jj

realman123's activity

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

upvoted a paper about 24 hours ago

NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation

Paper • 2606.03159 • Published 2 days ago • 14

upvoted 15 papers 1 day ago

Linear Ensembles Wash Away Watermarks: On the Fragility of Distributional Perturbations in LLMs

Paper • 2605.30501 • Published 7 days ago • 28

NITP: Next Implicit Token Prediction for LLM Pre-training

Paper • 2605.24956 • Published 11 days ago • 31

Where to Look: Can Foundation Models Reach a Target Viewpoint Through Active Exploration?

Paper • 2606.01247 • Published 4 days ago • 25

Joint Agent Memory and Exploration Learning via Novelty Signals

Paper • 2606.01528 • Published 3 days ago • 12

Brain-IT-VQA: From Brain Signals to Answers

Paper • 2605.29588 • Published 7 days ago • 13

StreamChar: Long-Horizon Streaming Character Audio-Video Generation with Decoupled Orchestration

Paper • 2605.25659 • Published 10 days ago • 14

SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories

Paper • 2606.01311 • Published 4 days ago • 27

Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism

Paper • 2606.00408 • Published 6 days ago • 53

RoboStressBench: Benchmarking VLM Robustness to Physical Visual Stress in Embodied Scenes

Paper • 2606.00828 • Published 5 days ago • 9

Speculative Pipeline Decoding: Higher-Accruacy and Zero-Bubble Speculation via Pipeline Parallelism

Paper • 2605.30852 • Published 6 days ago • 9

Skill is Not One-Size-Fits-All: Model-Aware Skill Alignment for LLM Agents

Paper • 2605.30723 • Published 6 days ago • 13

OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents

Paper • 2606.02031 • Published 3 days ago • 15

When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs

Paper • 2605.24202 • Published 13 days ago • 14

X-Stream: Exploring MLLMs as Multiplexers for Multi-Stream Understanding

Paper • 2606.02482 • Published 3 days ago • 30

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization

Paper • 2606.02564 • Published 3 days ago • 25

upvoted 2 papers 2 days ago

Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs

Paper • 2605.30611 • Published 7 days ago • 170

Which Pretraining Paradigm Better Serves Spatial Intelligence? An Empirical Comparison of Vision-Language and Video Generation Models

Paper • 2605.28132 • Published 8 days ago • 22

upvoted 2 papers 6 days ago

CollectionLoRA: Collecting 50 Effects in 1 LoRA via Multi-Teacher On-Policy Distillation

Paper • 2605.25378 • Published 10 days ago • 58

OmniRetrieval: Unified Retrieval across Heterogeneous Knowledge Sources

Paper • 2605.29250 • Published 7 days ago • 75