Barbara Perez

barbara-perez's activity

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

upvoted a paper 7 days ago

Player-1: Learning to Play from Synthetic Experience

Paper • 2610.20584 • Published 8 days ago • 349

upvoted a paper 10 days ago

Surfing the Activation Wave: Analyzing the Information and Geometry of LLM Hidden States for Speculative Decoding

Paper • 2610.12939 • Published 13 days ago • 18

upvoted a paper 14 days ago

SGF+: Decoupling Gradient Flows for Autoregressive Video Generation

Paper • 2610.10429 • Published 15 days ago • 61

upvoted a paper 15 days ago

Video2Skill: From Streaming Experience to Reusable Embodied Skills

Paper • 2609.36691 • Published 23 days ago • 17

upvoted a paper 19 days ago

Prompt2Skill: Unsupervised Skill Optimization From Natural Language Instructions

Paper • 2609.38593 • Published 23 days ago • 10

upvoted 5 papers about 1 month ago

What Does Privileged Information Add to On-Policy Self-Distillation?

Paper • 2609.20612 • Published Sep 17 • 36

EventEgoHands++: Event-based Egocentric 3D Hand Mesh Reconstruction with Real Dataset

Paper • 2609.17189 • Published Sep 15 • 28

Continual Learning Mechanisms Compose for Long-Horizon Memorization

Paper • 2609.06986 • Published Sep 7 • 370

Scaling Automatic Research Agents via World Models

Paper • 2608.12564 • Published Aug 29 • 483

Kalman Delta Networks: Uncertainty-aware Associative Memory

Paper • 2609.07816 • Published Sep 7 • 31

upvoted a paper about 2 months ago

Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments

Paper • 2609.04148 • Published Sep 3 • 134

upvoted 3 papers 2 months ago

Full-bandwidth transformer

Paper • 2608.08888 • Published Aug 9 • 25

DistilVDR: A Compact End-to-End Visual Document Retriever via Dual-Student Distillation

Paper • 2608.10636 • Published Aug 11 • 12

WeClawArena: An Auditable Sandbox and Benchmark for Cross-User Agents Collaboration and Security in Human-Centered Agent Networks

Paper • 2608.03499 • Published Aug 4 • 10

upvoted 5 papers 3 months ago

AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning

Paper • 2608.05987 • Published Aug 6 • 105

ContinualSkillBench: Can LLM Agents Truly Evolve Their Capabilities?

Paper • 2608.03874 • Published Aug 4 • 15

OmniPack: Unified Token Compression for Efficient Omni-modal Large Language Models

Paper • 2608.03812 • Published Aug 4 • 29

CADENA: Stepwise CAD Reverse Engineering

Paper • 2608.00799 • Published Aug 1 • 43

N_0-VTLA: Scaling Vision-Tactile-Language-Action Model with Latent Tactile Tokens

Paper • 2607.23782 • Published Jul 26 • 80