we introduce DEEPAMBIGQAGEN, an automatic data generation pipeline that constructs QA…
AI 服務暫時不可用,系統已先保留來源內容與降級元數據。
Large language models (LLMs) with integrated search tools show strong promise in open-domain question answering (QA), yet they often struggle to produce complete answer set to com…
AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:The quality of open-weight language models has dramatically improved in recent years. Sharing weights greatly facilitates model adoption by enabling their use across diverse hardware and software platforms. They also allow for more open research and testing, to the extent that users can use them as checkpoints, fine-tune them according to their needs, and potentially redistribute them. In some cases, however, concerns on modifying these weights towards unauthorized uses may outweigh the pros of giving users such a freedom. Defending against such adaptation is non-trivial: since an adaptive…
AI 服務暫時不可用,系統已先保留來源內容與降級元數據。
The quality of open-weight language models has dramatically improved in recent years. Sharing weights greatly facilitates model adoption by enabling their use across diverse hardw…
AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:We study outlier tokens in Diffusion Transformers (DiTs) for image generation. Prior work has shown that Vision Transformers (ViTs) can produce a small number of high-norm tokens that attract disproportionate attention while carrying limited local information, but their role in generative models remains underexplored. We show that this phenomenon appears in both the encoder and denoiser of modern Representation Autoencoder (RAE)-DiT pipelines: pretrained ViT encoders can produce outlier representations, and DiTs themselves can develop internal outlier tokens, especially in intermediate layers…
AI 服務暫時不可用,系統已先保留來源內容與降級元數據。
We study outlier tokens in Diffusion Transformers (DiTs) for image generation. Prior work has shown that Vision Transformers (ViTs) can produce a small number of high-norm tokens…
AI 服務暫時不可用,以下為來源摘要,待恢復後補全翻譯:Preference alignment has become a crucial component in enhancing the performance of Large Language Models (LLMs), yet its impact in Multimodal Large Language Models (MLLMs) remains comparatively underexplored. Similar to language models, MLLMs for image understanding tasks encounter challenges like hallucination. In MLLMs, hallucination can occur not only by stating incorrect facts but also by producing responses that are inconsistent with the image content. A primary objective of alignment for MLLMs is to encourage these models to align responses more closely with image information. Recently…
AI 服務暫時不可用,系統已先保留來源內容與降級元數據。
Preference alignment has become a crucial component in enhancing the performance of Large Language Models (LLMs), yet its impact in Multimodal Large Language Models (MLLMs) remain…
Apple Music為150多個地區、數十種語言的用户提供服務,每天新增數十萬首曲目。針對拼寫錯誤、音譯和跨語言查詢的搜索召回率成為影響用户體驗的關鍵。蘋果研究人員提出了一種基於3.05億參數Siamese雙編碼器的多語言語義檢索系統,通過混合檢索架構與現有索引結合,實現了69%的Hit@10相對改進,在線A/B測試中整體轉化率提升2.28%,無結果率降低86%,長尾查詢轉化率提升7.93%。
Apple Music推出多語言語義檢索系統,基於GTE-multilingual-base微調的3.05億參數Siamese雙編碼器。