Joshua Thomas

Vector-Joshua's activity

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

upvoted a paper 9 days ago

The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents

Paper • 2610.36077 • Published 12 days ago • 160

upvoted a paper 10 days ago

miniTE: Diagnosing and Bridging the Execution Gap in Native NVFP4 Reinforcement Learning

Paper • 2610.23928 • Published Oct 7 • 15

upvoted a paper 23 days ago

RAR: Rate-Adaptive Rollout for Time-Consistent Interactive World Models

Paper • 2610.16302 • Published 26 days ago • 13

upvoted a paper 26 days ago

AMLworld-Compact: Importance-Weighted Downsampling for Cost-Effective LLM Evaluation and Error Diagnosis

Paper • 2610.13627 • Published 29 days ago • 5

upvoted 4 papers about 2 months ago

Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation

Paper • 2609.20744 • Published Sep 17 • 20

Atria Dawn: The Dawn of Agentic Superintelligence

Paper • 2609.15818 • Published Sep 14 • 248

Scaling Automatic Research Agents via World Models

Paper • 2608.12564 • Published Aug 29 • 76

SceneMosaic: Efficient and Diverse Simulation-Ready Scene Generation via Hybrid Agentic Layout Evolution

Paper • 2609.05594 • Published Sep 4 • 19

upvoted a paper 2 months ago

A Common Measure of Communication for Speech Brain-Computer Interfaces

Paper • 2609.02887 • Published Sep 2 • 5

upvoted 7 papers 3 months ago

SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation

Paper • 2608.17426 • Published Aug 18 • 48

FM-Bench: A Benchmark for Long-Horizon Management with Competing Agents

Paper • 2608.18423 • Published Aug 19 • 11

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 • 117

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

Paper • 2608.00677 • Published Aug 1 • 26

VectraYX-Vision-1B: A Sub-2B Spanish/LATAM Cybersecurity Vision-Language Model with Structured Visual Reasoning and Native Tool Use

Paper • 2608.08477 • Published Aug 9 • 2

HarnessOpt-Bench: Evaluating LLMs at Harness Optimization

Paper • 2608.06301 • Published Aug 6 • 16

GROVE: Growing and Reasoning over Temporally Stratified Memory from Streaming Video Experience

Paper • 2608.02392 • Published Aug 3 • 4