Plumbline: When the Loss Lies, Validating LLM Training Correctly
arXiv:2611.13393v1 Announce Type: new Abstract: Correctness is a prerequisite for training large language models (LLMs) at scale, yet it is hard to ensure: a fa…
言栖资讯收录 248497 篇 AI、开发与建站文章,按发布时间排序,支持搜索与按语言筛选。
arXiv:2611.13393v1 Announce Type: new Abstract: Correctness is a prerequisite for training large language models (LLMs) at scale, yet it is hard to ensure: a fa…
arXiv:2611.13309v1 Announce Type: new Abstract: AI coding agents can now construct scientific workflows, but operating them on shared cyberinfrastructure (CI) r…
arXiv:2611.13293v1 Announce Type: new Abstract: Serving large language models at high concurrency with long contexts requires KV-cache capacity and attention ba…
arXiv:2611.13188v1 Announce Type: new Abstract: Expert parallelism (EP) shards the experts of a Mixture-of-Experts (MoE) layer across GPUs, so every MoE layer r…
arXiv:2611.13176v1 Announce Type: new Abstract: Per-step model routers send each LLM call of an agent to the cost-optimal model dynamically within each session.…
arXiv:2611.13019v1 Announce Type: new Abstract: The proliferation of maritime activities has spurred the emergence of numerous computation-intensive and delay-s…
arXiv:2611.10035v2 Announce Type: replace-cross Abstract: End-to-end VITS text-to-speech models synthesize natural speech in a single forward pass, yet standard…
arXiv:2611.10693v2 Announce Type: replace Abstract: Multimodal LLMs have made remarkable progress in perceiving the physical world, while their perceptual scope…
arXiv:2608.20394v2 Announce Type: replace Abstract: Industry pipelines that turn speech into supervised fine-tuning (SFT) data via multi-stage refinement are in…
arXiv:2606.18738v2 Announce Type: replace Abstract: The advancement of speech generation technologies has made artificial speech increasingly realistic. Althoug…
arXiv:2605.28063v2 Announce Type: replace Abstract: Generating unified audio that naturally integrates speech and sounds from free-form text prompts remains cha…
arXiv:2611.13957v1 Announce Type: cross Abstract: } Predicting who will speak next, and when, is a prerequisite for conversational agents and social robots that…
arXiv:2611.13845v1 Announce Type: cross Abstract: We present Alania-2, a Turkish text-to-speech (TTS) system with two built-in voices, voice design from text de…
arXiv:2611.13811v1 Announce Type: cross Abstract: Antalia-2 Mini is a single-voice Turkish text-to-speech model with 7,620,931 parameters. It reads characters a…
arXiv:2611.13614v1 Announce Type: cross Abstract: Generating long-form speech requires models to keep content, speaker identity, turn-taking, and expressive sty…
arXiv:2611.13430v1 Announce Type: cross Abstract: Spoken Language Diarization (SLD) models provide frame-level language information of a speech recording. SLD m…
arXiv:2611.14443v1 Announce Type: new Abstract: Automatic Music Transcription (AMT) relies on paired audio--MIDI datasets, implicitly assuming near-perfect temp…
arXiv:2611.14421v1 Announce Type: new Abstract: Streaming speech recognizers output a word only after the speaker has finished it, typically 90-400 ms later. Fo…
arXiv:2611.14415v1 Announce Type: new Abstract: Audio foundation models like CLAP, MuQ, and MERT excel at capturing general musical similarity. On the other han…
arXiv:2611.14003v1 Announce Type: new Abstract: Microphones let an autonomous vehicle sense into areas its cameras and LiDAR cannot see, by picking up the sound…