Léa Bernard

leabamelie's activity

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

upvoted a paper about 9 hours ago

SleuthVLM: Do We Really Need Audio-in-Video for Omni Video Understanding?

Paper • 2611.06083 • Published 4 days ago • 8

upvoted 2 papers 1 day ago

Supervising the Visible State: Separating Representation from View Selection in Streaming Video

Paper • 2610.34926 • Published 13 days ago • 7

Turns Matter: Advancing Streaming Video RL via Turn-Level Credit

Paper • 2611.06728 • Published 4 days ago • 90

upvoted 2 papers 3 days ago

You don't need long context

Paper • 2611.05306 • Published 5 days ago • 19

CoworkOS:Scaling Agent Coworkers for Real-world Automation

Paper • 2611.03178 • Published 6 days ago • 101

upvoted a paper 4 days ago

Reviso: Not All Visual Evidence Deserves Equal Attention in Video Captioning

Paper • 2611.03602 • Published 6 days ago • 26

upvoted a paper 5 days ago

WorldBridge: Bridging Video and Action for Task Generalization in World Action Models

Paper • 2610.40748 • Published 10 days ago • 16

upvoted a paper 6 days ago

OmniShowcase: Omnidirectional Subject-Consistent Video Generation from Multi-View Images

Paper • 2610.35684 • Published 13 days ago • 60

upvoted a paper 7 days ago

Verus-Insight: Towards Explainable Artifact Detection in AI-Generated Videos

Paper • 2610.30866 • Published 17 days ago • 15

upvoted a paper 9 days ago

Efficient Streaming Audio-Visual Target Speaker Extraction for Real-World Acoustic Scenes

Paper • 2610.32749 • Published 16 days ago • 29

upvoted 2 papers 11 days ago

Mycelium: A Meta-Study of Hallucination Detection Across Provenance, Typology, and Granularities

Paper • 2610.33608 • Published 15 days ago • 8

Continual Learning Exam: Benchmarking Long-Horizon RSI and Experiential Learning in LLM Agents

Paper • 2610.33956 • Published 14 days ago • 35

upvoted a paper 12 days ago

FocusVLA: Future-Intent Guided Dynamic View Routing for Vision-Language-Action Models

Paper • 2610.31423 • Published 17 days ago • 3

upvoted a paper 13 days ago

RouteWeaver: Weaving Mode Selection and Execution into Unified LLM Routing

Paper • 2610.19705 • Published 20 days ago • 22

upvoted 2 papers 14 days ago

Right Screen, Wrong Transition: World Models as Verifiers for GUI Agents

Paper • 2610.11942 • Published Oct 8 • 9

TraceForge: Distilling with Your Own Thinking

Paper • 2610.29680 • Published 18 days ago • 31

upvoted a paper 15 days ago

StreamEval: Evaluating Interactive Streaming Video Generation Models

Paper • 2610.28402 • Published 19 days ago • 28

upvoted 3 papers 17 days ago

Ask to Distill: Learning to Synthesize Data for On-Policy Distillation

Paper • 2610.27450 • Published 19 days ago • 15

Policy Is Not Capability: Some Safety Benchmarks Measure Which Definition of "Unsafe" You Trained On

Paper • 2610.25060 • Published 21 days ago • 8

Harnessing Textual Refusal Directions for Multimodal Safety

Paper • 2606.31876 • Published 23 days ago • 15