Browsing: Hugging Face
Simultaneous Speech Translation (SimulST) systems stream in audio while simultaneously emitting translated text or speech. Such systems face the significant…
This paper proposes and validates a controlled benchmarking framework to detect and quantify linguistic shibboleth bias—subtle language cues like hedging—in…
A sketch-based strand generation model using a learnable upsampling strategy and multi-scale adaptive conditioning mechanism outperforms existing methods in realism…
Reinforcement Learning with Verifiable Reward (RLVR) has significantly advanced the complex reasoning abilities of Large Language Models (LLMs). However, it…
EvoC2Rust is an automated framework that translates entire C projects to Rust using a skeleton-guided approach, combining rule-based and LLM-based…
DreamVVT, a two-stage framework using Diffusion Transformers and LoRA adapters, enhances video virtual try-on by leveraging unpaired human-centric data and…
A framework using entropy-preserving supervised fine-tuning and token-wise entropy-adaptive reinforcement learning improves instruction adherence in LLMs by fostering rigorous reasoning…
Instruction Following Decorator enhances RLVR by improving sample efficiency, intent alignment, and reducing reward hacking in large language models. Reinforcement…
MiDashengLM is an open audio-language model using general audio captions for efficient and comprehensive audio understanding, offering faster processing and…
Transformer-based text-to-image diffusion models show varying degrees of content-style separation in generated artworks, as revealed by cross-attention heatmaps. AI-generated summary…