HuggingFace
BiasReducer: Adaptive Bias Mitigation for Reward Models
Reward models score responses from large language models (LLMs) and guide LLM training toward human preferences. Howe...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
Tacit-TTS: From Autoregressive Decoding to Masked Prediction for Efficient Transcript-Free Voice Cloning
TTS systems with autoregressive semantic modeling have demonstrated strong zero-shot voice cloning performance and ri...
HuggingFace
Aligning One-Step Generative Models with Reward-Weighted Transport Distillation
One-step generators enable high-quality visual generation with a single network evaluation, but their post-training i...
HuggingFace
Training LLM Judges from Language Feedback via Position-Selective Self-Distillation
We study training LLM judges from natural language feedback, especially for subjective tasks where the verdict depend...
HuggingFace
PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation
Unified Multimodal Models (UMMs) often rely on separate visual representations for understanding and generation, incr...
arXiv
ComputerSD: Online Self-Distillation from Real-Time Feedback for Computer-Use Agents
Online training enables computer-use agents (CUAs) to improve through interaction with executable environments. Howev...
arXiv
Belief-Aware Multi-Agent Path Finding under Map Uncertainty
Multi-Agent Path Finding (MAPF) aims to find collision-free paths for multiple agents in a shared environment. Classi...
arXiv
cua-speedrun: Standardized Benchmarking of the Speed of Computer-Use Agents
Computer use agents (CUAs), which use graphical user interfaces (GUIs) to complete tasks on a computer, have recently...
arXiv
PivotOPD: Learning to Recover from Pivotal Mistakes in Multi-Turn Agents
On-policy distillation (OPD) is a promising approach for training language agents, providing dense teacher supervisio...
arXiv
Linguistic Loopholes in LLM Unlearning: From a 174-Language Benchmark to Coverage-Aware Unlearning
Unlearning a fact in one language does not guarantee its removal in others as changing the query or even the requeste...
arXiv
CAS II: Symmetric Partitions as Kolmogorov Models
In algorithmic statistics a string x is explained by a finite set containing it, and Kolmogorov's structure function ...
arXiv
How Much of a Harness Does a Strong Agent Need for Autonomous ML Engineering?
Recent autonomous machine learning engineering (MLE) agents have made significant progress on public leaderboards. Of...