Paper Archive

Browse and export your curated research paper collection

403
Archived Days
3953
Total Papers
7.3
Avg Score
12
Categories

Export Archive Data

Download your archived papers in various formats

JSON: Complete data with analysis | CSV: Tabular data for analysis | Markdown: Human-readable reports | BibTeX: Academic citations
Browse by Date

Papers for November 10, 2026

5 papers found

[object Object], [object Object] 11/9/2026 huggingface

generative models

This work proposes WaveGen, a fully end-to-end diffusion-based text-to-waveform framework based on Spectral Forcing, which jointly learns an internal spectral trajectory and the target waveform trajectory within a single model, enabling direct end-to-end text-to-waveform generation. Unlike recent TT...

Keywords: text-to-speech, diffusion models, end-to-end generation, spectral forcing, waveform synthesis

[object Object] 11/9/2026 huggingface

natural language processing

This technical report presents MNN-Pocket-0.3B, a compact 300M-parameter dense language model designed for efficient on-device deployment and supporting context lengths of up to 32K tokens. With an INT4 deployment footprint of only 173 MB and decoding throughput of up to 466 tokens/s on iPad Pro M5 ...

Keywords: on-device LLM, edge AI, model compression, quantization, MNN inference engine, vocabulary pruning, knowledge distillation, long-context

[object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 11/9/2026 huggingface

transformer architectures

Streaming Sortformer introduced an arrival-order speaker cache to maintain speaker identities across chunks in end-to-end streaming speaker diarization, with a single model supporting configurable latency profiles spanning offline operation to ultra-low-latency streaming. Nemotron 3 Diarization addr...

Keywords: speaker diarization, streaming, transformer, Nemotron, NVIDIA, Sortformer, upsampling

[object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 11/9/2026 huggingface

ethics ai

We introduce FraudBench, an evaluation of large language models' (LLMs) propensities to recommend, assist, or directly take actions that would constitute fraud under U.S. law. Our evaluation contains a novel dataset of 159 scenarios based on real-world U.S. court cases and validated by legal experts...

Keywords: LLM evaluation, AI deception, legal compliance, fraud detection, AI safety, benchmark, autonomy, concealment
View Paper

[object Object], [object Object], [object Object] 11/9/2026 huggingface

computer vision

Self-supervised learning in Vision Transformer models, such as DINO, enables robust visual perception without requiring labeled data by leveraging large-scale image datasets. However, these models lack a focusing mechanism during training, resulting in perceptual representations that are often ambig...

Keywords: Vision Transformers, Self-Supervised Learning, Attention Mechanisms, Spatial Attention, DINO, Zero-Shot Segmentation, Interpretability
Loading...

Preparing your export...