huggingface-daily-papers-2026-05-21

AI · May 21, 2026 · 1 min read

HuggingFace Daily Papers

Fetched: 2026-05-21T11:09:39Z

Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos

Upvotes: 0

A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook

Upvotes: 0

Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation

Upvotes: 0

Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining

Upvotes: 0

MOCHA: Multi-Objective Chebyshev Annealing for Agent Skill Optimization

Upvotes: 0

CutVerse: A Compositional GUI Agents Benchmark for Media Post-Production Editing

Upvotes: 0

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs

Upvotes: 0

You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories

Upvotes: 0

OCTOPUS: Optimized KV Cache for Transformers via Octahedral Parametrization Under optimal Squared error quantization

Upvotes: 0

Learn-by-Wire Training Control Governance: Bounded Autonomous Training Under Stress for Stability and Efficiency

Upvotes: 0

Stitched Value Model for Diffusion Alignment

Upvotes: 0

IndusAgent: Reinforcing Open-Vocabulary Industrial Anomaly Detection with Agentic Tools

Upvotes: 0

Safety Alignment as Continual Learning: Mitigating the Alignment Tax via Orthogonal Gradient Projection

Upvotes: 0

The Unlearnability Phenomenon in RLVR for Language Models

Upvotes: 0

OcclusionFormer: Arranging Z-Order for Layout-Grounded Image Generation

Upvotes: 0