Mary Hernandez

hernandez-m's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 4 days ago

Scaling Automatic Research Agents via World Models

Paper • 2608.12564 • Published 17 days ago • 452

upvoted a paper 5 days ago

Mask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rollout

Paper • 2609.09123 • Published 7 days ago • 55

upvoted 2 papers 10 days ago

FlashRender: Few-Step Generative Rendering via Camera-Controlled Video MeanFlow

Paper • 2609.03563 • Published 12 days ago • 19

Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Training

Paper • 2608.26730 • Published 19 days ago • 155

upvoted a paper 24 days ago

ForgeWM: Progressive Causal Training for Few-Step Action-Conditioned Video World Models

Paper • 2608.14022 • Published Aug 14 • 24

upvoted 2 papers 25 days ago

SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation

Paper • 2608.17426 • Published 28 days ago • 159

Co-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RL

Paper • 2608.17253 • Published 27 days ago • 97

upvoted 2 papers 28 days ago

Can We Defend Against AI-Generated Video Attacks on Real-World Crisis Events? A Systematic Evaluation of Detectors, Generators and Social Dissemination

Paper • 2608.14391 • Published Aug 14 • 282

Self-Supervised Visual On-Policy Distillation

Paper • 2608.14144 • Published Aug 14 • 170

upvoted a paper 30 days ago

H2R-Bench: Benchmarking Human-to-Robot Manipulation Video Generation in World Models

Paper • 2608.13049 • Published Aug 13 • 20

upvoted 7 papers about 1 month ago

SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries

Paper • 2608.05604 • Published Aug 6 • 80

OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution

Paper • 2608.00677 • Published Aug 1 • 263

On-Policy Self-Distillation without Any Supervision

Paper • 2608.06296 • Published Aug 9 • 219

WorldClaw: Agentic 3D Open-World Generation at Scale

Paper • 2608.05248 • Published Aug 5 • 85

Knowledge-Geometry Decoupling: Refreshable Pretrained Transfer for Streaming Recommendation

Paper • 2608.02738 • Published Aug 6 • 47

SkillJack: Persistent Skill Backdoors in Self-Evolving Agents

Paper • 2608.03509 • Published Aug 4 • 24

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks

Paper • 2608.02023 • Published Aug 3 • 158

upvoted 3 papers about 2 months ago

A New Role for Relevance: Guiding Corpus Interaction in Agentic Search

Paper • 2607.24223 • Published Jul 27 • 98

ReDesign: Recovering Editable Design Structures from Images via Agentic Decomposition

Paper • 2607.25565 • Published Jul 28 • 67

HiFi-UMI: Learning Deployable Manipulation Policies from High-Fidelity UMI Data Alone

Paper • 2607.25895 • Published Jul 28 • 160